Merge remote-tracking branch 'lts/linux-4.4.y' into v4.4/topic/optee

3304 files changed, 44515 insertions, 23625 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
index 6708c5e264aa..33e96f740639 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
@@ -1,4 +1,4 @@
-What		/sys/bus/iio/devices/iio:deviceX/in_proximity_raw
+What		/sys/bus/iio/devices/iio:deviceX/in_proximity_input
 Date:		March 2014
 KernelVersion:	3.15
 Contact:	Matt Ranostay <mranostay@gmail.com>
diff --git a/Documentation/Makefile b/Documentation/Makefile
index bc0548201755..fc759598c4c9 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,4 +1,4 @@
 subdir-y := accounting auxdisplay blackfin connector \
-	filesystems filesystems ia64 laptops mic misc-devices \
+	filesystems filesystems ia64 laptops misc-devices \
 	networking pcmcia prctl ptp spi timers vDSO video4linux \
 	watchdog
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
index d9995f1f51b3..a25a99e82bb1 100644
--- a/Documentation/arm64/tagged-pointers.txt
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -11,24 +11,56 @@ in AArch64 Linux.
 The kernel configures the translation tables so that translations made
 via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
 the virtual address ignored by the translation hardware. This frees up
-this byte for application use, with the following caveats:
+this byte for application use.
 
-	(1) The kernel requires that all user addresses passed to EL1
-	    are tagged with tag 0x00. This means that any syscall
-	    parameters containing user virtual addresses *must* have
-	    their top byte cleared before trapping to the kernel.
 
-	(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.
+Passing tagged addresses to the kernel
+--------------------------------------
 
-	(3) Special care should be taken when using tagged pointers,
-	    since it is likely that C compilers will not hazard two
-	    virtual addresses differing only in the upper byte.
+All interpretation of userspace memory addresses by the kernel assumes
+an address tag of 0x00.
+
+This includes, but is not limited to, addresses found in:
+
+ - pointer arguments to system calls, including pointers in structures
+   passed to system calls,
+
+ - the stack pointer (sp), e.g. when interpreting it to deliver a
+   signal,
+
+ - the frame pointer (x29) and frame records, e.g. when interpreting
+   them to generate a backtrace or call graph.
+
+Using non-zero address tags in any of these locations may result in an
+error code being returned, a (fatal) signal being raised, or other modes
+of failure.
+
+For these reasons, passing non-zero address tags to the kernel via
+system calls is forbidden, and using a non-zero address tag for sp is
+strongly discouraged.
+
+Programs maintaining a frame pointer and frame records that use non-zero
+address tags may suffer impaired or inaccurate debug and profiling
+visibility.
+
+
+Preserving tags
+---------------
+
+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.
 
 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.
+
+
+Other considerations
+--------------------
+
+Special care should be taken when using tagged pointers, since it is
+likely that C compilers will not hazard two virtual addresses differing
+only in the upper byte.
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index c2340eeeb97f..c000832a7fb9 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -30,6 +30,10 @@ Optional properties:
 - target-supply     : regulator for SATA target power
 - phys              : reference to the SATA PHY node
 - phy-names         : must be "sata-phy"
+- ports-implemented : Mask that indicates which ports that the HBA supports
+		      are available for software to use. Useful if PORTS_IMPL
+		      is not programmed by the BIOS, which is true with
+		      some embedded SOC's.
 
 Required properties when using sub-nodes:
 - #address-cells    : number of cells to encode an address
diff --git a/Documentation/devicetree/bindings/clock/imx31-clock.txt b/Documentation/devicetree/bindings/clock/imx31-clock.txt
index 19df842c694f..8163d565f697 100644
--- a/Documentation/devicetree/bindings/clock/imx31-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx31-clock.txt
@@ -77,7 +77,7 @@ Examples:
 clks: ccm@53f80000{
 	compatible = "fsl,imx31-ccm";
 	reg = <0x53f80000 0x4000>;
-	interrupts = <0 31 0x04 0 53 0x04>;
+	interrupts = <31>, <53>;
 	#clock-cells = <1>;
 };
 
diff --git a/Documentation/devicetree/bindings/clock/imx35-clock.txt b/Documentation/devicetree/bindings/clock/imx35-clock.txt
index a70356452a82..f49783213c56 100644
--- a/Documentation/devicetree/bindings/clock/imx35-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx35-clock.txt
@@ -94,6 +94,7 @@ clocks and IDs.
 	csi_sel			79
 	iim_gate		80
 	gpu2d_gate		81
+	ckli_gate		82
 
 Examples:
 
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index 8a47b77abfca..e8c74a6e738b 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -18,6 +18,7 @@ Required properties:
 	"allwinner,sun4i-a10-cpu-clk" - for the CPU multiplexer clock
 	"allwinner,sun4i-a10-axi-clk" - for the AXI clock
 	"allwinner,sun8i-a23-axi-clk" - for the AXI clock on A23
+	"allwinner,sun4i-a10-gates-clk" - for generic gates on all compatible SoCs
 	"allwinner,sun4i-a10-axi-gates-clk" - for the AXI gates
 	"allwinner,sun4i-a10-ahb-clk" - for the AHB clock
 	"allwinner,sun5i-a13-ahb-clk" - for the AHB clock on A13
@@ -43,6 +44,7 @@ Required properties:
 	"allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31
 	"allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20
 	"allwinner,sun8i-a23-apb0-gates-clk" - for the APB0 gates on A23
+	"allwinner,sun8i-h3-apb0-gates-clk" - for the APB0 gates on H3
 	"allwinner,sun9i-a80-apb0-gates-clk" - for the APB0 gates on A80
 	"allwinner,sun4i-a10-apb1-clk" - for the APB1 clock
 	"allwinner,sun9i-a80-apb1-clk" - for the APB1 bus clock on A80
diff --git a/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt b/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt
index a9a5fe19ff2a..ec9d65682702 100644
--- a/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/rockchip-saradc.txt
@@ -12,6 +12,11 @@ Required properties:
 - vref-supply: The regulator supply ADC reference voltage.
 - #io-channel-cells: Should be 1, see ../iio-bindings.txt
 
+Optional properties:
+- resets: Must contain an entry for each entry in reset-names if need support
+	  this option. See ../reset/reset.txt for details.
+- reset-names: Must include the name "saradc-apb".
+
 Example:
 	saradc: saradc@2006c000 {
 		compatible = "rockchip,saradc";
@@ -19,6 +24,8 @@ Example:
 		interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
 		clock-names = "saradc", "apb_pclk";
+		resets = <&cru SRST_SARADC>;
+		reset-names = "saradc-apb";
 		#io-channel-cells = <1>;
 		vref-supply = <&vcc18>;
 	};
diff --git a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
index 08a4a32c8eb0..0326154c7925 100644
--- a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
@@ -134,12 +134,12 @@ mfio80		ddr_debug, mips_trace_data, mips_debug
 mfio81		dreq0, mips_trace_data, eth_debug
 mfio82		dreq1, mips_trace_data, eth_debug
 mfio83		mips_pll_lock, mips_trace_data, usb_debug
-mfio84		sys_pll_lock, mips_trace_data, usb_debug
-mfio85		wifi_pll_lock, mips_trace_data, sdhost_debug
-mfio86		bt_pll_lock, mips_trace_data, sdhost_debug
-mfio87		rpu_v_pll_lock, dreq2, socif_debug
-mfio88		rpu_l_pll_lock, dreq3, socif_debug
-mfio89		audio_pll_lock, dreq4, dreq5
+mfio84		audio_pll_lock, mips_trace_data, usb_debug
+mfio85		rpu_v_pll_lock, mips_trace_data, sdhost_debug
+mfio86		rpu_l_pll_lock, mips_trace_data, sdhost_debug
+mfio87		sys_pll_lock, dreq2, socif_debug
+mfio88		wifi_pll_lock, dreq3, socif_debug
+mfio89		bt_pll_lock, dreq4, dreq5
 tck
 trstn
 tdi
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
index d00bfd8624a5..e0381c28773d 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
@@ -81,9 +81,9 @@ pm8916:
 	l14, l15, l16, l17, l18
 
 pm8941:
-	s1, s2, s3, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14,
-	l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3,
-	mvs1, mvs2
+	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
+	l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3,
+	5vs1, 5vs2
 
 The content of each sub-node is defined by the standard binding for regulators -
 see regulator.txt - with additional custom properties described below:
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 402ab99e409f..6716413c17ba 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -346,7 +346,7 @@ address           perms offset  dev   inode      pathname
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
@@ -378,7 +378,6 @@ is not associated with a file:
 
  [heap]                   = the heap of the program
  [stack]                  = the stack of the main process
- [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
 
@@ -386,10 +385,8 @@ is not associated with a file:
 
 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. This is a key difference from the
-content of /proc/PID/maps, where you will see all mappings that are being used
-as stack by all of those tasks. Hence, for the example above, the task-level
-map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
+as [stack] if that task sees it as a stack. Hence, for the example above, the
+task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 
 08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 21cf76dbba90..7c74bc412c3d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1255,6 +1255,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			When zero, profiling data is discarded and associated
 			debugfs files are removed at module unload time.
 
+	goldfish	[X86] Enable the goldfish android emulator platform.
+			Don't use this when you are not running on the
+			android emulator
+
 	gpt		[EFI] Forces disk with valid GPT signature but
 			invalid Protective MBR to be treated as GPT. If the
 			primary GPT is corrupted, it enables the backup/alternate
@@ -1371,7 +1375,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	i8042.nopnp	[HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
 			     controllers
 	i8042.notimeout	[HW] Ignore timeout condition signalled by controller
-	i8042.reset	[HW] Reset the controller during init and cleanup
+	i8042.reset	[HW] Reset the controller during init, cleanup and
+			     suspend-to-ram transitions, only during s2r
+			     transitions, or never reset
+			Format: { 1 | Y | y | 0 | N | n }
+			1, Y, y: always reset controller
+			0, N, n: don't ever reset controller
+			Default: only on s2r transitions on x86; most other
+			architectures force reset to be always executed
 	i8042.unlock	[HW] Unlock (ignore) the keylock
 	i8042.kbdreset  [HW] Reset device connected to KBD port
 
@@ -3573,6 +3584,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	spia_pedr=
 	spia_peddr=
 
+	stack_guard_gap=	[MM]
+			override the default stack gap protection. The value
+			is in page units and it defines how many pages prior
+			to (for stacks growing down) resp. after (for stacks
+			growing up) the main stack are reserved for no other
+			mapping. Default value is 256 pages.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.
 
@@ -3932,6 +3950,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					sector if the number is odd);
 				i = IGNORE_DEVICE (don't bind to this
 					device);
+				j = NO_REPORT_LUNS (don't use report luns
+					command, uas only);
 				l = NOT_LOCKABLE (don't try to lock and
 					unlock ejectable media);
 				m = MAX_SECTORS_64 (don't transfer more
diff --git a/Documentation/mic/Makefile b/Documentation/mic/Makefile
deleted file mode 100644
index a191d453badf..000000000000
--- a/Documentation/mic/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := mpssd
diff --git a/Documentation/mic/mpssd/Makefile b/Documentation/mic/mpssd/Makefile
deleted file mode 100644
index 06871b0c08a6..000000000000
--- a/Documentation/mic/mpssd/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-ifndef CROSS_COMPILE
-# List of programs to build
-hostprogs-$(CONFIG_X86_64) := mpssd
-
-mpssd-objs := mpssd.o sysfs.o
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS += -I$(objtree)/usr/include -I$(srctree)/tools/include
-
-ifdef DEBUG
-HOSTCFLAGS += -DDEBUG=$(DEBUG)
-endif
-
-HOSTLOADLIBES_mpssd := -lpthread
-
-install:
-	install mpssd /usr/sbin/mpssd
-	install micctrl /usr/sbin/micctrl
-endif
diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt
index a78bf1ffa68c..39b7f612c418 100644
--- a/Documentation/module-signing.txt
+++ b/Documentation/module-signing.txt
@@ -271,3 +271,9 @@ Since the private key is used to sign modules, viruses and malware could use
 the private key to sign modules and compromise the operating system.  The
 private key must be either destroyed or moved to a secure location and not kept
 in the root node of the kernel source tree.
+
+If you use the same private key to sign modules for multiple kernel
+configurations, you must ensure that the module version information is
+sufficient to prevent loading a module into a different kernel.  Either
+set CONFIG_MODVERSIONS=y or ensure that each configuration has a different
+kernel release string by changing EXTRAVERSION or CONFIG_LOCALVERSION.
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
deleted file mode 100644
index 54f10478e8e3..000000000000
--- a/Documentation/networking/netlink_mmap.txt
+++ /dev/null
@@ -1,332 +0,0 @@
-This file documents how to use memory mapped I/O with netlink.
-
-Author: Patrick McHardy <kaber@trash.net>
-
-Overview
---------
-
-Memory mapped netlink I/O can be used to increase throughput and decrease
-overhead of unicast receive and transmit operations. Some netlink subsystems
-require high throughput, these are mainly the netfilter subsystems
-nfnetlink_queue and nfnetlink_log, but it can also help speed up large
-dump operations of f.i. the routing database.
-
-Memory mapped netlink I/O used two circular ring buffers for RX and TX which
-are mapped into the processes address space.
-
-The RX ring is used by the kernel to directly construct netlink messages into
-user-space memory without copying them as done with regular socket I/O,
-additionally as long as the ring contains messages no recvmsg() or poll()
-syscalls have to be issued by user-space to get more message.
-
-The TX ring is used to process messages directly from user-space memory, the
-kernel processes all messages contained in the ring using a single sendmsg()
-call.
-
-Usage overview
---------------
-
-In order to use memory mapped netlink I/O, user-space needs three main changes:
-
-- ring setup
-- conversion of the RX path to get messages from the ring instead of recvmsg()
-- conversion of the TX path to construct messages into the ring
-
-Ring setup is done using setsockopt() to provide the ring parameters to the
-kernel, then a call to mmap() to map the ring into the processes address space:
-
-- setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &params, sizeof(params));
-- setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &params, sizeof(params));
-- ring = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0)
-
-Usage of either ring is optional, but even if only the RX ring is used the
-mapping still needs to be writable in order to update the frame status after
-processing.
-
-Conversion of the reception path involves calling poll() on the file
-descriptor, once the socket is readable the frames from the ring are
-processed in order until no more messages are available, as indicated by
-a status word in the frame header.
-
-On kernel side, in order to make use of memory mapped I/O on receive, the
-originating netlink subsystem needs to support memory mapped I/O, otherwise
-it will use an allocated socket buffer as usual and the contents will be
- copied to the ring on transmission, nullifying most of the performance gains.
-Dumps of kernel databases automatically support memory mapped I/O.
-
-Conversion of the transmit path involves changing message construction to
-use memory from the TX ring instead of (usually) a buffer declared on the
-stack and setting up the frame header appropriately. Optionally poll() can
-be used to wait for free frames in the TX ring.
-
-Structured and definitions for using memory mapped I/O are contained in
-<linux/netlink.h>.
-
-RX and TX rings
-----------------
-
-Each ring contains a number of continuous memory blocks, containing frames of
-fixed size dependent on the parameters used for ring setup.
-
-Ring:	[ block 0 ]
-		[ frame 0 ]
-		[ frame 1 ]
-	[ block 1 ]
-		[ frame 2 ]
-		[ frame 3 ]
-	...
-	[ block n ]
-		[ frame 2 * n ]
-		[ frame 2 * n + 1 ]
-
-The blocks are only visible to the kernel, from the point of view of user-space
-the ring just contains the frames in a continuous memory zone.
-
-The ring parameters used for setting up the ring are defined as follows:
-
-struct nl_mmap_req {
-	unsigned int	nm_block_size;
-	unsigned int	nm_block_nr;
-	unsigned int	nm_frame_size;
-	unsigned int	nm_frame_nr;
-};
-
-Frames are grouped into blocks, where each block is a continuous region of memory
-and holds nm_block_size / nm_frame_size frames. The total number of frames in
-the ring is nm_frame_nr. The following invariants hold:
-
-- frames_per_block = nm_block_size / nm_frame_size
-
-- nm_frame_nr = frames_per_block * nm_block_nr
-
-Some parameters are constrained, specifically:
-
-- nm_block_size must be a multiple of the architectures memory page size.
-  The getpagesize() function can be used to get the page size.
-
-- nm_frame_size must be equal or larger to NL_MMAP_HDRLEN, IOW a frame must be
-  able to hold at least the frame header
-
-- nm_frame_size must be smaller or equal to nm_block_size
-
-- nm_frame_size must be a multiple of NL_MMAP_MSG_ALIGNMENT
-
-- nm_frame_nr must equal the actual number of frames as specified above.
-
-When the kernel can't allocate physically continuous memory for a ring block,
-it will fall back to use physically discontinuous memory. This might affect
-performance negatively, in order to avoid this the nm_frame_size parameter
-should be chosen to be as small as possible for the required frame size and
-the number of blocks should be increased instead.
-
-Ring frames
-------------
-
-Each frames contain a frame header, consisting of a synchronization word and some
-meta-data, and the message itself.
-
-Frame:	[ header message ]
-
-The frame header is defined as follows:
-
-struct nl_mmap_hdr {
-	unsigned int	nm_status;
-	unsigned int	nm_len;
-	__u32		nm_group;
-	/* credentials */
-	__u32		nm_pid;
-	__u32		nm_uid;
-	__u32		nm_gid;
-};
-
-- nm_status is used for synchronizing processing between the kernel and user-
-  space and specifies ownership of the frame as well as the operation to perform
-
-- nm_len contains the length of the message contained in the data area
-
-- nm_group specified the destination multicast group of message
-
-- nm_pid, nm_uid and nm_gid contain the netlink pid, UID and GID of the sending
-  process. These values correspond to the data available using SOCK_PASSCRED in
-  the SCM_CREDENTIALS cmsg.
-
-The possible values in the status word are:
-
-- NL_MMAP_STATUS_UNUSED:
-	RX ring:	frame belongs to the kernel and contains no message
-			for user-space. Approriate action is to invoke poll()
-			to wait for new messages.
-
-	TX ring:	frame belongs to user-space and can be used for
-			message construction.
-
-- NL_MMAP_STATUS_RESERVED:
-	RX ring only:	frame is currently used by the kernel for message
-			construction and contains no valid message yet.
-			Appropriate action is to invoke poll() to wait for
-			new messages.
-
-- NL_MMAP_STATUS_VALID:
-	RX ring:	frame contains a valid message. Approriate action is
-			to process the message and release the frame back to
-			the kernel by setting the status to
-			NL_MMAP_STATUS_UNUSED or queue the frame by setting the
-			status to NL_MMAP_STATUS_SKIP.
-
-	TX ring:	the frame contains a valid message from user-space to
-			be processed by the kernel. After completing processing
-			the kernel will release the frame back to user-space by
-			setting the status to NL_MMAP_STATUS_UNUSED.
-
-- NL_MMAP_STATUS_COPY:
-	RX ring only:	a message is ready to be processed but could not be
-			stored in the ring, either because it exceeded the
-			frame size or because the originating subsystem does
-			not support memory mapped I/O. Appropriate action is
-			to invoke recvmsg() to receive the message and release
-			the frame back to the kernel by setting the status to
-			NL_MMAP_STATUS_UNUSED.
-
-- NL_MMAP_STATUS_SKIP:
-	RX ring only:	user-space queued the message for later processing, but
-			processed some messages following it in the ring. The
-			kernel should skip this frame when looking for unused
-			frames.
-
-The data area of a frame begins at a offset of NL_MMAP_HDRLEN relative to the
-frame header.
-
-TX limitations
---------------
-
-As of Jan 2015 the message is always copied from the ring frame to an
-allocated buffer due to unresolved security concerns.
-See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.").
-
-Example
--------
-
-Ring setup:
-
-	unsigned int block_size = 16 * getpagesize();
-	struct nl_mmap_req req = {
-		.nm_block_size		= block_size,
-		.nm_block_nr		= 64,
-		.nm_frame_size		= 16384,
-		.nm_frame_nr		= 64 * block_size / 16384,
-	};
-	unsigned int ring_size;
-	void *rx_ring, *tx_ring;
-
-	/* Configure ring parameters */
-	if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
-		exit(1);
-	if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
-		exit(1)
-
-	/* Calculate size of each individual ring */
-	ring_size = req.nm_block_nr * req.nm_block_size;
-
-	/* Map RX/TX rings. The TX ring is located after the RX ring */
-	rx_ring = mmap(NULL, 2 * ring_size, PROT_READ | PROT_WRITE,
-		       MAP_SHARED, fd, 0);
-	if ((long)rx_ring == -1L)
-		exit(1);
-	tx_ring = rx_ring + ring_size:
-
-Message reception:
-
-This example assumes some ring parameters of the ring setup are available.
-
-	unsigned int frame_offset = 0;
-	struct nl_mmap_hdr *hdr;
-	struct nlmsghdr *nlh;
-	unsigned char buf[16384];
-	ssize_t len;
-
-	while (1) {
-		struct pollfd pfds[1];
-
-		pfds[0].fd	= fd;
-		pfds[0].events	= POLLIN | POLLERR;
-		pfds[0].revents	= 0;
-
-		if (poll(pfds, 1, -1) < 0 && errno != -EINTR)
-			exit(1);
-
-		/* Check for errors. Error handling omitted */
-		if (pfds[0].revents & POLLERR)
-			<handle error>
-
-		/* If no new messages, poll again */
-		if (!(pfds[0].revents & POLLIN))
-			continue;
-
-		/* Process all frames */
-		while (1) {
-			/* Get next frame header */
-			hdr = rx_ring + frame_offset;
-
-			if (hdr->nm_status == NL_MMAP_STATUS_VALID) {
-				/* Regular memory mapped frame */
-				nlh = (void *)hdr + NL_MMAP_HDRLEN;
-				len = hdr->nm_len;
-
-				/* Release empty message immediately. May happen
-				 * on error during message construction.
-				 */
-				if (len == 0)
-					goto release;
-			} else if (hdr->nm_status == NL_MMAP_STATUS_COPY) {
-				/* Frame queued to socket receive queue */
-				len = recv(fd, buf, sizeof(buf), MSG_DONTWAIT);
-				if (len <= 0)
-					break;
-				nlh = buf;
-			} else
-				/* No more messages to process, continue polling */
-				break;
-
-			process_msg(nlh);
-release:
-			/* Release frame back to the kernel */
-			hdr->nm_status = NL_MMAP_STATUS_UNUSED;
-
-			/* Advance frame offset to next frame */
-			frame_offset = (frame_offset + frame_size) % ring_size;
-		}
-	}
-
-Message transmission:
-
-This example assumes some ring parameters of the ring setup are available.
-A single message is constructed and transmitted, to send multiple messages
-at once they would be constructed in consecutive frames before a final call
-to sendto().
-
-	unsigned int frame_offset = 0;
-	struct nl_mmap_hdr *hdr;
-	struct nlmsghdr *nlh;
-	struct sockaddr_nl addr = {
-		.nl_family	= AF_NETLINK,
-	};
-
-	hdr = tx_ring + frame_offset;
-	if (hdr->nm_status != NL_MMAP_STATUS_UNUSED)
-		/* No frame available. Use poll() to avoid. */
-		exit(1);
-
-	nlh = (void *)hdr + NL_MMAP_HDRLEN;
-
-	/* Build message */
-	build_message(nlh);
-
-	/* Fill frame header: length and status need to be set */
-	hdr->nm_len	= nlh->nlmsg_len;
-	hdr->nm_status	= NL_MMAP_STATUS_VALID;
-
-	if (sendto(fd, NULL, 0, 0, &addr, sizeof(addr)) < 0)
-		exit(1);
-
-	/* Advance frame offset to next frame */
-	frame_offset = (frame_offset + frame_size) % ring_size;
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 4976389e432d..dd15a699ee1c 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -831,7 +831,7 @@ separate memory range only intended for GPIO driving, and the register
 range dealing with pin config and pin multiplexing get placed into a
 different memory range and a separate section of the data sheet.
 
-A flag "strict" in struct pinctrl_desc is available to check and deny
+A flag "strict" in struct pinmux_ops is available to check and deny
 simultaneous access to the same pin from GPIO and pin multiplexing
 consumers on hardware of this type. The pinctrl driver should set this flag
 accordingly.
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61c8c9d..37eca00796ee 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@ scmd->allowed.
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-	- shost->host_failed--
 	- clear scmd->eh_eflags
 	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+		 keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-	    layer of failure.
+	    layer of failure. May be called concurrently but must have
+	    a no more than one thread per separate eh_work_q to
+	    manipulate the queue locklessly
 	- scmd is removed from eh_done_q and scmd->eh_entry is cleared
 	- if retry is necessary, scmd is requeued using
           scsi_queue_insert()
 	- otherwise, scsi_finish_command() is invoked for scmd
+	- zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 
diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt
index bc3842dc323a..e2dea3dc4307 100644
--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@@ -213,9 +213,6 @@ TTY_IO_ERROR		If set, causes all subsequent userspace read/write
 
 TTY_OTHER_CLOSED	Device is a pty and the other side has closed.
 
-TTY_OTHER_DONE		Device is a pty and the other side has closed and
-			all pending input processing has been completed.
-
 TTY_NO_WRITE_SPLIT	Prevent driver from splitting up writes into
 			smaller chunks.
 
diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 88152f214f48..35e17f748ca7 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@@ -159,6 +161,27 @@ The default is 65534.
 
 ==============================================================
 
+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based
@@ -242,6 +265,13 @@ aio-nr can grow to.
 
 ==============================================================
 
+mount-max:
+
+This denotes the maximum number of mounts that may exist
+in a mount namespace.
+
+==============================================================
+
 
 2. /proc/sys/fs/binfmt_misc
 ----------------------------------------------------------
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index af70d1541d3a..be61d53e997f 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -810,14 +810,13 @@ via the /proc/sys interface:
        Each write syscall must fully contain the sysctl value to be
        written, and multiple writes on the same sysctl file descriptor
        will rewrite the sysctl value, regardless of file position.
-   0 - (default) Same behavior as above, but warn about processes that
-       perform writes to a sysctl file descriptor when the file position
-       is not 0.
-   1 - Respect file position when writing sysctl strings. Multiple writes
-       will append to the sysctl value buffer. Anything past the max length
-       of the sysctl value buffer will be ignored. Writes to numeric sysctl
-       entries must always be at file position 0 and the value must be
-       fully contained in the buffer sent in the write syscall.
+   0 - Same behavior as above, but warn about processes that perform writes
+       to a sysctl file descriptor when the file position is not 0.
+   1 - (default) Respect file position when writing sysctl strings. Multiple
+       writes will append to the sysctl value buffer. Anything past the max
+       length of the sysctl value buffer will be ignored. Writes to numeric
+       sysctl entries must always be at file position 0 and the value must
+       be fully contained in the buffer sent in the write syscall.
 
 ==============================================================
 
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 092ee9fbaf2b..df8ab4fc240a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1991,6 +1991,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TM_VSCR           | 32
   PPC   | KVM_REG_PPC_TM_DSCR           | 64
   PPC   | KVM_REG_PPC_TM_TAR            | 64
+  PPC   | KVM_REG_PPC_TM_XER            | 64
         |                               |
   MIPS  | KVM_REG_MIPS_R0               | 64
           ...
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 54944c71b819..2a4ee6302122 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with
 "debugpat" boot parameter. With this parameter, various debug messages are
 printed to dmesg log.
 
+PAT Initialization
+------------------
+
+The following table describes how PAT is initialized under various
+configurations. The PAT MSR must be updated by Linux in order to support WC
+and WT attributes. Otherwise, the PAT MSR has the value programmed in it
+by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests.
+
+ MTRR PAT   Call Sequence               PAT State  PAT MSR
+ =========================================================
+ E    E     MTRR -> PAT init            Enabled    OS
+ E    D     MTRR -> PAT init            Disabled    -
+ D    E     MTRR -> PAT disable         Disabled   BIOS
+ D    D     MTRR -> PAT disable         Disabled    -
+ -    np/E  PAT  -> PAT disable         Disabled   BIOS
+ -    np/D  PAT  -> PAT disable         Disabled    -
+ E    !P/E  MTRR -> PAT init            Disabled   BIOS
+ D    !P/E  MTRR -> PAT disable         Disabled   BIOS
+ !M   !P/E  MTRR stub -> PAT disable    Disabled   BIOS
+
+ Legend
+ ------------------------------------------------
+ E         Feature enabled in CPU
+ D	   Feature disabled/unsupported in CPU
+ np	   "nopat" boot option specified
+ !P	   CONFIG_X86_PAT option unset
+ !M	   CONFIG_MTRR option unset
+ Enabled   PAT state set to enabled
+ Disabled  PAT state set to disabled
+ OS        PAT initializes PAT MSR with OS setting
+ BIOS      PAT keeps PAT MSR with BIOS setting
+
diff --git a/MAINTAINERS b/MAINTAINERS
index 67c412ff33ed..e1e620dd3f78 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -230,13 +230,13 @@ F:	kernel/sys_ni.c
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/abituguru.c
 
 ABIT UGURU 3 HARDWARE MONITOR DRIVER
 M:	Alistair John Strachan <alistair@devzero.co.uk>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/abituguru3.c
 
@@ -373,14 +373,14 @@ S:	Maintained
 
 ADM1025 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/adm1025
 F:	drivers/hwmon/adm1025.c
 
 ADM1029 HARDWARE MONITOR DRIVER
 M:	Corentin Labbe <clabbe.montjoie@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/adm1029.c
 
@@ -425,7 +425,7 @@ F:	drivers/video/backlight/adp8860_bl.c
 
 ADS1015 HARDWARE MONITOR DRIVER
 M:	Dirk Eibach <eibach@gdsys.de>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ads1015
 F:	drivers/hwmon/ads1015.c
@@ -438,7 +438,7 @@ F:	drivers/macintosh/therm_adt746x.c
 
 ADT7475 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/adt7475
 F:	drivers/hwmon/adt7475.c
@@ -615,7 +615,7 @@ F:	include/linux/ccp.h
 
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Andreas Herrmann <herrmann.der.user@googlemail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/fam15h_power
 F:	drivers/hwmon/fam15h_power.c
@@ -779,7 +779,7 @@ F:	drivers/input/mouse/bcm5974.c
 
 APPLE SMC DRIVER
 M:	Henrik Rydberg <rydberg@bitmath.org>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Odd fixes
 F:	drivers/hwmon/applesmc.c
 
@@ -1777,7 +1777,7 @@ F:	include/media/as3645a.h
 
 ASC7621 HARDWARE MONITOR DRIVER
 M:	George Joseph <george.joseph@fairview5.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/asc7621
 F:	drivers/hwmon/asc7621.c
@@ -1864,7 +1864,7 @@ F:	drivers/net/wireless/ath/carl9170/
 
 ATK0110 HWMON DRIVER
 M:	Luca Tettamanti <kronos.it@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/asus_atk0110.c
 
@@ -2984,7 +2984,7 @@ F:	mm/swap_cgroup.c
 
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/coretemp
 F:	drivers/hwmon/coretemp.c
@@ -3549,7 +3549,7 @@ T:	git git://git.infradead.org/users/vkoul/slave-dma.git
 
 DME1737 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/dme1737
 F:	drivers/hwmon/dme1737.c
@@ -4097,8 +4097,8 @@ F:	Documentation/efi-stub.txt
 F:	arch/ia64/kernel/efi.c
 F:	arch/x86/boot/compressed/eboot.[ch]
 F:	arch/x86/include/asm/efi.h
-F:	arch/x86/platform/efi/*
-F:	drivers/firmware/efi/*
+F:	arch/x86/platform/efi/
+F:	drivers/firmware/efi/
 F:	include/linux/efi*.h
 
 EFI VARIABLE FILESYSTEM
@@ -4262,7 +4262,7 @@ F:	include/video/exynos_mipi*
 
 F71805F HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/f71805f
 F:	drivers/hwmon/f71805f.c
@@ -4341,7 +4341,7 @@ F:	fs/*
 
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/f75375s.c
 F:	include/linux/f75375s.h
@@ -4883,8 +4883,8 @@ F:	drivers/media/usb/hackrf/
 HARDWARE MONITORING
 M:	Jean Delvare <jdelvare@suse.com>
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
-W:	http://www.lm-sensors.org/
+L:	linux-hwmon@vger.kernel.org
+W:	http://hwmon.wiki.kernel.org/
 T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
@@ -5393,7 +5393,7 @@ F:	drivers/usb/atm/ueagle-atm.c
 
 INA209 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ina209
 F:	Documentation/devicetree/bindings/i2c/ina209.txt
@@ -5401,7 +5401,7 @@ F:	drivers/hwmon/ina209.c
 
 INA2XX HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ina2xx
 F:	drivers/hwmon/ina2xx.c
@@ -5884,7 +5884,7 @@ F:	drivers/isdn/hardware/eicon/
 
 IT87 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/it87
 F:	drivers/hwmon/it87.c
@@ -5920,7 +5920,7 @@ F:	drivers/media/dvb-frontends/ix2505v*
 
 JC42.4 TEMPERATURE SENSOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/jc42.c
 F:	Documentation/hwmon/jc42
@@ -5970,14 +5970,14 @@ F:	drivers/tty/serial/jsm/
 
 K10TEMP HARDWARE MONITORING DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/k10temp
 F:	drivers/hwmon/k10temp.c
 
 K8TEMP HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/k8temp
 F:	drivers/hwmon/k8temp.c
@@ -6485,27 +6485,27 @@ F:	net/llc/
 
 LM73 HARDWARE MONITOR DRIVER
 M:	Guillaume Ligneul <guillaume.ligneul@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/lm73.c
 
 LM78 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/lm78
 F:	drivers/hwmon/lm78.c
 
 LM83 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/lm83
 F:	drivers/hwmon/lm83.c
 
 LM90 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/lm90
 F:	Documentation/devicetree/bindings/hwmon/lm90.txt
@@ -6513,7 +6513,7 @@ F:	drivers/hwmon/lm90.c
 
 LM95234 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/lm95234
 F:	drivers/hwmon/lm95234.c
@@ -6580,7 +6580,7 @@ F:	drivers/scsi/sym53c8xx_2/
 
 LTC4261 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ltc4261
 F:	drivers/hwmon/ltc4261.c
@@ -6749,28 +6749,28 @@ F:	include/uapi/linux/matroxfb.h
 
 MAX16065 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/max16065
 F:	drivers/hwmon/max16065.c
 
 MAX20751 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/max20751
 F:	drivers/hwmon/max20751.c
 
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/max6650
 F:	drivers/hwmon/max6650.c
 
 MAX6697 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/max6697
 F:	Documentation/devicetree/bindings/i2c/max6697.txt
@@ -7303,7 +7303,7 @@ F:	drivers/scsi/NCR_D700.*
 
 NCT6775 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/nct6775
 F:	drivers/hwmon/nct6775.c
@@ -8069,7 +8069,7 @@ F:	drivers/video/logo/logo_parisc*
 
 PC87360 HARDWARE MONITORING DRIVER
 M:	Jim Cromie <jim.cromie@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/pc87360
 F:	drivers/hwmon/pc87360.c
@@ -8081,7 +8081,7 @@ F:	drivers/char/pc8736x_gpio.c
 
 PC87427 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/pc87427
 F:	drivers/hwmon/pc87427.c
@@ -8420,8 +8420,8 @@ F:	drivers/rtc/rtc-puv3.c
 
 PMBUS HARDWARE MONITORING DRIVERS
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
-W:	http://www.lm-sensors.org/
+L:	linux-hwmon@vger.kernel.org
+W:	http://hwmon.wiki.kernel.org/
 W:	http://www.roeck-us.net/linux/drivers/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
@@ -8615,7 +8615,7 @@ F:	drivers/media/usb/pwc/*
 
 PWM FAN DRIVER
 M:	Kamil Debski <k.debski@samsung.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/hwmon/pwm-fan.txt
 F:	Documentation/hwmon/pwm-fan
@@ -9895,28 +9895,28 @@ F:	Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
 
 SMM665 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/smm665
 F:	drivers/hwmon/smm665.c
 
 SMSC EMC2103 HARDWARE MONITOR DRIVER
 M:	Steve Glendinning <steve.glendinning@shawell.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/emc2103
 F:	drivers/hwmon/emc2103.c
 
 SMSC SCH5627 HARDWARE MONITOR DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Supported
 F:	Documentation/hwmon/sch5627
 F:	drivers/hwmon/sch5627.c
 
 SMSC47B397 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/smsc47b397
 F:	drivers/hwmon/smsc47b397.c
@@ -10843,7 +10843,7 @@ F:	include/linux/mmc/sh_mobile_sdhi.h
 
 TMP401 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/tmp401
 F:	drivers/hwmon/tmp401.c
@@ -11577,14 +11577,14 @@ F:	Documentation/networking/vrf.txt
 
 VT1211 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/vt1211
 F:	drivers/hwmon/vt1211.c
 
 VT8231 HARDWARE MONITOR DRIVER
 M:	Roger Lucas <vt8231@hiddenengine.co.uk>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/vt8231.c
 
@@ -11603,21 +11603,21 @@ F:	drivers/w1/
 
 W83791D HARDWARE MONITORING DRIVER
 M:	Marc Hulsman <m.hulsman@tudelft.nl>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/w83791d
 F:	drivers/hwmon/w83791d.c
 
 W83793 HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/w83793
 F:	drivers/hwmon/w83793.c
 
 W83795 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
-L:	lm-sensors@lm-sensors.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/w83795.c
 
diff --git a/Makefile b/Makefile
index 87d12b44ab66..788d90a0051b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 6
+SUBLEVEL = 88
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
@@ -128,6 +128,10 @@ _all:
 # Cancel implicit rules on top Makefile
 $(CURDIR)/Makefile Makefile: ;
 
+ifneq ($(words $(subst :, ,$(CURDIR))), 1)
+  $(error main directory cannot contain spaces nor colons)
+endif
+
 ifneq ($(KBUILD_OUTPUT),)
 # Invoke a second make in the output directory, passing relevant variables
 # check that the output directory actually exists
@@ -364,7 +368,7 @@ AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
-CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage
+CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im
 
 
 # Use USERINCLUDE when you must reference the UAPI directories only.
@@ -391,11 +395,12 @@ KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common \
 		   -Werror-implicit-function-declaration \
 		   -Wno-format-security \
-		   -std=gnu89
+		   -std=gnu89 $(call cc-option,-fno-PIE)
+
 
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
-KBUILD_AFLAGS   := -D__ASSEMBLY__
+KBUILD_AFLAGS   := -D__ASSEMBLY__ $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS_MODULE  := -DMODULE
 KBUILD_CFLAGS_MODULE  := -DMODULE
 KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
@@ -495,6 +500,12 @@ ifeq ($(KBUILD_EXTMOD),)
                 endif
         endif
 endif
+# install and module_install need also be processed one by one
+ifneq ($(filter install,$(MAKECMDGOALS)),)
+        ifneq ($(filter modules_install,$(MAKECMDGOALS)),)
+	        mixed-targets := 1
+        endif
+endif
 
 ifeq ($(mixed-targets),1)
 # ===========================================================================
@@ -606,16 +617,31 @@ ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
+KBUILD_CFLAGS	+= $(call cc-disable-warning,maybe-uninitialized,)
+KBUILD_CFLAGS	+= $(call cc-disable-warning,frame-address,)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, format-truncation)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, format-overflow)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, int-in-bool-context)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS	+= -Os $(call cc-disable-warning,maybe-uninitialized,)
+KBUILD_CFLAGS	+= -Os
 else
+ifdef CONFIG_PROFILE_ALL_BRANCHES
 KBUILD_CFLAGS	+= -O2
+else
+KBUILD_CFLAGS   += -O2
+endif
 endif
 
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function
@@ -682,9 +708,10 @@ KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
 KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
 else
 
-# This warning generated too much noise in a regular build.
-# Use make W=1 to enable this warning (see scripts/Makefile.build)
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.build)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
 endif
 
 ifdef CONFIG_FRAME_POINTER
@@ -770,12 +797,6 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=date-time)
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
-	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
-	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 
@@ -1259,7 +1280,7 @@ help:
 	@echo  '  firmware_install- Install all firmware to INSTALL_FW_PATH'
 	@echo  '                    (default: $$(INSTALL_MOD_PATH)/lib/firmware)'
 	@echo  '  dir/            - Build all files in dir and below'
-	@echo  '  dir/file.[oisS] - Build specified target only'
+	@echo  '  dir/file.[ois]  - Build specified target only'
 	@echo  '  dir/file.lst    - Build specified mixed source/assembly target only'
 	@echo  '                    (requires a recent binutils and recent build (System.map))'
 	@echo  '  dir/file.ko     - Build module including final link'
@@ -1499,11 +1520,11 @@ image_name:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h
index 4cb4b6d3452c..0bc66e1d3a7e 100644
--- a/arch/alpha/include/asm/types.h
+++ b/arch/alpha/include/asm/types.h
@@ -1,6 +1,6 @@
 #ifndef _ALPHA_TYPES_H
 #define _ALPHA_TYPES_H
 
-#include <asm-generic/int-ll64.h>
+#include <uapi/asm/types.h>
 
 #endif /* _ALPHA_TYPES_H */
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 9b0d40093c9a..c0ddbbf73400 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -371,14 +371,6 @@ __copy_tofrom_user_nocheck(void *to, const void *from, long len)
 	return __cu_len;
 }
 
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
-	if (__access_ok((unsigned long)validate, len, get_fs()))
-		len = __copy_tofrom_user_nocheck(to, from, len);
-	return len;
-}
-
 #define __copy_to_user(to, from, n)					\
 ({									\
 	__chk_user_ptr(to);						\
@@ -393,17 +385,22 @@ __copy_tofrom_user(void *to, const void *from, long len, const void __user *vali
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
-
 extern inline long
 copy_to_user(void __user *to, const void *from, long n)
 {
-	return __copy_tofrom_user((__force void *)to, from, n, to);
+	if (likely(__access_ok((unsigned long)to, n, get_fs())))
+		n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+	return n;
 }
 
 extern inline long
 copy_from_user(void *to, const void __user *from, long n)
 {
-	return __copy_tofrom_user(to, (__force void *)from, n, from);
+	if (likely(__access_ok((unsigned long)from, n, get_fs())))
+		n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+	else
+		memset(to, 0, n);
+	return n;
 }
 
 extern void __do_clear_user(void);
diff --git a/arch/alpha/include/uapi/asm/types.h b/arch/alpha/include/uapi/asm/types.h
index 9fd3cd459777..8d1024d7be05 100644
--- a/arch/alpha/include/uapi/asm/types.h
+++ b/arch/alpha/include/uapi/asm/types.h
@@ -9,8 +9,18 @@
  * need to be careful to avoid a name clashes.
  */
 
-#ifndef __KERNEL__
+/*
+ * This is here because we used to use l64 for alpha
+ * and we don't want to impact user mode with our change to ll64
+ * in the kernel.
+ *
+ * However, some user programs are fine with this.  They can
+ * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here.
+ */
+#if !defined(__SANE_USERSPACE_TYPES__) && !defined(__KERNEL__)
 #include <asm-generic/int-l64.h>
+#else
+#include <asm-generic/int-ll64.h>
 #endif
 
 #endif /* _UAPI_ALPHA_TYPES_H */
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 6cc08166ff00..63f06a2b1f7f 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1188,8 +1188,10 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 	if (!access_ok(VERIFY_WRITE, ur, sizeof(*ur)))
 		return -EFAULT;
 
-	err = 0;
-	err |= put_user(status, ustatus);
+	err = put_user(status, ustatus);
+	if (ret < 0)
+		return err ? err : ret;
+
 	err |= __put_user(r.ru_utime.tv_sec, &ur->ru_utime.tv_sec);
 	err |= __put_user(r.ru_utime.tv_usec, &ur->ru_utime.tv_usec);
 	err |= __put_user(r.ru_stime.tv_sec, &ur->ru_stime.tv_sec);
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 6312f607932f..2d785f5a3041 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -387,7 +387,7 @@ config ARC_HAS_LLSC
 
 config ARC_STAR_9000923308
 	bool "Workaround for llock/scond livelock"
-	default y
+	default n
 	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
 
 config ARC_HAS_SWAPE
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aeb19021099e..c05ea2b54276 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -18,6 +18,20 @@ cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
+is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0)
+
+ifdef CONFIG_ISA_ARCOMPACT
+ifeq ($(is_700), 0)
+    $(error Toolchain not configured for ARCompact builds)
+endif
+endif
+
+ifdef CONFIG_ISA_ARCV2
+ifeq ($(is_700), 1)
+    $(error Toolchain not configured for ARCv2 builds)
+endif
+endif
+
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
 # We had a customer reported bug where some code built in kernel was NOT using
@@ -48,8 +62,6 @@ endif
 
 endif
 
-cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
-
 # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
 ifeq ($(atleast_gcc48),y)
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -gdwarf-2
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fac7d85ed6a..2c30a016cf15 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -374,12 +374,6 @@ static inline int is_isa_arcompact(void)
 	return IS_ENABLED(CONFIG_ISA_ARCOMPACT);
 }
 
-#if defined(CONFIG_ISA_ARCOMPACT) && !defined(_CPU_DEFAULT_A7)
-#error "Toolchain not configured for ARCompact builds"
-#elif defined(CONFIG_ISA_ARCV2) && !defined(_CPU_DEFAULT_HS)
-#error "Toolchain not configured for ARCv2 builds"
-#endif
-
 #endif /* __ASEMBLY__ */
 
 #endif /* _ASM_ARC_ARCREGS_H */
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 57c1f33844d4..0352fb8d21b9 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 									\
 	m += nr >> 5;							\
 									\
-	/*								\
-	 * ARC ISA micro-optimization:					\
-	 *								\
-	 * Instructions dealing with bitpos only consider lower 5 bits	\
-	 * e.g (x << 33) is handled like (x << 1) by ASL instruction	\
-	 *  (mem pointer still needs adjustment to point to next word)	\
-	 *								\
-	 * Hence the masking to clamp @nr arg can be elided in general.	\
-	 *								\
-	 * However if @nr is a constant (above assumed in a register),	\
-	 * and greater than 31, gcc can optimize away (x << 33) to 0,	\
-	 * as overflow, given the 32-bit ISA. Thus masking needs to be	\
-	 * done for const @nr, but no code is generated due to gcc	\
-	 * const prop.							\
-	 */								\
 	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 210ef3e72332..0ddd7144c492 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -88,7 +88,9 @@ extern int ioc_exists;
 #define ARC_REG_SLC_FLUSH	0x904
 #define ARC_REG_SLC_INVALIDATE	0x905
 #define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_START1	0x915
 #define ARC_REG_SLC_RGN_END	0x916
+#define ARC_REG_SLC_RGN_END1	0x917
 
 /* Bit val in SLC_CONTROL */
 #define SLC_CTRL_IM		0x040
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index fbe3587c4f36..56aeb5efe604 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -85,6 +85,10 @@ void flush_anon_page(struct vm_area_struct *vma,
  */
 #define PG_dc_clean	PG_arch_1
 
+#define CACHE_COLORS_NUM	4
+#define CACHE_COLORS_MSK	(CACHE_COLORS_NUM - 1)
+#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK)
+
 /*
  * Simple wrapper over config option
  * Bootup code ensures that hardware matches kernel configuration
@@ -94,8 +98,6 @@ static inline int cache_is_vipt_aliasing(void)
 	return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
 }
 
-#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & 1)
-
 /*
  * checks if two addresses (after page aligning) index into same cache set
  */
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 08e7e2a16ac1..d5da2115d78a 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -22,10 +22,13 @@
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
-	"	lp  1f	\n"
-	"	nop	\n"
-	"1:		\n"
-	: "+l"(loops));
+	"	mov lp_count, %0	\n"
+	"	lp  1f			\n"
+	"	nop			\n"
+	"1:				\n"
+	:
+        : "r"(loops)
+        : "lp_count");
 }
 
 extern void __bad_udelay(void);
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index b5ff87e6f4b7..aee1a77934cf 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -16,6 +16,7 @@
 	;
 	; Now manually save: r12, sp, fp, gp, r25
 
+	PUSH	r30
 	PUSH	r12
 
 	; Saving pt_regs->sp correctly requires some extra work due to the way
@@ -72,6 +73,7 @@
 	POPAX	AUX_USER_SP
 1:
 	POP	r12
+	POP	r30
 
 .endm
 
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index ad7860c5ce15..51597f344a62 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -142,7 +142,7 @@
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Retrieve orig r25 and save it with rest of callee_regs
-	ld.as   r12, [r12, PT_user_r25]
+	ld	r12, [r12, PT_user_r25]
 	PUSH	r12
 #else
 	PUSH	r25
@@ -198,7 +198,7 @@
 
 	; SP is back to start of pt_regs
 #ifdef CONFIG_ARC_CURR_IN_REG
-	st.as   r12, [sp, PT_user_r25]
+	st	r12, [sp, PT_user_r25]
 #endif
 .endm
 
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 694ece8a0243..cb69299a492e 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -13,6 +13,15 @@
 #include <asm/byteorder.h>
 #include <asm/page.h>
 
+#ifdef CONFIG_ISA_ARCV2
+#include <asm/barrier.h>
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
 extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
 extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 				  unsigned long flags);
@@ -22,6 +31,15 @@ extern void iounmap(const void __iomem *addr);
 #define ioremap_wc(phy, sz)		ioremap(phy, sz)
 #define ioremap_wt(phy, sz)		ioremap(phy, sz)
 
+/*
+ * io{read,write}{16,32}be() macros
+ */
+#define ioread16be(p)		({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)		({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); })
+
 /* Change struct page to physical address */
 #define page_to_phys(page)		(page_to_pfn(page) << PAGE_SHIFT)
 
@@ -99,15 +117,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
-#ifdef CONFIG_ISA_ARCV2
-#include <asm/barrier.h>
-#define __iormb()		rmb()
-#define __iowmb()		wmb()
-#else
-#define __iormb()		do { } while (0)
-#define __iowmb()		do { } while (0)
-#endif
-
 /*
  * MMIO can also get buffered/optimized in micro-arch, so barriers needed
  * Based on ARM model for the typical use case
@@ -129,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
 /*
- * Relaxed API for drivers which can handle any ordering themselves
+ * Relaxed API for drivers which can handle barrier ordering themselves
+ *
+ * Also these are defined to perform little endian accesses.
+ * To provide the typical device register semantics of fixed endian,
+ * swap the byte order for Big Endian
+ *
+ * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de
  */
 #define readb_relaxed(c)	__raw_readb(c)
-#define readw_relaxed(c)	__raw_readw(c)
-#define readl_relaxed(c)	__raw_readl(c)
+#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \
+					__raw_readw(c)); __r; })
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \
+					__raw_readl(c)); __r; })
 
 #define writeb_relaxed(v,c)	__raw_writeb(v,c)
-#define writew_relaxed(v,c)	__raw_writew(v,c)
-#define writel_relaxed(v,c)	__raw_writel(v,c)
+#define writew_relaxed(v,c)	__raw_writew((__force u16) cpu_to_le16(v),c)
+#define writel_relaxed(v,c)	__raw_writel((__force u32) cpu_to_le32(v),c)
 
 #include <asm-generic/io.h>
 
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index c1d36458bfb7..4c6eed80cd8b 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void)
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
 	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
 .endm
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 57af2f05ae84..e5fec320f158 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -110,7 +110,7 @@
 #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL)
 
 /* More Abbrevaited helpers */
 #define PAGE_U_NONE     __pgprot(___DEF)
@@ -277,8 +277,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
-#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | \
-				 pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	(__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 #define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
 /*
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 69095da1fcfd..47111d565a95 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -84,7 +84,7 @@ struct pt_regs {
 	unsigned long fp;
 	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	unsigned long r12;
+	unsigned long r12, r30;
 
 	/*------- Below list auto saved by h/w -----------*/
 	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da6032b715..d4d8df706efa 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -83,7 +83,10 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
@@ -101,7 +104,11 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
+	"	mov %R1, 0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index e1b87444ea9a..05131805aa33 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -332,10 +332,6 @@ static void arc_chk_core_config(void)
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
-
-	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
-	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
-		panic("llock/scond livelock workaround missing\n");
 }
 
 /*
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 004b7f0bc76c..257b8699efde 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -107,13 +107,13 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	struct user_regs_struct uregs;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
-	if (!err)
-		set_current_blocked(&set);
-
 	err |= __copy_from_user(&uregs.scratch,
 				&(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
+	if (err)
+		return err;
 
+	set_current_blocked(&set);
 	regs->bta	= uregs.scratch.bta;
 	regs->lp_start	= uregs.scratch.lp_start;
 	regs->lp_end	= uregs.scratch.lp_end;
@@ -138,7 +138,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	regs->r0	= uregs.scratch.r0;
 	regs->sp	= uregs.scratch.sp;
 
-	return err;
+	return 0;
 }
 
 static inline int is_do_ss_needed(unsigned int magic)
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index 001de4ce711e..11b50959f20e 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 	 * prelogue is setup (callee regs saved and then fp set and not other
 	 * way around
 	 */
-	pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+	pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
 	return 0;
 
 #endif
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index dfad287f1db1..dbedc576e4ca 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -130,14 +130,17 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 		cycle_t  full;
 	} stamp;
 
-
-	__asm__ __volatile(
-	"1:						\n"
-	"	lr		%0, [AUX_RTC_LOW]	\n"
-	"	lr		%1, [AUX_RTC_HIGH]	\n"
-	"	lr		%2, [AUX_RTC_CTRL]	\n"
-	"	bbit0.nt	%2, 31, 1b		\n"
-	: "=r" (stamp.low), "=r" (stamp.high), "=r" (status));
+	/*
+	 * hardware has an internal state machine which tracks readout of
+	 * low/high and updates the CTRL.status if
+	 *  - interrupt/exception taken between the two reads
+	 *  - high increments after low has been read
+	 */
+	do {
+		stamp.low = read_aux_reg(AUX_RTC_LOW);
+		stamp.high = read_aux_reg(AUX_RTC_HIGH);
+		status = read_aux_reg(AUX_RTC_CTRL);
+	} while (!(status & _BITUL(31)));
 
 	return stamp.full;
 }
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index abd961f3e763..5f69c3bd59bb 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 	if (state.fault)
 		goto fault;
 
+	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta;
+		regs->ret = regs->bta & ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index ff7ff6cbb811..9a84cbdd44b0 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -543,6 +543,7 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
+	phys_addr_t end;
 
 	spin_lock_irqsave(&lock, flags);
 
@@ -572,8 +573,16 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	 * END needs to be setup before START (latter triggers the operation)
 	 * END can't be same as START, so add (l2_line_sz - 1) to sz
 	 */
-	write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1));
-	write_aux_reg(ARC_REG_SLC_RGN_START, paddr);
+	end = paddr + sz + l2_line_sz - 1;
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end));
+
+	write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end));
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr));
+
+	write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr));
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
@@ -914,6 +923,15 @@ void arc_cache_init(void)
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
+	/*
+	 * Only master CPU needs to execute rest of function:
+	 *  - Assume SMP so all cores will have same cache config so
+	 *    any geomtry checks will be same for all
+	 *  - IOC setup / dma callbacks only need to be setup once
+	 */
+	if (cpu)
+		return;
+
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 
@@ -951,11 +969,16 @@ void arc_cache_init(void)
 		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
 		if (is_isa_arcompact()) {
 			int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-
-			if (dc->alias && !handled)
-				panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-			else if (!dc->alias && handled)
+			int num_colors = dc->sz_k/dc->assoc/TO_KB(PAGE_SIZE);
+
+			if (dc->alias) {
+				if (!handled)
+					panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+				if (CACHE_COLORS_NUM != num_colors)
+					panic("CACHE_COLORS_NUM not optimized for config\n");
+			} else if (!dc->alias && handled) {
 				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+			}
 		}
 	}
 
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
index 2e06d56e987b..cf4ae6958240 100644
--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 06e983f59980..856913705169 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -776,7 +776,7 @@ __armv7_mmu_cache_on:
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
 		bic     r6, r6, #1 << 31        @ 32-bit translation system
-		bic     r6, r6, #3 << 0         @ use only ttbr0
+		bic     r6, r6, #(7 << 0) | (1 << 4)	@ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
 		mcrne   p15, 0, r6, c2, c0, 2   @ load ttb control
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 47954ed990f8..00707aac72fc 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -792,3 +792,8 @@
 	tx-num-evt = <32>;
 	rx-num-evt = <32>;
 };
+
+&synctimer_32kclk {
+	assigned-clocks = <&mux_synctimer32k_ck>;
+	assigned-clock-parents = <&clkdiv32k_ick>;
+};
diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi
index 7ccce7529b0c..cc952cf8ec30 100644
--- a/arch/arm/boot/dts/armada-375.dtsi
+++ b/arch/arm/boot/dts/armada-375.dtsi
@@ -529,7 +529,7 @@
 			};
 
 			sata@a0000 {
-				compatible = "marvell,orion-sata";
+				compatible = "marvell,armada-370-sata";
 				reg = <0xa0000 0x5000>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gateclk 14>, <&gateclk 20>;
diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi
index 3710755c6d76..22f7a13e20b4 100644
--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
@@ -58,8 +58,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0xf1100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0xf1110000 0x10000>;
+			  MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
 
 		internal-regs {
 
@@ -117,7 +117,7 @@
 			};
 
 			/* USB part of the eSATA/USB 2.0 port */
-			usb@50000 {
+			usb@58000 {
 				status = "okay";
 			};
 
@@ -245,7 +245,7 @@
 		button@2 {
 			label = "Factory Reset Button";
 			linux,code = <KEY_RESTART>;
-			gpios = <&gpio1 15 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio0 29 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -260,7 +260,7 @@
 		};
 
 		sata {
-			gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 22 GPIO_ACTIVE_LOW>;
 			default-state = "off";
 		};
 	};
@@ -313,7 +313,7 @@
 
 &pinctrl {
 	keys_pin: keys-pin {
-		marvell,pins = "mpp24", "mpp47";
+		marvell,pins = "mpp24", "mpp29";
 		marvell,function = "gpio";
 	};
 
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index cd316021d6ce..6c1b45c1af66 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -89,7 +89,7 @@
 					pinctrl-names = "default";
 					pinctrl-0 = <&pca0_pins>;
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
@@ -101,7 +101,7 @@
 					compatible = "nxp,pca9555";
 					pinctrl-names = "default";
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
diff --git a/arch/arm/boot/dts/armada-390.dtsi b/arch/arm/boot/dts/armada-390.dtsi
index 094e39c66039..6cd18d8aaac7 100644
--- a/arch/arm/boot/dts/armada-390.dtsi
+++ b/arch/arm/boot/dts/armada-390.dtsi
@@ -47,6 +47,8 @@
 #include "armada-39x.dtsi"
 
 / {
+	compatible = "marvell,armada390";
+
 	soc {
 		internal-regs {
 			pinctrl@18000 {
@@ -54,4 +56,5 @@
 				reg = <0x18000 0x20>;
 			};
 		};
+	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
index b89e6cf1271a..7a461541ce50 100644
--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@@ -304,13 +304,13 @@
 		button@1 {
 			label = "WPS";
 			linux,code = <KEY_WPS_BUTTON>;
-			gpios = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
 		};
 
 		button@2 {
 			label = "Factory Reset Button";
 			linux,code = <KEY_RESTART>;
-			gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index e74df327cdd3..20618a897c99 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -122,6 +122,8 @@
 			uart1: serial@f8020000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_uart1_default>;
+				atmel,use-dma-rx;
+				atmel,use-dma-tx;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index ff888d21c786..0bd325c314e1 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -162,9 +162,10 @@
 			};
 
 			adc0: adc@f8018000 {
+				atmel,adc-vref = <3300>;
+				atmel,adc-channels-used = <0xfe>;
 				pinctrl-0 = <
 					&pinctrl_adc0_adtrg
-					&pinctrl_adc0_ad0
 					&pinctrl_adc0_ad1
 					&pinctrl_adc0_ad2
 					&pinctrl_adc0_ad3
@@ -172,8 +173,6 @@
 					&pinctrl_adc0_ad5
 					&pinctrl_adc0_ad6
 					&pinctrl_adc0_ad7
-					&pinctrl_adc0_ad8
-					&pinctrl_adc0_ad9
 					>;
 				status = "okay";
 			};
@@ -303,6 +302,7 @@
 		regulator-name = "mmc0-card-supply";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
 	};
 
 	gpio_keys {
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 569026e8f96c..e27024cdf48b 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -110,6 +110,8 @@
 			};
 
 			usart3: serial@fc00c000 {
+				atmel,use-dma-rx;
+				atmel,use-dma-tx;
 				status = "okay";
 			};
 
@@ -268,5 +270,6 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 		vin-supply = <&vcc_3v3_reg>;
+		regulator-always-on;
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 0827d594b1f0..cd0cd5fd09a3 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -106,7 +106,7 @@
 
 			pmc: pmc@fffffc00 {
 				compatible = "atmel,at91sam9x5-pmc", "syscon";
-				reg = <0xfffffc00 0x100>;
+				reg = <0xfffffc00 0x200>;
 				interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
 				interrupt-controller;
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 6f50f672efbd..de8ac998604d 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -54,14 +54,14 @@
 		timer@0200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x0200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};
 
 		local-timer@0600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x0600 0x100>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};
 
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 4f935ad9f27b..6881757b03e8 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -85,6 +85,7 @@
 				#size-cells = <1>;
 				compatible = "m25p64";
 				spi-max-frequency = <30000000>;
+				m25p,fast-read;
 				reg = <0>;
 				partition@0 {
 					label = "U-Boot-SPL";
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index a50be640f1b0..59411e447fa0 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -298,6 +298,8 @@
 		compatible = "maxim,max8997-pmic";
 
 		reg = <0x66>;
+		interrupt-parent = <&gpx0>;
+		interrupts = <7 0>;
 
 		max8997,pmic-buck1-uses-gpio-dvs;
 		max8997,pmic-buck2-uses-gpio-dvs;
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index 5fdb222636a7..cbe5fd5ed179 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -30,11 +30,11 @@
 		};
 	};
 
-	avic: avic-interrupt-controller@60000000 {
+	avic: interrupt-controller@68000000 {
 		compatible = "fsl,imx31-avic", "fsl,avic";
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		reg = <0x60000000 0x100000>;
+		reg = <0x68000000 0x100000>;
 	};
 
 	soc {
@@ -110,13 +110,6 @@
 				interrupts = <19>;
 				clocks = <&clks 25>;
 			};
-
-			clks: ccm@53f80000{
-				compatible = "fsl,imx31-ccm";
-				reg = <0x53f80000 0x4000>;
-				interrupts = <0 31 0x04 0 53 0x04>;
-				#clock-cells = <1>;
-			};
 		};
 
 		aips@53f00000 { /* AIPS2 */
@@ -126,6 +119,13 @@
 			reg = <0x53f00000 0x100000>;
 			ranges;
 
+			clks: ccm@53f80000{
+				compatible = "fsl,imx31-ccm";
+				reg = <0x53f80000 0x4000>;
+				interrupts = <31>, <53>;
+				#clock-cells = <1>;
+			};
+
 			gpt: timer@53f90000 {
 				compatible = "fsl,imx31-gpt";
 				reg = <0x53f90000 0x4000>;
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 4b0ec0703825..8ca9217204a0 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -30,7 +30,7 @@
 				/* kHz    uV */
 				996000  1250000
 				792000  1175000
-				396000  1075000
+				396000  1150000
 			>;
 			fsl,soc-operating-points = <
 				/* ARM kHz  SOC-PU uV */
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index a35d54fd9cd3..ddfdb75a6e90 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -319,8 +319,6 @@
 		compatible = "fsl,imx6q-nitrogen6_max-sgtl5000",
 			     "fsl,imx-audio-sgtl5000";
 		model = "imx6q-nitrogen6_max-sgtl5000";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_sgtl5000>;
 		ssi-controller = <&ssi1>;
 		audio-codec = <&codec>;
 		audio-routing =
@@ -401,6 +399,8 @@
 
 	codec: sgtl5000@0a {
 		compatible = "fsl,sgtl5000";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_sgtl5000>;
 		reg = <0x0a>;
 		clocks = <&clks 201>;
 		VDDA-supply = <&reg_2p5v>;
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 2b6cc8bf3c5c..e6af41c4bbc1 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -221,7 +221,7 @@
 					clocks = <&clks IMX6QDL_CLK_SPDIF_GCLK>, <&clks IMX6QDL_CLK_OSC>,
 						 <&clks IMX6QDL_CLK_SPDIF>, <&clks IMX6QDL_CLK_ASRC>,
 						 <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_ESAI_EXTAL>,
-						 <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_MLB>,
+						 <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_DUMMY>,
 						 <&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_SPBA>;
 					clock-names = "core",  "rxtx0",
 						      "rxtx1", "rxtx2",
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index bfa5edde179c..2c1e7f09205f 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -113,7 +113,7 @@
 
 	partition@e0000 {
 		label = "u-boot environment";
-		reg = <0xe0000 0x100000>;
+		reg = <0xe0000 0x20000>;
 	};
 
 	partition@100000 {
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 5f5e0f3d5b64..27cd4abfc74d 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -697,6 +697,8 @@
 	vmmc_aux-supply = <&vsim>;
 	bus-width = <8>;
 	non-removable;
+	no-sdio;
+	no-sd;
 };
 
 &mmc3 {
diff --git a/arch/arm/boot/dts/omap3-overo-base.dtsi b/arch/arm/boot/dts/omap3-overo-base.dtsi
index a29ad16cc9bb..64c5af30c1d0 100644
--- a/arch/arm/boot/dts/omap3-overo-base.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-base.dtsi
@@ -223,7 +223,9 @@
 };
 
 &gpmc {
-	ranges = <0 0 0x00000000 0x20000000>;
+	ranges = <0 0 0x30000000 0x1000000>,	/* CS0 */
+		 <4 0 0x2b000000 0x1000000>,	/* CS4 */
+		 <5 0 0x2c000000 0x1000000>;	/* CS5 */
 
 	nand@0,0 {
 		linux,mtd-name= "micron,mt29c4g96maz";
diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
index 17b82f82638a..64047788216b 100644
--- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
@@ -55,8 +55,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 9e24b6a1d07b..1b304e2f1bd2 100644
--- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -27,8 +27,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
index 334109e14613..82e98ee3023a 100644
--- a/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi
@@ -15,9 +15,6 @@
 #include "omap-gpmc-smsc9221.dtsi"
 
 &gpmc {
-	ranges = <4 0 0x2b000000 0x1000000>,	/* CS4 */
-		 <5 0 0x2c000000 0x1000000>;	/* CS5 */
-
 	smsc1: ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi
index cf6998a0804d..564341af7e97 100644
--- a/arch/arm/boot/dts/pxa3xx.dtsi
+++ b/arch/arm/boot/dts/pxa3xx.dtsi
@@ -30,7 +30,7 @@
 			reg = <0x43100000 90>;
 			interrupts = <45>;
 			clocks = <&clks CLK_NAND>;
-			dmas = <&pdma 97>;
+			dmas = <&pdma 97 3>;
 			dma-names = "data";
 			#address-cells = <1>;
 			#size-cells = <1>;	
diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi
index a4c1762b53ea..e00d50ef678f 100644
--- a/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -5,6 +5,7 @@
 #include <dt-bindings/reset/qcom,gcc-msm8960.h>
 #include <dt-bindings/clock/qcom,mmcc-msm8960.h>
 #include <dt-bindings/soc/qcom,gsbi.h>
+#include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 / {
 	model = "Qualcomm APQ8064";
@@ -354,22 +355,50 @@
 
 					compatible = "qcom,pm8921-gpio";
 					reg = <0x150>;
-					interrupts = <192 1>, <193 1>, <194 1>,
-						     <195 1>, <196 1>, <197 1>,
-						     <198 1>, <199 1>, <200 1>,
-						     <201 1>, <202 1>, <203 1>,
-						     <204 1>, <205 1>, <206 1>,
-						     <207 1>, <208 1>, <209 1>,
-						     <210 1>, <211 1>, <212 1>,
-						     <213 1>, <214 1>, <215 1>,
-						     <216 1>, <217 1>, <218 1>,
-						     <219 1>, <220 1>, <221 1>,
-						     <222 1>, <223 1>, <224 1>,
-						     <225 1>, <226 1>, <227 1>,
-						     <228 1>, <229 1>, <230 1>,
-						     <231 1>, <232 1>, <233 1>,
-						     <234 1>, <235 1>;
-
+					interrupts = <192 IRQ_TYPE_NONE>,
+						     <193 IRQ_TYPE_NONE>,
+						     <194 IRQ_TYPE_NONE>,
+						     <195 IRQ_TYPE_NONE>,
+						     <196 IRQ_TYPE_NONE>,
+						     <197 IRQ_TYPE_NONE>,
+						     <198 IRQ_TYPE_NONE>,
+						     <199 IRQ_TYPE_NONE>,
+						     <200 IRQ_TYPE_NONE>,
+						     <201 IRQ_TYPE_NONE>,
+						     <202 IRQ_TYPE_NONE>,
+						     <203 IRQ_TYPE_NONE>,
+						     <204 IRQ_TYPE_NONE>,
+						     <205 IRQ_TYPE_NONE>,
+						     <206 IRQ_TYPE_NONE>,
+						     <207 IRQ_TYPE_NONE>,
+						     <208 IRQ_TYPE_NONE>,
+						     <209 IRQ_TYPE_NONE>,
+						     <210 IRQ_TYPE_NONE>,
+						     <211 IRQ_TYPE_NONE>,
+						     <212 IRQ_TYPE_NONE>,
+						     <213 IRQ_TYPE_NONE>,
+						     <214 IRQ_TYPE_NONE>,
+						     <215 IRQ_TYPE_NONE>,
+						     <216 IRQ_TYPE_NONE>,
+						     <217 IRQ_TYPE_NONE>,
+						     <218 IRQ_TYPE_NONE>,
+						     <219 IRQ_TYPE_NONE>,
+						     <220 IRQ_TYPE_NONE>,
+						     <221 IRQ_TYPE_NONE>,
+						     <222 IRQ_TYPE_NONE>,
+						     <223 IRQ_TYPE_NONE>,
+						     <224 IRQ_TYPE_NONE>,
+						     <225 IRQ_TYPE_NONE>,
+						     <226 IRQ_TYPE_NONE>,
+						     <227 IRQ_TYPE_NONE>,
+						     <228 IRQ_TYPE_NONE>,
+						     <229 IRQ_TYPE_NONE>,
+						     <230 IRQ_TYPE_NONE>,
+						     <231 IRQ_TYPE_NONE>,
+						     <232 IRQ_TYPE_NONE>,
+						     <233 IRQ_TYPE_NONE>,
+						     <234 IRQ_TYPE_NONE>,
+						     <235 IRQ_TYPE_NONE>;
 					gpio-controller;
 					#gpio-cells = <2>;
 
@@ -381,9 +410,18 @@
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupts =
-					<128 1>, <129 1>, <130 1>, <131 1>,
-					<132 1>, <133 1>, <134 1>, <135 1>,
-					<136 1>, <137 1>, <138 1>, <139 1>;
+					<128 IRQ_TYPE_NONE>,
+					<129 IRQ_TYPE_NONE>,
+					<130 IRQ_TYPE_NONE>,
+					<131 IRQ_TYPE_NONE>,
+					<132 IRQ_TYPE_NONE>,
+					<133 IRQ_TYPE_NONE>,
+					<134 IRQ_TYPE_NONE>,
+					<135 IRQ_TYPE_NONE>,
+					<136 IRQ_TYPE_NONE>,
+					<137 IRQ_TYPE_NONE>,
+					<138 IRQ_TYPE_NONE>,
+					<139 IRQ_TYPE_NONE>;
 				};
 
 				rtc@11d {
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index a9977d6ee81a..169653586a9f 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -1023,7 +1023,7 @@
 		mstp7_clks: mstp7_clks@e615014c {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
-			clocks = <&mp_clk>, <&mp_clk>,
+			clocks = <&mp_clk>, <&hp_clk>,
 				 <&zs_clk>, <&p_clk>, <&p_clk>, <&zs_clk>,
 				 <&zs_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>;
 			#clock-cells = <1>;
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index b0c912feaa2f..8a394f336003 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -837,8 +837,8 @@
 #define PIN_PD23__ISC_FIELD		PINMUX_PIN(PIN_PD23, 6, 4)
 #define PIN_PD24			120
 #define PIN_PD24__GPIO			PINMUX_PIN(PIN_PD24, 0, 0)
-#define PIN_PD24__UTXD2			PINMUX_PIN(PIN_PD23, 1, 2)
-#define PIN_PD24__FLEXCOM4_IO3		PINMUX_PIN(PIN_PD23, 3, 3)
+#define PIN_PD24__UTXD2			PINMUX_PIN(PIN_PD24, 1, 2)
+#define PIN_PD24__FLEXCOM4_IO3		PINMUX_PIN(PIN_PD24, 3, 3)
 #define PIN_PD25			121
 #define PIN_PD25__GPIO			PINMUX_PIN(PIN_PD25, 0, 0)
 #define PIN_PD25__SPI1_SPCK		PINMUX_PIN(PIN_PD25, 1, 3)
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 4dfca8fc49b3..1bc61ece2589 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -856,6 +856,13 @@
 				compatible = "atmel,at91sam9260-usart";
 				reg = <0xf801c000 0x100>;
 				interrupts = <24 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(35))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(36))>;
+				dma-names = "tx", "rx";
 				clocks = <&uart0_clk>;
 				clock-names = "usart";
 				status = "disabled";
@@ -865,6 +872,13 @@
 				compatible = "atmel,at91sam9260-usart";
 				reg = <0xf8020000 0x100>;
 				interrupts = <25 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(37))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(38))>;
+				dma-names = "tx", "rx";
 				clocks = <&uart1_clk>;
 				clock-names = "usart";
 				status = "disabled";
@@ -874,6 +888,13 @@
 				compatible = "atmel,at91sam9260-usart";
 				reg = <0xf8024000 0x100>;
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(39))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(40))>;
+				dma-names = "tx", "rx";
 				clocks = <&uart2_clk>;
 				clock-names = "usart";
 				status = "disabled";
@@ -985,6 +1006,13 @@
 				compatible = "atmel,at91sam9260-usart";
 				reg = <0xfc008000 0x100>;
 				interrupts = <27 IRQ_TYPE_LEVEL_HIGH 7>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(41))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(42))>;
+				dma-names = "tx", "rx";
 				clocks = <&uart3_clk>;
 				clock-names = "usart";
 				status = "disabled";
@@ -993,6 +1021,13 @@
 			uart4: serial@fc00c000 {
 				compatible = "atmel,at91sam9260-usart";
 				reg = <0xfc00c000 0x100>;
+				dmas = <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(43))>,
+				       <&dma0
+					(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
+					 AT91_XDMAC_DT_PERID(44))>;
+				dma-names = "tx", "rx";
 				interrupts = <28 IRQ_TYPE_LEVEL_HIGH 7>;
 				clocks = <&uart4_clk>;
 				clock-names = "usart";
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index 81f81214cdf9..bbf95375cf99 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -497,8 +497,9 @@
 			interrupt-names = "mmcirq";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_mmc0>;
-			clock-names = "mmc";
-			clocks = <&clk_s_c0_flexgen CLK_MMC_0>;
+			clock-names = "mmc", "icn";
+			clocks = <&clk_s_c0_flexgen CLK_MMC_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
 			bus-width = <8>;
 			non-removable;
 		};
@@ -512,8 +513,9 @@
 			interrupt-names = "mmcirq";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_sd1>;
-			clock-names = "mmc";
-			clocks = <&clk_s_c0_flexgen CLK_MMC_1>;
+			clock-names = "mmc", "icn";
+			clocks = <&clk_s_c0_flexgen CLK_MMC_1>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
 			resets = <&softreset STIH407_MMC1_SOFTRESET>;
 			bus-width = <4>;
 		};
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 18ed1ad10d32..40318869c733 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -41,7 +41,8 @@
 			compatible = "st,st-ohci-300x";
 			reg = <0x9a03c00 0x100>;
 			interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT0_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -57,7 +58,8 @@
 			interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb0>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT0_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -71,7 +73,8 @@
 			compatible = "st,st-ohci-300x";
 			reg = <0x9a83c00 0x100>;
 			interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT1_SOFTRESET>;
 			reset-names = "power", "softreset";
@@ -87,7 +90,8 @@
 			interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usb1>;
-			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+			clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+				 <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
 			resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
 				 <&softreset STIH407_USB2_PORT1_SOFTRESET>;
 			reset-names = "power", "softreset";
diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts
index 97570cb7f2fc..1d23527d4ecf 100644
--- a/arch/arm/boot/dts/sun4i-a10-a1000.dts
+++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -84,6 +84,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 2b17c5199151..6de83a6187d0 100644
--- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -66,6 +66,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
index 7afc7a64eef1..e28f080b1fd5 100644
--- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
+++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
@@ -80,6 +80,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;   /* PH19 */
 	};
diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
index 9fea918f949e..39731a78f087 100644
--- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
@@ -79,6 +79,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index d910d3a6c41c..84bdba480d5a 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -83,7 +83,7 @@
 			trips {
 				cpu_alert0: cpu_alert0 {
 					/* milliCelsius */
-					temperature = <850000>;
+					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts
index 530ab28e9ca2..d21f50ba3172 100644
--- a/arch/arm/boot/dts/sun5i-r8-chip.dts
+++ b/arch/arm/boot/dts/sun5i-r8-chip.dts
@@ -52,7 +52,7 @@
 
 / {
 	model = "NextThing C.H.I.P.";
-	compatible = "nextthing,chip", "allwinner,sun5i-r8";
+	compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13";
 
 	aliases {
 		i2c0 = &i2c0;
diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts
index ed7e1009326c..d9ee0fd817e9 100644
--- a/arch/arm/boot/dts/tegra20-paz00.dts
+++ b/arch/arm/boot/dts/tegra20-paz00.dts
@@ -565,6 +565,7 @@
 			regulator-name = "+3VS,vdd_pnl";
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
+			regulator-boot-on;
 			gpio = <&gpio TEGRA_GPIO(A, 4) GPIO_ACTIVE_HIGH>;
 			enable-active-high;
 		};
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 3d224941b541..a3a9ad4dc3c6 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -869,9 +869,9 @@ struct sa1111_save_data {
 
 #ifdef CONFIG_PM
 
-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags;
 	unsigned int val;
@@ -934,9 +934,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
  *	restored by their respective drivers, and must be called
  *	via LDM after this function.
  */
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags, id;
 	void __iomem *base;
@@ -952,7 +952,7 @@ static int sa1111_resume(struct platform_device *dev)
 	id = sa1111_readl(sachip->base + SA1111_SKID);
 	if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
 		__sa1111_remove(sachip);
-		platform_set_drvdata(dev, NULL);
+		dev_set_drvdata(dev, NULL);
 		kfree(save);
 		return 0;
 	}
@@ -1003,8 +1003,8 @@ static int sa1111_resume(struct platform_device *dev)
 }
 
 #else
-#define sa1111_suspend NULL
-#define sa1111_resume  NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq  NULL
 #endif
 
 static int sa1111_probe(struct platform_device *pdev)
@@ -1038,6 +1038,11 @@ static int sa1111_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static struct dev_pm_ops sa1111_pm_ops = {
+	.suspend_noirq = sa1111_suspend_noirq,
+	.resume_noirq = sa1111_resume_noirq,
+};
+
 /*
  *	Not sure if this should be on the system bus or not yet.
  *	We really want some way to register a system device at
@@ -1050,10 +1055,9 @@ static int sa1111_remove(struct platform_device *pdev)
 static struct platform_driver sa1111_device_driver = {
 	.probe		= sa1111_probe,
 	.remove		= sa1111_remove,
-	.suspend	= sa1111_suspend,
-	.resume		= sa1111_resume,
 	.driver		= {
 		.name	= "sa1111",
+		.pm	= &sa1111_pm_ops,
 	},
 };
 
diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig
index f3142369f594..01116ee1284b 100644
--- a/arch/arm/configs/s3c2410_defconfig
+++ b/arch/arm/configs/s3c2410_defconfig
@@ -87,9 +87,9 @@ CONFIG_IPV6_TUNNEL=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index b445a5d56f43..679c589c4828 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -87,8 +87,13 @@ static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
 		rko[0] = rko[0] ^ rki[0] ^ rcon[i];
+#else
+		rko[0] = rol32(ce_aes_sub(rki[kwords - 1]), 8);
+		rko[0] = rko[0] ^ rki[0] ^ (rcon[i] << 24);
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
@@ -279,7 +284,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		err = blkcipher_walk_done(desc, &walk,
 					  walk.nbytes % AES_BLOCK_SIZE);
 	}
-	if (nbytes) {
+	if (walk.nbytes % AES_BLOCK_SIZE) {
 		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];
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 03a39fe29246..9d9ba9acdddc 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -226,6 +226,27 @@ static int ghash_async_digest(struct ahash_request *req)
 	}
 }
 
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
+	desc->flags = req->base.flags;
+
+	return crypto_shash_import(desc, in);
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	return crypto_shash_export(desc, out);
+}
+
 static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 			      unsigned int keylen)
 {
@@ -274,7 +295,10 @@ static struct ahash_alg ghash_async_alg = {
 	.final			= ghash_async_final,
 	.setkey			= ghash_async_setkey,
 	.digest			= ghash_async_digest,
+	.import			= ghash_async_import,
+	.export			= ghash_async_export,
 	.halg.digestsize	= GHASH_DIGEST_SIZE,
+	.halg.statesize		= sizeof(struct ghash_desc_ctx),
 	.halg.base		= {
 		.cra_name	= "ghash",
 		.cra_driver_name = "ghash-ce",
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 85e374f873ac..e9d04f475929 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -81,6 +81,9 @@
 #define ARM_CPU_XSCALE_ARCH_V2		0x4000
 #define ARM_CPU_XSCALE_ARCH_V3		0x6000
 
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION		0x510002d0
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index ccb3aa64640d..b91a2d17a521 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -119,7 +119,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 /* The ARM override for dma_max_pfn() */
 static inline unsigned long dma_max_pfn(struct device *dev)
 {
-	return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
+	return dma_to_pfn(dev, *dev->dma_mask);
 }
 #define dma_max_pfn(dev) dma_max_pfn(dev)
 
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index d2315ffd8f12..f13ae153fb24 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE	(TASK_SIZE / 3 * 2)
+/* This is the base location for PIE (ET_DYN with INTERP) loads. */
+#define ELF_ET_DYN_BASE		0x400000UL
 
 /* When the program starts, a1 contains a pointer to a function to be 
    registered with atexit, as per the SVR4 ABI.  A value of 0 means we 
diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h
index f4882553fbb0..85a34cc8316a 100644
--- a/arch/arm/include/asm/floppy.h
+++ b/arch/arm/include/asm/floppy.h
@@ -17,7 +17,7 @@
 
 #define fd_outb(val,port)			\
 	do {					\
-		if ((port) == FD_DOR)		\
+		if ((port) == (u32)FD_DOR)	\
 			fd_setdor((val));	\
 		else				\
 			outb((val),(port));	\
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index bfe2a2f5a644..22b73112b75f 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -54,6 +54,24 @@ static inline void *return_address(unsigned int level)
 
 #define ftrace_return_address(n) return_address(n)
 
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+
+static inline bool arch_syscall_match_sym_name(const char *sym,
+					       const char *name)
+{
+	if (!strcmp(sym, "sys_mmap2"))
+		sym = "sys_mmap_pgoff";
+	else if (!strcmp(sym, "sys_statfs64_wrapper"))
+		sym = "sys_statfs64";
+	else if (!strcmp(sym, "sys_fstatfs64_wrapper"))
+		sym = "sys_fstatfs64";
+	else if (!strcmp(sym, "sys_arm_fadvise64_64"))
+		sym = "sys_fadvise64_64";
+
+	/* Ignore case since sym may start with "SyS" instead of "sys" */
+	return !strcasecmp(sym, name);
+}
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* _ASM_ARM_FTRACE */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 405aa1883307..23d5cad56ddc 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -204,18 +204,12 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
 	 * and iterate over the range.
 	 */
 
-	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
-
 	VM_BUG_ON(size & ~PAGE_MASK);
 
-	if (!need_flush && !icache_is_pipt())
-		goto vipt_cache;
-
 	while (size) {
 		void *va = kmap_atomic_pfn(pfn);
 
-		if (need_flush)
-			kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
 
 		if (icache_is_pipt())
 			__cpuc_coherent_user_range((unsigned long)va,
@@ -227,7 +221,6 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
 		kunmap_atomic(va);
 	}
 
-vipt_cache:
 	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index aeddd28b3595..92fd2c8a9af0 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
 #define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+#define pmd_present(pmd)	(pmd_val(pmd))
 
 #define copy_pmd(pmdpd,pmdps)		\
 	do {				\
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a745a2a53853..fd929b5ded9e 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -212,6 +212,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 						: !!(pmd_val(pmd) & (val)))
 #define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
 
+#define pmd_present(pmd)	(pmd_isset((pmd), L_PMD_SECT_VALID))
 #define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 #define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -257,10 +258,10 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 #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 */
+/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 {
-	return __pmd(0);
+	return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 348caabb7625..d62204060cbe 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index d2d00424f044..599c950468fc 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -73,7 +73,6 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 				   perf_event_v7.o
-CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 obj-$(CONFIG_VDSO)		+= vdso.o
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 65addcbf5b30..b3b950fc8ea0 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -87,6 +87,8 @@ void __init arm_dt_init_cpu_maps(void)
 		return;
 
 	for_each_child_of_node(cpus, cpu) {
+		const __be32 *cell;
+		int prop_bytes;
 		u32 hwid;
 
 		if (of_node_cmp(cpu->type, "cpu"))
@@ -98,7 +100,8 @@ void __init arm_dt_init_cpu_maps(void)
 		 * properties is considered invalid to build the
 		 * cpu_logical_map.
 		 */
-		if (of_property_read_u32(cpu, "reg", &hwid)) {
+		cell = of_get_property(cpu, "reg", &prop_bytes);
+		if (!cell || prop_bytes < sizeof(*cell)) {
 			pr_debug(" * %s missing reg property\n",
 				     cpu->full_name);
 			of_node_put(cpu);
@@ -106,10 +109,15 @@ void __init arm_dt_init_cpu_maps(void)
 		}
 
 		/*
-		 * 8 MSBs must be set to 0 in the DT since the reg property
+		 * Bits n:24 must be set to 0 in the DT since the reg property
 		 * defines the MPIDR[23:0].
 		 */
-		if (hwid & ~MPIDR_HWID_BITMASK) {
+		do {
+			hwid = be32_to_cpu(*cell++);
+			prop_bytes -= sizeof(*cell);
+		} while (!hwid && prop_bytes > 0);
+
+		if (prop_bytes || (hwid & ~MPIDR_HWID_BITMASK)) {
 			of_node_put(cpu);
 			return;
 		}
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 6284779d64ee..abcbea1ae30b 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1066,6 +1066,22 @@ static int __init arch_hw_breakpoint_init(void)
 		return 0;
 	}
 
+	/*
+	 * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+	 * whenever a WFI is issued, even if the core is not powered down, in
+	 * violation of the architecture.  When DBGPRSR.SPD is set, accesses to
+	 * breakpoint and watchpoint registers are treated as undefined, so
+	 * this results in boot time and runtime failures when these are
+	 * accessed and we unexpectedly take a trap.
+	 *
+	 * It's not clear if/how this can be worked around, so we blacklist
+	 * Scorpion CPUs to avoid these issues.
+	*/
+	if (read_cpuid_part() == ARM_CPU_PART_SCORPION) {
+		pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+		return 0;
+	}
+
 	has_ossr = core_has_os_save_restore();
 
 	/* Determine how many BRPs/WRPs are available. */
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
index 8153e36b2491..7c9248b74d3f 100644
--- a/arch/arm/kernel/pj4-cp0.c
+++ b/arch/arm/kernel/pj4-cp0.c
@@ -66,9 +66,13 @@ static void __init pj4_cp_access_write(u32 value)
 
 	__asm__ __volatile__ (
 		"mcr	p15, 0, %1, c1, c0, 2\n\t"
+#ifdef CONFIG_THUMB2_KERNEL
+		"isb\n\t"
+#else
 		"mrc	p15, 0, %0, c1, c0, 2\n\t"
 		"mov	%0, %0\n\t"
 		"sub	pc, pc, #4\n\t"
+#endif
 		: "=r" (temp) : "r" (value));
 }
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f7462e..d54c53b7ab63 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs newregs;
+	struct pt_regs newregs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &newregs,
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 2e72be4f623e..7cb079e74010 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -9,6 +9,7 @@
  */
 #include <linux/preempt.h>
 #include <linux/smp.h>
+#include <linux/uaccess.h>
 
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
@@ -40,8 +41,11 @@ static inline void ipi_flush_tlb_mm(void *arg)
 static inline void ipi_flush_tlb_page(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_page(void *arg)
@@ -54,8 +58,11 @@ static inline void ipi_flush_tlb_kernel_page(void *arg)
 static inline void ipi_flush_tlb_range(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_range(void *arg)
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 087acb569b63..5f221acd21ae 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
 	mm_segment_t fs;
 	long ret, err, i;
 
-	if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+	if (maxevents <= 0 ||
+			maxevents > (INT_MAX/sizeof(*kbuf)) ||
+			maxevents > (INT_MAX/sizeof(*events)))
 		return -EINVAL;
+	if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+		return -EFAULT;
 	kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
 	if (!kbuf)
 		return -ENOMEM;
@@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 
 	if (nsops < 1 || nsops > SEMOPM)
 		return -EINVAL;
+	if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+		return -EFAULT;
 	sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
 	if (!sops)
 		return -ENOMEM;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index e06fd299de08..d7bef2144760 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -155,8 +155,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
-	kvm_free_stage2_pgd(kvm);
-
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_arch_vcpu_free(kvm->vcpus[i]);
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 3988e72d16ff..bfc5aae0c280 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -110,7 +110,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -118,8 +117,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	isb
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 61d96a645ff3..e8835d4e173c 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -300,6 +300,14 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
 			unmap_puds(kvm, pgd, addr, next);
+		/*
+		 * If we are dealing with a large range in
+		 * stage2 table, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector
+		 * warnings.
+		 */
+		if (kvm && (next != end))
+			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -738,6 +746,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
  */
 static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 {
+	assert_spin_locked(&kvm->mmu_lock);
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
@@ -796,6 +805,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
+	down_read(&current->mm->mmap_sem);
 	spin_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
@@ -803,6 +813,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 		stage2_unmap_memslot(kvm, memslot);
 
 	spin_unlock(&kvm->mmu_lock);
+	up_read(&current->mm->mmap_sem);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -813,21 +824,25 @@ void stage2_unmap_vm(struct kvm *kvm)
  * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all
  * underlying level-2 and level-3 tables before freeing the actual level-1 table
  * and setting the struct pointer to NULL.
- *
- * Note we don't need locking here as this is only called when the VM is
- * destroyed, which can only be done once.
  */
 void kvm_free_stage2_pgd(struct kvm *kvm)
 {
-	if (kvm->arch.pgd == NULL)
-		return;
+	void *pgd = NULL;
+	void *hwpgd = NULL;
 
-	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(kvm->arch.pgd);
+	spin_lock(&kvm->mmu_lock);
+	if (kvm->arch.pgd) {
+		unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+		pgd = READ_ONCE(kvm->arch.pgd);
+		hwpgd = kvm_get_hwpgd(kvm);
+		kvm->arch.pgd = NULL;
+	}
+	spin_unlock(&kvm->mmu_lock);
 
-	kvm->arch.pgd = NULL;
+	if (hwpgd)
+		kvm_free_hwpgd(hwpgd);
+	if (KVM_PREALLOC_LEVEL > 0 && pgd)
+		kfree(pgd);
 }
 
 static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -855,6 +870,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (pud_none(*pud)) {
 		if (!cache)
 			return NULL;
@@ -886,11 +904,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
 
 	old_pmd = *pmd;
-	kvm_set_pmd(pmd, *new_pmd);
-	if (pmd_present(old_pmd))
+	if (pmd_present(old_pmd)) {
+		pmd_clear(pmd);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pmd));
+	}
+
+	kvm_set_pmd(pmd, *new_pmd);
 	return 0;
 }
 
@@ -939,12 +960,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 
 	/* Create 2nd stage page table mapping - Level 3 */
 	old_pte = *pte;
-	kvm_set_pte(pte, *new_pte);
-	if (pte_present(old_pte))
+	if (pte_present(old_pte)) {
+		kvm_set_pte(pte, __pte(0));
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pte));
+	}
 
+	kvm_set_pte(pte, *new_pte);
 	return 0;
 }
 
@@ -1607,12 +1630,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
 }
@@ -1754,6 +1781,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
 		return -EFAULT;
 
+	down_read(&current->mm->mmap_sem);
 	/*
 	 * A memory region could potentially cover multiple VMAs, and any holes
 	 * between them, so iterate over all of them to find out if we can map
@@ -1797,8 +1825,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
-			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
-				return -EINVAL;
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
 
 			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
 						    vm_end - vm_start,
@@ -1810,7 +1840,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	} while (hva < reg_end);
 
 	if (change == KVM_MR_FLAGS_ONLY)
-		return ret;
+		goto out;
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
@@ -1818,6 +1848,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
+out:
+	up_read(&current->mm->mmap_sem);
 	return ret;
 }
 
@@ -1847,6 +1879,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
+	kvm_free_stage2_pgd(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index a9b3b905e661..443db0c43d7c 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -208,9 +208,10 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
-	int ret = 1;
+	struct kvm *kvm = vcpu->kvm;
 	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
+	int ret = 1;
 
 	switch (psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
@@ -230,7 +231,9 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	case PSCI_0_2_FN_CPU_ON:
 	case PSCI_0_2_FN64_CPU_ON:
+		mutex_lock(&kvm->lock);
 		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
 		break;
 	case PSCI_0_2_FN_AFFINITY_INFO:
 	case PSCI_0_2_FN64_AFFINITY_INFO:
@@ -279,6 +282,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
@@ -288,7 +292,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:
+		mutex_lock(&kvm->lock);
 		val = kvm_psci_vcpu_on(vcpu);
+		mutex_unlock(&kvm->lock);
 		break;
 	default:
 		val = PSCI_RET_NOT_SUPPORTED;
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 8ecfd15c3a02..df73914e81c8 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -67,7 +67,7 @@ ENTRY(__get_user_4)
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	check_uaccess r0, 8, r1, r2, __get_user_bad
+	check_uaccess r0, 8, r1, r2, __get_user_bad8
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(ldr)	r2, [r0]
 6: TUSER(ldr)	r3, [r0, #4]
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 23726fb31741..d687f860a2da 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -286,6 +286,22 @@ static void at91_ddr_standby(void)
 		at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1);
 }
 
+static void sama5d3_ddr_standby(void)
+{
+	u32 lpr0;
+	u32 saved_lpr0;
+
+	saved_lpr0 = at91_ramc_read(0, AT91_DDRSDRC_LPR);
+	lpr0 = saved_lpr0 & ~AT91_DDRSDRC_LPCB;
+	lpr0 |= AT91_DDRSDRC_LPCB_POWER_DOWN;
+
+	at91_ramc_write(0, AT91_DDRSDRC_LPR, lpr0);
+
+	cpu_do_idle();
+
+	at91_ramc_write(0, AT91_DDRSDRC_LPR, saved_lpr0);
+}
+
 /* We manage both DDRAM/SDRAM controllers, we need more than one value to
  * remember.
  */
@@ -320,7 +336,7 @@ static const struct of_device_id const ramc_ids[] __initconst = {
 	{ .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby },
 	{ .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby },
 	{ .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby },
-	{ .compatible = "atmel,sama5d3-ddramc", .data = at91_ddr_standby },
+	{ .compatible = "atmel,sama5d3-ddramc", .data = sama5d3_ddr_standby },
 	{ /*sentinel*/ }
 };
 
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 47905a50e075..318394ed5c7a 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -220,13 +220,13 @@ static void cns3xxx_write_config(struct cns3xxx_pcie *cnspci,
 	u32 mask = (0x1ull << (size * 8)) - 1;
 	int shift = (where % 4) * 8;
 
-	v = readl_relaxed(base + (where & 0xffc));
+	v = readl_relaxed(base);
 
 	v &= ~(mask << shift);
 	v |= (val & mask) << shift;
 
-	writel_relaxed(v, base + (where & 0xffc));
-	readl_relaxed(base + (where & 0xffc));
+	writel_relaxed(v, base);
+	readl_relaxed(base);
 }
 
 static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci)
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 676997895e13..f5f81a107309 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -298,6 +298,16 @@ static struct clk emac_clk = {
 	.gpsc		= 1,
 };
 
+/*
+ * In order to avoid adding the emac_clk to the clock lookup table twice (and
+ * screwing up the linked list in the process) create a separate clock for
+ * mdio inheriting the rate from emac_clk.
+ */
+static struct clk mdio_clk = {
+	.name		= "mdio",
+	.parent		= &emac_clk,
+};
+
 static struct clk mcasp_clk = {
 	.name		= "mcasp",
 	.parent		= &pll0_sysclk2,
@@ -462,7 +472,7 @@ static struct clk_lookup da850_clks[] = {
 	CLK(NULL,		"arm",		&arm_clk),
 	CLK(NULL,		"rmii",		&rmii_clk),
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
-	CLK("davinci_mdio.0",	"fck",		&emac_clk),
+	CLK("davinci_mdio.0",	"fck",		&mdio_clk),
 	CLK("davinci-mcasp.0",	NULL,		&mcasp_clk),
 	CLK("da8xx_lcdc.0",	"fck",		&lcdc_clk),
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 3a10f1a8317a..bfd8bb371477 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -26,6 +26,7 @@ menuconfig ARCH_EXYNOS
 	select S5P_DEV_MFC
 	select SRAM
 	select THERMAL
+	select THERMAL_OF
 	select MFD_SYSCON
 	help
 	  Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5)
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 7c21760f590f..875a2bab64f6 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 			if (IS_ERR(pd->clk[i]))
 				break;
 
-			if (IS_ERR(pd->clk[i]))
+			if (IS_ERR(pd->pclk[i]))
 				continue; /* Skip on first power up */
 			if (clk_set_parent(pd->clk[i], pd->pclk[i]))
 				pr_err("%s: error setting parent to clock%d\n",
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index acaf7056efa5..e08d02667c81 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev)
 static void __init imx6ul_enet_phy_init(void)
 {
 	if (IS_BUILTIN(CONFIG_PHYLIB))
-		phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff,
+		phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK,
 					   ksz8081_phy_fixup);
 }
 
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 4470376af5f8..a19d20f23e71 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -295,7 +295,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
 		val &= ~BM_CLPCR_SBYOS;
 		if (cpu_is_imx6sl())
 			val |= BM_CLPCR_BYPASS_PMIC_READY;
-		if (cpu_is_imx6sl() || cpu_is_imx6sx())
+		if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
 			val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
 		else
 			val |= BM_CLPCR_BYP_MMDC_CH1_LPM_HS;
@@ -310,7 +310,7 @@ int imx6_set_lpm(enum mxc_cpu_pwr_mode mode)
 		val |= 0x3 << BP_CLPCR_STBY_COUNT;
 		val |= BM_CLPCR_VSTBY;
 		val |= BM_CLPCR_SBYOS;
-		if (cpu_is_imx6sl())
+		if (cpu_is_imx6sl() || cpu_is_imx6sx())
 			val |= BM_CLPCR_BYPASS_PMIC_READY;
 		if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
 			val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 55348ee5a352..feed36b32ff6 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -162,22 +162,16 @@ exit:
 }
 
 /*
- * This ioremap hook is used on Armada 375/38x to ensure that PCIe
- * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This
- * is needed as a workaround for a deadlock issue between the PCIe
- * interface and the cache controller.
+ * This ioremap hook is used on Armada 375/38x to ensure that all MMIO
+ * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is
+ * needed for the HW I/O coherency mechanism to work properly without
+ * deadlock.
  */
 static void __iomem *
-armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
-			      unsigned int mtype, void *caller)
+armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
+			 unsigned int mtype, void *caller)
 {
-	struct resource pcie_mem;
-
-	mvebu_mbus_get_pcie_mem_aperture(&pcie_mem);
-
-	if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end)
-		mtype = MT_UNCACHED;
-
+	mtype = MT_UNCACHED;
 	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
 
@@ -186,7 +180,7 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
 	struct device_node *cache_dn;
 
 	coherency_cpu_base = of_iomap(np, 0);
-	arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
+	arch_ioremap_caller = armada_wa_ioremap_caller;
 
 	/*
 	 * We should switch the PL310 to I/O coherency mode only if
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index aa7b379e2661..2a3db0bd9e15 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -34,6 +34,7 @@
 #include "pm.h"
 #include "control.h"
 #include "common.h"
+#include "soc.h"
 
 /* Mach specific information to be recorded in the C-state driver_data */
 struct omap3_idle_statedata {
@@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = {
 	.safe_state_index = 0,
 };
 
+/*
+ * Numbers based on measurements made in October 2009 for PM optimized kernel
+ * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP,
+ * and worst case latencies).
+ */
+static struct cpuidle_driver omap3430_idle_driver = {
+	.name             = "omap3430_idle",
+	.owner            = THIS_MODULE,
+	.states = {
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 110 + 162,
+			.target_residency = 5,
+			.name		  = "C1",
+			.desc		  = "MPU ON + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 106 + 180,
+			.target_residency = 309,
+			.name		  = "C2",
+			.desc		  = "MPU ON + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 107 + 410,
+			.target_residency = 46057,
+			.name		  = "C3",
+			.desc		  = "MPU RET + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 121 + 3374,
+			.target_residency = 46057,
+			.name		  = "C4",
+			.desc		  = "MPU OFF + CORE ON",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 855 + 1146,
+			.target_residency = 46057,
+			.name		  = "C5",
+			.desc		  = "MPU RET + CORE RET",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 7580 + 4134,
+			.target_residency = 484329,
+			.name		  = "C6",
+			.desc		  = "MPU OFF + CORE RET",
+		},
+		{
+			.enter		  = omap3_enter_idle_bm,
+			.exit_latency	  = 7505 + 15274,
+			.target_residency = 484329,
+			.name		  = "C7",
+			.desc		  = "MPU OFF + CORE OFF",
+		},
+	},
+	.state_count = ARRAY_SIZE(omap3_idle_data),
+	.safe_state_index = 0,
+};
+
 /* Public functions */
 
 /**
@@ -333,5 +397,8 @@ int __init omap3_idle_init(void)
 	if (!mpu_pd || !core_pd || !per_pd || !cam_pd)
 		return -ENODEV;
 
-	return cpuidle_register(&omap3_idle_driver, NULL);
+	if (cpu_is_omap3430())
+		return cpuidle_register(&omap3430_idle_driver, NULL);
+	else
+		return cpuidle_register(&omap3_idle_driver, NULL);
 }
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 3eaeaca5da05..3a911d8dea8b 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -368,6 +368,7 @@ void __init omap5_map_io(void)
 void __init dra7xx_map_io(void)
 {
 	iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc));
+	omap_barriers_init();
 }
 #endif
 /*
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index 6d1dffca6c7b..748dde9fa4a5 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -17,6 +17,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <asm/assembler.h>
 
 #include "omap44xx.h"
 
@@ -56,7 +57,7 @@ wait_2:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	cmp	r0, r4
 	bne	wait_2
 	ldr	r12, =API_HYP_ENTRY
-	adr	r0, hyp_boot
+	badr	r0, hyp_boot
 	smc	#0
 hyp_boot:
 	b	secondary_startup
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 65024af169d3..d3c14da7d216 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -243,10 +243,9 @@ int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
 		save_state = 1;
 		break;
 	case PWRDM_POWER_RET:
-		if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE)) {
+		if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE))
 			save_state = 0;
-			break;
-		}
+		break;
 	default:
 		/*
 		 * CPUx CSWR is invalid hardware state. Also CPUx OSWR
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 8e0bd5939e5a..147c90e70b2e 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1416,9 +1416,7 @@ static void _enable_sysc(struct omap_hwmod *oh)
 	    (sf & SYSC_HAS_CLOCKACTIVITY))
 		_set_clockactivity(oh, oh->class->sysc->clockact, &v);
 
-	/* If the cached value is the same as the new value, skip the write */
-	if (oh->_sysc_cache != v)
-		_write_sysconfig(v, oh);
+	_write_sysconfig(v, oh);
 
 	/*
 	 * Set the autoidle bit only after setting the smartidle bit
@@ -1481,7 +1479,9 @@ static void _idle_sysc(struct omap_hwmod *oh)
 		_set_master_standbymode(oh, idlemode, &v);
 	}
 
-	_write_sysconfig(v, oh);
+	/* If the cached value is the same as the new value, skip the write */
+	if (oh->_sysc_cache != v)
+		_write_sysconfig(v, oh);
 }
 
 /**
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index 907a452b78ea..b31ad596be79 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -1474,6 +1474,7 @@ static void omap_hwmod_am43xx_rst(void)
 {
 	RSTCTRL(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTCTRL_OFFSET);
 	RSTCTRL(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTCTRL_OFFSET);
+	RSTST(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTST_OFFSET);
 	RSTST(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTST_OFFSET);
 }
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index aff78d5198d2..131f8967589b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -723,8 +723,20 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = {
  * display serial interface controller
  */
 
+static struct omap_hwmod_class_sysconfig omap3xxx_dsi_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
 static struct omap_hwmod_class omap3xxx_dsi_hwmod_class = {
 	.name = "dsi",
+	.sysc	= &omap3xxx_dsi_sysc,
 };
 
 static struct omap_hwmod_irq_info omap3xxx_dsi1_irqs[] = {
diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h
index 7c34c44eb0ae..babb5db5a3a4 100644
--- a/arch/arm/mach-omap2/prcm43xx.h
+++ b/arch/arm/mach-omap2/prcm43xx.h
@@ -39,6 +39,7 @@
 
 /* RM RSTST offsets */
 #define AM43XX_RM_GFX_RSTST_OFFSET			0x0014
+#define AM43XX_RM_PER_RSTST_OFFSET			0x0014
 #define AM43XX_RM_WKUP_RSTST_OFFSET			0x0014
 
 /* CM instances */
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index f86692dbcfd5..83fc403aec3c 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -496,8 +496,7 @@ void __init omap_init_time(void)
 	__omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon",
 			2, "timer_sys_ck", NULL, false);
 
-	if (of_have_populated_dt())
-		clocksource_probe();
+	clocksource_probe();
 }
 
 #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX)
@@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void)
 {
 	__omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure",
 			2, "timer_sys_ck", NULL, false);
+
+	clocksource_probe();
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
@@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void)
 {
 	__omap_sync32k_timer_init(2, "timer_sys_ck", NULL,
 			1, "timer_sys_ck", "ti,timer-alwon", true);
+
+	clocksource_probe();
 }
 #endif
 
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index 9ab8932403e5..56e55fd37d13 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -1,6 +1,7 @@
 menuconfig ARCH_SIRF
 	bool "CSR SiRF" if ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
+	select RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select NO_IOPORT_MAP
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index f6d02e4cbcda..5c87dff5d46e 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_USE_DMA | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
index 2385052b0ce1..e362f865fcd2 100644
--- a/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -41,30 +41,35 @@ static irqreturn_t cplds_irq_handler(int in_irq, void *d)
 	unsigned long pending;
 	unsigned int bit;
 
-	pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
-	for_each_set_bit(bit, &pending, CPLDS_NB_IRQ)
-		generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit));
+	do {
+		pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
+		for_each_set_bit(bit, &pending, CPLDS_NB_IRQ) {
+			generic_handle_irq(irq_find_mapping(fpga->irqdomain,
+							    bit));
+		}
+	} while (pending);
 
 	return IRQ_HANDLED;
 }
 
-static void cplds_irq_mask_ack(struct irq_data *d)
+static void cplds_irq_mask(struct irq_data *d)
 {
 	struct cplds *fpga = irq_data_get_irq_chip_data(d);
 	unsigned int cplds_irq = irqd_to_hwirq(d);
-	unsigned int set, bit = BIT(cplds_irq);
+	unsigned int bit = BIT(cplds_irq);
 
 	fpga->irq_mask &= ~bit;
 	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
-	set = readl(fpga->base + FPGA_IRQ_SET_CLR);
-	writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
 }
 
 static void cplds_irq_unmask(struct irq_data *d)
 {
 	struct cplds *fpga = irq_data_get_irq_chip_data(d);
 	unsigned int cplds_irq = irqd_to_hwirq(d);
-	unsigned int bit = BIT(cplds_irq);
+	unsigned int set, bit = BIT(cplds_irq);
+
+	set = readl(fpga->base + FPGA_IRQ_SET_CLR);
+	writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
 
 	fpga->irq_mask |= bit;
 	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
@@ -72,7 +77,8 @@ static void cplds_irq_unmask(struct irq_data *d)
 
 static struct irq_chip cplds_irq_chip = {
 	.name		= "pxa_cplds",
-	.irq_mask_ack	= cplds_irq_mask_ack,
+	.irq_ack	= cplds_irq_mask,
+	.irq_mask	= cplds_irq_mask,
 	.irq_unmask	= cplds_irq_unmask,
 	.flags		= IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE,
 };
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 13b1d4586d7d..9001312710f7 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata xcep_smc91x_info = {
-	.flags	= SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+	.flags	= SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		  SMC91X_NOWAIT | SMC91X_USE_DMA,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 44575edc44b1..cf0a7c2359f0 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -95,7 +95,8 @@ static struct smsc911x_platform_config smsc911x_config = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 };
 
 static struct platform_device realview_eth_device = {
diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c
index ff780a8d8366..9a42736ef4ac 100644
--- a/arch/arm/mach-s3c64xx/dev-audio.c
+++ b/arch/arm/mach-s3c64xx/dev-audio.c
@@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev)
 
 static struct resource s3c64xx_iis0_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_I2S0_OUT),
-	[2] = DEFINE_RES_DMA(DMACH_I2S0_IN),
 };
 
-static struct s3c_audio_pdata i2sv3_pdata = {
+static struct s3c_audio_pdata i2s0_pdata = {
 	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_I2S0_OUT,
+	.dma_capture = DMACH_I2S0_IN,
 };
 
 struct platform_device s3c64xx_device_iis0 = {
@@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = {
 	.num_resources	  = ARRAY_SIZE(s3c64xx_iis0_resource),
 	.resource	  = s3c64xx_iis0_resource,
 	.dev = {
-		.platform_data = &i2sv3_pdata,
+		.platform_data = &i2s0_pdata,
 	},
 };
 EXPORT_SYMBOL(s3c64xx_device_iis0);
 
 static struct resource s3c64xx_iis1_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_I2S1_OUT),
-	[2] = DEFINE_RES_DMA(DMACH_I2S1_IN),
+};
+
+static struct s3c_audio_pdata i2s1_pdata = {
+	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_I2S1_OUT,
+	.dma_capture = DMACH_I2S1_IN,
 };
 
 struct platform_device s3c64xx_device_iis1 = {
@@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = {
 	.num_resources	  = ARRAY_SIZE(s3c64xx_iis1_resource),
 	.resource	  = s3c64xx_iis1_resource,
 	.dev = {
-		.platform_data = &i2sv3_pdata,
+		.platform_data = &i2s1_pdata,
 	},
 };
 EXPORT_SYMBOL(s3c64xx_device_iis1);
 
 static struct resource s3c64xx_iisv4_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX),
-	[2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX),
 };
 
 static struct s3c_audio_pdata i2sv4_pdata = {
 	.cfg_gpio = s3c64xx_i2s_cfg_gpio,
+	.dma_playback = DMACH_HSI_I2SV40_TX,
+	.dma_capture = DMACH_HSI_I2SV40_RX,
 	.type = {
 		.i2s = {
 			.quirks = QUIRK_PRI_6CHAN,
@@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev)
 
 static struct resource s3c64xx_pcm0_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_PCM0_TX),
-	[2] = DEFINE_RES_DMA(DMACH_PCM0_RX),
 };
 
 static struct s3c_audio_pdata s3c_pcm0_pdata = {
 	.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+	.dma_capture = DMACH_PCM0_RX,
+	.dma_playback = DMACH_PCM0_TX,
 };
 
 struct platform_device s3c64xx_device_pcm0 = {
@@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0);
 
 static struct resource s3c64xx_pcm1_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_PCM1_TX),
-	[2] = DEFINE_RES_DMA(DMACH_PCM1_RX),
 };
 
 static struct s3c_audio_pdata s3c_pcm1_pdata = {
 	.cfg_gpio = s3c64xx_pcm_cfg_gpio,
+	.dma_playback = DMACH_PCM1_TX,
+	.dma_capture = DMACH_PCM1_RX,
 };
 
 struct platform_device s3c64xx_device_pcm1 = {
@@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev)
 
 static struct resource s3c64xx_ac97_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256),
-	[1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT),
-	[2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN),
-	[3] = DEFINE_RES_DMA(DMACH_AC97_MICIN),
-	[4] = DEFINE_RES_IRQ(IRQ_AC97),
+	[1] = DEFINE_RES_IRQ(IRQ_AC97),
 };
 
-static struct s3c_audio_pdata s3c_ac97_pdata;
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+	.dma_playback = DMACH_AC97_PCMOUT,
+	.dma_capture = DMACH_AC97_PCMIN,
+	.dma_capture_mic = DMACH_AC97_MICIN,
+};
 
 static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32);
 
diff --git a/arch/arm/mach-s3c64xx/include/mach/dma.h b/arch/arm/mach-s3c64xx/include/mach/dma.h
index 096e14073bd9..9c739eafe95c 100644
--- a/arch/arm/mach-s3c64xx/include/mach/dma.h
+++ b/arch/arm/mach-s3c64xx/include/mach/dma.h
@@ -14,38 +14,38 @@
 #define S3C64XX_DMA_CHAN(name)		((unsigned long)(name))
 
 /* DMA0/SDMA0 */
-#define DMACH_UART0		S3C64XX_DMA_CHAN("uart0_tx")
-#define DMACH_UART0_SRC2	S3C64XX_DMA_CHAN("uart0_rx")
-#define DMACH_UART1		S3C64XX_DMA_CHAN("uart1_tx")
-#define DMACH_UART1_SRC2	S3C64XX_DMA_CHAN("uart1_rx")
-#define DMACH_UART2		S3C64XX_DMA_CHAN("uart2_tx")
-#define DMACH_UART2_SRC2	S3C64XX_DMA_CHAN("uart2_rx")
-#define DMACH_UART3		S3C64XX_DMA_CHAN("uart3_tx")
-#define DMACH_UART3_SRC2	S3C64XX_DMA_CHAN("uart3_rx")
-#define DMACH_PCM0_TX		S3C64XX_DMA_CHAN("pcm0_tx")
-#define DMACH_PCM0_RX		S3C64XX_DMA_CHAN("pcm0_rx")
-#define DMACH_I2S0_OUT		S3C64XX_DMA_CHAN("i2s0_tx")
-#define DMACH_I2S0_IN		S3C64XX_DMA_CHAN("i2s0_rx")
+#define DMACH_UART0		"uart0_tx"
+#define DMACH_UART0_SRC2	"uart0_rx"
+#define DMACH_UART1		"uart1_tx"
+#define DMACH_UART1_SRC2	"uart1_rx"
+#define DMACH_UART2		"uart2_tx"
+#define DMACH_UART2_SRC2	"uart2_rx"
+#define DMACH_UART3		"uart3_tx"
+#define DMACH_UART3_SRC2	"uart3_rx"
+#define DMACH_PCM0_TX		"pcm0_tx"
+#define DMACH_PCM0_RX		"pcm0_rx"
+#define DMACH_I2S0_OUT		"i2s0_tx"
+#define DMACH_I2S0_IN		"i2s0_rx"
 #define DMACH_SPI0_TX		S3C64XX_DMA_CHAN("spi0_tx")
 #define DMACH_SPI0_RX		S3C64XX_DMA_CHAN("spi0_rx")
-#define DMACH_HSI_I2SV40_TX	S3C64XX_DMA_CHAN("i2s2_tx")
-#define DMACH_HSI_I2SV40_RX	S3C64XX_DMA_CHAN("i2s2_rx")
+#define DMACH_HSI_I2SV40_TX	"i2s2_tx"
+#define DMACH_HSI_I2SV40_RX	"i2s2_rx"
 
 /* DMA1/SDMA1 */
-#define DMACH_PCM1_TX		S3C64XX_DMA_CHAN("pcm1_tx")
-#define DMACH_PCM1_RX		S3C64XX_DMA_CHAN("pcm1_rx")
-#define DMACH_I2S1_OUT		S3C64XX_DMA_CHAN("i2s1_tx")
-#define DMACH_I2S1_IN		S3C64XX_DMA_CHAN("i2s1_rx")
+#define DMACH_PCM1_TX		"pcm1_tx"
+#define DMACH_PCM1_RX		"pcm1_rx"
+#define DMACH_I2S1_OUT		"i2s1_tx"
+#define DMACH_I2S1_IN		"i2s1_rx"
 #define DMACH_SPI1_TX		S3C64XX_DMA_CHAN("spi1_tx")
 #define DMACH_SPI1_RX		S3C64XX_DMA_CHAN("spi1_rx")
-#define DMACH_AC97_PCMOUT	S3C64XX_DMA_CHAN("ac97_out")
-#define DMACH_AC97_PCMIN	S3C64XX_DMA_CHAN("ac97_in")
-#define DMACH_AC97_MICIN	S3C64XX_DMA_CHAN("ac97_mic")
-#define DMACH_PWM		S3C64XX_DMA_CHAN("pwm")
-#define DMACH_IRDA		S3C64XX_DMA_CHAN("irda")
-#define DMACH_EXTERNAL		S3C64XX_DMA_CHAN("external")
-#define DMACH_SECURITY_RX	S3C64XX_DMA_CHAN("sec_rx")
-#define DMACH_SECURITY_TX	S3C64XX_DMA_CHAN("sec_tx")
+#define DMACH_AC97_PCMOUT	"ac97_out"
+#define DMACH_AC97_PCMIN	"ac97_in"
+#define DMACH_AC97_MICIN	"ac97_mic"
+#define DMACH_PWM		"pwm"
+#define DMACH_IRDA		"irda"
+#define DMACH_EXTERNAL		"external"
+#define DMACH_SECURITY_RX	"sec_rx"
+#define DMACH_SECURITY_TX	"sec_tx"
 
 enum dma_ch {
 	DMACH_MAX = 32
diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c
index cbf53bb9c814..0db46895c82a 100644
--- a/arch/arm/mach-sa1100/clock.c
+++ b/arch/arm/mach-sa1100/clock.c
@@ -125,6 +125,8 @@ static unsigned long clk_36864_get_rate(struct clk *clk)
 }
 
 static struct clkops clk_36864_ops = {
+	.enable		= clk_cpu_enable,
+	.disable	= clk_cpu_disable,
 	.get_rate	= clk_36864_get_rate,
 };
 
@@ -140,9 +142,8 @@ static struct clk_lookup sa11xx_clkregs[] = {
 	CLKDEV_INIT(NULL, "OSTIMER0", &clk_36864),
 };
 
-static int __init sa11xx_clk_init(void)
+int __init sa11xx_clk_init(void)
 {
 	clkdev_add_table(sa11xx_clkregs, ARRAY_SIZE(sa11xx_clkregs));
 	return 0;
 }
-core_initcall(sa11xx_clk_init);
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 345e63f4eb71..3e09beddb6e8 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -34,6 +34,7 @@
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
+#include <mach/reset.h>
 
 #include "generic.h"
 #include <clocksource/pxa.h>
@@ -95,6 +96,8 @@ static void sa1100_power_off(void)
 
 void sa11x0_restart(enum reboot_mode mode, const char *cmd)
 {
+	clear_reset_status(RESET_STATUS_ALL);
+
 	if (mode == REBOOT_SOFT) {
 		/* Jump into ROM at address 0 */
 		soft_restart(0);
@@ -388,6 +391,7 @@ void __init sa1100_init_irq(void)
 	sa11x0_init_irq_nodt(IRQ_GPIO0_SC, irq_resource.start);
 
 	sa1100_init_gpio();
+	sa11xx_clk_init();
 }
 
 /*
diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h
index 0d92e119b36b..68199b603ff7 100644
--- a/arch/arm/mach-sa1100/generic.h
+++ b/arch/arm/mach-sa1100/generic.h
@@ -44,3 +44,5 @@ int sa11x0_pm_init(void);
 #else
 static inline int sa11x0_pm_init(void) { return 0; }
 #endif
+
+int sa11xx_clk_init(void);
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 1525d7b5f1b7..88149f85bc49 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 62437b57813e..73e3adbc1330 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -41,39 +41,26 @@
 
 #define REGULATOR_IRQ_MASK	BIT(2)	/* IRQ2, active low */
 
-static void __iomem *irqc;
-
-static const u8 da9063_mask_regs[] = {
-	DA9063_REG_IRQ_MASK_A,
-	DA9063_REG_IRQ_MASK_B,
-	DA9063_REG_IRQ_MASK_C,
-	DA9063_REG_IRQ_MASK_D,
-};
-
-/* DA9210 System Control and Event Registers */
+/* start of DA9210 System Control and Event Registers */
 #define DA9210_REG_MASK_A		0x54
-#define DA9210_REG_MASK_B		0x55
-
-static const u8 da9210_mask_regs[] = {
-	DA9210_REG_MASK_A,
-	DA9210_REG_MASK_B,
-};
-
-static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
-			     unsigned int nregs)
-{
-	unsigned int i;
 
-	dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+static void __iomem *irqc;
 
-	for (i = 0; i < nregs; i++) {
-		int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
-		if (error) {
-			dev_err(&client->dev, "i2c error %d\n", error);
-			return;
-		}
-	}
-}
+/* first byte sets the memory pointer, following are consecutive reg values */
+static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff };
+static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff };
+
+static struct i2c_msg da9xxx_msgs[2] = {
+	{
+		.addr = 0x58,
+		.len = ARRAY_SIZE(da9063_irq_clr),
+		.buf = da9063_irq_clr,
+	}, {
+		.addr = 0x68,
+		.len = ARRAY_SIZE(da9210_irq_clr),
+		.buf = da9210_irq_clr,
+	},
+};
 
 static int regulator_quirk_notify(struct notifier_block *nb,
 				  unsigned long action, void *data)
@@ -93,12 +80,15 @@ static int regulator_quirk_notify(struct notifier_block *nb,
 	client = to_i2c_client(dev);
 	dev_dbg(dev, "Detected %s\n", client->name);
 
-	if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
-		da9xxx_mask_irqs(client, da9063_mask_regs,
-				 ARRAY_SIZE(da9063_mask_regs));
-	else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
-		da9xxx_mask_irqs(client, da9210_mask_regs,
-				 ARRAY_SIZE(da9210_mask_regs));
+	if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) ||
+	    (client->addr == 0x68 && !strcmp(client->name, "da9210"))) {
+		int ret;
+
+		dev_info(&client->dev, "clearing da9063/da9210 interrupts\n");
+		ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs));
+		if (ret != ARRAY_SIZE(da9xxx_msgs))
+			dev_err(&client->dev, "i2c error %d\n", ret);
+	}
 
 	mon = ioread32(irqc + IRQC_MONITOR);
 	if (mon & REGULATOR_IRQ_MASK)
diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S
index 5d94b7a2fb10..c160fa3007e9 100644
--- a/arch/arm/mach-socfpga/headsmp.S
+++ b/arch/arm/mach-socfpga/headsmp.S
@@ -13,6 +13,7 @@
 #include <asm/assembler.h>
 
 	.arch	armv7-a
+	.arm
 
 ENTRY(secondary_trampoline)
 	/* CPU1 will always fetch from 0x0 when it is brought out of reset.
diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c
index 8538910db202..a970e7fcba9e 100644
--- a/arch/arm/mach-ux500/pm.c
+++ b/arch/arm/mach-ux500/pm.c
@@ -134,8 +134,8 @@ bool prcmu_pending_irq(void)
  */
 bool prcmu_is_cpu_in_wfi(int cpu)
 {
-	return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
-		     PRCM_ARM_WFI_STANDBY_WFI0;
+	return readl(PRCM_ARM_WFI_STANDBY) &
+		(cpu ? PRCM_ARM_WFI_STANDBY_WFI1 : PRCM_ARM_WFI_STANDBY_WFI0);
 }
 
 /*
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 6f39d03cc27e..0a43143e9ceb 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -59,7 +59,7 @@ void __iomem *zynq_scu_base;
 static void __init zynq_memory_init(void)
 {
 	if (!__pa(PAGE_OFFSET))
-		memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+		memblock_reserve(__pa(PAGE_OFFSET), 0x80000);
 }
 
 static struct platform_device zynq_cpuidle_device = {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index daafcf121ce0..0d20cd594017 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -314,8 +314,11 @@ retry:
 	 * 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 ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return 0;
+	}
 
 	/*
 	 * Major/minor page fault accounting is only done on the
@@ -610,9 +613,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
 
 void __init early_abt_enable(void)
 {
-	fsr_info[22].fn = early_abort_handler;
+	fsr_info[FSR_FS_AEA].fn = early_abort_handler;
 	local_abt_enable();
-	fsr_info[22].fn = do_bad;
+	fsr_info[FSR_FS_AEA].fn = do_bad;
 }
 
 #ifndef CONFIG_ARM_LPAE
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 05ec5e0df32d..78830657cab3 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -11,11 +11,15 @@
 #define FSR_FS5_0		(0x3f)
 
 #ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA		17
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return fsr & FSR_FS5_0;
 }
 #else
+#define FSR_FS_AEA		22
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 407dc786583a..c469c0665752 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4867f5daf82c..e47cffd25c6c 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1184,15 +1184,15 @@ void __init sanity_check_meminfo(void)
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
 	/*
 	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
 	 * last full pmd, which should be mapped.
 	 */
-	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, PMD_SIZE);
-	if (!memblock_limit)
-		memblock_limit = arm_lowmem_limit;
+	memblock_limit = round_down(memblock_limit, PMD_SIZE);
 
 	memblock_set_current_limit(memblock_limit);
 }
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 82074625de5c..e212f9d804bd 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -65,6 +65,7 @@
 #include <linux/platform_data/usb-ohci-s3c2410.h>
 #include <plat/usb-phy.h>
 #include <plat/regs-spi.h>
+#include <linux/platform_data/asoc-s3c.h>
 #include <linux/platform_data/spi-s3c64xx.h>
 
 static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
@@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32);
 static struct resource s3c_ac97_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97),
 	[1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97),
-	[2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"),
-	[3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"),
-	[4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"),
+};
+
+static struct s3c_audio_pdata s3c_ac97_pdata = {
+	.dma_playback = (void *)DMACH_PCM_OUT,
+	.dma_capture = (void *)DMACH_PCM_IN,
+	.dma_capture_mic = (void *)DMACH_MIC_IN,
 };
 
 struct platform_device s3c_device_ac97 = {
@@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = {
 	.dev		= {
 		.dma_mask		= &samsung_device_dma_mask,
 		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.platform_data		= &s3c_ac97_pdata,
 	}
 };
 #endif /* CONFIG_CPU_S3C2440 */
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index fc7ea529f462..52c8c1f642fe 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -239,8 +239,7 @@ static int __init xen_guest_init(void)
 	 * for secondary CPUs as they are brought up.
 	 * For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
 	 */
-	xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
-			                       sizeof(struct vcpu_info));
+	xen_vcpu_info = alloc_percpu(struct vcpu_info);
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 96513d09d345..0df138c41bdf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -392,6 +392,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
@@ -402,6 +411,17 @@ config CAVIUM_ERRATUM_23154
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_27456
+	bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption"
+	default y
+	help
+	  On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI
+	  instructions may cause the icache to become corrupted if it
+	  contains data for a non-current ASID.  The fix is to
+	  invalidate the icache when changing the mm context.
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index cc093a482aa4..e0ee2b00d573 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -262,6 +262,8 @@
 		#io-channel-cells = <1>;
 		clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
 		clock-names = "saradc", "apb_pclk";
+		resets = <&cru SRST_SARADC>;
+		reset-names = "saradc-apb";
 		status = "disabled";
 	};
 
@@ -517,7 +519,7 @@
 		#address-cells = <0>;
 
 		reg = <0x0 0xffb71000 0x0 0x1000>,
-		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x2000>,
 		      <0x0 0xffb74000 0x0 0x2000>,
 		      <0x0 0xffb76000 0x0 0x2000>;
 		interrupts = <GIC_PPI 9
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
index ce5d848251fa..7b34822d61e9 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
@@ -26,7 +26,7 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x0 0x0 0x40000000>;
 	};
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 857eda5c7217..172402cc1a0f 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -71,7 +71,7 @@
 			     <1 10 0xf01>;
 	};
 
-	amba_apu {
+	amba_apu: amba_apu@0 {
 		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <1>;
@@ -191,7 +191,7 @@
 		};
 
 		i2c0: i2c@ff020000 {
-			compatible = "cdns,i2c-r1p10";
+			compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 17 4>;
@@ -202,7 +202,7 @@
 		};
 
 		i2c1: i2c@ff030000 {
-			compatible = "cdns,i2c-r1p10";
+			compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 18 4>;
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index a2a7fbcacc14..3363560c79b7 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 	.text
 	.arch	armv8-a+crypto
@@ -19,7 +20,7 @@
 	 */
 ENTRY(ce_aes_ccm_auth_data)
 	ldr	w8, [x3]			/* leftover from prev round? */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cbz	w8, 1f
 	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
@@ -31,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	8f				/* out of input? */
 	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.2d}, [x4]			/* load first round key */
+1:	ld1	{v3.16b}, [x4]			/* load first round key */
 	prfm	pldl1strm, [x1]
 	cmp	w5, #12				/* which key size? */
 	add	x6, x4, #16
@@ -41,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
 	mov	v5.16b, v3.16b
 	b	4f
 2:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [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 */
+4:	ld1	{v3.16b}, [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 */
+5:	ld1	{v4.16b}, [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 */
+	ld1	{v5.16b}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
 	subs	w2, w2, #16			/* last data? */
@@ -60,7 +61,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	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 */
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
 	adds	w2, w2, #16
 	beq	10f
@@ -79,7 +80,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.2d}, [x0]
+	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
@@ -89,27 +90,27 @@ ENDPROC(ce_aes_ccm_auth_data)
 	 * 			 u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_final)
-	ld1	{v3.2d}, [x2], #16		/* load first round key */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v3.16b}, [x2], #16		/* load first round key */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cmp	w3, #12				/* which key size? */
 	sub	w3, w3, #2			/* modified # of rounds */
-	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	ld1	{v1.16b}, [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 */
+1:	ld1	{v5.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+2:	ld1	{v3.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+3:	ld1	{v4.16b}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
@@ -120,47 +121,47 @@ ENTRY(ce_aes_ccm_final)
 	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 */
+	st1	{v0.16b}, [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 */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	ld1	{v1.8b}, [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 */
+	ld1	{v3.16b}, [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 */
+	ld1	{v5.16b}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+3:	ld1	{v3.16b}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+4:	ld1	{v4.16b}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
-	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	ld1	{v5.16b}, [x10], #16		/* load next round key */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
@@ -177,14 +178,14 @@ ENDPROC(ce_aes_ccm_final)
 	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 */
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [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 */
+	st1	{v0.16b}, [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 */
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index f7bd9bf0bbb3..50d9fe11d0c8 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -47,24 +47,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[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		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aese	v0.16b, v2.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aese	v0.16b, v3.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aese	v0.16b, v1.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aese	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -92,24 +92,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[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		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aesd	v0.16b, v2.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aesd	v0.16b, v3.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aesd	v0.16b, v1.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aesd	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -173,7 +173,12 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+#else
+		rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
+			 rki[0];
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 78f3cfe92c08..b46093d567e5 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -10,6 +10,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(ce_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 05d9e16c0dfd..6a51dfccfe71 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -211,7 +211,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		err = blkcipher_walk_done(desc, &walk,
 					  walk.nbytes % AES_BLOCK_SIZE);
 	}
-	if (nbytes) {
+	if (walk.nbytes % AES_BLOCK_SIZE) {
 		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];
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index f6e372c528eb..838dad5c209f 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
 	cbz		w6, .Lcbcencloop
 
 	ld1		{v0.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x5
+	enc_prepare	w3, x2, x6
 
 .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
+	encrypt_block	v0, w3, x2, x6, w7
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
+	st1		{v0.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	cbz		w6, .LcbcdecloopNx
 
 	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x5
+	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
 #if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
 .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
+	decrypt_block	v0, w3, x2, x6, w7
 	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
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	bne		.Lcbcdecloop
 .Lcbcdecout:
 	FRAME_POP
+	st1		{v7.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
 
 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:
+	cbz		w6, .Lctrnotfirst	/* 1st time around? */
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
+
+.Lctrnotfirst:
+	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x8, x8
 #if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
+	cmn		w8, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
 	subs		w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
 #if INTERLEAVE == 2
 	mov		v0.8b, v4.8b
 	mov		v1.8b, v4.8b
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v0.d[1], x7
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v1.d[1], x7
 	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
 	do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
 	st1		{v0.16b-v1.16b}, [x0], #32
 #else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w5
+	dup		v7.4s, w8
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
 	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
+	add		x8, x8, #INTERLEAVE
 #endif
-	cbz		w4, .LctroutNx
-.LctrincNx:
-	rev		x7, x5
+	rev		x7, x8
 	ins		v4.d[1], x7
+	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.LctroutNx:
-	sub		x5, x5, #1
-	rev		x7, x5
-	ins		v4.d[1], x7
-	b		.Lctrout
 .Lctr1x:
 	adds		w4, w4, #INTERLEAVE
 	beq		.Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
 .Lctrloop:
 	mov		v0.16b, v4.16b
 	encrypt_block	v0, w3, x2, x6, w7
+
+	adds		x8, x8, #1		/* increment BE ctr */
+	rev		x7, x8
+	ins		v4.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
 	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
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{v4.16b}, [x5]		/* return next CTR value */
+	FRAME_POP
+	ret
+
 .Lctrhalfblock:
 	ld1		{v3.8b}, [x1]
 	eor		v3.8b, v0.8b, v3.8b
 	st1		{v3.8b}, [x0]
-.Lctrout:
 	FRAME_POP
 	ret
+
+.Lctrcarry:
+	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		.Lctrcarrydone
 AES_ENDPROC(aes_ctr_encrypt)
 	.ltorg
 
@@ -386,7 +382,8 @@ AES_ENDPROC(aes_ctr_encrypt)
 	.endm
 
 .Lxts_mul_x:
-	.word		1, 0, 0x87, 0
+CPU_LE(	.quad		1, 0x87		)
+CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
 	FRAME_PUSH
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index b93170e1cc93..85f07ead7c5c 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(neon_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
@@ -83,13 +84,13 @@
 	.endm
 
 	.macro		do_block, enc, in, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\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
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -229,7 +230,7 @@
 	.endm
 
 	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -237,7 +238,7 @@
 	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
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -254,7 +255,7 @@
 	.endm
 
 	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -266,7 +267,7 @@
 	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
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -306,12 +307,16 @@
 	.text
 	.align		4
 .LForward_ShiftRows:
-	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
-	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+CPU_LE(	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3	)
+CPU_LE(	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb	)
+CPU_BE(	.byte		0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8	)
+CPU_BE(	.byte		0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0	)
 
 .LReverse_ShiftRows:
-	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
-	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+CPU_LE(	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb	)
+CPU_LE(	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3	)
+CPU_BE(	.byte		0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8	)
+CPU_BE(	.byte		0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0	)
 
 .LForward_Sbox:
 	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index dc457015884e..f0bb9f0b524f 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -29,8 +29,8 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{SHASH.16b}, [x3]
-	ld1		{XL.16b}, [x1]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	shl		MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.16b}, [x1]
+	st1		{XL.2d}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 033aae6d732a..c98e7e849f06 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -78,7 +78,7 @@ ENTRY(sha1_ce_transform)
 	ld1r		{k3.4s}, [x6]
 
 	/* load state */
-	ldr		dga, [x0]
+	ld1		{dgav.4s}, [x0]
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
@@ -144,7 +144,7 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	b		1b
 
 	/* store new state */
-3:	str		dga, [x0]
+3:	st1		{dgav.4s}, [x0]
 	str		dgb, [x0, #16]
 	ret
 ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 5df9d9d470ad..01cfee066837 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -85,7 +85,7 @@ ENTRY(sha2_ce_transform)
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ldp		dga, dgb, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
@@ -148,6 +148,6 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	b		1b
 
 	/* store new state */
-3:	stp		dga, dgb, [x0]
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
 	ret
 ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index caafd63b8092..40d1351e7573 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -22,9 +22,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
 
-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 000000000000..be2d2347d995
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+/*
+ * Remove the address tag from a virtual address, if present.
+ */
+	.macro	clear_address_tag, dst, addr
+	tst	\addr, #(1 << 55)
+	bic	\dst, \addr, #(0xff << 56)
+	csel	\dst, \dst, \addr, eq
+	.endm
+
+#endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 9622eb48f894..f2d2c0bbe21b 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -41,23 +41,33 @@
 
 #define smp_store_release(p, v)						\
 do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (__force typeof(*p)) (v) }; 			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u8 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u16 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u32 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u64 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	}								\
 } while (0)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 9ea611ea69df..91ceeb7b4530 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -49,7 +49,7 @@ static inline unsigned long __xchg_case_##name(unsigned long x,		\
 	"	swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n"	\
 	"	nop\n"							\
 	"	" #nop_lse)						\
-	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)			\
+	: "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr)	\
 	: "r" (x)							\
 	: cl);								\
 									\
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8f271b83f910..8884b5d5f48c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,9 @@
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
+#define ARM64_WORKAROUND_CAVIUM_27456		8
 
-#define ARM64_NCAPS				8
+#define ARM64_NCAPS				9
 
 #ifndef __ASSEMBLY__
 
@@ -76,7 +77,7 @@ struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
-	void (*enable)(void *);		/* Called on all active CPUs */
+	int (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index faad6df49e5b..329c127e13dc 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -120,12 +120,11 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
 /*
- * This is the location that an ET_DYN program is loaded if exec'ed.  Typical
- * use of this is to invoke "./ld.so someprog" to test out a new version of
- * the loader.  We need to make sure that it is out of the way of the program
- * that it will "exec", and that there is sufficient room for the brk.
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
  */
-#define ELF_ET_DYN_BASE	(2 * TASK_SIZE_64 / 3)
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE_64 / 3)
 
 /*
  * When the program starts, a1 contains a pointer to a function to be
@@ -136,6 +135,7 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 
 #define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);
 
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
 do {									\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
@@ -156,15 +156,16 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
-#define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
+#ifdef CONFIG_COMPAT
+
+/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
+#define COMPAT_ELF_ET_DYN_BASE		0x000400000UL
 
 /* AArch32 registers. */
 #define COMPAT_ELF_NGREG		18
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 007a69fc4f40..5f3ab8c1db55 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -121,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -137,6 +138,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 "	.align	3\n"
 "	.quad	1b, 4b, 2b, 4b\n"
 "	.popsection\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5e6857b6bdc4..2d960f8588b0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,8 +107,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 61505676d085..819b21a9851c 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -236,8 +236,7 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
 {
 	void *va = page_address(pfn_to_page(pfn));
 
-	if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
-		kvm_flush_dcache_to_poc(va, size);
+	kvm_flush_dcache_to_poc(va, size);
 
 	if (!icache_is_aliasing()) {		/* PIPT */
 		flush_icache_range((unsigned long)va,
diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h
index 4e603ea36ad3..123f45d92cd1 100644
--- a/arch/arm64/include/asm/opcodes.h
+++ b/arch/arm64/include/asm/opcodes.h
@@ -1 +1,5 @@
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN
+#endif
+
 #include <../../arm/include/asm/opcodes.h>
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 0a456bef8c79..8a336852eeba 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 									\
 	switch (size) {							\
 	case 1:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_1\n"			\
-			"ldxrb	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_1\n"				\
+		"1:	ldxrb	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u8 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u8 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 2:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_2\n"			\
-			"ldxrh	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_2\n"				\
+		"1:	ldxrh	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr]  "+Q"(*(u16 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr]  "+Q"(*(u16 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 4:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_4\n"			\
-			"ldxr	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_4\n"				\
+		"1:	ldxr	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u32 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u32 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 8:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_8\n"			\
-			"ldxr	  %[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_8\n"				\
+		"1:	ldxr	  %[ret], %[ptr]\n"			\
 			#asm_op " %[ret], %[ret], %[val]\n"		\
-			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u64 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u64 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 
 	switch (size) {
 	case 1:
-		do {
-			asm ("//__percpu_xchg_1\n"
-			"ldxrb %w[ret], %[ptr]\n"
-			"stxrb %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u8 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_1\n"
+		"1:	ldxrb	%w[ret], %[ptr]\n"
+		"	stxrb	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u8 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 2:
-		do {
-			asm ("//__percpu_xchg_2\n"
-			"ldxrh %w[ret], %[ptr]\n"
-			"stxrh %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u16 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_2\n"
+		"1:	ldxrh	%w[ret], %[ptr]\n"
+		"	stxrh	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u16 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 4:
-		do {
-			asm ("//__percpu_xchg_4\n"
-			"ldxr %w[ret], %[ptr]\n"
-			"stxr %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u32 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_4\n"
+		"1:	ldxr	%w[ret], %[ptr]\n"
+		"	stxr	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u32 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 8:
-		do {
-			asm ("//__percpu_xchg_8\n"
-			"ldxr %[ret], %[ptr]\n"
-			"stxr %w[loop], %[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u64 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_8\n"
+		"1:	ldxr	%[ret], %[ptr]\n"
+		"	stxr	%w[loop], %[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u64 *)ptr)
+		: [val] "r" (val));
 		break;
 	default:
 		BUILD_BUG();
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e836f7b..b9da9545b442 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -117,7 +117,6 @@
  * Section
  */
 #define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE	(_AT(pmdval_t, 1) << 58)
 #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)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index eaa9cabf4066..67c2ad6d33b7 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -69,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -83,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -155,6 +155,7 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -165,8 +166,6 @@ extern struct page *empty_zero_page;
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
@@ -264,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (pte_valid_user(pte)) {
-		if (!pte_special(pte) && pte_exec(pte))
-			__sync_icache_dcache(pte, addr);
+	if (pte_present(pte)) {
 		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
+		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+			__sync_icache_dcache(pte, addr);
 	}
 
 	/*
@@ -348,6 +347,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -356,7 +356,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
@@ -395,7 +395,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				     unsigned long size, pgprot_t vma_prot);
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
 #define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
 
@@ -539,6 +538,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 
 #ifdef CONFIG_ARM64_HW_AFDBM
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+#endif
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -591,9 +605,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
 }
@@ -641,6 +655,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
  *	bits 0-1:	present (must be zero)
  *	bits 2-7:	swap type
  *	bits 8-57:	swap offset
+ *	bit  58:	PTE_PROT_NONE (must be zero)
  */
 #define __SWP_TYPE_SHIFT	2
 #define __SWP_TYPE_BITS		6
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 4acb7ca94fcd..d08559528927 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
+int cpu_enable_pan(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index e9e5467e0bf4..7f94755089e2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -58,6 +58,7 @@
 #define COMPAT_PSR_Z_BIT	0x40000000
 #define COMPAT_PSR_N_BIT	0x80000000
 #define COMPAT_PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+#define COMPAT_PSR_GE_MASK	0x000f0000
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define COMPAT_PSR_ENDSTATE	COMPAT_PSR_E_BIT
@@ -116,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)
@@ -151,35 +154,9 @@ 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
- * security in signal handlers)
- */
-static inline int valid_user_regs(struct user_pt_regs *regs)
-{
-	if (user_mode(regs) && (regs->pstate & PSR_I_BIT) == 0) {
-		regs->pstate &= ~(PSR_F_BIT | PSR_A_BIT);
-
-		/* The T bit is reserved for AArch64 */
-		if (!(regs->pstate & PSR_MODE32_BIT))
-			regs->pstate &= ~COMPAT_PSR_T_BIT;
-
-		return 1;
-	}
-
-	/*
-	 * Force PSR to something logical...
-	 */
-	regs->pstate &= PSR_f | PSR_s | (PSR_x & ~PSR_A_BIT) | \
-			COMPAT_PSR_T_BIT | PSR_MODE32_BIT;
-
-	if (!(regs->pstate & PSR_MODE32_BIT)) {
-		regs->pstate &= ~COMPAT_PSR_T_BIT;
-		regs->pstate |= PSR_MODE_EL0t;
-	}
-
-	return 0;
-}
+/* We must avoid circular header include via sched.h */
+struct task_struct;
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
 
 #define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index c85e96d174a5..499e8de33a00 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -312,4 +312,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock()	smp_mb()
+
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index b2ede967fe7d..829fa6d3e561 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -21,6 +21,7 @@
 /*
  * User space memory access functions
  */
+#include <linux/bitops.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
@@ -92,16 +93,24 @@ static inline void set_fs(mm_segment_t fs)
  */
 #define __range_ok(addr, size)						\
 ({									\
+	unsigned long __addr = (unsigned long __force)(addr);		\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"		\
 		: "=&r" (flag), "=&r" (roksum)				\
-		: "1" (addr), "Ir" (size),				\
+		: "1" (__addr), "Ir" (size),				\
 		  "r" (current_thread_info()->addr_limit)		\
 		: "cc");						\
 	flag;								\
 })
 
+/*
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
+ * pass on to access_ok(), for instance.
+ */
+#define untagged_addr(addr)		sign_extend64(addr, 55)
+
 #define access_ok(type, addr, size)	__range_ok(addr, size)
 #define user_addr_max			get_fs
 
diff --git a/arch/arm64/include/uapi/asm/auxvec.h b/arch/arm64/include/uapi/asm/auxvec.h
index 22d6d8885854..4cf0c17787a8 100644
--- a/arch/arm64/include/uapi/asm/auxvec.h
+++ b/arch/arm64/include/uapi/asm/auxvec.h
@@ -19,4 +19,6 @@
 /* vDSO location */
 #define AT_SYSINFO_EHDR	33
 
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 208db3df135a..3378238b5d8b 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -76,6 +76,7 @@ struct user_fpsimd_state {
 	__uint128_t	vregs[32];
 	__u32		fpsr;
 	__u32		fpcr;
+	__u32		__reserved[2];
 };
 
 struct user_hwdebug_state {
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 937f5e58a4d3..478a00b9732b 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -305,7 +305,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
 	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
 		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "r" ((unsigned long)addr), "i" (-EAGAIN),		\
+	  "i" (-EFAULT)						\
 	: "memory")
 
 #define __user_swp_asm(data, addr, res, temp) \
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index bb493d44445f..7c4146a4257b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -59,6 +59,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index feb6b4efa641..a3e846a28b05 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -100,6 +100,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+	{
+	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 1),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0669c63281ea..2735bf814592 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -764,7 +766,13 @@ static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 
 	for (i = 0; caps[i].desc; i++)
 		if (caps[i].enable && cpus_have_cap(caps[i].capability))
-			on_each_cpu(caps[i].enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps[i].enable, NULL, cpu_online_mask);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 212ae6361d8b..0166cfbc866c 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -85,7 +87,8 @@ static const char *const compat_hwcap_str[] = {
 	"idivt",
 	"vfpd32",
 	"lpae",
-	"evtstrm"
+	"evtstrm",
+	NULL
 };
 
 static const char *const compat_hwcap2_str[] = {
@@ -101,6 +104,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -112,6 +116,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -124,7 +131,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 8aee3aeec3e6..c8875b64be90 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -152,7 +152,6 @@ static int debug_monitors_init(void)
 	/* Clear the OS lock. */
 	on_each_cpu(clear_os_lock, NULL, 1);
 	isb();
-	local_dbg_enable();
 
 	/* Register hotplug handler. */
 	__register_cpu_notifier(&os_lock_nb);
@@ -186,20 +185,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
-static DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(step_hook_lock);
 
 void register_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_add(&hook->node, &step_hook);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_add_rcu(&hook->node, &step_hook);
+	spin_unlock(&step_hook_lock);
 }
 
 void unregister_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&step_hook_lock);
+	synchronize_rcu();
 }
 
 /*
@@ -213,15 +213,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	struct step_hook *hook;
 	int retval = DBG_HOOK_ERROR;
 
-	read_lock(&step_hook_lock);
+	rcu_read_lock();
 
-	list_for_each_entry(hook, &step_hook, node)	{
+	list_for_each_entry_rcu(hook, &step_hook, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
 	}
 
-	read_unlock(&step_hook_lock);
+	rcu_read_unlock();
 
 	return retval;
 }
@@ -422,8 +422,10 @@ int kernel_active_single_step(void)
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
 {
-	set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
-	set_regs_spsr_ss(task_pt_regs(task));
+	struct thread_info *ti = task_thread_info(task);
+
+	if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+		set_regs_spsr_ss(task_pt_regs(task));
 }
 
 void user_disable_single_step(struct task_struct *task)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7ed3d75f6304..dccd0c2e9023 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -27,7 +27,9 @@
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*
@@ -93,7 +95,13 @@
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -117,6 +125,12 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -303,12 +317,13 @@ el1_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x3, far_el1
 	enable_dbg
 	// re-enable interrupts if they were enabled in the aborted context
 	tbnz	x23, #7, 1f			// PSR_I_BIT
 	enable_irq
 1:
+	clear_address_tag x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
@@ -470,7 +485,7 @@ el0_da:
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
 	ct_user_exit
-	bic	x0, x26, #(0xff << 56)
+	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
@@ -549,7 +564,7 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
-	bl	bad_mode
+	bl	bad_el0_sync
 	b	ret_to_user
 ENDPROC(el0_sync)
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 4c46c54a3ad7..6638903f0cb9 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -157,9 +157,11 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 void fpsimd_flush_thread(void)
 {
+	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
+	preempt_enable();
 }
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b685257926f0..20ceb5edf7b8 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -518,8 +518,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-	msr	mdcr_el2, x0			// all PMU counters from EL1
 4:
+	csel	x0, xzr, x0, lt			// all PMU counters from EL1
+	msr	mdcr_el2, x0			// (if they exist)
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index b45c95d34b83..eeebfc315526 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -35,6 +35,7 @@
 #include <asm/traps.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
+#include <asm/uaccess.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -690,7 +691,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 
 		/* Check if the watchpoint value matches. */
 		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
-		if (val != (addr & ~alignment_mask))
+		if (val != (untagged_addr(addr) & ~alignment_mask))
 			goto unlock;
 
 		/* Possible match, check the byte address select to confirm. */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index ff7f13239515..55909b2208cc 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -39,6 +39,7 @@
 #include <linux/elf.h>
 
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/syscall.h>
@@ -449,6 +450,8 @@ static int hw_break_set(struct task_struct *target,
 	/* (address, ctrl) registers */
 	limit = regset->n * regset->size;
 	while (count && offset < limit) {
+		if (count < PTRACE_HBP_ADDR_SZ)
+			return -EINVAL;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
 					 offset, offset + PTRACE_HBP_ADDR_SZ);
 		if (ret)
@@ -458,6 +461,8 @@ static int hw_break_set(struct task_struct *target,
 			return ret;
 		offset += PTRACE_HBP_ADDR_SZ;
 
+		if (!count)
+			break;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
 					 offset, offset + PTRACE_HBP_CTRL_SZ);
 		if (ret)
@@ -494,13 +499,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_pt_regs newregs;
+	struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
 	if (ret)
 		return ret;
 
-	if (!valid_user_regs(&newregs))
+	if (!valid_user_regs(&newregs, target))
 		return -EINVAL;
 
 	task_pt_regs(target)->user_regs = newregs;
@@ -524,7 +529,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate;
+	struct user_fpsimd_state newstate =
+		target->thread.fpsimd_state.user_fpsimd;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
 	if (ret)
@@ -548,7 +554,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	unsigned long tls;
+	unsigned long tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -574,7 +580,8 @@ static int system_call_set(struct task_struct *target,
 			   unsigned int pos, unsigned int count,
 			   const void *kbuf, const void __user *ubuf)
 {
-	int syscallno, ret;
+	int syscallno = task_pt_regs(target)->syscallno;
+	int ret;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
 	if (ret)
@@ -770,7 +777,7 @@ static int compat_gpr_set(struct task_struct *target,
 
 	}
 
-	if (valid_user_regs(&newregs.user_regs))
+	if (valid_user_regs(&newregs.user_regs, target))
 		*task_pt_regs(target) = newregs;
 	else
 		ret = -EINVAL;
@@ -846,7 +853,7 @@ static int compat_tls_set(struct task_struct *target,
 			  const void __user *ubuf)
 {
 	int ret;
-	compat_ulong_t tls;
+	compat_ulong_t tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -1272,3 +1279,79 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 }
+
+/*
+ * Bits which are always architecturally RES0 per ARM DDI 0487A.h
+ * Userspace cannot use these until they have an architectural meaning.
+ * We also reserve IL for the kernel; SS is handled dynamically.
+ */
+#define SPSR_EL1_AARCH64_RES0_BITS \
+	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \
+	 GENMASK_ULL(5, 5))
+#define SPSR_EL1_AARCH32_RES0_BITS \
+	(GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20))
+
+static int valid_compat_regs(struct user_pt_regs *regs)
+{
+	regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS;
+
+	if (!system_supports_mixed_endian_el0()) {
+		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+			regs->pstate |= COMPAT_PSR_E_BIT;
+		else
+			regs->pstate &= ~COMPAT_PSR_E_BIT;
+	}
+
+	if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) &&
+	    (regs->pstate & COMPAT_PSR_A_BIT) == 0 &&
+	    (regs->pstate & COMPAT_PSR_I_BIT) == 0 &&
+	    (regs->pstate & COMPAT_PSR_F_BIT) == 0) {
+		return 1;
+	}
+
+	/*
+	 * Force PSR to a valid 32-bit EL0t, preserving the same bits as
+	 * arch/arm.
+	 */
+	regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT |
+			COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT |
+			COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK |
+			COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT |
+			COMPAT_PSR_T_BIT;
+	regs->pstate |= PSR_MODE32_BIT;
+
+	return 0;
+}
+
+static int valid_native_regs(struct user_pt_regs *regs)
+{
+	regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS;
+
+	if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) &&
+	    (regs->pstate & PSR_D_BIT) == 0 &&
+	    (regs->pstate & PSR_A_BIT) == 0 &&
+	    (regs->pstate & PSR_I_BIT) == 0 &&
+	    (regs->pstate & PSR_F_BIT) == 0) {
+		return 1;
+	}
+
+	/* Force PSR to a valid 64-bit EL0t */
+	regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT;
+
+	return 0;
+}
+
+/*
+ * Are the current registers suitable for user mode? (used to maintain
+ * security in signal handlers)
+ */
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
+{
+	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		regs->pstate &= ~DBG_SPSR_SS;
+
+	if (is_compat_thread(task_thread_info(task)))
+		return valid_compat_regs(regs);
+	else
+		return valid_native_regs(regs);
+}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e18c48cb6db1..a8eafdbc7cb8 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -115,7 +115,7 @@ static int restore_sigframe(struct pt_regs *regs,
 	 */
 	regs->syscallno = ~0UL;
 
-	err |= !valid_user_regs(&regs->user_regs);
+	err |= !valid_user_regs(&regs->user_regs, current);
 
 	if (err == 0) {
 		struct fpsimd_context *fpsimd_ctx =
@@ -307,7 +307,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	/*
 	 * Check that the resulting registers are actually sane.
 	 */
-	ret |= !valid_user_regs(&regs->user_regs);
+	ret |= !valid_user_regs(&regs->user_regs, current);
 
 	/*
 	 * Fast forward the stepping logic so we step into the signal
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 71ef6dc89ae5..107335637390 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -356,7 +356,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	 */
 	regs->syscallno = ~0UL;
 
-	err |= !valid_user_regs(&regs->user_regs);
+	err |= !valid_user_regs(&regs->user_regs, current);
 
 	aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace;
 	if (err == 0)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b1adc51b2c2e..f3c3d8fee5ba 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -188,7 +188,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_dbg_enable();
 	local_irq_enable();
 	local_async_enable();
 
@@ -334,8 +333,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	cpuinfo_store_boot_cpu();
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	cpuinfo_store_boot_cpu();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 1095aa483a1c..00c1372bf57b 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,7 +1,9 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
@@ -111,6 +113,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
+		 * PSTATE was not saved over suspend/resume, re-enable any
+		 * detected features that might not have been set correctly.
+		 */
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+				CONFIG_ARM64_PAN));
+
+		/*
 		 * Restore HW breakpoint registers to sane values
 		 * before debug exceptions are possibly reenabled
 		 * through local_dbg_restore.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e9b9b5364393..ca7f0ac5f708 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -434,16 +434,33 @@ const char *esr_get_class_string(u32 esr)
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
  */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 {
-	siginfo_t info;
-	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
 	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
 		handler[reason], esr, esr_get_class_string(esr));
+
+	die("Oops - bad mode", regs, 0);
+	local_irq_disable();
+	panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+	siginfo_t info;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+	console_verbose();
+
+	pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
@@ -451,7 +468,10 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	info.si_code  = ILL_ILLOPC;
 	info.si_addr  = pc;
 
-	arm64_notify_die("Oops - bad mode", regs, &info, 0);
+	current->thread.fault_address = 0;
+	current->thread.fault_code = 0;
+
+	force_sig_info(info.si_signo, &info, current);
 }
 
 void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 178ba2248a98..84c338f017b2 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,15 +85,18 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2 and VTCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
+
+	msr	tcr_el2, x4
+
+	ldr	x4, =VTCR_EL2_FLAGS
+	bfi	x4, x5, #16, #3
+
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 648112e90ed5..3972e65fbd5a 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 		esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
 
 	if (!is_iabt)
-		esr |= ESR_ELx_EC_DABT_LOW;
+		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
 
 	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d2650e84faf2..c2489f62c4fb 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1054,8 +1054,8 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	int Rt = (hsr >> 5) & 0xf;
-	int Rt2 = (hsr >> 10) & 0xf;
+	int Rt = (hsr >> 5) & 0x1f;
+	int Rt2 = (hsr >> 10) & 0x1f;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
@@ -1106,7 +1106,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	int Rt  = (hsr >> 5) & 0xf;
+	int Rt  = (hsr >> 5) & 0x1f;
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 92ddac1e8ca2..7fabf49f2aeb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -64,23 +66,73 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pud = pud_offset(pgd, addr);
-		printk(", *pud=%016llx", pud_val(*pud));
+		pr_cont(", *pud=%016llx", pud_val(*pud));
 		if (pud_none(*pud) || pud_bad(*pud))
 			break;
 
 		pmd = pmd_offset(pud, addr);
-		printk(", *pmd=%016llx", pmd_val(*pmd));
+		pr_cont(", *pmd=%016llx", pmd_val(*pmd));
 		if (pmd_none(*pmd) || pmd_bad(*pmd))
 			break;
 
 		pte = pte_offset_map(pmd, addr);
-		printk(", *pte=%016llx", pte_val(*pte));
+		pr_cont(", *pte=%016llx", pte_val(*pte));
 		pte_unmap(pte);
 	} while(0);
 
-	printk("\n");
+	pr_cont("\n");
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	if (pte_same(*ptep, entry))
+		return 0;
+
+	/* only preserve the access flags and write permission */
+	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+	/*
+	 * PTE_RDONLY is cleared by default in the asm below, so set it in
+	 * back if necessary (read-only or clean PTE).
+	 */
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
+		pte_val(entry) |= PTE_RDONLY;
+
+	/*
+	 * Setting the flags must be done atomically to avoid racing with the
+	 * hardware update of the access/dirty state.
+	 */
+	asm volatile("//	ptep_set_access_flags\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	orr	%0, %0, %4		// set flags\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+
+	flush_tlb_fix_spurious_fault(vma, address);
+	return 1;
+}
+#endif
+
 /*
  * The kernel tried to access some page that wasn't present.
  */
@@ -261,8 +313,11 @@ retry:
 	 * 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 ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		if (!user_mode(regs))
+			goto no_context;
 		return 0;
+	}
 
 	/*
 	 * Major/minor page fault accounting is only done on the initial
@@ -556,8 +611,16 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 }
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 116ad654dd59..653735a8c58a 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -652,9 +652,9 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 	/*
 	 * Check whether the physical FDT address is set and meets the minimum
 	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the size field of the
-	 * FDT header after mapping the first chunk, double check here if that
-	 * is indeed the case.
+	 * at least 8 bytes so that we can always access the magic and size
+	 * fields of the FDT header after mapping the first chunk, double check
+	 * here if that is indeed the case.
 	 */
 	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
 	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
@@ -682,7 +682,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 	create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
 		       SWAPPER_BLOCK_SIZE, prot);
 
-	if (fdt_check_header(dt_virt) != 0)
+	if (fdt_magic(dt_virt) != FDT_MAGIC)
 		return NULL;
 
 	size = fdt_totalsize(dt_virt);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index b8f04b3f2786..18201e9e8cc7 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,6 +25,8 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
@@ -137,7 +139,17 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
+alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
 	ret
+	nop
+	nop
+	nop
+alternative_else
+	ic	iallu
+	dsb	nsh
+	isb
+	ret
+alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.section ".text.init", #alloc, #execinstr
@@ -156,6 +168,8 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	isb					// Unmask debug exceptions now,
+	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index b162ad70effc..6297140dd84f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -728,14 +728,14 @@ static int build_body(struct jit_ctx *ctx)
 		int ret;
 
 		ret = build_insn(insn, ctx);
-
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
-
 		if (ret > 0) {
 			i++;
+			if (ctx->image == NULL)
+				ctx->offset[i] = ctx->idx;
 			continue;
 		}
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index 68cf638faf48..b1ec1fa06463 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -74,7 +74,7 @@ extern __kernel_size_t __copy_user(void *to, const void *from,
 
 extern __kernel_size_t copy_to_user(void __user *to, const void *from,
 				    __kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
 				      __kernel_size_t n);
 
 static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
@@ -88,6 +88,15 @@ static inline __kernel_size_t __copy_from_user(void *to,
 {
 	return __copy_user(to, (const void __force *)from, n);
 }
+static inline __kernel_size_t copy_from_user(void *to,
+					       const void __user *from,
+					       __kernel_size_t n)
+{
+	size_t res = ___copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}
 
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
index d93ead02daed..7c6cf14f0985 100644
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ b/arch/avr32/kernel/avr32_ksyms.c
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(copy_page);
 /*
  * Userspace access stuff.
  */
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(__copy_user);
 EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/avr32/lib/copy_user.S b/arch/avr32/lib/copy_user.S
index ea59c04b07de..075373471da1 100644
--- a/arch/avr32/lib/copy_user.S
+++ b/arch/avr32/lib/copy_user.S
@@ -23,13 +23,13 @@
 	 */
 	.text
 	.align	1
-	.global	copy_from_user
-	.type	copy_from_user, @function
-copy_from_user:
+	.global	___copy_from_user
+	.type	___copy_from_user, @function
+___copy_from_user:
 	branch_if_kernel r8, __copy_user
 	ret_if_privileged r8, r11, r10, r10
 	rjmp	__copy_user
-	.size	copy_from_user, . - copy_from_user
+	.size	___copy_from_user, . - ___copy_from_user
 
 	.global	copy_to_user
 	.type	copy_to_user, @function
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
index 4f61378c3453..456128174b17 100644
--- a/arch/avr32/mach-at32ap/pio.c
+++ b/arch/avr32/mach-at32ap/pio.c
@@ -435,7 +435,7 @@ void __init at32_init_pio(struct platform_device *pdev)
 	struct resource *regs;
 	struct pio_device *pio;
 
-	if (pdev->id > MAX_NR_PIO_DEVICES) {
+	if (pdev->id >= MAX_NR_PIO_DEVICES) {
 		dev_err(&pdev->dev, "only %d PIO devices supported\n",
 			MAX_NR_PIO_DEVICES);
 		return;
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 90612a7f2cf3..8cd0184ea9ef 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -177,11 +177,12 @@ static inline int bad_user_access_length(void)
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n))) {
 		memcpy(to, (const void __force *)from, n);
-	else
-		return n;
-	return 0;
+		return 0;
+	}
+	memset(to, 0, n);
+	return n;
 }
 
 static inline unsigned long __must_check
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index c6db52ba3a06..10c57771822d 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index 2de71e8c104b..93c22468cc14 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c
index 3c494e84444d..a511ac16a8e3 100644
--- a/arch/c6x/kernel/ptrace.c
+++ b/arch/c6x/kernel/ptrace.c
@@ -69,46 +69,6 @@ static int gpr_get(struct task_struct *target,
 				   0, sizeof(*regs));
 }
 
-static int gpr_set(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-	struct pt_regs *regs = task_pt_regs(target);
-
-	/* Don't copyin TSR or CSR */
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 0, PT_TSR * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					PT_TSR * sizeof(long),
-					(PT_TSR + 1) * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 (PT_TSR + 1) * sizeof(long),
-				 PT_CSR * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					PT_CSR * sizeof(long),
-					(PT_CSR + 1) * sizeof(long));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &regs,
-				 (PT_CSR + 1) * sizeof(long), -1);
-	return ret;
-}
-
 enum c6x_regset {
 	REGSET_GPR,
 };
@@ -120,7 +80,6 @@ static const struct user_regset c6x_regsets[] = {
 		.size = sizeof(u32),
 		.align = sizeof(u32),
 		.get = gpr_get,
-		.set = gpr_set
 	},
 };
 
diff --git a/arch/cris/boot/rescue/Makefile b/arch/cris/boot/rescue/Makefile
index 52bd0bd1dd22..d98edbb30a18 100644
--- a/arch/cris/boot/rescue/Makefile
+++ b/arch/cris/boot/rescue/Makefile
@@ -10,6 +10,9 @@
 
 asflags-y += $(LINUXINCLUDE)
 ccflags-y += -O2 $(LINUXINCLUDE)
+
+ifdef CONFIG_ETRAX_AXISFLASHMAP
+
 arch-$(CONFIG_ETRAX_ARCH_V10) = v10
 arch-$(CONFIG_ETRAX_ARCH_V32) = v32
 
@@ -28,6 +31,11 @@ $(obj)/rescue.bin: $(obj)/rescue.o FORCE
 	$(call if_changed,objcopy)
 	cp -p $(obj)/rescue.bin $(objtree)
 
+else
+$(obj)/rescue.bin:
+
+endif
+
 $(obj)/testrescue.bin: $(obj)/testrescue.o
 	$(OBJCOPY) $(OBJCOPYFLAGS) $(obj)/testrescue.o tr.bin
 # Pad it to 784 bytes
diff --git a/arch/cris/include/asm/uaccess.h b/arch/cris/include/asm/uaccess.h
index e3530d0f13ee..56c7d5750abd 100644
--- a/arch/cris/include/asm/uaccess.h
+++ b/arch/cris/include/asm/uaccess.h
@@ -194,30 +194,6 @@ extern unsigned long __copy_user(void __user *to, const void *from, unsigned lon
 extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
 extern unsigned long __do_clear_user(void __user *to, unsigned long n);
 
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_user(to, from, n);
-	return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_user_zeroing(to, from, n);
-	return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __do_clear_user(to, n);
-	return n;
-}
-
 static inline long
 __strncpy_from_user(char *dst, const char __user *src, long count)
 {
@@ -282,7 +258,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_from_user_24(to, from, ret);
 	else
-		ret = __generic_copy_from_user(to, from, n);
+		ret = __copy_user_zeroing(to, from, n);
 
 	return ret;
 }
@@ -333,7 +309,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_to_user_24(to, from, ret);
 	else
-		ret = __generic_copy_to_user(to, from, n);
+		ret = __copy_user(to, from, n);
 
 	return ret;
 }
@@ -366,26 +342,43 @@ __constant_clear_user(void __user *to, unsigned long n)
 	else if (n == 24)
 		__asm_clear_24(to, ret);
 	else
-		ret = __generic_clear_user(to, n);
+		ret = __do_clear_user(to, n);
 
 	return ret;
 }
 
 
-#define clear_user(to, n)				\
-	(__builtin_constant_p(n) ?			\
-	 __constant_clear_user(to, n) :			\
-	 __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_clear_user(to, n);
+	else
+		return __do_clear_user(to, n);
+}
 
-#define copy_from_user(to, from, n)			\
-	(__builtin_constant_p(n) ?			\
-	 __constant_copy_from_user(to, from, n) :	\
-	 __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+		memset(to, 0, n);
+		return n;
+	}
+	if (__builtin_constant_p(n))
+		return __constant_copy_from_user(to, from, n);
+	else
+		return __copy_user_zeroing(to, from, n);
+}
 
-#define copy_to_user(to, from, n)			\
-	(__builtin_constant_p(n) ?			\
-	 __constant_copy_to_user(to, from, n) :		\
-	 __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_copy_to_user(to, from, n);
+	else
+		return __copy_user(to, from, n);
+}
 
 /* We let the __ versions of copy_from/to_user inline, because they're often
  * used in fast paths and have only a small space overhead.
diff --git a/arch/frv/include/asm/uaccess.h b/arch/frv/include/asm/uaccess.h
index 3ac9a59d65d4..87d9e34c5df8 100644
--- a/arch/frv/include/asm/uaccess.h
+++ b/arch/frv/include/asm/uaccess.h
@@ -263,19 +263,25 @@ do {							\
 extern long __memset_user(void *dst, unsigned long count);
 extern long __memcpy_user(void *dst, const void *src, unsigned long count);
 
-#define clear_user(dst,count)			__memset_user(____force(dst), (count))
+#define __clear_user(dst,count)			__memset_user(____force(dst), (count))
 #define __copy_from_user_inatomic(to, from, n)	__memcpy_user((to), ____force(from), (n))
 #define __copy_to_user_inatomic(to, from, n)	__memcpy_user(____force(to), (from), (n))
 
 #else
 
-#define clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
 #define __copy_from_user_inatomic(to, from, n)	(memcpy((to), ____force(from), (n)), 0)
 #define __copy_to_user_inatomic(to, from, n)	(memcpy(____force(to), (from), (n)), 0)
 
 #endif
 
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+	if (likely(__access_ok(to, n)))
+		n = __clear_user(to, n);
+	return n;
+}
 
 static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c
index 836f14707a62..efa59f1f8022 100644
--- a/arch/frv/mm/elf-fdpic.c
+++ b/arch/frv/mm/elf-fdpic.c
@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(current->mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			goto success;
 	}
 
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index b408fe660cf8..3cef06875f5c 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	int		   cpu;			/* cpu we're on */
 	int		   preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;
-	struct restart_block restart_block;
 };
 
 /*
@@ -44,9 +43,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
index 92075544a19a..0dc1c8f622bc 100644
--- a/arch/h8300/kernel/ptrace.c
+++ b/arch/h8300/kernel/ptrace.c
@@ -95,7 +95,8 @@ static int regs_get(struct task_struct *target,
 	long *reg = (long *)&regs;
 
 	/* build user regs in buffer */
-	for (r = 0; r < ARRAY_SIZE(register_offset); r++)
+	BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+	for (r = 0; r < sizeof(regs) / sizeof(long); r++)
 		*reg++ = h8300_get_reg(target, r);
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
@@ -113,7 +114,8 @@ static int regs_set(struct task_struct *target,
 	long *reg;
 
 	/* build user regs in buffer */
-	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+	BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0);
+	for (reg = (long *)&regs, r = 0; r < sizeof(regs) / sizeof(long); r++)
 		*reg++ = h8300_get_reg(target, r);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
@@ -122,7 +124,7 @@ static int regs_set(struct task_struct *target,
 		return ret;
 
 	/* write back to pt_regs */
-	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+	for (reg = (long *)&regs, r = 0; r < sizeof(regs) / sizeof(long); r++)
 		h8300_put_reg(target, r, *reg++);
 	return 0;
 }
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index 380fffd081b2..036ad04edd2d 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0)
 	unsigned int er0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore passed registers */
 #define COPY(r)  do { err |= get_user(regs->r, &usc->sc_##r); } while (0)
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index f000a382bc7f..f61cfb28e9f2 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -103,7 +103,8 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src,
 {
 	long res = __strnlen_user(src, n);
 
-	/* return from strnlen can't be zero -- that would be rubbish. */
+	if (unlikely(!res))
+		return -EFAULT;
 
 	if (res > n) {
 		copy_from_user(dst, src, n);
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 9041bbe2b7b4..8fdb9c7eeb66 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -436,6 +436,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 	return ioremap(phys_addr, size);
 }
 #define ioremap_cache ioremap_cache
+#define ioremap_uc ioremap_nocache
 
 
 /*
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 4f3fb6ccbf21..40c2027a2bf4 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -263,17 +263,15 @@ __copy_from_user (void *to, const void __user *from, unsigned long count)
 	__cu_len;									\
 })
 
-#define copy_from_user(to, from, n)							\
-({											\
-	void *__cu_to = (to);								\
-	const void __user *__cu_from = (from);						\
-	long __cu_len = (n);								\
-											\
-	__chk_user_ptr(__cu_from);							\
-	if (__access_ok(__cu_from, __cu_len, get_fs()))					\
-		__cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len);	\
-	__cu_len;									\
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (likely(__access_ok(from, n, get_fs())))
+		n = __copy_user((__force void __user *) to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}
 
 #define __copy_in_user(to, from, size)	__copy_user((to), (from), (size))
 
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index cac7014daef3..6f8982157a75 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -219,7 +219,7 @@ extern int fixup_exception(struct pt_regs *regs);
 #define __get_user_nocheck(x, ptr, size)				\
 ({									\
 	long __gu_err = 0;						\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	might_fault();							\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err);		\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h
index d28fa8fe26fe..c598d847d56b 100644
--- a/arch/m68k/include/asm/delay.h
+++ b/arch/m68k/include/asm/delay.h
@@ -114,6 +114,6 @@ static inline void __udelay(unsigned long usecs)
  */
 #define	HZSCALE		(268435456 / (1000000 / HZ))
 
-#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000));
+#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000))
 
 #endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/metag/include/asm/atomic.h b/arch/metag/include/asm/atomic.h
index 470e365f04ea..8ff0a70865f6 100644
--- a/arch/metag/include/asm/atomic.h
+++ b/arch/metag/include/asm/atomic.h
@@ -39,11 +39,10 @@
 #define atomic_dec(v) atomic_sub(1, (v))
 
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+#define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)
 
 #endif
 
-#define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)
-
 #include <asm-generic/atomic64.h>
 
 #endif /* __ASM_METAG_ATOMIC_H */
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index a62581815624..88fa25fae8bd 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -61,7 +61,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 		"	CMPT	%0, #HI(0x02000000)\n"			\
 		"	BNZ 1b\n"					\
 		: "=&d" (temp), "=&da" (result)				\
-		: "da" (&v->counter), "bd" (i)				\
+		: "da" (&v->counter), "br" (i)				\
 		: "cc");						\
 									\
 	smp_mb();							\
diff --git a/arch/metag/include/asm/cmpxchg_lnkget.h b/arch/metag/include/asm/cmpxchg_lnkget.h
index 0154e2807ebb..2369ad394876 100644
--- a/arch/metag/include/asm/cmpxchg_lnkget.h
+++ b/arch/metag/include/asm/cmpxchg_lnkget.h
@@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
 		      "	DCACHE	[%2], %0\n"
 #endif
 		      "2:\n"
-		      : "=&d" (temp), "=&da" (retval)
+		      : "=&d" (temp), "=&d" (retval)
 		      : "da" (m), "bd" (old), "da" (new)
 		      : "cc"
 		      );
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 8282cbce7e39..3db381205928 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -28,24 +28,32 @@
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
-/*
- * Explicitly allow NULL pointers here. Parts of the kernel such
- * as readv/writev use access_ok to validate pointers, but want
- * to allow NULL pointers for various reasons. NULL pointers are
- * safe to allow through because the first page is not mappable on
- * Meta.
- *
- * We also wish to avoid letting user code access the system area
- * and the kernel half of the address space.
- */
-#define __user_bad(addr, size) (((addr) > 0 && (addr) < META_MEMORY_BASE) || \
-				((addr) > PAGE_OFFSET &&		\
-				 (addr) < LINCORE_BASE))
-
 static inline int __access_ok(unsigned long addr, unsigned long size)
 {
-	return __kernel_ok || !__user_bad(addr, size);
+	/*
+	 * Allow access to the user mapped memory area, but not the system area
+	 * before it. The check extends to the top of the address space when
+	 * kernel access is allowed (there's no real reason to user copy to the
+	 * system area in any case).
+	 */
+	if (likely(addr >= META_MEMORY_BASE && addr < get_fs().seg &&
+		   size <= get_fs().seg - addr))
+		return true;
+	/*
+	 * Explicitly allow NULL pointers here. Parts of the kernel such
+	 * as readv/writev use access_ok to validate pointers, but want
+	 * to allow NULL pointers for various reasons. NULL pointers are
+	 * safe to allow through because the first page is not mappable on
+	 * Meta.
+	 */
+	if (!addr)
+		return true;
+	/* Allow access to core code memory area... */
+	if (addr >= LINCORE_CODE_BASE && addr <= LINCORE_CODE_LIMIT &&
+	    size <= LINCORE_CODE_LIMIT + 1 - addr)
+		return true;
+	/* ... but no other areas. */
+	return false;
 }
 
 #define access_ok(type, addr, size) __access_ok((unsigned long)(addr),	\
@@ -186,8 +194,13 @@ do {                                                            \
 extern long __must_check __strncpy_from_user(char *dst, const char __user *src,
 					     long count);
 
-#define strncpy_from_user(dst, src, count) __strncpy_from_user(dst, src, count)
-
+static inline long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	if (!access_ok(VERIFY_READ, src, 1))
+		return -EFAULT;
+	return __strncpy_from_user(dst, src, count);
+}
 /*
  * Return the size of a string (including the ending 0)
  *
@@ -197,19 +210,21 @@ extern long __must_check strnlen_user(const char __user *src, long count);
 
 #define strlen_user(str) strnlen_user(str, 32767)
 
-extern unsigned long __must_check __copy_user_zeroing(void *to,
-						      const void __user *from,
-						      unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+					unsigned long n);
 
 static inline unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_user_zeroing(to, from, n);
-	return n;
+	unsigned long res = n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = raw_copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
+#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n)
 #define __copy_from_user_inatomic __copy_from_user
 
 extern unsigned long __must_check __copy_user(void __user *to,
diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c
index 7563628822bd..5e2dc7defd2c 100644
--- a/arch/metag/kernel/ptrace.c
+++ b/arch/metag/kernel/ptrace.c
@@ -24,6 +24,16 @@
  * user_regset definitions.
  */
 
+static unsigned long user_txstatus(const struct pt_regs *regs)
+{
+	unsigned long data = (unsigned long)regs->ctx.Flags;
+
+	if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
+		data |= USER_GP_REGS_STATUS_CATCH_BIT;
+
+	return data;
+}
+
 int metag_gp_regs_copyout(const struct pt_regs *regs,
 			  unsigned int pos, unsigned int count,
 			  void *kbuf, void __user *ubuf)
@@ -62,9 +72,7 @@ int metag_gp_regs_copyout(const struct pt_regs *regs,
 	if (ret)
 		goto out;
 	/* TXSTATUS */
-	data = (unsigned long)regs->ctx.Flags;
-	if (regs->ctx.SaveMask & TBICTX_CBUF_BIT)
-		data |= USER_GP_REGS_STATUS_CATCH_BIT;
+	data = user_txstatus(regs);
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				  &data, 4*25, 4*26);
 	if (ret)
@@ -119,6 +127,7 @@ int metag_gp_regs_copyin(struct pt_regs *regs,
 	if (ret)
 		goto out;
 	/* TXSTATUS */
+	data = user_txstatus(regs);
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &data, 4*25, 4*26);
 	if (ret)
@@ -244,6 +253,8 @@ int metag_rp_state_copyin(struct pt_regs *regs,
 	unsigned long long *ptr;
 	int ret, i;
 
+	if (count < 4*13)
+		return -EINVAL;
 	/* Read the entire pipeline before making any changes */
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &rp, 0, 4*13);
@@ -303,7 +314,7 @@ static int metag_tls_set(struct task_struct *target,
 			const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	void __user *tls;
+	void __user *tls = target->thread.tls_ptr;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
diff --git a/arch/metag/lib/usercopy.c b/arch/metag/lib/usercopy.c
index b3ebfe9c8e88..2792fc621088 100644
--- a/arch/metag/lib/usercopy.c
+++ b/arch/metag/lib/usercopy.c
@@ -29,7 +29,6 @@
 		COPY						 \
 		"1:\n"						 \
 		"	.section .fixup,\"ax\"\n"		 \
-		"	MOV D1Ar1,#0\n"				 \
 		FIXUP						 \
 		"	MOVT    D1Ar1,#HI(1b)\n"		 \
 		"	JUMP    D1Ar1,#LO(1b)\n"		 \
@@ -260,27 +259,31 @@
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #32\n"					\
 		"23:\n"							\
-		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"SUB	%3, %3, #32\n"					\
 		"24:\n"							\
+		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"25:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #32\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"25:\n"							\
+		"27:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"28:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
 		"SUB	%3, %3, #32\n"					\
-		"27:\n"							\
+		"30:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"28:\n"							\
+		"31:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%0, %0, #8\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"SETL	[%0++], D0.7, D1.7\n"				\
 		"SUB	%3, %3, #32\n"					\
 		"1:"							\
@@ -312,11 +315,15 @@
 		"	.long 26b,3b\n"					\
 		"	.long 27b,3b\n"					\
 		"	.long 28b,3b\n"					\
-		"	.long 29b,4b\n"					\
+		"	.long 29b,3b\n"					\
+		"	.long 30b,3b\n"					\
+		"	.long 31b,3b\n"					\
+		"	.long 32b,3b\n"					\
+		"	.long 33b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -342,7 +349,7 @@
 #define __asm_copy_to_user_64bit_rapf_loop(to,	from, ret, n, id)\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -403,47 +410,55 @@
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #16\n"					\
 		"23:\n"							\
-		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"24:\n"							\
-		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
 		"SUB	%3, %3, #16\n"					\
-		"25:\n"							\
+		"24:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"25:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"27:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"28:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
+		"SUB	%3, %3, #16\n"					\
+		"30:\n"							\
+		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"31:\n"							\
+		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"30:\n"							\
+		"34:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"35:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"31:\n"							\
+		"36:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"32:\n"							\
+		"37:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"38:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"33:\n"							\
+		"39:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"34:\n"							\
+		"40:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"41:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"35:\n"							\
+		"42:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"36:\n"							\
+		"43:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"44:\n"							\
 		"SUB	%0, %0, #4\n"					\
-		"37:\n"							\
+		"45:\n"							\
 		"SETD	[%0++], D0.7\n"					\
 		"SUB	%3, %3, #16\n"					\
 		"1:"							\
@@ -483,11 +498,19 @@
 		"	.long 34b,3b\n"					\
 		"	.long 35b,3b\n"					\
 		"	.long 36b,3b\n"					\
-		"	.long 37b,4b\n"					\
+		"	.long 37b,3b\n"					\
+		"	.long 38b,3b\n"					\
+		"	.long 39b,3b\n"					\
+		"	.long 40b,3b\n"					\
+		"	.long 41b,3b\n"					\
+		"	.long 42b,3b\n"					\
+		"	.long 43b,3b\n"					\
+		"	.long 44b,3b\n"					\
+		"	.long 45b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -513,7 +536,7 @@
 #define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -538,23 +561,31 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_to_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
 		while (n > 0) {
 			__asm_copy_to_user_1(dst, src, retn);
 			n--;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_to_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
 		while (n >= 2) {
 			__asm_copy_to_user_2(dst, src, retn);
 			n -= 2;
+			if (retn)
+				return retn + n;
 		}
 	}
 
@@ -569,6 +600,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (n >= RAPF_MIN_BUF_SIZE) {
@@ -581,6 +614,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 #endif
@@ -588,11 +623,15 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	while (n >= 16) {
 		__asm_copy_to_user_16(dst, src, retn);
 		n -= 16;
+		if (retn)
+			return retn + n;
 	}
 
 	while (n >= 4) {
 		__asm_copy_to_user_4(dst, src, retn);
 		n -= 4;
+		if (retn)
+			return retn + n;
 	}
 
 	switch (n) {
@@ -609,6 +648,10 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		break;
 	}
 
+	/*
+	 * If we get here, retn correctly reflects the number of failing
+	 * bytes.
+	 */
 	return retn;
 }
 EXPORT_SYMBOL(__copy_user);
@@ -617,16 +660,14 @@ EXPORT_SYMBOL(__copy_user);
 	__asm_copy_user_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"	\
 		"2:	SETB [%0++],D1Ar1\n",	\
-		"3:	ADD  %2,%2,#1\n"	\
-		"	SETB [%0++],D1Ar1\n",	\
+		"3:	ADD  %2,%2,#1\n",	\
 		"	.long 2b,3b\n")
 
 #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETW D1Ar1,[%1++]\n"		\
 		"2:	SETW [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#2\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_2(to, from, ret) \
@@ -636,145 +677,26 @@ EXPORT_SYMBOL(__copy_user);
 	__asm_copy_from_user_2x_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"		\
 		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
+		"5:	ADD  %2,%2,#1\n",		\
 		"	.long 4b,5b\n")
 
 #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETD D1Ar1,[%1++]\n"		\
 		"2:	SETD [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#4\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_4(to, from, ret) \
 	__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
 
-#define __asm_copy_from_user_5(to, from, ret) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"4:	SETW [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"4:	SETD [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#4\n"			\
-		"	SETD [%0++],D1Ar1\n" FIXUP,		\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"6:	SETW [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
-	__asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret)		\
-	__asm_copy_from_user_10x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"6:	SETD [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"8:	SETW [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"10:	SETB [%0++],D1Ar1\n",		\
-		"11:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"8:	SETD [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
-	__asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
 #define __asm_copy_from_user_8x64(to, from, ret) \
 	asm volatile (				\
 		"	GETL D0Ar2,D1Ar1,[%1++]\n"	\
 		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"1:\n"					\
 		"	.section .fixup,\"ax\"\n"	\
-		"	MOV D1Ar1,#0\n"			\
-		"	MOV D0Ar2,#0\n"			\
 		"3:	ADD  %2,%2,#8\n"		\
-		"	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"	MOVT    D0Ar2,#HI(1b)\n"	\
 		"	JUMP    D0Ar2,#LO(1b)\n"	\
 		"	.previous\n"			\
@@ -789,36 +711,57 @@ EXPORT_SYMBOL(__copy_user);
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 8 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*8 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #8\n")
+		"LSR	D0Ar2, D0Ar2, #5\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x38\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #32\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 /*	rewind 'from' pointer when a fault occurs
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 4 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*4 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #4\n")
+		"LSR	D0Ar2, D0Ar2, #6\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x1c\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #16\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
-   userland.  The return-value is the number of bytes that were
-   inaccessible.  */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
-				  unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+				 unsigned long n)
 {
 	register char *dst asm ("A0.2") = pdst;
 	register const char __user *src asm ("A1.2") = psrc;
@@ -830,6 +773,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_from_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
@@ -837,12 +782,14 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_1(dst, src, retn);
 			n--;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_from_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
@@ -850,16 +797,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_2(dst, src, retn);
 			n -= 2;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
-	/* We only need one check after the unalignment-adjustments,
-	   because if both adjustments were done, either both or
-	   neither reference had an exception.  */
-	if (retn != 0)
-		goto copy_exception_bytes;
-
 #ifdef USE_RAPF
 	/* 64 bit copy loop */
 	if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
@@ -872,7 +813,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
@@ -888,7 +829,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 #endif
@@ -898,7 +839,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 		n -= 4;
 
 		if (retn)
-			goto copy_exception_bytes;
+			return retn + n;
 	}
 
 	/* If we get here, there were no memory read faults.  */
@@ -924,21 +865,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	/* If we get here, retn correctly reflects the number of failing
 	   bytes.  */
 	return retn;
-
- copy_exception_bytes:
-	/* We already have "retn" bytes cleared, and need to clear the
-	   remaining "n" bytes.  A non-optimized simple byte-for-byte in-line
-	   memset is preferred here, since this isn't speed-critical code and
-	   we'd rather have this a leaf-function than calling memset.  */
-	{
-		char *endp;
-		for (endp = dst + n; dst < endp; dst++)
-			*dst = 0;
-	}
-
-	return retn + n;
 }
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 #define __asm_clear_8x64(to, ret) \
 	asm volatile (					\
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 331b0d35f89c..826676778094 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -227,7 +227,7 @@ extern long __user_bad(void);
 
 #define __get_user(x, ptr)						\
 ({									\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	/*unsigned long __gu_ptr = (unsigned long)(ptr);*/		\
 	long __gu_err;							\
 	switch (sizeof(*(ptr))) {					\
@@ -373,10 +373,13 @@ extern long __user_bad(void);
 static inline long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long res = n;
 	might_fault();
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_from_user(to, from, n);
-	return n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 #define __copy_to_user(to, from, n)	\
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index db459612de44..8b0424abc84c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -9,6 +9,7 @@ config MIPS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IDE
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
@@ -1463,7 +1464,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
-	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+	select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
 	help
 	  Choose this option to build a kernel for release 6 or later of the
 	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index f0e314ceb8ba..7f975b20b20c 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -113,42 +113,6 @@ config SPINLOCK_TEST
 	help
 	  Add several files to the debugfs to test spinlock speed.
 
-if CPU_MIPSR6
-
-choice
-	prompt "Compact branch policy"
-	default MIPS_COMPACT_BRANCHES_OPTIMAL
-
-config MIPS_COMPACT_BRANCHES_NEVER
-	bool "Never (force delay slot branches)"
-	help
-	  Pass the -mcompact-branches=never flag to the compiler in order to
-	  force it to always emit branches with delay slots, and make no use
-	  of the compact branch instructions introduced by MIPSr6. This is
-	  useful if you suspect there may be an issue with compact branches in
-	  either the compiler or the CPU.
-
-config MIPS_COMPACT_BRANCHES_OPTIMAL
-	bool "Optimal (use where beneficial)"
-	help
-	  Pass the -mcompact-branches=optimal flag to the compiler in order for
-	  it to make use of compact branch instructions where it deems them
-	  beneficial, and use branches with delay slots elsewhere. This is the
-	  default compiler behaviour, and should be used unless you have a
-	  reason to choose otherwise.
-
-config MIPS_COMPACT_BRANCHES_ALWAYS
-	bool "Always (force compact branches)"
-	help
-	  Pass the -mcompact-branches=always flag to the compiler in order to
-	  force it to always emit compact branches, making no use of branch
-	  instructions with delay slots. This can result in more compact code
-	  which may be beneficial in some scenarios.
-
-endchoice
-
-endif # CPU_MIPSR6
-
 config SCACHE_DEBUGFS
 	bool "L2 cache debugfs entries"
 	depends on DEBUG_FS
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 3f70ba54ae21..252e347958f3 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -204,10 +204,6 @@ toolchain-msa				:= $(call cc-option-yn,$(mips-cflags) -mhard-float -mfp64 -Wa$(
 cflags-$(toolchain-msa)			+= -DTOOLCHAIN_SUPPORTS_MSA
 endif
 
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_NEVER)	+= -mcompact-branches=never
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_OPTIMAL)	+= -mcompact-branches=optimal
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_ALWAYS)	+= -mcompact-branches=always
-
 #
 # Firmware support
 #
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index bdeed9d13c6f..433c4b9a9f0a 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -503,15 +503,15 @@ int __init db1000_dev_setup(void)
 	if (board == BCSR_WHOAMI_DB1500) {
 		c0 = AU1500_GPIO2_INT;
 		c1 = AU1500_GPIO5_INT;
-		d0 = AU1500_GPIO0_INT;
-		d1 = AU1500_GPIO3_INT;
+		d0 = 0;	/* GPIO number, NOT irq! */
+		d1 = 3; /* GPIO number, NOT irq! */
 		s0 = AU1500_GPIO1_INT;
 		s1 = AU1500_GPIO4_INT;
 	} else if (board == BCSR_WHOAMI_DB1100) {
 		c0 = AU1100_GPIO2_INT;
 		c1 = AU1100_GPIO5_INT;
-		d0 = AU1100_GPIO0_INT;
-		d1 = AU1100_GPIO3_INT;
+		d0 = 0; /* GPIO number, NOT irq! */
+		d1 = 3; /* GPIO number, NOT irq! */
 		s0 = AU1100_GPIO1_INT;
 		s1 = AU1100_GPIO4_INT;
 
@@ -545,15 +545,15 @@ int __init db1000_dev_setup(void)
 	} else if (board == BCSR_WHOAMI_DB1000) {
 		c0 = AU1000_GPIO2_INT;
 		c1 = AU1000_GPIO5_INT;
-		d0 = AU1000_GPIO0_INT;
-		d1 = AU1000_GPIO3_INT;
+		d0 = 0; /* GPIO number, NOT irq! */
+		d1 = 3; /* GPIO number, NOT irq! */
 		s0 = AU1000_GPIO1_INT;
 		s1 = AU1000_GPIO4_INT;
 		platform_add_devices(db1000_devs, ARRAY_SIZE(db1000_devs));
 	} else if ((board == BCSR_WHOAMI_PB1500) ||
 		   (board == BCSR_WHOAMI_PB1500R2)) {
 		c0 = AU1500_GPIO203_INT;
-		d0 = AU1500_GPIO201_INT;
+		d0 = 1; /* GPIO number, NOT irq! */
 		s0 = AU1500_GPIO202_INT;
 		twosocks = 0;
 		flashsize = 64;
@@ -566,7 +566,7 @@ int __init db1000_dev_setup(void)
 		 */
 	} else if (board == BCSR_WHOAMI_PB1100) {
 		c0 = AU1100_GPIO11_INT;
-		d0 = AU1100_GPIO9_INT;
+		d0 = 9; /* GPIO number, NOT irq! */
 		s0 = AU1100_GPIO10_INT;
 		twosocks = 0;
 		flashsize = 64;
@@ -583,7 +583,6 @@ int __init db1000_dev_setup(void)
 	} else
 		return 0; /* unknown board, no further dev setup to do */
 
-	irq_set_irq_type(d0, IRQ_TYPE_EDGE_BOTH);
 	irq_set_irq_type(c0, IRQ_TYPE_LEVEL_LOW);
 	irq_set_irq_type(s0, IRQ_TYPE_LEVEL_LOW);
 
@@ -597,7 +596,6 @@ int __init db1000_dev_setup(void)
 		c0, d0, /*s0*/0, 0, 0);
 
 	if (twosocks) {
-		irq_set_irq_type(d1, IRQ_TYPE_EDGE_BOTH);
 		irq_set_irq_type(c1, IRQ_TYPE_LEVEL_LOW);
 		irq_set_irq_type(s1, IRQ_TYPE_LEVEL_LOW);
 
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index 5740bcfdfc7f..6c37b9326f41 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -514,7 +514,7 @@ static void __init db1550_devices(void)
 		AU1000_PCMCIA_MEM_PHYS_ADDR  + 0x000400000 - 1,
 		AU1000_PCMCIA_IO_PHYS_ADDR,
 		AU1000_PCMCIA_IO_PHYS_ADDR   + 0x000010000 - 1,
-		AU1550_GPIO3_INT, AU1550_GPIO0_INT,
+		AU1550_GPIO3_INT, 0,
 		/*AU1550_GPIO21_INT*/0, 0, 0);
 
 	db1x_register_pcmcia_socket(
@@ -524,7 +524,7 @@ static void __init db1550_devices(void)
 		AU1000_PCMCIA_MEM_PHYS_ADDR  + 0x004400000 - 1,
 		AU1000_PCMCIA_IO_PHYS_ADDR   + 0x004000000,
 		AU1000_PCMCIA_IO_PHYS_ADDR   + 0x004010000 - 1,
-		AU1550_GPIO5_INT, AU1550_GPIO1_INT,
+		AU1550_GPIO5_INT, 1,
 		/*AU1550_GPIO22_INT*/0, 0, 1);
 
 	platform_device_register(&db1550_nand_dev);
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 3cedd1f95e0f..8ae4067a5eda 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -76,14 +76,14 @@ void ath79_ddr_set_pci_windows(void)
 {
 	BUG_ON(!ath79_ddr_pci_win_base);
 
-	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0);
-	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 1);
-	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 2);
-	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 3);
-	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 4);
-	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 5);
-	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 6);
-	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 7);
+	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0);
+	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4);
+	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8);
+	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc);
+	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10);
+	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14);
+	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18);
+	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c);
 }
 EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows);
 
diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index b955fafc58ba..d1adc59af5bf 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -31,13 +31,15 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 	} while (1);
 }
 
+#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
+
 static void prom_putchar_ar71xx(unsigned char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
 
-	prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 	__raw_writel(ch, base + UART_TX * 4);
-	prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 }
 
 static void prom_putchar_ar933x(unsigned char ch)
diff --git a/arch/mips/bcm47xx/buttons.c b/arch/mips/bcm47xx/buttons.c
index 52caa75bfe4e..e2f50d690624 100644
--- a/arch/mips/bcm47xx/buttons.c
+++ b/arch/mips/bcm47xx/buttons.c
@@ -17,6 +17,12 @@
 		.active_low	= 1,					\
 	}
 
+#define BCM47XX_GPIO_KEY_H(_gpio, _code)				\
+	{								\
+		.code		= _code,				\
+		.gpio		= _gpio,				\
+	}
+
 /* Asus */
 
 static const struct gpio_keys_button
@@ -79,8 +85,8 @@ bcm47xx_buttons_asus_wl500gpv2[] __initconst = {
 
 static const struct gpio_keys_button
 bcm47xx_buttons_asus_wl500w[] __initconst = {
-	BCM47XX_GPIO_KEY(6, KEY_RESTART),
-	BCM47XX_GPIO_KEY(7, KEY_WPS_BUTTON),
+	BCM47XX_GPIO_KEY_H(6, KEY_RESTART),
+	BCM47XX_GPIO_KEY_H(7, KEY_WPS_BUTTON),
 };
 
 static const struct gpio_keys_button
diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S
index 64e08df51d65..8b7004132491 100644
--- a/arch/mips/cavium-octeon/octeon-memcpy.S
+++ b/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -208,18 +208,18 @@ EXC(	STORE	t2, UNIT(6)(dst),	s_exc_p10u)
 	ADD	src, src, 16*NBYTES
 EXC(	STORE	t3, UNIT(7)(dst),	s_exc_p9u)
 	ADD	dst, dst, 16*NBYTES
-EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-8)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-7)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-6)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-5)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-8)(dst),	s_exc_p8u)
 EXC(	STORE	t1, UNIT(-7)(dst),	s_exc_p7u)
 EXC(	STORE	t2, UNIT(-6)(dst),	s_exc_p6u)
 EXC(	STORE	t3, UNIT(-5)(dst),	s_exc_p5u)
-EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(-4)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t1, UNIT(-3)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t2, UNIT(-2)(src),	l_exc_copy_rewind16)
+EXC(	LOAD	t3, UNIT(-1)(src),	l_exc_copy_rewind16)
 EXC(	STORE	t0, UNIT(-4)(dst),	s_exc_p4u)
 EXC(	STORE	t1, UNIT(-3)(dst),	s_exc_p3u)
 EXC(	STORE	t2, UNIT(-2)(dst),	s_exc_p2u)
@@ -383,6 +383,10 @@ done:
 	 nop
 	END(memcpy)
 
+l_exc_copy_rewind16:
+	/* Rewind src and dst by 16*NBYTES for l_exc_copy */
+	SUB	src, src, 16*NBYTES
+	SUB	dst, dst, 16*NBYTES
 l_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index 57ed466e00db..2f140d75d01c 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -68,8 +68,8 @@ CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index 48e16d98b2cc..b15508447366 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -134,7 +134,7 @@ CONFIG_LIBFC=m
 CONFIG_SCSI_QLOGIC_1280=y
 CONFIG_SCSI_PMCRAID=m
 CONFIG_SCSI_BFA_FC=m
-CONFIG_SCSI_DH=m
+CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
@@ -206,7 +206,6 @@ CONFIG_MLX4_EN=m
 # CONFIG_MLX4_DEBUG is not set
 CONFIG_TEHUTI=m
 CONFIG_BNX2X=m
-CONFIG_QLGE=m
 CONFIG_SFC=m
 CONFIG_BE2NET=m
 CONFIG_LIBERTAS_THINFIRM=m
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 004cf52d1b7d..c24b87819ccb 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -39,7 +39,7 @@ CONFIG_HIBERNATION=y
 CONFIG_PM_STD_PARTITION="/dev/hda3"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEBUG=y
-CONFIG_CPU_FREQ_STAT=m
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_STAT_DETAILS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 5afb4840aec7..739ccd0dca64 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -59,8 +59,8 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 98f13879bb8f..47f4ecf125ba 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -60,8 +60,8 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 3b5d5913f548..e79d325aa085 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -59,8 +59,8 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 732215732751..ae87ad86243b 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -61,8 +61,8 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig
index b3d1d37f85ea..47492fee2952 100644
--- a/arch/mips/configs/nlm_xlp_defconfig
+++ b/arch/mips/configs/nlm_xlp_defconfig
@@ -111,7 +111,7 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig
index 3d8016d6cf3e..472a818f1eb8 100644
--- a/arch/mips/configs/nlm_xlr_defconfig
+++ b/arch/mips/configs/nlm_xlr_defconfig
@@ -91,7 +91,7 @@ CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index 8c6f508e59de..554d1da97743 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -146,7 +146,25 @@
 		/*
 		 * Find irq with highest priority
 		 */
-		 PTR_LA	t1,cpu_mask_nr_tbl
+		# open coded PTR_LA t1, cpu_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+		# open coded la t1, cpu_mask_nr_tbl
+		lui	t1, %hi(cpu_mask_nr_tbl)
+		addiu	t1, %lo(cpu_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+		# open coded dla t1, cpu_mask_nr_tbl
+		.set	push
+		.set	noat
+		lui	t1, %highest(cpu_mask_nr_tbl)
+		lui	AT, %hi(cpu_mask_nr_tbl)
+		daddiu	t1, t1, %higher(cpu_mask_nr_tbl)
+		daddiu	AT, AT, %lo(cpu_mask_nr_tbl)
+		dsll	t1, 32
+		daddu	t1, t1, AT
+		.set	pop
+#endif
 1:		lw	t2,(t1)
 		nop
 		and	t2,t0
@@ -195,7 +213,25 @@
 		/*
 		 * Find irq with highest priority
 		 */
-		 PTR_LA	t1,asic_mask_nr_tbl
+		# open coded PTR_LA t1,asic_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+		# open coded la t1, asic_mask_nr_tbl
+		lui	t1, %hi(asic_mask_nr_tbl)
+		addiu	t1, %lo(asic_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+		# open coded dla t1, asic_mask_nr_tbl
+		.set	push
+		.set	noat
+		lui	t1, %highest(asic_mask_nr_tbl)
+		lui	AT, %hi(asic_mask_nr_tbl)
+		daddiu	t1, t1, %higher(asic_mask_nr_tbl)
+		daddiu	AT, AT, %lo(asic_mask_nr_tbl)
+		dsll	t1, 32
+		daddu	t1, t1, AT
+		.set	pop
+#endif
 2:		lw	t2,(t1)
 		nop
 		and	t2,t0
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 867f924b05c7..8dedee1def83 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -135,6 +135,7 @@
 	ldc1	$f28, THREAD_FPR28(\thread)
 	ldc1	$f30, THREAD_FPR30(\thread)
 	ctc1	\tmp, fcr31
+	.set	pop
 	.endm
 
 	.macro	fpu_restore_16odd thread
@@ -298,21 +299,21 @@
 	.set	pop
 	.endm
 
-	.macro	copy_u_w	ws, n
+	.macro	copy_s_w	ws, n
 	.set	push
 	.set	mips32r2
 	.set	fp=64
 	.set	msa
-	copy_u.w $1, $w\ws[\n]
+	copy_s.w $1, $w\ws[\n]
 	.set	pop
 	.endm
 
-	.macro	copy_u_d	ws, n
+	.macro	copy_s_d	ws, n
 	.set	push
 	.set	mips64r2
 	.set	fp=64
 	.set	msa
-	copy_u.d $1, $w\ws[\n]
+	copy_s.d $1, $w\ws[\n]
 	.set	pop
 	.endm
 
@@ -346,8 +347,8 @@
 #define STH_MSA_INSN		0x5800081f
 #define STW_MSA_INSN		0x5800082f
 #define STD_MSA_INSN		0x5800083f
-#define COPY_UW_MSA_INSN	0x58f00056
-#define COPY_UD_MSA_INSN	0x58f80056
+#define COPY_SW_MSA_INSN	0x58b00056
+#define COPY_SD_MSA_INSN	0x58b80056
 #define INSERT_W_MSA_INSN	0x59300816
 #define INSERT_D_MSA_INSN	0x59380816
 #else
@@ -361,8 +362,8 @@
 #define STH_MSA_INSN		0x78000825
 #define STW_MSA_INSN		0x78000826
 #define STD_MSA_INSN		0x78000827
-#define COPY_UW_MSA_INSN	0x78f00059
-#define COPY_UD_MSA_INSN	0x78f80059
+#define COPY_SW_MSA_INSN	0x78b00059
+#define COPY_SD_MSA_INSN	0x78b80059
 #define INSERT_W_MSA_INSN	0x79300819
 #define INSERT_D_MSA_INSN	0x79380819
 #endif
@@ -393,7 +394,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDB_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -402,7 +403,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDH_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -411,7 +412,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDW_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -420,7 +421,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -429,7 +430,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STB_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -438,7 +439,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STH_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -447,7 +448,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STW_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -456,26 +457,26 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
 
-	.macro	copy_u_w	ws, n
+	.macro	copy_s_w	ws, n
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
 	.insn
-	.word	COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11)
+	.word	COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11)
 	.set	pop
 	.endm
 
-	.macro	copy_u_d	ws, n
+	.macro	copy_s_d	ws, n
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
 	.insn
-	.word	COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11)
+	.word	COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11)
 	.set	pop
 	.endm
 
diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h
index de781cf54bc7..da80878f2c0d 100644
--- a/arch/mips/include/asm/branch.h
+++ b/arch/mips/include/asm/branch.h
@@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs)
 			return __microMIPS_compute_return_epc(regs);
 		if (cpu_has_mips16)
 			return __MIPS16e_compute_return_epc(regs);
-		return regs->cp0_epc;
-	}
-
-	if (!delay_slot(regs)) {
+	} else if (!delay_slot(regs)) {
 		regs->cp0_epc += 4;
 		return 0;
 	}
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index 723229f4cf27..176de586a71a 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -51,7 +51,6 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma,
 	unsigned long start, unsigned long end);
 extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn);
 extern void __flush_dcache_page(struct page *page);
-extern void __flush_icache_page(struct vm_area_struct *vma, struct page *page);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 static inline void flush_dcache_page(struct page *page)
@@ -77,11 +76,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 static inline void flush_icache_page(struct vm_area_struct *vma,
 	struct page *page)
 {
-	if (!cpu_has_ic_fills_f_dc && (vma->vm_flags & VM_EXEC) &&
-	    Page_dcache_dirty(page)) {
-		__flush_icache_page(vma, page);
-		ClearPageDcacheDirty(page);
-	}
 }
 
 extern void (*flush_icache_range)(unsigned long start, unsigned long end);
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 3ceacde5eb6e..17f89f9670b2 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -186,7 +186,9 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr,
 	"	daddu	%0, %4		\n"
 	"	dsll32	$1, %0, 0	\n"
 	"	daddu	%0, $1		\n"
+	"	sltu	$1, %0, $1	\n"
 	"	dsra32	%0, %0, 0	\n"
+	"	addu	%0, $1		\n"
 #endif
 	"	.set	pop"
 	: "=r" (sum)
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 15e0fecbc300..ebb9efb02502 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -17,6 +17,18 @@
 
 #include <irq.h>
 
+#define IRQ_STACK_SIZE			THREAD_SIZE
+
+extern void *irq_stack[NR_CPUS];
+
+static inline bool on_irq_stack(int cpu, unsigned long sp)
+{
+	unsigned long low = (unsigned long)irq_stack[cpu];
+	unsigned long high = low + IRQ_STACK_SIZE;
+
+	return (low <= sp && sp <= high);
+}
+
 #ifdef CONFIG_I8259
 static inline int irq_canonicalize(int irq)
 {
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6ded8d347af9..c8c04a1f1c9f 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -372,6 +372,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
 	void *host_ebase, *guest_ebase;
+	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	unsigned long host_stack;
 	unsigned long host_gp;
 
@@ -399,7 +400,10 @@ struct kvm_vcpu_arch {
 	/* Host KSEG0 address of the EI/DI offset */
 	void *kseg0_commpage;
 
-	u32 io_gpr;		/* GPR used as IO source/target */
+	/* Resume PC after MMIO completion */
+	unsigned long io_pc;
+	/* GPR used as IO source/target */
+	u32 io_gpr;
 
 	struct hrtimer comparecount_timer;
 	/* Count timer control KVM register */
@@ -421,8 +425,6 @@ struct kvm_vcpu_arch {
 	/* Bitmask of pending exceptions to be cleared */
 	unsigned long pending_exceptions_clr;
 
-	unsigned long pending_load_cause;
-
 	/* Save/Restore the entryhi register when are are preempted/scheduled back in */
 	unsigned long preempt_entryhi;
 
@@ -784,7 +786,7 @@ extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 
 uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
 void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack);
 void kvm_mips_init_count(struct kvm_vcpu *vcpu);
 int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
 int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
index 2f82bfa3a773..c9f5769dfc8f 100644
--- a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
@@ -11,11 +11,13 @@
 #define CP0_EBASE $15, 1
 
 	.macro  kernel_entry_setup
+#ifdef CONFIG_SMP
 	mfc0	t0, CP0_EBASE
 	andi	t0, t0, 0x3ff		# CPUNum
 	beqz	t0, 1f
 	# CPUs other than zero goto smp_bootstrap
 	j	smp_bootstrap
+#endif /* CONFIG_SMP */
 
 1:
 	.endm
diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h
index bbb85fe21642..6e4effa6f626 100644
--- a/arch/mips/include/asm/msa.h
+++ b/arch/mips/include/asm/msa.h
@@ -147,6 +147,19 @@ static inline void restore_msa(struct task_struct *t)
 		_restore_msa(t);
 }
 
+static inline void init_msa_upper(void)
+{
+	/*
+	 * Check cpu_has_msa only if it's a constant. This will allow the
+	 * compiler to optimise out code for CPUs without MSA without adding
+	 * an extra redundant check for CPUs with MSA.
+	 */
+	if (__builtin_constant_p(cpu_has_msa) && !cpu_has_msa)
+		return;
+
+	_init_msa_upper();
+}
+
 #ifdef TOOLCHAIN_SUPPORTS_MSA
 
 #define __BUILD_MSA_CTL_REG(name, cs)				\
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 18826aa15a7c..4e68c644acc5 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -127,10 +127,14 @@ do {									\
 	}								\
 } while(0)
 
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval);
+
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
 
 #define pte_none(pte)		(!(((pte).pte_high) & ~_PAGE_GLOBAL))
 #define pte_present(pte)	((pte).pte_low & _PAGE_PRESENT)
+#define pte_no_exec(pte)	((pte).pte_low & _PAGE_NO_EXEC)
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
@@ -148,7 +152,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 			buddy->pte_high |= _PAGE_GLOBAL;
 	}
 }
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
@@ -166,6 +169,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 
 #define pte_none(pte)		(!(pte_val(pte) & ~_PAGE_GLOBAL))
 #define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
+#define pte_no_exec(pte)	(pte_val(pte) & _PAGE_NO_EXEC)
 
 /*
  * Certain architectures need to do special things when pte's
@@ -218,7 +222,6 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 	}
 #endif
 }
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
@@ -234,6 +237,22 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 }
 #endif
 
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	extern void __update_cache(unsigned long address, pte_t pte);
+
+	if (!pte_present(pteval))
+		goto cache_sync_done;
+
+	if (pte_present(*ptep) && (pte_pfn(*ptep) == pte_pfn(pteval)))
+		goto cache_sync_done;
+
+	__update_cache(addr, pteval);
+cache_sync_done:
+	set_pte(ptep, pteval);
+}
+
 /*
  * (pmds are folded into puds so this doesn't get actually called,
  * but the define is needed for a generic inline function.)
@@ -430,15 +449,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 extern void __update_tlb(struct vm_area_struct *vma, unsigned long address,
 	pte_t pte);
-extern void __update_cache(struct vm_area_struct *vma, unsigned long address,
-	pte_t pte);
 
 static inline void update_mmu_cache(struct vm_area_struct *vma,
 	unsigned long address, pte_t *ptep)
 {
 	pte_t pte = *ptep;
 	__update_tlb(vma, address, pte);
-	__update_cache(vma, address, pte);
 }
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 3f832c3dd8f5..041153f5cf93 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index f6fc6aac5496..b6578611dddb 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -152,7 +152,7 @@ static inline int is_syscall_success(struct pt_regs *regs)
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	if (is_syscall_success(regs))
+	if (is_syscall_success(regs) || !user_mode(regs))
 		return regs->regs[2];
 	else
 		return -regs->regs[2];
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 40196bebe849..2365ce0ad8f2 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -112,7 +112,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	bne	%[ticket], %[my_ticket], 4f		\n"
 		"	 subu	%[ticket], %[my_ticket], %[ticket]	\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"4:	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	sll	%[ticket], 5				\n"
@@ -187,7 +187,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	sc	%[ticket], %[ticket_ptr]		\n"
 		"	beqz	%[ticket], 1b				\n"
 		"	 li	%[ticket], 1				\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"3:	b	2b					\n"
 		"	 li	%[ticket], 0				\n"
@@ -367,7 +367,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		"	.set	reorder					\n"
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
 		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
@@ -407,7 +407,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	lui	%1, 0x8000			\n"
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
-			"2:						\n"
+			"2:	.insn					\n"
 			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
 			: GCC_OFF_SMALL_ASM() (rw->lock)
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index a71da576883c..5347f130f536 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -216,12 +216,19 @@
 		LONG_S	$25, PT_R25(sp)
 		LONG_S	$28, PT_R28(sp)
 		LONG_S	$31, PT_R31(sp)
+
+		/* Set thread_info if we're coming from user mode */
+		mfc0	k0, CP0_STATUS
+		sll	k0, 3		/* extract cu0 bit */
+		bltz	k0, 9f
+
 		ori	$28, sp, _THREAD_MASK
 		xori	$28, _THREAD_MASK
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 		.set    mips64
 		pref    0, 0($28)       /* Prefetch the current pointer */
 #endif
+9:
 		.set	pop
 		.endm
 
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index 28b5d84a5022..ebb5c0f2f90d 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -105,7 +105,7 @@ do {									\
 	__clear_software_ll_bit();					\
 	if (cpu_has_userlocal)						\
 		write_c0_userlocal(task_thread_info(next)->tp_value);	\
-	__restore_watch();						\
+	__restore_watch(next);						\
 	(last) = resume(prev, next, task_thread_info(next));		\
 } while (0)
 
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 095ecafe6bd3..c74c32ccc647 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/thread_info.h>
+#include <linux/string.h>
 #include <asm/asm-eva.h>
 
 /*
@@ -1170,6 +1171,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
 			__cu_len = __invoke_copy_from_user(__cu_to,	\
 							   __cu_from,	\
 							   __cu_len);   \
+		} else {						\
+			memset(__cu_to, 0, __cu_len);			\
 		}							\
 	}								\
 	__cu_len;							\
diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h
index 34c325c674c4..70a4a2f173ff 100644
--- a/arch/mips/include/asm/uprobes.h
+++ b/arch/mips/include/asm/uprobes.h
@@ -36,7 +36,6 @@ struct arch_uprobe {
 	unsigned long	resume_epc;
 	u32	insn[2];
 	u32	ixol[2];
-	union	mips_instruction orig_inst[MAX_UINSN_BYTES / 4];
 };
 
 struct arch_uprobe_task {
diff --git a/arch/mips/include/asm/watch.h b/arch/mips/include/asm/watch.h
index 20126ec79359..6ffe3eadf105 100644
--- a/arch/mips/include/asm/watch.h
+++ b/arch/mips/include/asm/watch.h
@@ -12,21 +12,21 @@
 
 #include <asm/mipsregs.h>
 
-void mips_install_watch_registers(void);
+void mips_install_watch_registers(struct task_struct *t);
 void mips_read_watch_registers(void);
 void mips_clear_watch_registers(void);
 void mips_probe_watch_registers(struct cpuinfo_mips *c);
 
 #ifdef CONFIG_HARDWARE_WATCHPOINTS
-#define __restore_watch() do {						\
+#define __restore_watch(task) do {					\
 	if (unlikely(test_bit(TIF_LOAD_WATCH,				\
-			      &current_thread_info()->flags))) {	\
-		mips_install_watch_registers();				\
+			      &task_thread_info(task)->flags))) {	\
+		mips_install_watch_registers(task);			\
 	}								\
 } while (0)
 
 #else
-#define __restore_watch() do {} while (0)
+#define __restore_watch(task) do {} while (0)
 #endif
 
 #endif /* _ASM_WATCH_H */
diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h
index 2cb7fdead570..e2b5337e840f 100644
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@@ -28,7 +28,7 @@
 
 #define __ARCH_SIGSYS
 
-#include <uapi/asm-generic/siginfo.h>
+#include <asm-generic/siginfo.h>
 
 /* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
 typedef struct siginfo {
@@ -42,13 +42,13 @@ typedef struct siginfo {
 
 		/* kill() */
 		struct {
-			pid_t _pid;		/* sender's pid */
+			__kernel_pid_t _pid;	/* sender's pid */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 		} _kill;
 
 		/* POSIX.1b timers */
 		struct {
-			timer_t _tid;		/* timer id */
+			__kernel_timer_t _tid;	/* timer id */
 			int _overrun;		/* overrun count */
 			char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)];
 			sigval_t _sigval;	/* same as below */
@@ -57,26 +57,26 @@ typedef struct siginfo {
 
 		/* POSIX.1b signals */
 		struct {
-			pid_t _pid;		/* sender's pid */
+			__kernel_pid_t _pid;	/* sender's pid */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 			sigval_t _sigval;
 		} _rt;
 
 		/* SIGCHLD */
 		struct {
-			pid_t _pid;		/* which child */
+			__kernel_pid_t _pid;	/* which child */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 			int _status;		/* exit code */
-			clock_t _utime;
-			clock_t _stime;
+			__kernel_clock_t _utime;
+			__kernel_clock_t _stime;
 		} _sigchld;
 
 		/* IRIX SIGCHLD */
 		struct {
-			pid_t _pid;		/* which child */
-			clock_t _utime;
+			__kernel_pid_t _pid;	/* which child */
+			__kernel_clock_t _utime;
 			int _status;		/* exit code */
-			clock_t _stime;
+			__kernel_clock_t _stime;
 		} _irix_sigchld;
 
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
@@ -118,6 +118,4 @@ typedef struct siginfo {
 #define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */
 #define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */
 
-#include <asm-generic/siginfo.h>
-
 #endif /* _UAPI_ASM_SIGINFO_H */
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index 154e2039ea5e..ec053ce7bb38 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -101,6 +101,7 @@ void output_thread_info_defines(void)
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
+	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
 	BLANK();
 }
 
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index d8f9b357b222..71e8f4c0b8da 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs)
  *
  * @regs:	Pointer to pt_regs
  * @insn:	branch instruction to decode
- * @returns:	-EFAULT on error and forces SIGBUS, and on success
+ * @returns:	-EFAULT on error and forces SIGILL, and on success
  *		returns 0 or BRANCH_LIKELY_TAKEN as appropriate after
  *		evaluating the branch.
  *
@@ -431,7 +431,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			/* Fall through */
 		case jr_op:
 			if (NO_R6EMU && insn.r_format.func == jr_op)
-				goto sigill_r6;
+				goto sigill_r2r6;
 			regs->cp0_epc = regs->regs[insn.r_format.rs];
 			break;
 		}
@@ -446,7 +446,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		switch (insn.i_format.rt) {
 		case bltzl_op:
 			if (NO_R6EMU)
-				goto sigill_r6;
+				goto sigill_r2r6;
 		case bltz_op:
 			if ((long)regs->regs[insn.i_format.rs] < 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -459,7 +459,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 		case bgezl_op:
 			if (NO_R6EMU)
-				goto sigill_r6;
+				goto sigill_r2r6;
 		case bgez_op:
 			if ((long)regs->regs[insn.i_format.rs] >= 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -473,10 +473,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		case bltzal_op:
 		case bltzall_op:
 			if (NO_R6EMU && (insn.i_format.rs ||
-			    insn.i_format.rt == bltzall_op)) {
-				ret = -SIGILL;
-				break;
-			}
+			    insn.i_format.rt == bltzall_op))
+				goto sigill_r2r6;
 			regs->regs[31] = epc + 8;
 			/*
 			 * OK we are here either because we hit a NAL
@@ -507,10 +505,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		case bgezal_op:
 		case bgezall_op:
 			if (NO_R6EMU && (insn.i_format.rs ||
-			    insn.i_format.rt == bgezall_op)) {
-				ret = -SIGILL;
-				break;
-			}
+			    insn.i_format.rt == bgezall_op))
+				goto sigill_r2r6;
 			regs->regs[31] = epc + 8;
 			/*
 			 * OK we are here either because we hit a BAL
@@ -556,6 +552,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	/*
 	 * These are unconditional and in j_format.
 	 */
+	case jalx_op:
 	case jal_op:
 		regs->regs[31] = regs->cp0_epc + 8;
 	case j_op:
@@ -573,7 +570,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	 */
 	case beql_op:
 		if (NO_R6EMU)
-			goto sigill_r6;
+			goto sigill_r2r6;
 	case beq_op:
 		if (regs->regs[insn.i_format.rs] ==
 		    regs->regs[insn.i_format.rt]) {
@@ -587,7 +584,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 	case bnel_op:
 		if (NO_R6EMU)
-			goto sigill_r6;
+			goto sigill_r2r6;
 	case bne_op:
 		if (regs->regs[insn.i_format.rs] !=
 		    regs->regs[insn.i_format.rt]) {
@@ -601,7 +598,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 	case blezl_op: /* not really i_format */
 		if (!insn.i_format.rt && NO_R6EMU)
-			goto sigill_r6;
+			goto sigill_r2r6;
 	case blez_op:
 		/*
 		 * Compact branches for R6 for the
@@ -636,7 +633,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 	case bgtzl_op:
 		if (!insn.i_format.rt && NO_R6EMU)
-			goto sigill_r6;
+			goto sigill_r2r6;
 	case bgtz_op:
 		/*
 		 * Compact branches for R6 for the
@@ -816,8 +813,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			break;
 		}
 		/* Compact branch: BNEZC || JIALC */
-		if (insn.i_format.rs)
+		if (!insn.i_format.rs) {
+			/* JIALC: set $31/ra */
 			regs->regs[31] = epc + 4;
+		}
 		regs->cp0_epc += 8;
 		break;
 #endif
@@ -841,11 +840,12 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	return ret;
 
 sigill_dsp:
-	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
-	force_sig(SIGBUS, current);
+	pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n",
+		current->comm);
+	force_sig(SIGILL, current);
 	return -EFAULT;
-sigill_r6:
-	pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n",
+sigill_r2r6:
+	pr_info("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n",
 		current->comm);
 	force_sig(SIGILL, current);
 	return -EFAULT;
diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c
index d434d5d5ae6e..610f0f3bdb34 100644
--- a/arch/mips/kernel/crash.c
+++ b/arch/mips/kernel/crash.c
@@ -14,12 +14,22 @@ static int crashing_cpu = -1;
 static cpumask_t cpus_in_crash = CPU_MASK_NONE;
 
 #ifdef CONFIG_SMP
-static void crash_shutdown_secondary(void *ignore)
+static void crash_shutdown_secondary(void *passed_regs)
 {
-	struct pt_regs *regs;
+	struct pt_regs *regs = passed_regs;
 	int cpu = smp_processor_id();
 
-	regs = task_pt_regs(current);
+	/*
+	 * If we are passed registers, use those.  Otherwise get the
+	 * regs from the last interrupt, which should be correct, as
+	 * we are in an interrupt.  But if the regs are not there,
+	 * pull them from the top of the stack.  They are probably
+	 * wrong, but we need something to keep from crashing again.
+	 */
+	if (!regs)
+		regs = get_irq_regs();
+	if (!regs)
+		regs = task_pt_regs(current);
 
 	if (!cpu_online(cpu))
 		return;
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index 1f910563fdf6..d76275da54cb 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index 4a4d9e067c89..3afffc30ee12 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -206,7 +206,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
 	else if ((prog_req.fr1 && prog_req.frdefault) ||
 		 (prog_req.single && !prog_req.frdefault))
 		/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
-		state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+		state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
 					  cpu_has_mips_r2_r6) ?
 					  FP_FR1 : FP_FR0;
 	else if (prog_req.fr1)
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 7791840cf22c..db07793f7b43 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -137,6 +138,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and
@@ -173,6 +175,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index baa7b6fc0a60..619e30e2c4f0 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -188,9 +188,44 @@ NESTED(handle_int, PT_SIZE, sp)
 
 	LONG_L	s0, TI_REGS($28)
 	LONG_S	sp, TI_REGS($28)
-	PTR_LA	ra, ret_from_irq
-	PTR_LA  v0, plat_irq_dispatch
-	jr	v0
+
+	/*
+	 * SAVE_ALL ensures we are using a valid kernel stack for the thread.
+	 * Check if we are already using the IRQ stack.
+	 */
+	move	s1, sp # Preserve the sp
+
+	/* Get IRQ stack for this CPU */
+	ASM_CPUID_MFC0	k0, ASM_SMP_CPUID_REG
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
+	lui	k1, %hi(irq_stack)
+#else
+	lui	k1, %highest(irq_stack)
+	daddiu	k1, %higher(irq_stack)
+	dsll	k1, 16
+	daddiu	k1, %hi(irq_stack)
+	dsll	k1, 16
+#endif
+	LONG_SRL	k0, SMP_CPUID_PTRSHIFT
+	LONG_ADDU	k1, k0
+	LONG_L	t0, %lo(irq_stack)(k1)
+
+	# Check if already on IRQ stack
+	PTR_LI	t1, ~(_THREAD_SIZE-1)
+	and	t1, t1, sp
+	beq	t0, t1, 2f
+
+	/* Switch to IRQ stack */
+	li	t1, _IRQ_STACK_SIZE
+	PTR_ADD sp, t0, t1
+
+2:
+	jal	plat_irq_dispatch
+
+	/* Restore sp */
+	move	sp, s1
+
+	j	ret_from_irq
 #ifdef CONFIG_CPU_MICROMIPS
 	nop
 #endif
@@ -263,8 +298,44 @@ NESTED(except_vec_vi_handler, 0, sp)
 
 	LONG_L	s0, TI_REGS($28)
 	LONG_S	sp, TI_REGS($28)
-	PTR_LA	ra, ret_from_irq
-	jr	v0
+
+	/*
+	 * SAVE_ALL ensures we are using a valid kernel stack for the thread.
+	 * Check if we are already using the IRQ stack.
+	 */
+	move	s1, sp # Preserve the sp
+
+	/* Get IRQ stack for this CPU */
+	ASM_CPUID_MFC0	k0, ASM_SMP_CPUID_REG
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
+	lui	k1, %hi(irq_stack)
+#else
+	lui	k1, %highest(irq_stack)
+	daddiu	k1, %higher(irq_stack)
+	dsll	k1, 16
+	daddiu	k1, %hi(irq_stack)
+	dsll	k1, 16
+#endif
+	LONG_SRL	k0, SMP_CPUID_PTRSHIFT
+	LONG_ADDU	k1, k0
+	LONG_L	t0, %lo(irq_stack)(k1)
+
+	# Check if already on IRQ stack
+	PTR_LI	t1, ~(_THREAD_SIZE-1)
+	and	t1, t1, sp
+	beq	t0, t1, 2f
+
+	/* Switch to IRQ stack */
+	li	t1, _IRQ_STACK_SIZE
+	PTR_ADD sp, t0, t1
+
+2:
+	jalr	v0
+
+	/* Restore sp */
+	move	sp, s1
+
+	j	ret_from_irq
 	END(except_vec_vi_handler)
 
 /*
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 8eb5af805964..dc1180a8bfa1 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -25,6 +25,8 @@
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
 
+void *irq_stack[NR_CPUS];
+
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.
@@ -55,6 +57,15 @@ void __init init_IRQ(void)
 		irq_set_noprobe(i);
 
 	arch_init_irq();
+
+	for_each_possible_cpu(i) {
+		int irq_pages = IRQ_STACK_SIZE / PAGE_SIZE;
+		void *s = (void *)__get_free_pages(GFP_KERNEL, irq_pages);
+
+		irq_stack[i] = s;
+		pr_debug("CPU%d IRQ stack at 0x%p - 0x%p\n", i,
+			irq_stack[i], irq_stack[i] + IRQ_STACK_SIZE);
+	}
 }
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index de63d36af895..732d6171ac6a 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -244,9 +244,6 @@ static int compute_signal(int tt)
 void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
 	int reg;
-	struct thread_info *ti = task_thread_info(p);
-	unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32;
-	struct pt_regs *regs = (struct pt_regs *)ksp - 1;
 #if (KGDB_GDB_REG_SIZE == 32)
 	u32 *ptr = (u32 *)gdb_regs;
 #else
@@ -254,25 +251,46 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 #endif
 
 	for (reg = 0; reg < 16; reg++)
-		*(ptr++) = regs->regs[reg];
+		*(ptr++) = 0;
 
 	/* S0 - S7 */
-	for (reg = 16; reg < 24; reg++)
-		*(ptr++) = regs->regs[reg];
+	*(ptr++) = p->thread.reg16;
+	*(ptr++) = p->thread.reg17;
+	*(ptr++) = p->thread.reg18;
+	*(ptr++) = p->thread.reg19;
+	*(ptr++) = p->thread.reg20;
+	*(ptr++) = p->thread.reg21;
+	*(ptr++) = p->thread.reg22;
+	*(ptr++) = p->thread.reg23;
 
 	for (reg = 24; reg < 28; reg++)
 		*(ptr++) = 0;
 
 	/* GP, SP, FP, RA */
-	for (reg = 28; reg < 32; reg++)
-		*(ptr++) = regs->regs[reg];
-
-	*(ptr++) = regs->cp0_status;
-	*(ptr++) = regs->lo;
-	*(ptr++) = regs->hi;
-	*(ptr++) = regs->cp0_badvaddr;
-	*(ptr++) = regs->cp0_cause;
-	*(ptr++) = regs->cp0_epc;
+	*(ptr++) = (long)p;
+	*(ptr++) = p->thread.reg29;
+	*(ptr++) = p->thread.reg30;
+	*(ptr++) = p->thread.reg31;
+
+	*(ptr++) = p->thread.cp0_status;
+
+	/* lo, hi */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * BadVAddr, Cause
+	 * Ideally these would come from the last exception frame up the stack
+	 * but that requires unwinding, otherwise we can't know much for sure.
+	 */
+	*(ptr++) = 0;
+	*(ptr++) = 0;
+
+	/*
+	 * PC
+	 * use return address (RA), i.e. the moment after return from resume()
+	 */
+	*(ptr++) = p->thread.reg31;
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 1f5aac7f9ec3..e3384065f5e7 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -28,6 +28,7 @@
 #include <asm/inst.h>
 #include <asm/mips-r2-to-r6-emul.h>
 #include <asm/local.h>
+#include <asm/mipsregs.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
@@ -433,8 +434,8 @@ static int multu_func(struct pt_regs *regs, u32 ir)
 	rs = regs->regs[MIPSInst_RS(ir)];
 	res = (u64)rt * (u64)rs;
 	rt = res;
-	regs->lo = (s64)rt;
-	regs->hi = (s64)(res >> 32);
+	regs->lo = (s64)(s32)rt;
+	regs->hi = (s64)(s32)(res >> 32);
 
 	MIPS_R2_STATS(muls);
 
@@ -670,9 +671,9 @@ static int maddu_func(struct pt_regs *regs, u32 ir)
 	res += ((((s64)rt) << 32) | (u32)rs);
 
 	rt = res;
-	regs->lo = (s64)rt;
+	regs->lo = (s64)(s32)rt;
 	rs = res >> 32;
-	regs->hi = (s64)rs;
+	regs->hi = (s64)(s32)rs;
 
 	MIPS_R2_STATS(dsps);
 
@@ -728,9 +729,9 @@ static int msubu_func(struct pt_regs *regs, u32 ir)
 	res = ((((s64)rt) << 32) | (u32)rs) - res;
 
 	rt = res;
-	regs->lo = (s64)rt;
+	regs->lo = (s64)(s32)rt;
 	rs = res >> 32;
-	regs->hi = (s64)rs;
+	regs->hi = (s64)(s32)rs;
 
 	MIPS_R2_STATS(dsps);
 
@@ -1163,7 +1164,9 @@ fpu_emul:
 		regs->regs[31] = r31;
 		regs->cp0_epc = epc;
 		if (!used_math()) {     /* First time FPU user.  */
+			preempt_disable();
 			err = init_fpu();
+			preempt_enable();
 			set_used_math();
 		}
 		lose_fpu(1);    /* Save FPU state for the emulator. */
@@ -1251,10 +1254,10 @@ fpu_emul:
 			"	j	10b\n"
 			"	.previous\n"
 			"	.section	__ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1326,10 +1329,10 @@ fpu_emul:
 			"	j	10b\n"
 			"       .previous\n"
 			"	.section	__ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1397,10 +1400,10 @@ fpu_emul:
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1467,10 +1470,10 @@ fpu_emul:
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1582,14 +1585,14 @@ fpu_emul:
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
-			"	.word	5b,8b\n"
-			"	.word	6b,8b\n"
-			"	.word	7b,8b\n"
-			"	.word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1701,14 +1704,14 @@ fpu_emul:
 			"	j      9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word  1b,8b\n"
-			"	.word  2b,8b\n"
-			"	.word  3b,8b\n"
-			"	.word  4b,8b\n"
-			"	.word  5b,8b\n"
-			"	.word  6b,8b\n"
-			"	.word  7b,8b\n"
-			"	.word  0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set    pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1820,14 +1823,14 @@ fpu_emul:
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
-			"	.word	5b,8b\n"
-			"	.word	6b,8b\n"
-			"	.word	7b,8b\n"
-			"	.word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -1938,14 +1941,14 @@ fpu_emul:
 			"       j	9b\n"
 			"       .previous\n"
 			"       .section        __ex_table,\"a\"\n"
-			"       .word	1b,8b\n"
-			"       .word	2b,8b\n"
-			"       .word	3b,8b\n"
-			"       .word	4b,8b\n"
-			"       .word	5b,8b\n"
-			"       .word	6b,8b\n"
-			"       .word	7b,8b\n"
-			"       .word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"       .previous\n"
 			"       .set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@@ -2000,7 +2003,7 @@ fpu_emul:
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word  1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "=&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV)
@@ -2058,7 +2061,7 @@ fpu_emul:
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word	1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "+&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV));
@@ -2119,7 +2122,7 @@ fpu_emul:
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word  1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "=&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV)
@@ -2182,7 +2185,7 @@ fpu_emul:
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word	1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "+&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV));
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index f63a289977cc..0b3e58a3189f 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -55,7 +55,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
  * state. Actually per-core rather than per-CPU.
  */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
 
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
@@ -625,7 +624,6 @@ static int __init cps_gen_core_entries(unsigned cpu)
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
@@ -645,16 +643,11 @@ static int __init cps_gen_core_entries(unsigned cpu)
 	}
 
 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}
 
diff --git a/arch/mips/kernel/pm.c b/arch/mips/kernel/pm.c
index fefdf39d3df3..dc814892133c 100644
--- a/arch/mips/kernel/pm.c
+++ b/arch/mips/kernel/pm.c
@@ -56,7 +56,7 @@ static void mips_cpu_restore(void)
 		write_c0_userlocal(current_thread_info()->tp_value);
 
 	/* Restore watch registers */
-	__restore_watch();
+	__restore_watch(current);
 }
 
 /**
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 298b2b773d12..f1fab6ff53e6 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	}
 
 	seq_printf(m, "isa\t\t\t:"); 
-	if (cpu_has_mips_r1)
+	if (cpu_has_mips_1)
 		seq_printf(m, " mips1");
 	if (cpu_has_mips_2)
 		seq_printf(m, "%s", " mips2");
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index f2975d4d1e44..8c26ecac930d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -32,6 +32,7 @@
 #include <asm/cpu.h>
 #include <asm/dsp.h>
 #include <asm/fpu.h>
+#include <asm/irq.h>
 #include <asm/msa.h>
 #include <asm/pgtable.h>
 #include <asm/mipsregs.h>
@@ -191,11 +192,9 @@ struct mips_frame_info {
 #define J_TARGET(pc,target)	\
 		(((unsigned long)(pc) & 0xf0000000) | ((target) << 2))
 
-static inline int is_ra_save_ins(union mips_instruction *ip)
+static inline int is_ra_save_ins(union mips_instruction *ip, int *poff)
 {
 #ifdef CONFIG_CPU_MICROMIPS
-	union mips_instruction mmi;
-
 	/*
 	 * swsp ra,offset
 	 * swm16 reglist,offset(sp)
@@ -205,29 +204,71 @@ static inline int is_ra_save_ins(union mips_instruction *ip)
 	 *
 	 * microMIPS is way more fun...
 	 */
-	if (mm_insn_16bit(ip->halfword[0])) {
-		mmi.word = (ip->halfword[0] << 16);
-		return (mmi.mm16_r5_format.opcode == mm_swsp16_op &&
-			mmi.mm16_r5_format.rt == 31) ||
-		       (mmi.mm16_m_format.opcode == mm_pool16c_op &&
-			mmi.mm16_m_format.func == mm_swm16_op);
+	if (mm_insn_16bit(ip->halfword[1])) {
+		switch (ip->mm16_r5_format.opcode) {
+		case mm_swsp16_op:
+			if (ip->mm16_r5_format.rt != 31)
+				return 0;
+
+			*poff = ip->mm16_r5_format.simmediate;
+			*poff = (*poff << 2) / sizeof(ulong);
+			return 1;
+
+		case mm_pool16c_op:
+			switch (ip->mm16_m_format.func) {
+			case mm_swm16_op:
+				*poff = ip->mm16_m_format.imm;
+				*poff += 1 + ip->mm16_m_format.rlist;
+				*poff = (*poff << 2) / sizeof(ulong);
+				return 1;
+
+			default:
+				return 0;
+			}
+
+		default:
+			return 0;
+		}
 	}
-	else {
-		mmi.halfword[0] = ip->halfword[1];
-		mmi.halfword[1] = ip->halfword[0];
-		return (mmi.mm_m_format.opcode == mm_pool32b_op &&
-			mmi.mm_m_format.rd > 9 &&
-			mmi.mm_m_format.base == 29 &&
-			mmi.mm_m_format.func == mm_swm32_func) ||
-		       (mmi.i_format.opcode == mm_sw32_op &&
-			mmi.i_format.rs == 29 &&
-			mmi.i_format.rt == 31);
+
+	switch (ip->i_format.opcode) {
+	case mm_sw32_op:
+		if (ip->i_format.rs != 29)
+			return 0;
+		if (ip->i_format.rt != 31)
+			return 0;
+
+		*poff = ip->i_format.simmediate / sizeof(ulong);
+		return 1;
+
+	case mm_pool32b_op:
+		switch (ip->mm_m_format.func) {
+		case mm_swm32_func:
+			if (ip->mm_m_format.rd < 0x10)
+				return 0;
+			if (ip->mm_m_format.base != 29)
+				return 0;
+
+			*poff = ip->mm_m_format.simmediate;
+			*poff += (ip->mm_m_format.rd & 0xf) * sizeof(u32);
+			*poff /= sizeof(ulong);
+			return 1;
+		default:
+			return 0;
+		}
+
+	default:
+		return 0;
 	}
 #else
 	/* sw / sd $ra, offset($sp) */
-	return (ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) &&
-		ip->i_format.rs == 29 &&
-		ip->i_format.rt == 31;
+	if ((ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) &&
+		ip->i_format.rs == 29 && ip->i_format.rt == 31) {
+		*poff = ip->i_format.simmediate / sizeof(ulong);
+		return 1;
+	}
+
+	return 0;
 #endif
 }
 
@@ -242,13 +283,16 @@ static inline int is_jump_ins(union mips_instruction *ip)
 	 *
 	 * microMIPS is kind of more fun...
 	 */
-	union mips_instruction mmi;
-
-	mmi.word = (ip->halfword[0] << 16);
+	if (mm_insn_16bit(ip->halfword[1])) {
+		if ((ip->mm16_r5_format.opcode == mm_pool16c_op &&
+		    (ip->mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op))
+			return 1;
+		return 0;
+	}
 
-	if ((mmi.mm16_r5_format.opcode == mm_pool16c_op &&
-	    (mmi.mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op) ||
-	    ip->j_format.opcode == mm_jal32_op)
+	if (ip->j_format.opcode == mm_j32_op)
+		return 1;
+	if (ip->j_format.opcode == mm_jal32_op)
 		return 1;
 	if (ip->r_format.opcode != mm_pool32a_op ||
 			ip->r_format.func != mm_pool32axf_op)
@@ -276,15 +320,13 @@ static inline int is_sp_move_ins(union mips_instruction *ip)
 	 *
 	 * microMIPS is not more fun...
 	 */
-	if (mm_insn_16bit(ip->halfword[0])) {
-		union mips_instruction mmi;
-
-		mmi.word = (ip->halfword[0] << 16);
-		return (mmi.mm16_r3_format.opcode == mm_pool16d_op &&
-			mmi.mm16_r3_format.simmediate && mm_addiusp_func) ||
-		       (mmi.mm16_r5_format.opcode == mm_pool16d_op &&
-			mmi.mm16_r5_format.rt == 29);
+	if (mm_insn_16bit(ip->halfword[1])) {
+		return (ip->mm16_r3_format.opcode == mm_pool16d_op &&
+			ip->mm16_r3_format.simmediate && mm_addiusp_func) ||
+		       (ip->mm16_r5_format.opcode == mm_pool16d_op &&
+			ip->mm16_r5_format.rt == 29);
 	}
+
 	return ip->mm_i_format.opcode == mm_addiu32_op &&
 	       ip->mm_i_format.rt == 29 && ip->mm_i_format.rs == 29;
 #else
@@ -299,30 +341,36 @@ static inline int is_sp_move_ins(union mips_instruction *ip)
 
 static int get_frame_info(struct mips_frame_info *info)
 {
-#ifdef CONFIG_CPU_MICROMIPS
-	union mips_instruction *ip = (void *) (((char *) info->func) - 1);
-#else
-	union mips_instruction *ip = info->func;
-#endif
-	unsigned max_insns = info->func_size / sizeof(union mips_instruction);
-	unsigned i;
+	bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
+	union mips_instruction insn, *ip, *ip_end;
+	const unsigned int max_insns = 128;
+	unsigned int i;
 
 	info->pc_offset = -1;
 	info->frame_size = 0;
 
+	ip = (void *)msk_isa16_mode((ulong)info->func);
 	if (!ip)
 		goto err;
 
-	if (max_insns == 0)
-		max_insns = 128U;	/* unknown function size */
-	max_insns = min(128U, max_insns);
+	ip_end = (void *)ip + info->func_size;
 
-	for (i = 0; i < max_insns; i++, ip++) {
+	for (i = 0; i < max_insns && ip < ip_end; i++, ip++) {
+		if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
+			insn.halfword[0] = 0;
+			insn.halfword[1] = ip->halfword[0];
+		} else if (is_mmips) {
+			insn.halfword[0] = ip->halfword[1];
+			insn.halfword[1] = ip->halfword[0];
+		} else {
+			insn.word = ip->word;
+		}
 
-		if (is_jump_ins(ip))
+		if (is_jump_ins(&insn))
 			break;
+
 		if (!info->frame_size) {
-			if (is_sp_move_ins(ip))
+			if (is_sp_move_ins(&insn))
 			{
 #ifdef CONFIG_CPU_MICROMIPS
 				if (mm_insn_16bit(ip->halfword[0]))
@@ -345,11 +393,9 @@ static int get_frame_info(struct mips_frame_info *info)
 			}
 			continue;
 		}
-		if (info->pc_offset == -1 && is_ra_save_ins(ip)) {
-			info->pc_offset =
-				ip->i_format.simmediate / sizeof(long);
+		if (info->pc_offset == -1 &&
+		    is_ra_save_ins(&insn, &info->pc_offset))
 			break;
-		}
 	}
 	if (info->frame_size && info->pc_offset >= 0) /* nested */
 		return 0;
@@ -457,7 +503,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 		    *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
 			regs = (struct pt_regs *)*sp;
 			pc = regs->cp0_epc;
-			if (__kernel_text_address(pc)) {
+			if (!user_mode(regs) && __kernel_text_address(pc)) {
 				*sp = regs->regs[29];
 				*ra = regs->regs[31];
 				return pc;
@@ -507,7 +553,19 @@ EXPORT_SYMBOL(unwind_stack_by_address);
 unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 			   unsigned long pc, unsigned long *ra)
 {
-	unsigned long stack_page = (unsigned long)task_stack_page(task);
+	unsigned long stack_page = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (on_irq_stack(cpu, *sp)) {
+			stack_page = (unsigned long)irq_stack[cpu];
+			break;
+		}
+	}
+
+	if (!stack_page)
+		stack_page = (unsigned long)task_stack_page(task);
+
 	return unwind_stack_by_address(stack_page, sp, pc, ra);
 }
 #endif
@@ -593,16 +651,19 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 		return -EOPNOTSUPP;
 
 	/* Avoid inadvertently triggering emulation */
-	if ((value & PR_FP_MODE_FR) && cpu_has_fpu &&
-	    !(current_cpu_data.fpu_id & MIPS_FPIR_F64))
+	if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
+	    !(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
 		return -EOPNOTSUPP;
-	if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre)
+	if ((value & PR_FP_MODE_FRE) && raw_cpu_has_fpu && !cpu_has_fre)
 		return -EOPNOTSUPP;
 
 	/* FR = 0 not supported in MIPS R6 */
-	if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6)
+	if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
 		return -EOPNOTSUPP;
 
+	/* Proceed with the mode switch */
+	preempt_disable();
+
 	/* Save FP & vector context, then disable FPU & MSA */
 	if (task->signal == current->signal)
 		lose_fpu(1);
@@ -661,6 +722,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 
 	/* Allow threads to use FP again */
 	atomic_set(&task->mm->context.fp_mode_switching, 0);
+	preempt_enable();
 
 	return 0;
 }
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 4f0ac78d17f1..24c115a0721a 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -57,8 +57,7 @@ static void init_fp_ctx(struct task_struct *target)
 	/* Begin with data registers set to all 1s... */
 	memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr));
 
-	/* ...and FCSR zeroed */
-	target->thread.fpu.fcr31 = 0;
+	/* FCSR has been preset by `mips_set_personality_nan'.  */
 
 	/*
 	 * Record that the target has "used" math, such that the context
@@ -80,6 +79,22 @@ void ptrace_disable(struct task_struct *child)
 }
 
 /*
+ * Poke at FCSR according to its mask.  Don't set the cause bits as
+ * this is currently not handled correctly in FP context restoration
+ * and will cause an oops if a corresponding enable bit is set.
+ */
+static void ptrace_setfcr31(struct task_struct *child, u32 value)
+{
+	u32 fcr31;
+	u32 mask;
+
+	value &= ~FPU_CSR_ALL_X;
+	fcr31 = child->thread.fpu.fcr31;
+	mask = boot_cpu_data.fpu_msk31;
+	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+}
+
+/*
  * Read a general register set.	 We always use the 64-bit format, even
  * for 32-bit kernels and for 32-bit processes on a 64-bit kernel.
  * Registers are sign extended to fill the available space.
@@ -159,9 +174,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 {
 	union fpureg *fregs;
 	u64 fpr_val;
-	u32 fcr31;
 	u32 value;
-	u32 mask;
 	int i;
 
 	if (!access_ok(VERIFY_READ, data, 33 * 8))
@@ -176,9 +189,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 	}
 
 	__get_user(value, data + 64);
-	fcr31 = child->thread.fpu.fcr31;
-	mask = boot_cpu_data.fpu_msk31;
-	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+	ptrace_setfcr31(child, value);
 
 	/* FIR may not be written.  */
 
@@ -474,7 +485,8 @@ static int fpr_set(struct task_struct *target,
 					  &target->thread.fpu,
 					  0, sizeof(elf_fpregset_t));
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
 		err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					 &fpr_val, i * sizeof(elf_fpreg_t),
 					 (i + 1) * sizeof(elf_fpreg_t));
@@ -808,7 +820,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
-			child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
+			ptrace_setfcr31(child, data);
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;
@@ -915,7 +927,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->regs[2]);
+		trace_sys_exit(regs, regs_return_value(regs));
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index f09546ee2cdc..bc74485ec805 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -244,17 +244,17 @@ LEAF(\name)
 	.set	push
 	.set	noat
 #ifdef CONFIG_64BIT
-	copy_u_d \wr, 1
+	copy_s_d \wr, 1
 	EX sd	$1, \off(\base)
 #elif defined(CONFIG_CPU_LITTLE_ENDIAN)
-	copy_u_w \wr, 2
+	copy_s_w \wr, 2
 	EX sw	$1, \off(\base)
-	copy_u_w \wr, 3
+	copy_s_w \wr, 3
 	EX sw	$1, (\off+4)(\base)
 #else /* CONFIG_CPU_BIG_ENDIAN */
-	copy_u_w \wr, 2
+	copy_s_w \wr, 2
 	EX sw	$1, (\off+4)(\base)
-	copy_u_w \wr, 3
+	copy_s_w \wr, 3
 	EX sw	$1, \off(\base)
 #endif
 	.set	pop
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 2d23c834ba96..29b0c5f978e4 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -372,7 +372,7 @@ EXPORT(sys_call_table)
 	PTR	sys_writev
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_ni_syscall			/* 4150 */
 	PTR	sys_getsid
 	PTR	sys_fdatasync
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index deac63315d0e..a6323a969919 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -312,7 +312,7 @@ EXPORT(sys_call_table)
 	PTR	sys_sched_getaffinity
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_io_setup			/* 5200 */
 	PTR	sys_io_destroy
 	PTR	sys_io_getevents
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5a69eb48d0a8..e0fdca8d3abe 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -298,7 +298,7 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_sched_getaffinity
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	compat_sys_io_setup			/* 6200 */
 	PTR	sys_io_destroy
 	PTR	compat_sys_io_getevents
@@ -344,7 +344,7 @@ EXPORT(sysn32_call_table)
 	PTR	sys_ni_syscall			/* available, was setaltroot */
 	PTR	sys_add_key
 	PTR	sys_request_key
-	PTR	sys_keyctl			/* 6245 */
+	PTR	compat_sys_keyctl		/* 6245 */
 	PTR	sys_set_thread_area
 	PTR	sys_inotify_init
 	PTR	sys_inotify_add_watch
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index e4b6d7c97822..87c697181d25 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -367,7 +367,7 @@ EXPORT(sys32_call_table)
 	PTR	compat_sys_writev
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_ni_syscall			/* 4150 */
 	PTR	sys_getsid
 	PTR	sys_fdatasync
@@ -500,7 +500,7 @@ EXPORT(sys32_call_table)
 	PTR	sys_ni_syscall			/* available, was setaltroot */
 	PTR	sys_add_key			/* 4280 */
 	PTR	sys_request_key
-	PTR	sys_keyctl
+	PTR	compat_sys_keyctl
 	PTR	sys_set_thread_area
 	PTR	sys_inotify_init
 	PTR	sys_inotify_add_watch		/* 4285 */
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 66aac55df349..8acae316f26b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -706,6 +706,9 @@ static void __init arch_mem_init(char **cmdline_p)
 	for_each_memblock(reserved, reg)
 		if (reg->size != 0)
 			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+
+	reserve_bootmem_region(__pa_symbol(&__nosave_begin),
+			__pa_symbol(&__nosave_end)); /* Reserve for hibernation */
 }
 
 static void __init resource_init(void)
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index bf792e2839a6..9e35b6b26aa8 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -195,6 +195,9 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size)
 	unsigned int csr;
 	int i, err;
 
+	if (!config_enabled(CONFIG_CPU_HAS_MSA))
+		return SIGSYS;
+
 	if (size != sizeof(*msa))
 		return -EINVAL;
 
@@ -398,8 +401,8 @@ int protected_restore_fp_context(void __user *sc)
 	}
 
 fp_done:
-	if (used & USED_EXTCONTEXT)
-		err |= restore_extcontext(sc_to_extcontext(sc));
+	if (!err && (used & USED_EXTCONTEXT))
+		err = restore_extcontext(sc_to_extcontext(sc));
 
 	return err ?: sig;
 }
@@ -767,15 +770,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 	struct mips_abi *abi = current->thread.abi;
-#ifdef CONFIG_CPU_MICROMIPS
-	void *vdso;
-	unsigned long tmp = (unsigned long)current->mm->context.vdso;
-
-	set_isa16_mode(tmp);
-	vdso = (void *)tmp;
-#else
 	void *vdso = current->mm->context.vdso;
-#endif
 
 	if (regs->regs[0]) {
 		switch(regs->regs[2]) {
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 2b521e07b860..7fef02a9eb85 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -174,6 +174,9 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
+	cpumask_set_cpu(cpu, &cpu_callin_map);
+	synchronise_count_slave(cpu);
+
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -181,10 +184,6 @@ asmlinkage void start_secondary(void)
 
 	calculate_cpu_foreign_map();
 
-	cpumask_set_cpu(cpu, &cpu_callin_map);
-
-	synchronise_count_slave(cpu);
-
 	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 53a7ef9a8f32..4234b2d726c5 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -28,6 +28,7 @@
 #include <linux/elf.h>
 
 #include <asm/asm.h>
+#include <asm/asm-eva.h>
 #include <asm/branch.h>
 #include <asm/cachectl.h>
 #include <asm/cacheflush.h>
@@ -138,10 +139,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 		__asm__ __volatile__ (
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"	li	%[err], 0				\n"
-		"1:	ll	%[old], (%[addr])			\n"
+		"1:							\n"
+		user_ll("%[old]", "(%[addr])")
 		"	move	%[tmp], %[new]				\n"
-		"2:	sc	%[tmp], (%[addr])			\n"
-		"	bnez	%[tmp], 4f				\n"
+		"2:							\n"
+		user_sc("%[tmp]", "(%[addr])")
+		"	beqz	%[tmp], 4f				\n"
 		"3:							\n"
 		"	.insn						\n"
 		"	.subsection 2					\n"
@@ -199,6 +202,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 	unreachable();
 }
 
+/*
+ * mips_atomic_set() normally returns directly via syscall_exit potentially
+ * clobbering static registers, so be sure to preserve them.
+ */
+save_static_function(sys_sysmips);
+
 SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2)
 {
 	switch (cmd) {
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ca9a81007489..31ca2edd7218 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -144,7 +144,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
 	if (!task)
 		task = current;
 
-	if (raw_show_trace || !__kernel_text_address(pc)) {
+	if (raw_show_trace || user_mode(regs) || !__kernel_text_address(pc)) {
 		show_raw_backtrace(sp);
 		return;
 	}
@@ -194,6 +194,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
@@ -1241,7 +1243,7 @@ static int enable_restore_fp_context(int msa)
 		err = init_fpu();
 		if (msa && !err) {
 			enable_msa();
-			_init_msa_upper();
+			init_msa_upper();
 			set_thread_flag(TIF_USEDMSA);
 			set_thread_flag(TIF_MSA_CTX_LIVE);
 		}
@@ -1304,7 +1306,7 @@ static int enable_restore_fp_context(int msa)
 	 */
 	prior_msa = test_and_set_thread_flag(TIF_MSA_CTX_LIVE);
 	if (!prior_msa && was_fpu_owner) {
-		_init_msa_upper();
+		init_msa_upper();
 
 		goto out;
 	}
@@ -1321,7 +1323,7 @@ static int enable_restore_fp_context(int msa)
 		 * of each vector register such that it cannot see data left
 		 * behind by another task.
 		 */
-		_init_msa_upper();
+		init_msa_upper();
 	} else {
 		/* We need to restore the vector context. */
 		restore_msa(current);
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 490cea569d57..5c62065cbf22 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 {
 	union mips_instruction insn;
 	unsigned long value;
-	unsigned int res;
+	unsigned int res, preempted;
 	unsigned long origpc;
 	unsigned long orig31;
 	void __user *fault_addr = NULL;
@@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			if (!access_ok(VERIFY_READ, addr, sizeof(*fpr)))
 				goto sigbus;
 
-			/*
-			 * Disable preemption to avoid a race between copying
-			 * state from userland, migrating to another CPU and
-			 * updating the hardware vector register below.
-			 */
-			preempt_disable();
-
-			res = __copy_from_user_inatomic(fpr, addr,
-							sizeof(*fpr));
-			if (res)
-				goto fault;
-
-			/*
-			 * Update the hardware register if it is in use by the
-			 * task in this quantum, in order to avoid having to
-			 * save & restore the whole vector context.
-			 */
-			if (test_thread_flag(TIF_USEDMSA))
-				write_msa_wr(wd, fpr, df);
+			do {
+				/*
+				 * If we have live MSA context keep track of
+				 * whether we get preempted in order to avoid
+				 * the register context we load being clobbered
+				 * by the live context as it's saved during
+				 * preemption. If we don't have live context
+				 * then it can't be saved to clobber the value
+				 * we load.
+				 */
+				preempted = test_thread_flag(TIF_USEDMSA);
+
+				res = __copy_from_user_inatomic(fpr, addr,
+								sizeof(*fpr));
+				if (res)
+					goto fault;
 
-			preempt_enable();
+				/*
+				 * Update the hardware register if it is in use
+				 * by the task in this quantum, in order to
+				 * avoid having to save & restore the whole
+				 * vector context.
+				 */
+				preempt_disable();
+				if (test_thread_flag(TIF_USEDMSA)) {
+					write_msa_wr(wd, fpr, df);
+					preempted = 0;
+				}
+				preempt_enable();
+			} while (preempted);
 			break;
 
 		case msa_st_op:
diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c
index 8452d933a645..4e7b89f2e244 100644
--- a/arch/mips/kernel/uprobes.c
+++ b/arch/mips/kernel/uprobes.c
@@ -157,7 +157,6 @@ bool is_trap_insn(uprobe_opcode_t *insn)
 int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;
-	union mips_instruction insn;
 
 	/*
 	 * Now find the EPC where to resume after the breakpoint has been
@@ -168,10 +167,10 @@ int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
 		unsigned long epc;
 
 		epc = regs->cp0_epc;
-		__compute_return_epc_for_insn(regs, insn);
+		__compute_return_epc_for_insn(regs,
+			(union mips_instruction) aup->insn[0]);
 		aup->resume_epc = regs->cp0_epc;
 	}
-
 	utask->autask.saved_trap_nr = current->thread.trap_nr;
 	current->thread.trap_nr = UPROBE_TRAP_NR;
 	regs->cp0_epc = current->utask->xol_vaddr;
@@ -257,7 +256,7 @@ unsigned long arch_uretprobe_hijack_return_addr(
 	ra = regs->regs[31];
 
 	/* Replace the return address with the trampoline address */
-	regs->regs[31] = ra;
+	regs->regs[31] = trampoline_vaddr;
 
 	return ra;
 }
@@ -280,24 +279,6 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
 }
 
-/**
- * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
- * @auprobe: arch specific probepoint information.
- * @vaddr: the virtual address to insert the opcode.
- *
- * For mm @mm, restore the original opcode (opcode) at @vaddr.
- * Return 0 (success) or a negative errno.
- *
- * This overrides the weak version in kernel/events/uprobes.c.
- */
-int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
-		 unsigned long vaddr)
-{
-	return uprobe_write_opcode(mm, vaddr,
-			*(uprobe_opcode_t *)&auprobe->orig_inst[0].word);
-}
-
 void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 				  void *src, unsigned long len)
 {
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 975e99759bab..5649a9e429e0 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -39,16 +39,16 @@ static struct vm_special_mapping vdso_vvar_mapping = {
 static void __init init_vdso_image(struct mips_vdso_image *image)
 {
 	unsigned long num_pages, i;
+	unsigned long data_pfn;
 
 	BUG_ON(!PAGE_ALIGNED(image->data));
 	BUG_ON(!PAGE_ALIGNED(image->size));
 
 	num_pages = image->size / PAGE_SIZE;
 
-	for (i = 0; i < num_pages; i++) {
-		image->mapping.pages[i] =
-			virt_to_page(image->data + (i * PAGE_SIZE));
-	}
+	data_pfn = __phys_to_pfn(__pa_symbol(image->data));
+	for (i = 0; i < num_pages; i++)
+		image->mapping.pages[i] = pfn_to_page(data_pfn + i);
 }
 
 static int __init init_vdso(void)
diff --git a/arch/mips/kernel/watch.c b/arch/mips/kernel/watch.c
index 2a03abb5bd2c..9b78e375118e 100644
--- a/arch/mips/kernel/watch.c
+++ b/arch/mips/kernel/watch.c
@@ -15,10 +15,9 @@
  * Install the watch registers for the current thread.	A maximum of
  * four registers are installed although the machine may have more.
  */
-void mips_install_watch_registers(void)
+void mips_install_watch_registers(struct task_struct *t)
 {
-	struct mips3264_watch_reg_state *watches =
-		&current->thread.watch.mips3264;
+	struct mips3264_watch_reg_state *watches = &t->thread.watch.mips3264;
 	switch (current_cpu_data.watch_reg_use_cnt) {
 	default:
 		BUG();
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 41b1b090f56f..4c85ab808f99 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
  */
 static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 {
-	ktime_t expires;
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	ktime_t expires, threshold;
+	uint32_t count, compare;
 	int running;
 
-	/* Is the hrtimer pending? */
+	/* Calculate the biased and scaled guest CP0_Count */
+	count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+	compare = kvm_read_c0_guest_compare(cop0);
+
+	/*
+	 * Find whether CP0_Count has reached the closest timer interrupt. If
+	 * not, we shouldn't inject it.
+	 */
+	if ((int32_t)(count - compare) < 0)
+		return count;
+
+	/*
+	 * The CP0_Count we're going to return has already reached the closest
+	 * timer interrupt. Quickly check if it really is a new interrupt by
+	 * looking at whether the interval until the hrtimer expiry time is
+	 * less than 1/4 of the timer period.
+	 */
 	expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
-	if (ktime_compare(now, expires) >= 0) {
+	threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
+	if (ktime_before(expires, threshold)) {
 		/*
 		 * Cancel it while we handle it so there's no chance of
 		 * interference with the timeout handler.
@@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 		}
 	}
 
-	/* Return the biased and scaled guest CP0_Count */
-	return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+	return count;
 }
 
 /**
@@ -420,32 +438,6 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
 }
 
 /**
- * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer.
- * @vcpu:	Virtual CPU.
- *
- * Recalculates and updates the expiry time of the hrtimer. This can be used
- * after timer parameters have been altered which do not depend on the time that
- * the change occurs (in those cases kvm_mips_freeze_hrtimer() and
- * kvm_mips_resume_hrtimer() are used directly).
- *
- * It is guaranteed that no timer interrupts will be lost in the process.
- *
- * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
- */
-static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu)
-{
-	ktime_t now;
-	uint32_t count;
-
-	/*
-	 * freeze_hrtimer takes care of a timer interrupts <= count, and
-	 * resume_hrtimer the hrtimer takes care of a timer interrupts > count.
-	 */
-	now = kvm_mips_freeze_hrtimer(vcpu, &count);
-	kvm_mips_resume_hrtimer(vcpu, now, count);
-}
-
-/**
  * kvm_mips_write_count() - Modify the count and update timer.
  * @vcpu:	Virtual CPU.
  * @count:	Guest CP0_Count value to set.
@@ -540,23 +532,42 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
  * kvm_mips_write_compare() - Modify compare and update timer.
  * @vcpu:	Virtual CPU.
  * @compare:	New CP0_Compare value.
+ * @ack:	Whether to acknowledge timer interrupt.
  *
  * Update CP0_Compare to a new value and update the timeout.
+ * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
+ * any pending timer interrupt is preserved.
  */
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare)
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int dc;
+	u32 old_compare = kvm_read_c0_guest_compare(cop0);
+	ktime_t now;
+	uint32_t count;
 
 	/* if unchanged, must just be an ack */
-	if (kvm_read_c0_guest_compare(cop0) == compare)
+	if (old_compare == compare) {
+		if (!ack)
+			return;
+		kvm_mips_callbacks->dequeue_timer_int(vcpu);
+		kvm_write_c0_guest_compare(cop0, compare);
 		return;
+	}
+
+	/* freeze_hrtimer() takes care of timer interrupts <= count */
+	dc = kvm_mips_count_disabled(vcpu);
+	if (!dc)
+		now = kvm_mips_freeze_hrtimer(vcpu, &count);
+
+	if (ack)
+		kvm_mips_callbacks->dequeue_timer_int(vcpu);
 
-	/* Update compare */
 	kvm_write_c0_guest_compare(cop0, compare);
 
-	/* Update timeout if count enabled */
-	if (!kvm_mips_count_disabled(vcpu))
-		kvm_mips_update_hrtimer(vcpu);
+	/* resume_hrtimer() takes care of timer interrupts > count */
+	if (!dc)
+		kvm_mips_resume_hrtimer(vcpu, now, count);
 }
 
 /**
@@ -741,15 +752,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
 
-	if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+	if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+		kvm_clear_c0_guest_status(cop0, ST0_ERL);
+		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+	} else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
 		kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
 			  kvm_read_c0_guest_epc(cop0));
 		kvm_clear_c0_guest_status(cop0, ST0_EXL);
 		vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);
 
-	} else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
-		kvm_clear_c0_guest_status(cop0, ST0_ERL);
-		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
 	} else {
 		kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
 			vcpu->arch.pc);
@@ -796,6 +807,47 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
 	return EMULATE_FAIL;
 }
 
+/**
+ * kvm_mips_invalidate_guest_tlb() - Indicates a change in guest MMU map.
+ * @vcpu:	VCPU with changed mappings.
+ * @tlb:	TLB entry being removed.
+ *
+ * This is called to indicate a single change in guest MMU mappings, so that we
+ * can arrange TLB flushes on this and other CPUs.
+ */
+static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu,
+					  struct kvm_mips_tlb *tlb)
+{
+	int cpu, i;
+	bool user;
+
+	/* No need to flush for entries which are already invalid */
+	if (!((tlb->tlb_lo0 | tlb->tlb_lo1) & MIPS3_PG_V))
+		return;
+	/* User address space doesn't need flushing for KSeg2/3 changes */
+	user = tlb->tlb_hi < KVM_GUEST_KSEG0;
+
+	preempt_disable();
+
+	/*
+	 * Probe the shadow host TLB for the entry being overwritten, if one
+	 * matches, invalidate it
+	 */
+	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+	/* Invalidate the whole ASID on other CPUs */
+	cpu = smp_processor_id();
+	for_each_possible_cpu(i) {
+		if (i == cpu)
+			continue;
+		if (user)
+			vcpu->arch.guest_user_asid[i] = 0;
+		vcpu->arch.guest_kernel_asid[i] = 0;
+	}
+
+	preempt_enable();
+}
+
 /* Write Guest TLB Entry @ Index */
 enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 {
@@ -815,11 +867,8 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 	}
 
 	tlb = &vcpu->arch.guest_tlb[index];
-	/*
-	 * Probe the shadow host TLB for the entry being overwritten, if one
-	 * matches, invalidate it
-	 */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -848,11 +897,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 
 	tlb = &vcpu->arch.guest_tlb[index];
 
-	/*
-	 * Probe the shadow host TLB for the entry being overwritten, if one
-	 * matches, invalidate it
-	 */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -971,6 +1016,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 	int32_t rt, rd, copz, sel, co_bit, op;
 	uint32_t pc = vcpu->arch.pc;
 	unsigned long curr_pc;
+	int cpu, i;
 
 	/*
 	 * Update PC and hold onto current PC in case there is
@@ -1078,8 +1124,16 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 						vcpu->arch.gprs[rt]
 						& ASID_MASK);
 
+					preempt_disable();
 					/* Blow away the shadow host TLBs */
 					kvm_mips_flush_host_tlb(1);
+					cpu = smp_processor_id();
+					for_each_possible_cpu(i)
+						if (i != cpu) {
+							vcpu->arch.guest_user_asid[i] = 0;
+							vcpu->arch.guest_kernel_asid[i] = 0;
+						}
+					preempt_enable();
 				}
 				kvm_write_c0_guest_entryhi(cop0,
 							   vcpu->arch.gprs[rt]);
@@ -1095,9 +1149,9 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 
 				/* If we are writing to COMPARE */
 				/* Clear pending timer interrupt, if any */
-				kvm_mips_callbacks->dequeue_timer_int(vcpu);
 				kvm_mips_write_compare(vcpu,
-						       vcpu->arch.gprs[rt]);
+						       vcpu->arch.gprs[rt],
+						       true);
 			} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
 				unsigned int old_val, val, change;
 
@@ -1419,6 +1473,7 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
+	unsigned long curr_pc;
 	int32_t op, base, rt, offset;
 	uint32_t bytes;
 
@@ -1427,7 +1482,18 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 	offset = inst & 0xffff;
 	op = (inst >> 26) & 0x3f;
 
-	vcpu->arch.pending_load_cause = cause;
+	/*
+	 * Find the resume PC now while we have safe and easy access to the
+	 * prior branch instruction, and save it for
+	 * kvm_mips_complete_mmio_load() to restore later.
+	 */
+	curr_pc = vcpu->arch.pc;
+	er = update_pc(vcpu, cause);
+	if (er == EMULATE_FAIL)
+		return er;
+	vcpu->arch.io_pc = vcpu->arch.pc;
+	vcpu->arch.pc = curr_pc;
+
 	vcpu->arch.io_gpr = rt;
 
 	switch (op) {
@@ -1618,8 +1684,14 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 
 	preempt_disable();
 	if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
-		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
-			kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+		    kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+			kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+				__func__, va, vcpu, read_c0_entryhi());
+			er = EMULATE_FAIL;
+			preempt_enable();
+			goto done;
+		}
 	} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
 		   KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
 		int index;
@@ -1654,14 +1726,19 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 								run, vcpu);
 				preempt_enable();
 				goto dont_update_pc;
-			} else {
-				/*
-				 * We fault an entry from the guest tlb to the
-				 * shadow host TLB
-				 */
-				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
-								     NULL,
-								     NULL);
+			}
+			/*
+			 * We fault an entry from the guest tlb to the
+			 * shadow host TLB
+			 */
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+				preempt_enable();
+				goto done;
 			}
 		}
 	} else {
@@ -2396,9 +2473,8 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		goto done;
 	}
 
-	er = update_pc(vcpu, vcpu->arch.pending_load_cause);
-	if (er == EMULATE_FAIL)
-		return er;
+	/* Restore saved resume PC */
+	vcpu->arch.pc = vcpu->arch.io_pc;
 
 	switch (run->mmio.len) {
 	case 4:
@@ -2420,11 +2496,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	if (vcpu->arch.pending_load_cause & CAUSEF_BD)
-		kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
-			  vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
-			  vcpu->mmio_needed);
-
 done:
 	return er;
 }
@@ -2622,8 +2693,13 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
 			 * OK we have a Guest TLB entry, now inject it into the
 			 * shadow host TLB
 			 */
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
-							     NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+			}
 		}
 	}
 
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703..2143884709e4 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 7e2210846b8b..77706433651b 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -227,6 +227,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 
 	/* Jump to guest */
 	eret
+EXPORT(__kvm_mips_vcpu_run_end)
 
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 2683d04fdda5..a017b23ee4aa 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -314,9 +314,18 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	memcpy(gebase + offset, mips32_GuestException,
 	       mips32_GuestExceptionEnd - mips32_GuestException);
 
+#ifdef MODULE
+	offset += mips32_GuestExceptionEnd - mips32_GuestException;
+	memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+	       __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+	vcpu->arch.vcpu_run = gebase + offset;
+#else
+	vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
 	/* Invalidate the icache for these ranges */
-	local_flush_icache_range((unsigned long)gebase,
-				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
+	flush_icache_range((unsigned long)gebase,
+			   (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
 
 	/*
 	 * Allocate comm page for guest kernel, a TLB will be reserved for
@@ -403,7 +412,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
 
-	r = __kvm_mips_vcpu_run(run, vcpu);
+	r = vcpu->arch.vcpu_run(run, vcpu);
 
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index aed0ac2a4972..eff71c75dc27 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -152,7 +152,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	pfn = kvm_mips_gfn_to_pfn(kvm, gfn);
 
-	if (kvm_mips_is_error_pfn(pfn)) {
+	if (is_error_noslot_pfn(pfn)) {
 		kvm_err("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn);
 		err = -EFAULT;
 		goto out;
@@ -276,7 +276,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	}
 
 	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
-	if (gfn >= kvm->arch.guest_pmap_npages) {
+	if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
 		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
 			gfn, badvaddr);
 		kvm_mips_dump_host_tlbs();
@@ -361,25 +361,39 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
 	struct kvm *kvm = vcpu->kvm;
 	pfn_t pfn0, pfn1;
-
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
-		pfn0 = 0;
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					    >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					    >> PAGE_SHIFT];
+	gfn_t gfn0, gfn1;
+	long tlb_lo[2];
+
+	tlb_lo[0] = tlb->tlb_lo0;
+	tlb_lo[1] = tlb->tlb_lo1;
+
+	/*
+	 * The commpage address must not be mapped to anything else if the guest
+	 * TLB contains entries nearby, or commpage accesses will break.
+	 */
+	if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+			VPN2_MASK & (PAGE_MASK << 1)))
+		tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+	gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+	gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+	if (gfn0 >= kvm->arch.guest_pmap_npages ||
+	    gfn1 >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+			__func__, gfn0, gfn1, tlb->tlb_hi);
+		kvm_mips_dump_guest_tlbs(vcpu);
+		return -1;
 	}
 
+	if (kvm_mips_map_page(kvm, gfn0) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(kvm, gfn1) < 0)
+		return -1;
+
+	pfn0 = kvm->arch.guest_pmap[gfn0];
+	pfn1 = kvm->arch.guest_pmap[gfn1];
+
 	if (hpa0)
 		*hpa0 = pfn0 << PAGE_SHIFT;
 
@@ -391,9 +405,9 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 					       kvm_mips_get_kernel_asid(vcpu) :
 					       kvm_mips_get_user_asid(vcpu));
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
+		   (tlb_lo[0] & MIPS3_PG_D) | (tlb_lo[0] & MIPS3_PG_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
+		   (tlb_lo[1] & MIPS3_PG_D) | (tlb_lo[1] & MIPS3_PG_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo0, tlb->tlb_lo1);
@@ -794,10 +808,16 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 				local_irq_restore(flags);
 				return KVM_INVALID_INST;
 			}
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
-							     &vcpu->arch.
-							     guest_tlb[index],
-							     NULL, NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+						&vcpu->arch.guest_tlb[index],
+						NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, index, vcpu,
+					read_c0_entryhi());
+				kvm_mips_dump_guest_tlbs(vcpu);
+				local_irq_restore(flags);
+				return KVM_INVALID_INST;
+			}
 			inst = *(opc);
 		}
 		local_irq_restore(flags);
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index d836ed5b0bc7..307cc4c98bdd 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -547,7 +547,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu,
 		kvm_mips_write_count(vcpu, v);
 		break;
 	case KVM_REG_MIPS_CP0_COMPARE:
-		kvm_mips_write_compare(vcpu, v);
+		kvm_mips_write_compare(vcpu, v, false);
 		break;
 	case KVM_REG_MIPS_CP0_CAUSE:
 		/*
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 80554e8f6037..daf580ce5ca2 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -467,7 +467,7 @@ void __init ltq_soc_init(void)
 
 		if (!np_xbar)
 			panic("Failed to load xbar nodes from devicetree");
-		if (of_address_to_resource(np_pmu, 0, &res_xbar))
+		if (of_address_to_resource(np_xbar, 0, &res_xbar))
 			panic("Failed to get xbar resources");
 		if (request_mem_region(res_xbar.start, resource_size(&res_xbar),
 			res_xbar.name) < 0)
@@ -545,7 +545,7 @@ void __init ltq_soc_init(void)
 		clkdev_add_pmu("1a800000.pcie", "msi", 1, 1, PMU1_PCIE2_MSI);
 		clkdev_add_pmu("1a800000.pcie", "pdi", 1, 1, PMU1_PCIE2_PDI);
 		clkdev_add_pmu("1a800000.pcie", "ctl", 1, 1, PMU1_PCIE2_CTL);
-		clkdev_add_pmu("1e108000.eth", NULL, 1, 0, PMU_SWITCH | PMU_PPE_DP);
+		clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP);
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 	} else if (of_machine_is_compatible("lantiq,ar10")) {
@@ -553,7 +553,7 @@ void __init ltq_soc_init(void)
 				  ltq_ar10_fpi_hz(), ltq_ar10_pp32_hz());
 		clkdev_add_pmu("1e101000.usb", "ctl", 1, 0, PMU_USB0);
 		clkdev_add_pmu("1e106000.usb", "ctl", 1, 0, PMU_USB1);
-		clkdev_add_pmu("1e108000.eth", NULL, 1, 0, PMU_SWITCH |
+		clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH |
 			       PMU_PPE_DP | PMU_PPE_TC);
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
 		clkdev_add_pmu("1f203000.rcu", "gphy", 1, 0, PMU_GPHY);
@@ -575,11 +575,11 @@ void __init ltq_soc_init(void)
 		clkdev_add_pmu(NULL, "ahb", 1, 0, PMU_AHBM | PMU_AHBS);
 
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
-		clkdev_add_pmu("1e108000.eth", NULL, 1, 0,
+		clkdev_add_pmu("1e108000.eth", NULL, 0, 0,
 				PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM |
 				PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 |
 				PMU_PPE_QSB | PMU_PPE_TOP);
-		clkdev_add_pmu("1f203000.rcu", "gphy", 1, 0, PMU_GPHY);
+		clkdev_add_pmu("1f203000.rcu", "gphy", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
diff --git a/arch/mips/lib/ashldi3.c b/arch/mips/lib/ashldi3.c
index beb80f316095..927dc94a030f 100644
--- a/arch/mips/lib/ashldi3.c
+++ b/arch/mips/lib/ashldi3.c
@@ -2,7 +2,7 @@
 
 #include "libgcc.h"
 
-long long __ashldi3(long long u, word_type b)
+long long notrace __ashldi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
diff --git a/arch/mips/lib/ashrdi3.c b/arch/mips/lib/ashrdi3.c
index c884a912b660..9fdf1a598428 100644
--- a/arch/mips/lib/ashrdi3.c
+++ b/arch/mips/lib/ashrdi3.c
@@ -2,7 +2,7 @@
 
 #include "libgcc.h"
 
-long long __ashrdi3(long long u, word_type b)
+long long notrace __ashrdi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c
index 77e5f9c1f005..e3e77aa52c95 100644
--- a/arch/mips/lib/bswapdi.c
+++ b/arch/mips/lib/bswapdi.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 
-unsigned long long __bswapdi2(unsigned long long u)
+unsigned long long notrace __bswapdi2(unsigned long long u)
 {
 	return (((u) & 0xff00000000000000ull) >> 56) |
 	       (((u) & 0x00ff000000000000ull) >> 40) |
diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c
index 2b302ff121d2..530a8afe6fda 100644
--- a/arch/mips/lib/bswapsi.c
+++ b/arch/mips/lib/bswapsi.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 
-unsigned int __bswapsi2(unsigned int u)
+unsigned int notrace __bswapsi2(unsigned int u)
 {
 	return (((u) & 0xff000000) >> 24) |
 	       (((u) & 0x00ff0000) >>  8) |
diff --git a/arch/mips/lib/cmpdi2.c b/arch/mips/lib/cmpdi2.c
index 8c1306437ed1..06857da96993 100644
--- a/arch/mips/lib/cmpdi2.c
+++ b/arch/mips/lib/cmpdi2.c
@@ -2,7 +2,7 @@
 
 #include "libgcc.h"
 
-word_type __cmpdi2(long long a, long long b)
+word_type notrace __cmpdi2(long long a, long long b)
 {
 	const DWunion au = {
 		.ll = a
diff --git a/arch/mips/lib/lshrdi3.c b/arch/mips/lib/lshrdi3.c
index dcf8d6810b7c..364547449c65 100644
--- a/arch/mips/lib/lshrdi3.c
+++ b/arch/mips/lib/lshrdi3.c
@@ -2,7 +2,7 @@
 
 #include "libgcc.h"
 
-long long __lshrdi3(long long u, word_type b)
+long long notrace __lshrdi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
diff --git a/arch/mips/lib/ucmpdi2.c b/arch/mips/lib/ucmpdi2.c
index bb4cb2f828ea..bd599f58234c 100644
--- a/arch/mips/lib/ucmpdi2.c
+++ b/arch/mips/lib/ucmpdi2.c
@@ -2,7 +2,7 @@
 
 #include "libgcc.h"
 
-word_type __ucmpdi2(unsigned long long a, unsigned long long b)
+word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b)
 {
 	const DWunion au = {.ll = a};
 	const DWunion bu = {.ll = b};
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index a2631a52ca99..444802e78554 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -13,8 +13,8 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
-#define HPET_MIN_CYCLES		64
-#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES		16
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES * 12)
 
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
 static int hpet_next_event(unsigned long delta,
 		struct clock_event_device *evt)
 {
-	unsigned int cnt;
-	int res;
+	u32 cnt;
+	s32 res;
 
 	cnt = hpet_read(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = (int)(cnt - hpet_read(HPET_COUNTER));
+	res = (s32)(cnt - hpet_read(HPET_COUNTER));
 
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
 
 	cd = &per_cpu(hpet_clockevent_device, cpu);
 	cd->name = "hpet";
-	cd->rating = 320;
+	cd->rating = 100;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	cd->set_state_shutdown = hpet_set_state_shutdown;
 	cd->set_state_periodic = hpet_set_state_periodic;
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 6f9e010cec4d..282c5a8c2fcd 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -213,10 +213,10 @@ static void __init node_mem_init(unsigned int node)
 		BOOTMEM_DEFAULT);
 
 	if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) {
-		/* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */
+		/* Reserve 0xfe000000~0xffffffff for RS780E integrated GPU */
 		reserve_bootmem_node(NODE_DATA(node),
-				(node_addrspace_offset | 0xff800000),
-				8 << 20, BOOTMEM_DEFAULT);
+				(node_addrspace_offset | 0xfe000000),
+				32 << 20, BOOTMEM_DEFAULT);
 	}
 
 	sparse_memory_present_with_active_regions(node);
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 32f0e19a0d7f..6da2e4a6ba39 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -445,9 +445,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 	case spec_op:
 		switch (insn.r_format.func) {
 		case jalr_op:
-			regs->regs[insn.r_format.rd] =
-				regs->cp0_epc + dec_insn.pc_inc +
-				dec_insn.next_pc_inc;
+			if (insn.r_format.rd != 0) {
+				regs->regs[insn.r_format.rd] =
+					regs->cp0_epc + dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			}
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
@@ -2494,6 +2496,35 @@ dcopuop:
 	return 0;
 }
 
+/*
+ * Emulate FPU instructions.
+ *
+ * If we use FPU hardware, then we have been typically called to handle
+ * an unimplemented operation, such as where an operand is a NaN or
+ * denormalized.  In that case exit the emulation loop after a single
+ * iteration so as to let hardware execute any subsequent instructions.
+ *
+ * If we have no FPU hardware or it has been disabled, then continue
+ * emulating floating-point instructions until one of these conditions
+ * has occurred:
+ *
+ * - a non-FPU instruction has been encountered,
+ *
+ * - an attempt to emulate has ended with a signal,
+ *
+ * - the ISA mode has been switched.
+ *
+ * We need to terminate the emulation loop if we got switched to the
+ * MIPS16 mode, whether supported or not, so that we do not attempt
+ * to emulate a MIPS16 instruction as a regular MIPS FPU instruction.
+ * Similarly if we got switched to the microMIPS mode and only the
+ * regular MIPS mode is supported, so that we do not attempt to emulate
+ * a microMIPS instruction as a regular MIPS FPU instruction.  Or if
+ * we got switched to the regular MIPS mode and only the microMIPS mode
+ * is supported, so that we do not attempt to emulate a regular MIPS
+ * instruction that should cause an Address Error exception instead.
+ * For simplicity we always terminate upon an ISA mode switch.
+ */
 int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	int has_fpu, void *__user *fault_addr)
 {
@@ -2579,6 +2610,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 		if (sig)
 			break;
+		/*
+		 * We have to check for the ISA bit explicitly here,
+		 * because `get_isa16_mode' may return 0 if support
+		 * for code compression has been globally disabled,
+		 * or otherwise we may produce the wrong signal or
+		 * even proceed successfully where we must not.
+		 */
+		if ((xcp->cp0_epc ^ prevepc) & 0x1)
+			break;
 
 		cond_resched();
 	} while (xcp->cp0_epc > prevepc);
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index aab218c36e0d..e87bccd6e0aa 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 
 #include <asm/cacheflush.h>
+#include <asm/highmem.h>
 #include <asm/processor.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
@@ -83,8 +84,6 @@ void __flush_dcache_page(struct page *page)
 	struct address_space *mapping = page_mapping(page);
 	unsigned long addr;
 
-	if (PageHighMem(page))
-		return;
 	if (mapping && !mapping_mapped(mapping)) {
 		SetPageDcacheDirty(page);
 		return;
@@ -95,8 +94,15 @@ void __flush_dcache_page(struct page *page)
 	 * case is for exec env/arg pages and those are %99 certainly going to
 	 * get faulted into the tlb (and thus flushed) anyways.
 	 */
-	addr = (unsigned long) page_address(page);
+	if (PageHighMem(page))
+		addr = (unsigned long)kmap_atomic(page);
+	else
+		addr = (unsigned long)page_address(page);
+
 	flush_data_cache_page(addr);
+
+	if (PageHighMem(page))
+		__kunmap_atomic((void *)addr);
 }
 
 EXPORT_SYMBOL(__flush_dcache_page);
@@ -119,33 +125,28 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr)
 
 EXPORT_SYMBOL(__flush_anon_page);
 
-void __flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long addr;
-
-	if (PageHighMem(page))
-		return;
-
-	addr = (unsigned long) page_address(page);
-	flush_data_cache_page(addr);
-}
-EXPORT_SYMBOL_GPL(__flush_icache_page);
-
-void __update_cache(struct vm_area_struct *vma, unsigned long address,
-	pte_t pte)
+void __update_cache(unsigned long address, pte_t pte)
 {
 	struct page *page;
 	unsigned long pfn, addr;
-	int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;
+	int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;
 
 	pfn = pte_pfn(pte);
 	if (unlikely(!pfn_valid(pfn)))
 		return;
 	page = pfn_to_page(pfn);
-	if (page_mapping(page) && Page_dcache_dirty(page)) {
-		addr = (unsigned long) page_address(page);
+	if (Page_dcache_dirty(page)) {
+		if (PageHighMem(page))
+			addr = (unsigned long)kmap_atomic(page);
+		else
+			addr = (unsigned long)page_address(page);
+
 		if (exec || pages_do_alias(addr, address & PAGE_MASK))
 			flush_data_cache_page(addr);
+
+		if (PageHighMem(page))
+			__kunmap_atomic((void *)addr);
+
 		ClearPageDcacheDirty(page);
 	}
 }
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 5c81fdd032c3..025cb31aa0a2 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/mips/mm/sc-ip22.c b/arch/mips/mm/sc-ip22.c
index dc7c5a5214a9..efaf364fe581 100644
--- a/arch/mips/mm/sc-ip22.c
+++ b/arch/mips/mm/sc-ip22.c
@@ -31,26 +31,40 @@ static inline void indy_sc_wipe(unsigned long first, unsigned long last)
 	unsigned long tmp;
 
 	__asm__ __volatile__(
-	".set\tpush\t\t\t# indy_sc_wipe\n\t"
-	".set\tnoreorder\n\t"
-	".set\tmips3\n\t"
-	".set\tnoat\n\t"
-	"mfc0\t%2, $12\n\t"
-	"li\t$1, 0x80\t\t\t# Go 64 bit\n\t"
-	"mtc0\t$1, $12\n\t"
-
-	"dli\t$1, 0x9000000080000000\n\t"
-	"or\t%0, $1\t\t\t# first line to flush\n\t"
-	"or\t%1, $1\t\t\t# last line to flush\n\t"
-	".set\tat\n\t"
-
-	"1:\tsw\t$0, 0(%0)\n\t"
-	"bne\t%0, %1, 1b\n\t"
-	" daddu\t%0, 32\n\t"
-
-	"mtc0\t%2, $12\t\t\t# Back to 32 bit\n\t"
-	"nop; nop; nop; nop;\n\t"
-	".set\tpop"
+	"	.set	push			# indy_sc_wipe		\n"
+	"	.set	noreorder					\n"
+	"	.set	mips3						\n"
+	"	.set	noat						\n"
+	"	mfc0	%2, $12						\n"
+	"	li	$1, 0x80		# Go 64 bit		\n"
+	"	mtc0	$1, $12						\n"
+	"								\n"
+	"	#							\n"
+	"	# Open code a dli $1, 0x9000000080000000		\n"
+	"	#							\n"
+	"	# Required because binutils 2.25 will happily accept	\n"
+	"	# 64 bit instructions in .set mips3 mode but puke on	\n"
+	"	# 64 bit constants when generating 32 bit ELF		\n"
+	"	#							\n"
+	"	lui	$1,0x9000					\n"
+	"	dsll	$1,$1,0x10					\n"
+	"	ori	$1,$1,0x8000					\n"
+	"	dsll	$1,$1,0x10					\n"
+	"								\n"
+	"	or	%0, $1			# first line to flush	\n"
+	"	or	%1, $1			# last line to flush	\n"
+	"	.set	at						\n"
+	"								\n"
+	"1:	sw	$0, 0(%0)					\n"
+	"	bne	%0, %1, 1b					\n"
+	"	 daddu	%0, 32						\n"
+	"								\n"
+	"	mtc0	%2, $12			# Back to 32 bit	\n"
+	"	nop				# pipeline hazard	\n"
+	"	nop							\n"
+	"	nop							\n"
+	"	nop							\n"
+	"	.set	pop						\n"
 	: "=r" (first), "=r" (last), "=&r" (tmp)
 	: "0" (first), "1" (last));
 }
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 29f73e00253d..63b7d6f82d24 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -757,7 +757,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte,
 static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 				    struct uasm_label **l,
 				    unsigned int pte,
-				    unsigned int ptr)
+				    unsigned int ptr,
+				    unsigned int flush)
 {
 #ifdef CONFIG_SMP
 	UASM_i_SC(p, pte, 0, ptr);
@@ -766,6 +767,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 #else
 	UASM_i_SW(p, pte, 0, ptr);
 #endif
+	if (cpu_has_ftlb && flush) {
+		BUG_ON(!cpu_has_tlbinv);
+
+		UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+		uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_tlb_write_entry(p, l, r, tlb_indexed);
+
+		uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_huge_update_entries(p, pte, ptr);
+		build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+		return;
+	}
+
 	build_huge_update_entries(p, pte, ptr);
 	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
 }
@@ -2082,7 +2099,7 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_l_tlbl_goaround2(&l, p);
 	}
 	uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbl(&l, p);
@@ -2137,7 +2154,7 @@ static void build_r4000_tlb_store_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbs(&l, p);
@@ -2193,7 +2210,7 @@ static void build_r4000_tlb_modify_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
 #endif
 
 	uasm_l_nopage_tlbm(&l, p);
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index b4a837893562..5abe51cad899 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -65,7 +65,7 @@ static struct insn insn_table[] = {
 #ifndef CONFIG_CPU_MIPSR6
 	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 #else
-	{ insn_cache,  M6(cache_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
+	{ insn_cache,  M6(spec3_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
 #endif
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 4740c82fb97a..36b09b2ea972 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -39,6 +39,9 @@
 #include <linux/console.h>
 #endif
 
+#define ROCIT_CONFIG_GEN0		0x1f403000
+#define  ROCIT_CONFIG_GEN0_PCI_IOCU	BIT(7)
+
 extern void malta_be_init(void);
 extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
 
@@ -107,6 +110,8 @@ static void __init fd_activate(void)
 static int __init plat_enable_iocoherency(void)
 {
 	int supported = 0;
+	u32 cfg;
+
 	if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) {
 		if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
 			BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
@@ -129,7 +134,8 @@ static int __init plat_enable_iocoherency(void)
 	} else if (mips_cm_numiocu() != 0) {
 		/* Nothing special needs to be done to enable coherency */
 		pr_info("CMP IOCU detected\n");
-		if ((*(unsigned int *)0xbf403000 & 0x81) != 0x81) {
+		cfg = __raw_readl((u32 *)CKSEG1ADDR(ROCIT_CONFIG_GEN0));
+		if (!(cfg & ROCIT_CONFIG_GEN0_PCI_IOCU)) {
 			pr_crit("IOCU OPERATION DISABLED BY SWITCH - DEFAULTING TO SW IO COHERENCY\n");
 			return 0;
 		}
diff --git a/arch/mips/netlogic/common/reset.S b/arch/mips/netlogic/common/reset.S
index edbab9b8691f..c474981a6c0d 100644
--- a/arch/mips/netlogic/common/reset.S
+++ b/arch/mips/netlogic/common/reset.S
@@ -50,7 +50,6 @@
 #include <asm/netlogic/xlp-hal/sys.h>
 #include <asm/netlogic/xlp-hal/cpucontrol.h>
 
-#define CP0_EBASE	$15
 #define SYS_CPU_COHERENT_BASE	CKSEG1ADDR(XLP_DEFAULT_IO_BASE) + \
 			XLP_IO_SYS_OFFSET(0) + XLP_IO_PCI_HDRSZ + \
 			SYS_CPU_NONCOHERENT_MODE * 4
@@ -92,7 +91,7 @@
  * registers. On XLPII CPUs, usual cache instructions work.
  */
 .macro	xlp_flush_l1_dcache
-	mfc0	t0, CP0_EBASE, 0
+	mfc0	t0, CP0_PRID
 	andi	t0, t0, PRID_IMP_MASK
 	slt	t1, t0, 0x1200
 	beqz	t1, 15f
@@ -171,7 +170,7 @@ FEXPORT(nlm_reset_entry)
 	nop
 
 1:	/* Entry point on core wakeup */
-	mfc0	t0, CP0_EBASE, 0	/* processor ID */
+	mfc0	t0, CP0_PRID		/* processor ID */
 	andi	t0, PRID_IMP_MASK
 	li	t1, 0x1500		/* XLP 9xx */
 	beq	t0, t1, 2f		/* does not need to set coherent */
@@ -182,8 +181,8 @@ FEXPORT(nlm_reset_entry)
 	nop
 
 	/* set bit in SYS coherent register for the core */
-	mfc0	t0, CP0_EBASE, 1
-	mfc0	t1, CP0_EBASE, 1
+	mfc0	t0, CP0_EBASE
+	mfc0	t1, CP0_EBASE
 	srl	t1, 5
 	andi	t1, 0x3			/* t1 <- node */
 	li	t2, 0x40000
@@ -232,7 +231,7 @@ EXPORT(nlm_boot_siblings)
 
 	 * NOTE: All GPR contents are lost after the mtcr above!
 	 */
-	mfc0	v0, CP0_EBASE, 1
+	mfc0	v0, CP0_EBASE
 	andi	v0, 0x3ff		/* v0 <- node/core */
 
 	/*
diff --git a/arch/mips/netlogic/common/smpboot.S b/arch/mips/netlogic/common/smpboot.S
index 805355b0bd05..f0cc4c9de2bb 100644
--- a/arch/mips/netlogic/common/smpboot.S
+++ b/arch/mips/netlogic/common/smpboot.S
@@ -48,8 +48,6 @@
 #include <asm/netlogic/xlp-hal/sys.h>
 #include <asm/netlogic/xlp-hal/cpucontrol.h>
 
-#define CP0_EBASE	$15
-
 	.set	noreorder
 	.set	noat
 	.set	arch=xlr		/* for mfcr/mtcr, XLR is sufficient */
@@ -86,7 +84,7 @@ NESTED(nlm_boot_secondary_cpus, 16, sp)
 	PTR_L	gp, 0(t1)
 
 	/* a0 has the processor id */
-	mfc0	a0, CP0_EBASE, 1
+	mfc0	a0, CP0_EBASE
 	andi	a0, 0x3ff		/* a0 <- node/core */
 	PTR_LA	t0, nlm_early_init_secondary
 	jalr	t0
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index dfb04fcedb04..48d6349fd9d7 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -107,31 +107,31 @@ static struct rt2880_pmx_group mt7620a_pinmux_data[] = {
 };
 
 static struct rt2880_pmx_func pwm1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 19, 1),
+	FUNC("sdxc d6", 3, 19, 1),
 	FUNC("utif", 2, 19, 1),
 	FUNC("gpio", 1, 19, 1),
-	FUNC("pwm", 0, 19, 1),
+	FUNC("pwm1", 0, 19, 1),
 };
 
 static struct rt2880_pmx_func pwm0_grp_mt7628[] = {
-	FUNC("sdcx", 3, 18, 1),
+	FUNC("sdxc d7", 3, 18, 1),
 	FUNC("utif", 2, 18, 1),
 	FUNC("gpio", 1, 18, 1),
-	FUNC("pwm", 0, 18, 1),
+	FUNC("pwm0", 0, 18, 1),
 };
 
 static struct rt2880_pmx_func uart2_grp_mt7628[] = {
-	FUNC("sdcx", 3, 20, 2),
+	FUNC("sdxc d5 d4", 3, 20, 2),
 	FUNC("pwm", 2, 20, 2),
 	FUNC("gpio", 1, 20, 2),
-	FUNC("uart", 0, 20, 2),
+	FUNC("uart2", 0, 20, 2),
 };
 
 static struct rt2880_pmx_func uart1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 45, 2),
+	FUNC("sw_r", 3, 45, 2),
 	FUNC("pwm", 2, 45, 2),
 	FUNC("gpio", 1, 45, 2),
-	FUNC("uart", 0, 45, 2),
+	FUNC("uart1", 0, 45, 2),
 };
 
 static struct rt2880_pmx_func i2c_grp_mt7628[] = {
@@ -143,21 +143,21 @@ static struct rt2880_pmx_func i2c_grp_mt7628[] = {
 
 static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) };
 static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) };
-static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 15, 38) };
+static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
 static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };
 
 static struct rt2880_pmx_func sd_mode_grp_mt7628[] = {
 	FUNC("jtag", 3, 22, 8),
 	FUNC("utif", 2, 22, 8),
 	FUNC("gpio", 1, 22, 8),
-	FUNC("sdcx", 0, 22, 8),
+	FUNC("sdxc", 0, 22, 8),
 };
 
 static struct rt2880_pmx_func uart0_grp_mt7628[] = {
 	FUNC("-", 3, 12, 2),
 	FUNC("-", 2, 12, 2),
 	FUNC("gpio", 1, 12, 2),
-	FUNC("uart", 0, 12, 2),
+	FUNC("uart0", 0, 12, 2),
 };
 
 static struct rt2880_pmx_func i2s_grp_mt7628[] = {
@@ -171,7 +171,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = {
 	FUNC("-", 3, 6, 1),
 	FUNC("refclk", 2, 6, 1),
 	FUNC("gpio", 1, 6, 1),
-	FUNC("spi", 0, 6, 1),
+	FUNC("spi cs1", 0, 6, 1),
 };
 
 static struct rt2880_pmx_func spis_grp_mt7628[] = {
@@ -188,28 +188,44 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = {
 	FUNC("gpio", 0, 11, 1),
 };
 
-#define MT7628_GPIO_MODE_MASK	0x3
-
-#define MT7628_GPIO_MODE_PWM1	30
-#define MT7628_GPIO_MODE_PWM0	28
-#define MT7628_GPIO_MODE_UART2	26
-#define MT7628_GPIO_MODE_UART1	24
-#define MT7628_GPIO_MODE_I2C	20
-#define MT7628_GPIO_MODE_REFCLK	18
-#define MT7628_GPIO_MODE_PERST	16
-#define MT7628_GPIO_MODE_WDT	14
-#define MT7628_GPIO_MODE_SPI	12
-#define MT7628_GPIO_MODE_SDMODE	10
-#define MT7628_GPIO_MODE_UART0	8
-#define MT7628_GPIO_MODE_I2S	6
-#define MT7628_GPIO_MODE_CS1	4
-#define MT7628_GPIO_MODE_SPIS	2
-#define MT7628_GPIO_MODE_GPIO	0
+static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
+	FUNC("rsvd", 3, 35, 1),
+	FUNC("rsvd", 2, 35, 1),
+	FUNC("gpio", 1, 35, 1),
+	FUNC("wled_kn", 0, 35, 1),
+};
+
+static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
+	FUNC("rsvd", 3, 44, 1),
+	FUNC("rsvd", 2, 44, 1),
+	FUNC("gpio", 1, 44, 1),
+	FUNC("wled_an", 0, 44, 1),
+};
+
+#define MT7628_GPIO_MODE_MASK		0x3
+
+#define MT7628_GPIO_MODE_WLED_KN	48
+#define MT7628_GPIO_MODE_WLED_AN	32
+#define MT7628_GPIO_MODE_PWM1		30
+#define MT7628_GPIO_MODE_PWM0		28
+#define MT7628_GPIO_MODE_UART2		26
+#define MT7628_GPIO_MODE_UART1		24
+#define MT7628_GPIO_MODE_I2C		20
+#define MT7628_GPIO_MODE_REFCLK		18
+#define MT7628_GPIO_MODE_PERST		16
+#define MT7628_GPIO_MODE_WDT		14
+#define MT7628_GPIO_MODE_SPI		12
+#define MT7628_GPIO_MODE_SDMODE		10
+#define MT7628_GPIO_MODE_UART0		8
+#define MT7628_GPIO_MODE_I2S		6
+#define MT7628_GPIO_MODE_CS1		4
+#define MT7628_GPIO_MODE_SPIS		2
+#define MT7628_GPIO_MODE_GPIO		0
 
 static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
-	GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pmw1", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM0),
 	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_UART2),
@@ -233,6 +249,10 @@ static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
 				1, MT7628_GPIO_MODE_SPIS),
 	GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_GPIO),
+	GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_AN),
+	GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_KN),
 	{ 0 }
 };
 
@@ -439,7 +459,7 @@ void __init ralink_clk_init(void)
 	ralink_clk_add("10000c00.uartlite", periph_rate);
 	ralink_clk_add("10180000.wmac", xtal_rate);
 
-	if (IS_ENABLED(CONFIG_USB) && is_mt76x8()) {
+	if (IS_ENABLED(CONFIG_USB) && !is_mt76x8()) {
 		/*
 		 * When the CPU goes into sleep mode, the BUS clock will be
 		 * too low for USB to function properly. Adjust the busses
diff --git a/arch/mips/ralink/prom.c b/arch/mips/ralink/prom.c
index 39a9142f71be..7ecb4af79b7b 100644
--- a/arch/mips/ralink/prom.c
+++ b/arch/mips/ralink/prom.c
@@ -30,8 +30,10 @@ const char *get_system_type(void)
 	return soc_info.sys_type;
 }
 
-static __init void prom_init_cmdline(int argc, char **argv)
+static __init void prom_init_cmdline(void)
 {
+	int argc;
+	char **argv;
 	int i;
 
 	pr_debug("prom: fw_arg0=%08x fw_arg1=%08x fw_arg2=%08x fw_arg3=%08x\n",
@@ -60,14 +62,11 @@ static __init void prom_init_cmdline(int argc, char **argv)
 
 void __init prom_init(void)
 {
-	int argc;
-	char **argv;
-
 	prom_soc_init(&soc_info);
 
 	pr_info("SoC Type: %s\n", get_system_type());
 
-	prom_init_cmdline(argc, argv);
+	prom_init_cmdline();
 }
 
 void __init prom_free_prom_memory(void)
diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c
index 844f5cd55c8f..9dd67749c592 100644
--- a/arch/mips/ralink/rt288x.c
+++ b/arch/mips/ralink/rt288x.c
@@ -40,16 +40,6 @@ static struct rt2880_pmx_group rt2880_pinmux_data_act[] = {
 	{ 0 }
 };
 
-static void rt288x_wdt_reset(void)
-{
-	u32 t;
-
-	/* enable WDT reset output on pin SRAM_CS_N */
-	t = rt_sysc_r32(SYSC_REG_CLKCFG);
-	t |= CLKCFG_SRAM_CS_N_WDT;
-	rt_sysc_w32(t, SYSC_REG_CLKCFG);
-}
-
 void __init ralink_clk_init(void)
 {
 	unsigned long cpu_rate, wmac_rate = 40000000;
@@ -119,5 +109,5 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 	soc_info->mem_size_max = RT2880_MEM_SIZE_MAX;
 
 	rt2880_pinmux_data = rt2880_pinmux_data_act;
-	ralink_soc == RT2880_SOC;
+	ralink_soc = RT2880_SOC;
 }
diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c
index 9e4572592065..15b32cd01906 100644
--- a/arch/mips/ralink/rt305x.c
+++ b/arch/mips/ralink/rt305x.c
@@ -89,17 +89,6 @@ static struct rt2880_pmx_group rt5350_pinmux_data[] = {
 	{ 0 }
 };
 
-static void rt305x_wdt_reset(void)
-{
-	u32 t;
-
-	/* enable WDT reset output on pin SRAM_CS_N */
-	t = rt_sysc_r32(SYSC_REG_SYSTEM_CONFIG);
-	t |= RT305X_SYSCFG_SRAM_CS0_MODE_WDT <<
-		RT305X_SYSCFG_SRAM_CS0_MODE_SHIFT;
-	rt_sysc_w32(t, SYSC_REG_SYSTEM_CONFIG);
-}
-
 static unsigned long rt5350_get_mem_size(void)
 {
 	void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE);
diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c
index 582995aaaf4e..3c575093f8f1 100644
--- a/arch/mips/ralink/rt3883.c
+++ b/arch/mips/ralink/rt3883.c
@@ -36,7 +36,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
 static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
 static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
 static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
 static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-dev", 0, 40, 32),
 	FUNC("pci-host2", 1, 40, 32),
@@ -44,7 +44,7 @@ static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-fnc", 3, 40, 32)
 };
 static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
 
 static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
@@ -63,16 +63,6 @@ static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 	{ 0 }
 };
 
-static void rt3883_wdt_reset(void)
-{
-	u32 t;
-
-	/* enable WDT reset output on GPIO 2 */
-	t = rt_sysc_r32(RT3883_SYSC_REG_SYSCFG1);
-	t |= RT3883_SYSCFG1_GPIO2_AS_WDT_OUT;
-	rt_sysc_w32(t, RT3883_SYSC_REG_SYSCFG1);
-}
-
 void __init ralink_clk_init(void)
 {
 	unsigned long cpu_rate, sys_rate;
diff --git a/arch/mips/sgi-ip22/Platform b/arch/mips/sgi-ip22/Platform
index b7a4b7e04c38..e8f6b3a42a48 100644
--- a/arch/mips/sgi-ip22/Platform
+++ b/arch/mips/sgi-ip22/Platform
@@ -25,7 +25,7 @@ endif
 # Simplified: what IP22 does at 128MB+ in ksegN, IP28 does at 512MB+ in xkphys
 #
 ifdef CONFIG_SGI_IP28
-  ifeq ($(call cc-option-yn,-mr10k-cache-barrier=store), n)
+  ifeq ($(call cc-option-yn,-march=r10000 -mr10k-cache-barrier=store), n)
       $(error gcc doesn't support needed option -mr10k-cache-barrier=store)
   endif
 endif
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 14568900fc1d..6c7d78546eee 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -5,10 +5,12 @@ obj-vdso-y := elf.o gettimeofday.o sigreturn.o
 ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
+	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS))
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-	-O2 -g -fPIC -fno-common -fno-builtin -G 0 -DDISABLE_BRANCH_PROFILING \
+	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+	-DDISABLE_BRANCH_PROFILING \
 	$(call cc-option, -fno-stack-protector)
 aflags-vdso := $(ccflags-vdso) \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
@@ -73,7 +75,7 @@ obj-vdso := $(obj-vdso-y:%.o=$(obj)/%.o)
 $(obj-vdso): KBUILD_CFLAGS := $(cflags-vdso) $(native-abi)
 $(obj-vdso): KBUILD_AFLAGS := $(aflags-vdso) $(native-abi)
 
-$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(native-abi)
+$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) $(native-abi)
 
 $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h
index 537278746a15..4af43d9ba495 100644
--- a/arch/mn10300/include/asm/uaccess.h
+++ b/arch/mn10300/include/asm/uaccess.h
@@ -181,6 +181,7 @@ struct __large_struct { unsigned long buf[100]; };
 		"2:\n"						\
 		"	.section	.fixup,\"ax\"\n"	\
 		"3:\n\t"					\
+		"	mov		0,%1\n"			\
 		"	mov		%3,%0\n"		\
 		"	jmp		2b\n"			\
 		"	.previous\n"				\
diff --git a/arch/mn10300/lib/usercopy.c b/arch/mn10300/lib/usercopy.c
index 7826e6c364e7..ce8899e5e171 100644
--- a/arch/mn10300/lib/usercopy.c
+++ b/arch/mn10300/lib/usercopy.c
@@ -9,7 +9,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long
 __generic_copy_to_user(void *to, const void *from, unsigned long n)
@@ -24,6 +24,8 @@ __generic_copy_from_user(void *to, const void *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
 		__copy_user_zeroing(to, from, n);
+	else
+		memset(to, 0, n);
 	return n;
 }
 
diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h
index caa51ff85a3c..0ab82324c817 100644
--- a/arch/nios2/include/asm/uaccess.h
+++ b/arch/nios2/include/asm/uaccess.h
@@ -102,9 +102,12 @@ extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
 static inline long copy_from_user(void *to, const void __user *from,
 				unsigned long n)
 {
-	if (!access_ok(VERIFY_READ, from, n))
-		return n;
-	return __copy_from_user(to, from, n);
+	unsigned long res = n;
+	if (access_ok(VERIFY_READ, from, n))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline long copy_to_user(void __user *to, const void *from,
@@ -139,7 +142,7 @@ extern long strnlen_user(const char __user *s, long n);
 
 #define __get_user_unknown(val, size, ptr, err) do {			\
 	err = 0;							\
-	if (copy_from_user(&(val), ptr, size)) {			\
+	if (__copy_from_user(&(val), ptr, size)) {			\
 		err = -EFAULT;						\
 	}								\
 	} while (0)
@@ -166,7 +169,7 @@ do {									\
 	({								\
 	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
 	(x) = (__force __typeof__(x))__gu_val;				\
 	__gu_err;							\
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 718dd197909f..de73beb36910 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -48,6 +48,13 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return alloc_bootmem_align(size, align);
 }
 
+int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+					     bool nomap)
+{
+	reserve_bootmem(base, size, BOOTMEM_DEFAULT);
+	return 0;
+}
+
 void __init early_init_devtree(void *params)
 {
 	__be32 *dtb = (u32 *)__dtb_start;
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index a4ff86d58d5c..6c4e351a7930 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -195,6 +195,9 @@ void __init setup_arch(char **cmdline_p)
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
 	unflatten_and_copy_device_tree();
 
 	setup_cpuinfo();
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index a6bd07ca3d6c..5cc6b4f1b795 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -273,28 +273,20 @@ __copy_tofrom_user(void *to, const void *from, unsigned long size);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
-	return n;
+	unsigned long res = n;
+
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_tofrom_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		n = __copy_tofrom_user(to, from, n);
 	return n;
 }
 
@@ -303,13 +295,8 @@ extern unsigned long __clear_user(void *addr, unsigned long size);
 static inline __must_check unsigned long
 clear_user(void *addr, unsigned long size)
 {
-
-	if (access_ok(VERIFY_WRITE, addr, size))
-		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, addr, size)))
+		size = __clear_user(addr, size);
 	return size;
 }
 
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 2d69a853b742..3a08b55609b6 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -38,6 +38,8 @@ SECTIONS
         /* Read-only sections, merged into text segment: */
         . = LOAD_BASE ;
 
+	_text = .;
+
 	/* _s_kernel_ro must be page aligned */
 	. = ALIGN(PAGE_SIZE);
 	_s_kernel_ro = .;
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 3f9406d9b9d6..da87943328a5 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -6,7 +6,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <linux/atomic.h>
@@ -17,6 +17,12 @@
  * to include/asm-i386/bitops.h or kerneldoc
  */
 
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index d8d60a57183f..f53725202955 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -39,6 +39,8 @@ struct hppa_dma_ops {
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
+#define DMA_ERROR_CODE	(~(dma_addr_t)0)
+
 #ifdef CONFIG_PA11
 extern struct hppa_dma_ops pcxl_dma_ops;
 extern struct hppa_dma_ops pcx_dma_ops;
@@ -209,12 +211,13 @@ parisc_walk_tree(struct device *dev)
 			break;
 		}
 	}
-	BUG_ON(!dev->platform_data);
 	return dev->platform_data;
 }
-		
-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu)
-	
+
+#define GET_IOC(dev) ({					\
+	void *__pdata = parisc_walk_tree(dev);		\
+	__pdata ? HBA_DATA(__pdata)->iommu : NULL;	\
+})
 
 #ifdef CONFIG_IOMMU_CCIO
 struct parisc_device;
diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h
index 59be25764433..a81226257878 100644
--- a/arch/parisc/include/asm/mmu_context.h
+++ b/arch/parisc/include/asm/mmu_context.h
@@ -49,15 +49,26 @@ static inline void load_context(mm_context_t context)
 	mtctl(__space_to_prot(context), 8);
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+		struct mm_struct *next, struct task_struct *tsk)
 {
-
 	if (prev != next) {
 		mtctl(__pa(next->pgd), 25);
 		load_context(next->context);
 	}
 }
 
+static inline void switch_mm(struct mm_struct *prev,
+		struct mm_struct *next, struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
 #define deactivate_mm(tsk,mm)	do { } while (0)
 
 static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 291cee28ccb6..3a4ed9f91d57 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -65,9 +65,9 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 		unsigned long flags;				\
 		spin_lock_irqsave(&pa_tlb_lock, flags);		\
 		old_pte = *ptep;				\
-		set_pte(ptep, pteval);				\
 		if (pte_inserted(old_pte))			\
 			purge_tlb_entries(mm, addr);		\
+		set_pte(ptep, pteval);				\
 		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
@@ -83,10 +83,10 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#ifdef CONFIG_64BIT
-#define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */
+#if defined(CONFIG_64BIT)
+#define KERNEL_INITIAL_ORDER	26	/* 1<<26 = 64MB */
 #else
-#define KERNEL_INITIAL_ORDER	24	/* 1<<24 = 16MB */
+#define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */
 #endif
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
@@ -478,8 +478,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
-	set_pte(ptep, pte_mkold(pte));
 	purge_tlb_entries(vma->vm_mm, addr);
+	set_pte(ptep, pte_mkold(pte));
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
@@ -492,9 +492,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 
 	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	set_pte(ptep, __pte(0));
 	if (pte_inserted(old_pte))
 		purge_tlb_entries(mm, addr);
+	set_pte(ptep, __pte(0));
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
@@ -504,8 +504,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 {
 	unsigned long flags;
 	spin_lock_irqsave(&pa_tlb_lock, flags);
-	set_pte(ptep, pte_wrprotect(*ptep));
 	purge_tlb_entries(mm, addr);
+	set_pte(ptep, pte_wrprotect(*ptep));
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 0abdd4c607ed..4ad51465890b 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -10,6 +10,7 @@
 #include <asm-generic/uaccess-unaligned.h>
 
 #include <linux/bug.h>
+#include <linux/string.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
@@ -76,6 +77,7 @@ struct exception_table_entry {
  */
 struct exception_data {
 	unsigned long fault_ip;
+	unsigned long fault_gp;
 	unsigned long fault_space;
 	unsigned long fault_addr;
 };
@@ -244,13 +246,14 @@ static inline unsigned long __must_check copy_from_user(void *to,
                                           unsigned long n)
 {
         int sz = __compiletime_object_size(to);
-        int ret = -EFAULT;
+        unsigned long ret = n;
 
         if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n))
                 ret = __copy_from_user(to, from, n);
         else
                 copy_from_user_overflow();
-
+	if (unlikely(ret))
+		memset(to + (n - ret), 0, ret);
         return ret;
 }
 
diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7bdd43..07fa7e50bdc0 100644
--- a/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -3,10 +3,8 @@
 
 #if defined(__LP64__)
 #define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
 #else
 #define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
 #endif
 
 #include <asm-generic/bitsperlong.h>
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index c0ae62520d15..274d5bc6ecce 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -97,10 +97,10 @@
 #define	ENOTCONN	235	/* Transport endpoint is not connected */
 #define	ESHUTDOWN	236	/* Cannot send after transport endpoint shutdown */
 #define	ETOOMANYREFS	237	/* Too many references: cannot splice */
-#define EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
-#define EREMOTERELEASE	240	/* Remote peer released connection */
+#define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
+#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h
index e78403b129ef..928e1bbac98f 100644
--- a/arch/parisc/include/uapi/asm/swab.h
+++ b/arch/parisc/include/uapi/asm/swab.h
@@ -1,6 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
+#include <asm/bitsperlong.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 }
 #define __arch_swab32 __arch_swab32
 
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
 /*
 ** From "PA-RISC 2.0 Architecture", HP Professional Books.
 ** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 	return x;
 }
 #define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
 
 #endif /* _PARISC_SWAB_H */
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index d2f62570a7b1..78d30d2ea2d8 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -299,6 +299,7 @@ int main(void)
 #endif
 	BLANK();
 	DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip));
+	DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp));
 	DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space));
 	DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr));
 	BLANK();
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index cda6dbbe9842..6857a104b2f9 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -351,6 +351,7 @@ void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
 	unsigned long size, start;
+	unsigned long threshold;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -364,26 +365,30 @@ void __init parisc_setup_cache_timing(void)
 	printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n",
 		alltime, size, rangetime);
 
-	/* Racy, but if we see an intermediate value, it's ok too... */
-	parisc_cache_flush_threshold = size * alltime / rangetime;
-
-	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
-	if (!parisc_cache_flush_threshold)
-		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
-
-	if (parisc_cache_flush_threshold > cache_info.dc_size)
-		parisc_cache_flush_threshold = cache_info.dc_size;
-
-	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+	threshold = L1_CACHE_ALIGN(size * alltime / rangetime);
+	if (threshold > cache_info.dc_size)
+		threshold = cache_info.dc_size;
+	if (threshold)
+		parisc_cache_flush_threshold = threshold;
+	printk(KERN_INFO "Cache flush threshold set to %lu KiB\n",
 		parisc_cache_flush_threshold/1024);
 
 	/* calculate TLB flush threshold */
 
+	/* On SMP machines, skip the TLB measure of kernel text which
+	 * has been mapped as huge pages. */
+	if (num_online_cpus() > 1 && !parisc_requires_coherency()) {
+		threshold = max(cache_info.it_size, cache_info.dt_size);
+		threshold *= PAGE_SIZE;
+		threshold /= num_online_cpus();
+		goto set_tlb_threshold;
+	}
+
 	alltime = mfctl(16);
 	flush_tlb_all();
 	alltime = mfctl(16) - alltime;
 
-	size = PAGE_SIZE;
+	size = 0;
 	start = (unsigned long) _text;
 	rangetime = mfctl(16);
 	while (start < (unsigned long) _end) {
@@ -396,13 +401,12 @@ void __init parisc_setup_cache_timing(void)
 	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
 		alltime, size, rangetime);
 
-	parisc_tlb_flush_threshold = size * alltime / rangetime;
-	parisc_tlb_flush_threshold *= num_online_cpus();
-	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
-	if (!parisc_tlb_flush_threshold)
-		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+	threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime);
 
-	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+set_tlb_threshold:
+	if (threshold)
+		parisc_tlb_flush_threshold = threshold;
+	printk(KERN_INFO "TLB flush threshold set to %lu KiB\n",
 		parisc_tlb_flush_threshold/1024);
 }
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index b743a80eaba0..a4761b772406 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -96,7 +96,7 @@ fitmanyloop:					/* Loop if LOOP >= 2 */
 
 fitmanymiddle:					/* Loop if LOOP >= 2 */
 	addib,COND(>)		-1, %r31, fitmanymiddle	/* Adjusted inner loop decr */
-	pitlbe		0(%sr1, %r28)
+	pitlbe		%r0(%sr1, %r28)
 	pitlbe,m	%arg1(%sr1, %r28)	/* Last pitlbe and addr adjust */
 	addib,COND(>)		-1, %r29, fitmanymiddle	/* Middle loop decr */
 	copy		%arg3, %r31		/* Re-init inner loop count */
@@ -139,7 +139,7 @@ fdtmanyloop:					/* Loop if LOOP >= 2 */
 
 fdtmanymiddle:					/* Loop if LOOP >= 2 */
 	addib,COND(>)		-1, %r31, fdtmanymiddle	/* Adjusted inner loop decr */
-	pdtlbe		0(%sr1, %r28)
+	pdtlbe		%r0(%sr1, %r28)
 	pdtlbe,m	%arg1(%sr1, %r28)	/* Last pdtlbe and addr adjust */
 	addib,COND(>)		-1, %r29, fdtmanymiddle	/* Middle loop decr */
 	copy		%arg3, %r31		/* Re-init inner loop count */
@@ -620,12 +620,12 @@ ENTRY(copy_user_page_asm)
 	/* Purge any old translations */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
-	pdtlb,l		0(%r29)
+	pdtlb,l		%r0(%r28)
+	pdtlb,l		%r0(%r29)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
-	pdtlb		0(%r29)
+	pdtlb		%r0(%r28)
+	pdtlb		%r0(%r29)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -768,10 +768,10 @@ ENTRY(clear_user_page_asm)
 	/* Purge any old translation */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
+	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
+	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -852,10 +852,10 @@ ENTRY(flush_dcache_page_asm)
 	/* Purge any old translation */
 
 #ifdef CONFIG_PA20
-	pdtlb,l		0(%r28)
+	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r28)
+	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
 #endif
 
@@ -886,19 +886,10 @@ ENTRY(flush_dcache_page_asm)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
-	cmpb,COND(<<)		%r28, %r25,1b
+	cmpb,COND(<<)	%r28, %r25,1b
 	fdc,m		r31(%r28)
 
 	sync
-
-#ifdef CONFIG_PA20
-	pdtlb,l		0(%r25)
-#else
-	tlb_lock	%r20,%r21,%r22
-	pdtlb		0(%r25)
-	tlb_unlock	%r20,%r21,%r22
-#endif
-
 	bv		%r0(%r2)
 	nop
 	.exit
@@ -925,13 +916,18 @@ ENTRY(flush_icache_page_asm)
 	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
 #endif
 
-	/* Purge any old translation */
+	/* Purge any old translation.  Note that the FIC instruction
+	 * may use either the instruction or data TLB.  Given that we
+	 * have a flat address space, it's not clear which TLB will be
+	 * used.  So, we purge both entries.  */
 
 #ifdef CONFIG_PA20
+	pdtlb,l		%r0(%r28)
 	pitlb,l         %r0(%sr4,%r28)
 #else
 	tlb_lock        %r20,%r21,%r22
-	pitlb           (%sr4,%r28)
+	pdtlb		%r0(%r28)
+	pitlb           %r0(%sr4,%r28)
 	tlb_unlock      %r20,%r21,%r22
 #endif
 
@@ -968,15 +964,6 @@ ENTRY(flush_icache_page_asm)
 	fic,m		%r31(%sr4,%r28)
 
 	sync
-
-#ifdef CONFIG_PA20
-	pitlb,l         %r0(%sr4,%r25)
-#else
-	tlb_lock        %r20,%r21,%r22
-	pitlb           (%sr4,%r25)
-	tlb_unlock      %r20,%r21,%r22
-#endif
-
 	bv		%r0(%r2)
 	nop
 	.exit
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 568b2c61ea02..3cad8aadc69e 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64);
 EXPORT_SYMBOL(lclear_user);
 EXPORT_SYMBOL(lstrnlen_user);
 
-/* Global fixups */
-extern void fixup_get_user_skip_1(void);
-extern void fixup_get_user_skip_2(void);
-extern void fixup_put_user_skip_1(void);
-extern void fixup_put_user_skip_2(void);
+/* Global fixups - defined as int to avoid creation of function pointers */
+extern int fixup_get_user_skip_1;
+extern int fixup_get_user_skip_2;
+extern int fixup_put_user_skip_1;
+extern int fixup_put_user_skip_2;
 EXPORT_SYMBOL(fixup_get_user_skip_1);
 EXPORT_SYMBOL(fixup_get_user_skip_2);
 EXPORT_SYMBOL(fixup_put_user_skip_1);
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index b9402c9b3454..af0d7fae7aa7 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -95,8 +95,8 @@ static inline int map_pte_uncached(pte_t * pte,
 
 		if (!pte_none(*pte))
 			printk(KERN_ERR "map_pte_uncached: page already exists\n");
-		set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
 		purge_tlb_start(flags);
+		set_pte(pte, __mk_pte(*paddr_ptr, PAGE_KERNEL_UNC));
 		pdtlb_kernel(orig_vaddr);
 		purge_tlb_end(flags);
 		vaddr += PAGE_SIZE;
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index f7ea626e29c9..2e66a887788e 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -38,6 +38,7 @@
 #include <linux/export.h>
 
 #include <asm/processor.h>
+#include <asm/sections.h>
 #include <asm/pdc.h>
 #include <asm/led.h>
 #include <asm/machdep.h>	/* for pa7300lc_init() proto */
@@ -140,6 +141,13 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	printk(KERN_CONT ".\n");
 
+	/*
+	 * Check if initial kernel page mappings are sufficient.
+	 * panic early if not, else we may access kernel functions
+	 * and variables which can't be reached.
+	 */
+	if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
+		panic("KERNEL_INITIAL_ORDER too small!");
 
 	pdc_console_init();
 
@@ -326,6 +334,10 @@ static int __init parisc_init(void)
 	/* tell PDC we're Linux. Nevermind failure. */
 	pdc_stable_write(0x40, &osid, sizeof(osid));
 	
+	/* start with known state */
+	flush_cache_all_local();
+	flush_tlb_all_local(NULL);
+
 	processor_init();
 #ifdef CONFIG_SMP
 	pr_info("CPU(s): %d out of %d %s at %d.%06d MHz online\n",
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 5aba01ac457f..4dda73c44fee 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	unsigned long task_size = TASK_SIZE;
 	int do_color_align, last_mmap;
 	struct vm_unmapped_area_info info;
@@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		else
 			addr = PAGE_ALIGN(addr);
 
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}
 
@@ -141,7 +142,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
 			  const unsigned long flags)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	int do_color_align, last_mmap;
@@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = COLOR_ALIGN(addr, last_mmap, pgoff);
 		else
 			addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}
 
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index fbafa0d0e2bf..a86b19fccb63 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -106,8 +106,6 @@ linux_gateway_entry:
 	mtsp	%r0,%sr4			/* get kernel space into sr4 */
 	mtsp	%r0,%sr5			/* get kernel space into sr5 */
 	mtsp	%r0,%sr6			/* get kernel space into sr6 */
-	mfsp    %sr7,%r1                        /* save user sr7 */
-	mtsp    %r1,%sr3                        /* and store it in sr3 */
 
 #ifdef CONFIG_64BIT
 	/* for now we can *always* set the W bit on entry to the syscall
@@ -133,6 +131,14 @@ linux_gateway_entry:
 	depdi	0, 31, 32, %r21
 1:	
 #endif
+
+	/* We use a rsm/ssm pair to prevent sr3 from being clobbered
+	 * by external interrupts.
+	 */
+	mfsp    %sr7,%r1                        /* save user sr7 */
+	rsm	PSW_SM_I, %r0			/* disable interrupts */
+	mtsp    %r1,%sr3                        /* and store it in sr3 */
+
 	mfctl   %cr30,%r1
 	xor     %r1,%r30,%r30                   /* ye olde xor trick */
 	xor     %r1,%r30,%r1
@@ -147,6 +153,7 @@ linux_gateway_entry:
 	 */
 
 	mtsp	%r0,%sr7			/* get kernel space into sr7 */
+	ssm	PSW_SM_I, %r0			/* enable interrupts */
 	STREGM	%r1,FRAME_SIZE(%r30)		/* save r1 (usp) here for now */
 	mfctl	%cr30,%r1			/* get task ptr in %r1 */
 	LDREG	TI_TASK(%r1),%r1
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index d4ffcfbc9885..041e1f9ec129 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -361,7 +361,7 @@
 	ENTRY_SAME(ni_syscall)	/* 263: reserved for vserver */
 	ENTRY_SAME(add_key)
 	ENTRY_SAME(request_key)		/* 265 */
-	ENTRY_SAME(keyctl)
+	ENTRY_COMP(keyctl)
 	ENTRY_SAME(ioprio_set)
 	ENTRY_SAME(ioprio_get)
 	ENTRY_SAME(inotify_init)
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 553b09855cfd..77e2262c97f6 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	    if (fault_space == 0 && !faulthandler_disabled())
 	    {
+		/* Clean up and return if in exception table. */
+		if (fixup_exception(regs))
+			return;
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
 	    }
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb35ec2..8d49614d600d 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -666,7 +666,7 @@ void handle_unaligned(struct pt_regs *regs)
 		break;
 	}
 
-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;
 
 
@@ -677,6 +677,14 @@ void handle_unaligned(struct pt_regs *regs)
 
 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);
 
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 308f29081d46..60771df10fde 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -88,8 +88,9 @@ SECTIONS
 	/* Start of data section */
 	_sdata = .;
 
-	RO_DATA_SECTION(8)
-
+	/* Architecturally we need to keep __gp below 0x1000000 and thus
+	 * in front of RO_DATA_SECTION() which stores lots of tracepoint
+	 * and ftrace symbols. */
 #ifdef CONFIG_64BIT
 	. = ALIGN(16);
 	/* Linkage tables */
@@ -104,6 +105,8 @@ SECTIONS
 	}
 #endif
 
+	RO_DATA_SECTION(8)
+
 	/* unwind info */
 	.PARISC.unwind : {
 		__start___unwind = .;
diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S
index 536ef66bb94b..1052b747e011 100644
--- a/arch/parisc/lib/fixup.S
+++ b/arch/parisc/lib/fixup.S
@@ -26,6 +26,7 @@
 
 #ifdef CONFIG_SMP
 	.macro  get_fault_ip t1 t2
+	loadgp
 	addil LT%__per_cpu_offset,%r27
 	LDREG RT%__per_cpu_offset(%r1),\t1
 	/* t2 = smp_processor_id() */
@@ -40,14 +41,19 @@
 	LDREG RT%exception_data(%r1),\t1
 	/* t1 = this_cpu_ptr(&exception_data) */
 	add,l \t1,\t2,\t1
+	/* %r27 = t1->fault_gp - restore gp */
+	LDREG EXCDATA_GP(\t1), %r27
 	/* t1 = t1->fault_ip */
 	LDREG EXCDATA_IP(\t1), \t1
 	.endm
 #else
 	.macro  get_fault_ip t1 t2
+	loadgp
 	/* t1 = this_cpu_ptr(&exception_data) */
 	addil LT%exception_data,%r27
 	LDREG RT%exception_data(%r1),\t2
+	/* %r27 = t2->fault_gp - restore gp */
+	LDREG EXCDATA_GP(\t2), %r27
 	/* t1 = t2->fault_ip */
 	LDREG EXCDATA_IP(\t2), \t1
 	.endm
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index a762864ec92e..d8c2f3bcfc18 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs)
 		struct exception_data *d;
 		d = this_cpu_ptr(&exception_data);
 		d->fault_ip = regs->iaoq[0];
+		d->fault_gp = regs->gr[27];
 		d->fault_space = regs->isr;
 		d->fault_addr = regs->ior;
 
@@ -302,7 +303,7 @@ bad_area:
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
 			if (!vma ||
-			    address < vma->vm_start || address > vma->vm_end) {
+			    address < vma->vm_start || address >= vma->vm_end) {
 				si.si_signo = SIGSEGV;
 				si.si_code = SEGV_MAPERR;
 				break;
diff --git a/arch/powerpc/boot/ps3-head.S b/arch/powerpc/boot/ps3-head.S
index b6fcbaf5027b..3dc44b05fb97 100644
--- a/arch/powerpc/boot/ps3-head.S
+++ b/arch/powerpc/boot/ps3-head.S
@@ -57,11 +57,6 @@ __system_reset_overlay:
 	bctr
 
 1:
-	/* Save the value at addr zero for a null pointer write check later. */
-
-	li	r4, 0
-	lwz	r3, 0(r4)
-
 	/* Primary delays then goes to _zimage_start in wrapper. */
 
 	or	31, 31, 31 /* db16cyc */
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index 4ec2d86d3c50..a05558a7e51a 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -119,13 +119,12 @@ void ps3_copy_vectors(void)
 	flush_cache((void *)0x100, 512);
 }
 
-void platform_init(unsigned long null_check)
+void platform_init(void)
 {
 	const u32 heapsize = 0x1000000 - (u32)_end; /* 16MiB */
 	void *chosen;
 	unsigned long ft_addr;
 	u64 rm_size;
-	unsigned long val;
 
 	console_ops.write = ps3_console_write;
 	platform_ops.exit = ps3_exit;
@@ -153,11 +152,6 @@ void platform_init(unsigned long null_check)
 
 	printf(" flat tree at 0x%lx\n\r", ft_addr);
 
-	val = *(unsigned long *)0;
-
-	if (val != null_check)
-		printf("null check failed: %lx != %lx\n\r", val, null_check);
-
 	((kernel_entry_t)0)(ft_addr, 0, NULL);
 
 	ps3_exit();
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 861e72109df2..f080abfc2f83 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,7 @@ SECTIONS
   }
 
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
+  . = ALIGN(256);
   .got :
   {
     __toc_start = .;
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 55f106ed12bf..039c4b910615 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -460,7 +460,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
  * Atomically increments @v by 1, so long as @v is non-zero.
  * Returns non-zero if @v was non-zero, and zero otherwise.
  */
-static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
+static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 {
 	long t1, t2;
 
@@ -479,7 +479,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
 
-	return t1;
+	return t1 != 0;
 }
 
 #endif /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index ee46ffef608e..743ad7a400d6 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -23,12 +23,13 @@
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE	0x20000000
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_32bit_task() ? 0x000400000UL : \
+						   0x100000000UL)
 
 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
 
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 9f8402b35115..27e588f6c72e 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -164,6 +164,7 @@ struct coprocessor_request_block {
 #define ICSWX_INITIATED		(0x8)
 #define ICSWX_BUSY		(0x4)
 #define ICSWX_REJECTED		(0x2)
+#define ICSWX_XERS0		(0x1)	/* undefined or set from XERSO. */
 
 static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
 {
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index cfa758c6b4f6..a92d95aee42d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -545,6 +545,7 @@ struct kvm_vcpu_arch {
 	u64 tfiar;
 
 	u32 cr_tm;
+	u64 xer_tm;
 	u64 lr_tm;
 	u64 ctr_tm;
 	u64 amr_tm;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 2220f7a60def..ca372bbc0ffe 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -707,7 +707,8 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
+#define SPRN_UMMCR2	769
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -744,13 +745,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
@@ -1235,7 +1236,7 @@ static inline unsigned long mfvtb (void)
 				"	.llong 0\n"			\
 				".previous"				\
 			: "=r" (rval) \
-			: "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \
+			: "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \
 			rval;})
 #else
 #define mftb()		({unsigned long rval;	\
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 2a8ebae0936b..a5ffe0207c16 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -323,30 +323,17 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 static inline unsigned long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n)))
 		return __copy_tofrom_user((__force void __user *)to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user((__force void __user *)to, from,
-				n - over) + over;
-	}
+	memset(to, 0, n);
 	return n;
 }
 
 static inline unsigned long copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
-	unsigned long over;
-
 	if (access_ok(VERIFY_WRITE, to, n))
 		return __copy_tofrom_user(to, (__force void __user *)from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, (__force void __user *)from,
-				n - over) + over;
-	}
 	return n;
 }
 
@@ -437,10 +424,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_fault();
 	if (likely(access_ok(VERIFY_WRITE, addr, size)))
 		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
 	return size;
 }
 
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index e4396a7d0f7c..4afe66aa1400 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits)
 	    "andc	%1,%1,%2\n\t"
 	    "popcntd	%0,%1"
 		: "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask)
-		: "r" (bits));
+		: "b" (bits));
 
 	return leading_zero_bits;
 }
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 43686043e297..2734c005da21 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -31,6 +31,7 @@
 #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \
 					0x00000040
 
+/* Reserved - do not use		0x00000004 */
 #define PPC_FEATURE_TRUE_LE		0x00000002
 #define PPC_FEATURE_PPC_LE		0x00000001
 
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index ab4d4732c492..720b71a636c8 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -587,6 +587,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
 #define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
 #define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 86150fbb42c3..91e5c1758b5c 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -808,14 +808,25 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
-	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
-	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
-		nb = 8;
-		flags = LD+SW;
-	} else if (IS_XFORM(instruction) &&
-		   ((instruction >> 1) & 0x3ff) == 660) {
-		nb = 8;
-		flags = ST+SW;
+	/*
+	 * Handle some cases which give overlaps in the DSISR values.
+	 */
+	if (IS_XFORM(instruction)) {
+		switch (get_xop(instruction)) {
+		case 532:	/* ldbrx */
+			nb = 8;
+			flags = LD+SW;
+			break;
+		case 660:	/* stdbrx */
+			nb = 8;
+			flags = ST+SW;
+			break;
+		case 20:	/* lwarx */
+		case 84:	/* ldarx */
+		case 116:	/* lharx */
+		case 276:	/* lqarx */
+			return 0;	/* not emulated ever */
+		}
 	}
 
 	/* Byteswap little endian loads and stores */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 221d584d089f..40da69163d51 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -584,6 +584,7 @@ int main(void)
 	DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
 	DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
 	DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
+	DEFINE(VCPU_XER_TM, offsetof(struct kvm_vcpu, arch.xer_tm));
 	DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
 	DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
 	DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 40e4d4a27663..6696c1986844 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -304,9 +304,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*
@@ -677,7 +685,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 	/* Check if the request is finished successfully */
 	if (active_flag) {
 		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if (rc <= 0)
+		if (rc < 0)
 			return rc;
 
 		if (rc & active_flag)
@@ -1072,7 +1080,7 @@ void eeh_add_device_early(struct pci_dn *pdn)
 	struct pci_controller *phb;
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-	if (!edev || !eeh_enabled())
+	if (!edev)
 		return;
 
 	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 52c1e273f8cd..9837c98caabe 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -166,6 +166,16 @@ static void *eeh_dev_save_state(void *data, void *userdata)
 	if (!edev)
 		return NULL;
 
+	/*
+	 * We cannot access the config space on some adapters.
+	 * Otherwise, it will cause fenced PHB. We don't save
+	 * the content in their config space and will restore
+	 * from the initial config space saved when the EEH
+	 * device is created.
+	 */
+	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED))
+		return NULL;
+
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
 		return NULL;
@@ -305,6 +315,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata)
 	if (!edev)
 		return NULL;
 
+	/*
+	 * The content in the config space isn't saved because
+	 * the blocked config space on some adapters. We have
+	 * to restore the initial saved config space when the
+	 * EEH device is created.
+	 */
+	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
+		if (list_is_last(&edev->list, &edev->pe->edevs))
+			eeh_pe_restore_bars(edev->pe);
+
+		return NULL;
+	}
+
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
 		return NULL;
@@ -462,7 +485,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
-	bool *clear_sw_state = flag;
+	bool clear_sw_state = *(bool *)flag;
 	int i, rc = 1;
 
 	for (i = 0; rc && i < 3; i++)
@@ -504,9 +527,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	/* Save states */
 	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
 
-	/* Report error */
-	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
-
 	/* Issue reset */
 	ret = eeh_reset_pe(pe);
 	if (ret) {
@@ -592,8 +612,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
-	if (rc)
+	if (rc) {
+		pci_unlock_rescan_remove();
 		return rc;
+	}
 
 	/* Give the system 5 seconds to finish running the user-space
 	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
@@ -633,7 +655,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
  */
 #define MAX_WAIT_FOR_RECOVERY 300
 
-static void eeh_handle_normal_event(struct eeh_pe *pe)
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
 {
 	struct pci_bus *frozen_bus;
 	int rc = 0;
@@ -643,7 +665,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	if (!frozen_bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return;
+		return false;
 	}
 
 	eeh_pe_update_time_stamp(pe);
@@ -768,7 +790,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
-	return;
+	return false;
 
 excess_failures:
 	/*
@@ -809,7 +831,11 @@ perm_error:
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(frozen_bus);
 		pci_unlock_rescan_remove();
+
+		/* The passed PE should no longer be used */
+		return true;
 	}
+	return false;
 }
 
 static void eeh_handle_special_event(void)
@@ -875,7 +901,14 @@ static void eeh_handle_special_event(void)
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			eeh_handle_normal_event(pe);
+			/*
+			 * eeh_handle_normal_event() can make the PE stale if it
+			 * determines that the PE cannot possibly be recovered.
+			 * Don't modify the PE state if that's the case.
+			 */
+			if (eeh_handle_normal_event(pe))
+				continue;
+
 			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		} else {
 			pci_lock_rescan_remove();
@@ -889,6 +922,14 @@ static void eeh_handle_special_event(void)
 				/* Notify all devices to be down */
 				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 				bus = eeh_pe_bus_get(phb_pe);
+				if (!bus) {
+					pr_err("%s: Cannot find PCI bus for "
+					       "PHB#%d-PE#%x\n",
+					       __func__,
+					       pe->phb->global_number,
+					       pe->addr);
+					break;
+				}
 				eeh_pe_dev_traverse(pe,
 					eeh_report_failure, NULL);
 				pcibios_remove_pci_devices(bus);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a94f155db78e..f6fd0332c3a2 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -334,13 +334,13 @@ syscall_exit_work:
 tabort_syscall:
 	/* Firstly we need to enable TM in the kernel */
 	mfmsr	r10
-	li	r13, 1
-	rldimi	r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+	li	r9, 1
+	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
 	mtmsrd	r10, 0
 
 	/* tabort, this dooms the transaction, nothing else */
-	li	r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R13)
+	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R9)
 
 	/*
 	 * Return directly to userspace. We have corrupted user register state,
@@ -348,8 +348,8 @@ tabort_syscall:
 	 * resume after the tbegin of the aborted transaction with the
 	 * checkpointed register state.
 	 */
-	li	r13, MSR_RI
-	andc	r10, r10, r13
+	li	r9, MSR_RI
+	andc	r10, r10, r9
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
@@ -716,7 +716,7 @@ resume_kernel:
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
 
-	lwz	r3,GPR1(r1)
+	ld	r3,GPR1(r1)
 	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
 	mr	r4,r1			/* src:  current exception frame */
 	mr	r1,r3			/* Reroute the trampoline frame to r1 */
@@ -730,8 +730,8 @@ resume_kernel:
 	addi	r6,r6,8
 	bdnz	2b
 
-	/* Do real store operation to complete stwu */
-	lwz	r5,GPR1(r1)
+	/* Do real store operation to complete stdu */
+	ld	r5,GPR1(r1)
 	std	r8,0(r5)
 
 	/* Clear _TIF_EMULATE_STACK_STORE flag */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 488e6314f993..5cc93f0b52ca 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -735,8 +735,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
@@ -799,8 +805,14 @@ kernel_dbg_exc:
 	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
+#ifdef CONFIG_RELOCATABLE
+	ld	r15,PACATOC(r13)
+	ld	r14,interrupt_base_book3e@got(r15)
+	ld	r15,__end_interrupts@got(r15)
+#else
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
 	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
 	blt+	cr0,1f
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0a0399c2af11..b81ccc5fb32d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -962,11 +962,6 @@ hv_facility_unavailable_relon_trampoline:
 #endif
 	STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist)
 
-	/* Other future vectors */
-	.align	7
-	.globl	__end_interrupts
-__end_interrupts:
-
 	.align	7
 system_call_entry:
 	b	system_call_common
@@ -1253,6 +1248,17 @@ __end_handlers:
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
 	STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
 
+	/*
+	 * The __end_interrupts marker must be past the out-of-line (OOL)
+	 * handlers, so that they are copied to real address 0x100 when running
+	 * a relocatable kernel. This ensures they can be reached from the short
+	 * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch
+	 * directly, without using LOAD_HANDLER().
+	 */
+	.align	7
+	.globl	__end_interrupts
+__end_interrupts:
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
  * Data area reserved for FWNMI option.
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 05e804cdecaa..fdf48785d3e9 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -227,8 +227,10 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	rcu_read_lock();
 
 	bp = __this_cpu_read(bp_per_reg);
-	if (!bp)
+	if (!bp) {
+		rc = NOTIFY_DONE;
 		goto out;
+	}
 	info = counter_arch_bp(bp);
 
 	/*
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index ac86c53e2542..e524a775fa5c 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -180,6 +180,7 @@ static int ibmebus_create_device(struct device_node *dn)
 static int ibmebus_create_devices(const struct of_device_id *matches)
 {
 	struct device_node *root, *child;
+	struct device *dev;
 	int ret = 0;
 
 	root = of_find_node_by_path("/");
@@ -188,9 +189,12 @@ static int ibmebus_create_devices(const struct of_device_id *matches)
 		if (!of_match_node(matches, child))
 			continue;
 
-		if (bus_find_device(&ibmebus_bus_type, NULL, child,
-				    ibmebus_match_node))
+		dev = bus_find_device(&ibmebus_bus_type, NULL, child,
+				      ibmebus_match_node);
+		if (dev) {
+			put_device(dev);
 			continue;
+		}
 
 		ret = ibmebus_create_device(child);
 		if (ret) {
@@ -262,6 +266,7 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device_node *dn = NULL;
+	struct device *dev;
 	char *path;
 	ssize_t rc = 0;
 
@@ -269,8 +274,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 	if (!path)
 		return -ENOMEM;
 
-	if (bus_find_device(&ibmebus_bus_type, NULL, path,
-			    ibmebus_match_path)) {
+	dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+			      ibmebus_match_path);
+	if (dev) {
+		put_device(dev);
 		printk(KERN_WARNING "%s: %s has already been probed\n",
 		       __func__, path);
 		rc = -EEXIST;
@@ -307,6 +314,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 	if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
 				   ibmebus_match_path))) {
 		of_device_unregister(to_platform_device(dev));
+		put_device(dev);
 
 		kfree(path);
 		return count;
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 112ccf497562..73f638789a38 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -44,7 +44,7 @@
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmp	cr0,r0,r0;					\
+1:	cmpd	cr0,r0,r0;					\
 	bne	1b;						\
 	IDLE_INST;						\
 	b	.
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 7c053f281406..1138fec3dd65 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -514,6 +514,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 #endif
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 
@@ -536,6 +545,8 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b2eb4686bd8f..da3c4c3f4ec8 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -204,6 +204,8 @@ static void machine_check_process_queued_event(struct irq_work *work)
 {
 	int index;
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	/*
 	 * For now just print it to console.
 	 * TODO: log this error event to FSP or nvram.
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index ed3ab509faca..df4efa304b2c 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -313,7 +313,7 @@ _GLOBAL(flush_instruction_cache)
 	lis	r3, KERNELBASE@h
 	iccci	0,r3
 #endif
-#elif CONFIG_FSL_BOOKE
+#elif defined(CONFIG_FSL_BOOKE)
 BEGIN_FTR_SECTION
 	mfspr   r3,SPRN_L1CSR0
 	ori     r3,r3,L1CSR0_CFI|L1CSR0_CLFC
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 32e26526f7e4..1eb698f653b4 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -969,7 +969,7 @@ int __init nvram_remove_partition(const char *name, int sig,
 
 		/* Make partition a free partition */
 		part->header.signature = NVRAM_SIG_FREE;
-		strncpy(part->header.name, "wwwwwwwwwwww", 12);
+		memset(part->header.name, 'w', 12);
 		part->header.checksum = nvram_checksum(&part->header);
 		rc = nvram_write_header(part);
 		if (rc <= 0) {
@@ -987,8 +987,8 @@ int __init nvram_remove_partition(const char *name, int sig,
 		}
 		if (prev) {
 			prev->header.length += part->header.length;
-			prev->header.checksum = nvram_checksum(&part->header);
-			rc = nvram_write_header(part);
+			prev->header.checksum = nvram_checksum(&prev->header);
+			rc = nvram_write_header(prev);
 			if (rc <= 0) {
 				printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
 				return rc;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ef2ad2d682da..cf788d7d7e56 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -569,24 +569,6 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
 
-	/*
-	 * Use the current MSR TM suspended bit to track if we have
-	 * checkpointed state outstanding.
-	 * On signal delivery, we'd normally reclaim the checkpointed
-	 * state to obtain stack pointer (see:get_tm_stackpointer()).
-	 * This will then directly return to userspace without going
-	 * through __switch_to(). However, if the stack frame is bad,
-	 * we need to exit this thread which calls __switch_to() which
-	 * will again attempt to reclaim the already saved tm state.
-	 * Hence we need to check that we've not already reclaimed
-	 * this state.
-	 * We do this using the current MSR, rather tracking it in
-	 * some specific thread_struct bit, as it has the additional
-	 * benifit of checking for a potential TM bad thing exception.
-	 */
-	if (!MSR_TM_SUSPENDED(mfmsr()))
-		return;
-
 	tm_reclaim(thr, thr->regs->msr, cause);
 
 	/* Having done the reclaim, we now have the checkpointed
@@ -1257,6 +1239,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		current->thread.regs = regs - 1;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Clear any transactional state, we're exec()ing. The cause is
+	 * not important as there will never be a recheckpoint so it's not
+	 * user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+#endif
+
 	memset(regs->gpr, 0, sizeof(regs->gpr));
 	regs->ctr = 0;
 	regs->link = 0;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 7030b035905d..a15fe1d4e84a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -148,23 +148,25 @@ static struct ibm_pa_feature {
 	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
 	unsigned long	mmu_features;	/* MMU_FTR_xxx bit */
 	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
+	unsigned int	cpu_user_ftrs2;	/* PPC_FEATURE2_xxx bit */
 	unsigned char	pabyte;		/* byte number in ibm,pa-features */
 	unsigned char	pabit;		/* bit number (big-endian) */
 	unsigned char	invert;		/* if 1, pa bit set => clear feature */
 } ibm_pa_features[] __initdata = {
-	{0, 0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
-	{0, 0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
-	{CPU_FTR_CTRL, 0, 0,		0, 3, 0},
-	{CPU_FTR_NOEXECUTE, 0, 0,	0, 6, 0},
-	{CPU_FTR_NODSISRALIGN, 0, 0,	1, 1, 1},
-	{0, MMU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
-	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
+	{0, 0, PPC_FEATURE_HAS_MMU, 0,		0, 0, 0},
+	{0, 0, PPC_FEATURE_HAS_FPU, 0,		0, 1, 0},
+	{CPU_FTR_CTRL, 0, 0, 0,			0, 3, 0},
+	{CPU_FTR_NOEXECUTE, 0, 0, 0,		0, 6, 0},
+	{CPU_FTR_NODSISRALIGN, 0, 0, 0,		1, 1, 1},
+	{0, MMU_FTR_CI_LARGE_PAGE, 0, 0,		1, 2, 0},
+	{CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0},
 	/*
-	 * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
-	 * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
-	 * which is 0 if the kernel doesn't support TM.
+	 * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
+	 * we don't want to turn on TM here, so we use the *_COMP versions
+	 * which are 0 if the kernel doesn't support TM.
 	 */
-	{CPU_FTR_TM_COMP, 0, 0,		22, 0, 0},
+	{CPU_FTR_TM_COMP, 0, 0,
+	 PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 		if (bit ^ fp->invert) {
 			cur_cpu_spec->cpu_features |= fp->cpu_features;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+			cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
 			cur_cpu_spec->mmu_features |= fp->mmu_features;
 		} else {
 			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
 			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+			cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
 			cur_cpu_spec->mmu_features &= ~fp->mmu_features;
 		}
 	}
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 92dea8df6b26..3139533640fc 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -655,6 +655,7 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
@@ -693,7 +694,7 @@ unsigned char ibm_architecture_vec[] = {
 	OV4_MIN_ENT_CAP,		/* minimum VP entitled capacity */
 
 	/* option vector 5: PAPR/OF options */
-	VECTOR_LENGTH(18),		/* length */
+	VECTOR_LENGTH(21),		/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
 	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
@@ -717,15 +718,18 @@ unsigned char ibm_architecture_vec[] = {
 	 * must match by the macro below. Update the definition if
 	 * the structure layout changes.
 	 */
-#define IBM_ARCH_VEC_NRCORES_OFFSET	125
+#define IBM_ARCH_VEC_NRCORES_OFFSET	133
 	W(NR_CPUS),			/* number of cores supported */
 	0,
 	0,
 	0,
 	0,
 	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
-	OV5_FEAT(OV5_PFO_HW_842),
-	OV5_FEAT(OV5_SUB_PROCESSORS),
+	OV5_FEAT(OV5_PFO_HW_842),				/* Byte 17 */
+	0,							/* Byte 18 */
+	0,							/* Byte 19 */
+	0,							/* Byte 20 */
+	OV5_FEAT(OV5_SUB_PROCESSORS),				/* Byte 21 */
 
 	/* option vector 6: IBM PAPR hints */
 	VECTOR_LENGTH(3),		/* length */
@@ -2660,6 +2664,9 @@ static void __init prom_find_boot_cpu(void)
 
 	cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
 
+	if (!PHANDLE_VALID(cpu_pkg))
+		return;
+
 	prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
 	prom.cpu = be32_to_cpu(rval);
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 737c0d0b53ac..b38fd081b222 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -376,7 +376,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 
 #else
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32][0]));
+		     offsetof(struct thread_fp_state, fpr[32]));
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.fp_state, 0, -1);
@@ -404,7 +404,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 	return 0;
 #else
 	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32][0]));
+		     offsetof(struct thread_fp_state, fpr[32]));
 
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				  &target->thread.fp_state, 0, -1);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5c03a6a9b054..a20823210ac0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -220,6 +220,15 @@ static void cpu_ready_for_interrupts(void)
 		unsigned long lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
 	}
+
+	/*
+	 * Fixup HFSCR:TM based on CPU features. The bit is set by our
+	 * early asm init because at that point we haven't updated our
+	 * CPU features from firmware and device-tree. Here we have,
+	 * so let's do it.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+		mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
 }
 
 /*
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a58670..b7019b559ddb 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@ dont_backup_fp:
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@ restore_gprs:
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 37de90f8a845..e4dcb0a43e3f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -297,8 +297,6 @@ long machine_check_early(struct pt_regs *regs)
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
-	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
@@ -704,6 +702,8 @@ void machine_check_exception(struct pt_regs *regs)
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	/* See if any machine dependent calls. In theory, we would want
 	 * to call the CPU first, and call the ppc_md. one if the CPU
 	 * one returns a positive number. However there is existing code
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index 2f01c4a0d8a0..7612eeb31da1 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -59,7 +59,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	bl	V_LOCAL_FUNC(__get_datapage)
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP64
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	li	r0,__NR_syscalls
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index a76b4af37ef2..382021324883 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	bne	cr0,99f
 
 	li	r3,0
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	lis	r5,CLOCK_REALTIME_RES@h
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 2afdb9c0937d..729f8faa95c5 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -498,6 +498,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_MMCR0:
 	case SPRN_MMCR1:
 	case SPRN_MMCR2:
+	case SPRN_UMMCR2:
 #endif
 		break;
 unprivileged:
@@ -640,6 +641,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 	case SPRN_MMCR0:
 	case SPRN_MMCR1:
 	case SPRN_MMCR2:
+	case SPRN_UMMCR2:
 	case SPRN_TIR:
 #endif
 		*spr_val = 0;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a7352b59e6f9..428563b195c3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1186,6 +1186,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_TM_CR:
 		*val = get_reg_val(id, vcpu->arch.cr_tm);
 		break;
+	case KVM_REG_PPC_TM_XER:
+		*val = get_reg_val(id, vcpu->arch.xer_tm);
+		break;
 	case KVM_REG_PPC_TM_LR:
 		*val = get_reg_val(id, vcpu->arch.lr_tm);
 		break;
@@ -1393,6 +1396,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_TM_CR:
 		vcpu->arch.cr_tm = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_TM_XER:
+		vcpu->arch.xer_tm = set_reg_val(id, *val);
+		break;
 	case KVM_REG_PPC_TM_LR:
 		vcpu->arch.lr_tm = set_reg_val(id, *val);
 		break;
@@ -2681,12 +2687,38 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
+	unsigned long ebb_regs[3] = {};	/* shut up GCC */
+	unsigned long user_tar = 0;
+	unsigned long proc_fscr = 0;
+	unsigned int user_vrsave;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
+	/*
+	 * Don't allow entry with a suspended transaction, because
+	 * the guest entry/exit code will lose it.
+	 * If the guest has TM enabled, save away their TM-related SPRs
+	 * (they will get restored by the TM unavailable interrupt).
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+	    (current->thread.regs->msr & MSR_TM)) {
+		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
+			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+			run->fail_entry.hardware_entry_failure_reason = 0;
+			return -EINVAL;
+		}
+		/* Enable TM so we can read the TM SPRs */
+		mtmsr(mfmsr() | MSR_TM);
+		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+	}
+#endif
+
 	kvmppc_core_prepare_to_enter(vcpu);
 
 	/* No need to go into the guest when all we'll do is come back out */
@@ -2709,6 +2741,17 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	flush_fp_to_thread(current);
 	flush_altivec_to_thread(current);
 	flush_vsx_to_thread(current);
+
+	/* Save userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		ebb_regs[0] = mfspr(SPRN_EBBHR);
+		ebb_regs[1] = mfspr(SPRN_EBBRR);
+		ebb_regs[2] = mfspr(SPRN_BESCR);
+		user_tar = mfspr(SPRN_TAR);
+		proc_fscr = mfspr(SPRN_FSCR);
+	}
+	user_vrsave = mfspr(SPRN_VRSAVE);
+
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
 	vcpu->arch.pgdir = current->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
@@ -2730,6 +2773,29 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	} while (is_kvmppc_resume_guest(r));
 
+	/* Restore userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		mtspr(SPRN_EBBHR, ebb_regs[0]);
+		mtspr(SPRN_EBBRR, ebb_regs[1]);
+		mtspr(SPRN_BESCR, ebb_regs[2]);
+		mtspr(SPRN_TAR, user_tar);
+		mtspr(SPRN_FSCR, proc_fscr);
+	}
+	mtspr(SPRN_VRSAVE, user_vrsave);
+
+	/*
+	 * Since we don't do lazy TM reload, we need to reload
+	 * the TM registers here.
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+	    (current->thread.regs->msr & MSR_TM)) {
+		mtspr(SPRN_TFHAR, current->thread.tm_tfhar);
+		mtspr(SPRN_TFIAR, current->thread.tm_tfiar);
+		mtspr(SPRN_TEXASR, current->thread.tm_texasr);
+	}
+#endif
+
  out:
 	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	atomic_dec(&vcpu->kvm->arch.vcpus_running);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 91700518bbf3..d509ff5c87b0 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -653,6 +653,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 					      HPTE_V_ABSENT);
 			do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags),
 				  true);
+			/* Don't lose R/C bit updates done by hardware */
+			r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C);
 			hpte[1] = cpu_to_be64(r);
 		}
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 463af88c95a2..ffab9269bfe4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -36,6 +36,13 @@
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
 
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS			112
+#define STACK_SLOT_TRAP		(SFS-4)
+#define STACK_SLOT_CIABR	(SFS-16)
+#define STACK_SLOT_DAWR		(SFS-24)
+#define STACK_SLOT_DAWRX	(SFS-32)
+
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -274,10 +281,10 @@ kvm_novcpu_exit:
 	bl	kvmhv_accumulate_time
 #endif
 13:	mr	r3, r12
-	stw	r12, 112-4(r1)
+	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, 112-4(r1)
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -489,7 +496,7 @@ kvmppc_hv_entry:
 	 */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -112(r1)
+	stdu	r1, -SFS(r1)
 
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
@@ -643,6 +650,16 @@ kvmppc_got_guest:
 	mtspr	SPRN_PURR,r7
 	mtspr	SPRN_SPURR,r8
 
+	/* Save host values of some registers */
+BEGIN_FTR_SECTION
+	mfspr	r5, SPRN_CIABR
+	mfspr	r6, SPRN_DAWR
+	mfspr	r7, SPRN_DAWRX
+	std	r5, STACK_SLOT_CIABR(r1)
+	std	r6, STACK_SLOT_DAWR(r1)
+	std	r7, STACK_SLOT_DAWRX(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -655,112 +672,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	skip_tm
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
-	/* Turn on TM/FP/VSX/VMX so we can restore them. */
-	mfmsr	r5
-	li	r6, MSR_TM >> 32
-	sldi	r6, r6, 32
-	or	r5, r5, r6
-	ori	r5, r5, MSR_FP
-	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
-	mtmsrd	r5
-
-	/*
-	 * The user may change these outside of a transaction, so they must
-	 * always be context switched.
-	 */
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
-	mtspr	SPRN_TFHAR, r5
-	mtspr	SPRN_TFIAR, r6
-	mtspr	SPRN_TEXASR, r7
-
-	ld	r5, VCPU_MSR(r4)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	skip_tm	/* TM not active in guest */
-
-	/* Make sure the failure summary is set, otherwise we'll program check
-	 * when we trechkpt.  It's possible that this might have been not set
-	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
-	 * host.
-	 */
-	oris	r7, r7, (TEXASR_FS)@h
-	mtspr	SPRN_TEXASR, r7
-
-	/*
-	 * We need to load up the checkpointed state for the guest.
-	 * We need to do this early as it will blow away any GPRs, VSRs and
-	 * some SPRs.
-	 */
-
-	mr	r31, r4
-	addi	r3, r31, VCPU_FPRS_TM
-	bl	load_fp_state
-	addi	r3, r31, VCPU_VRS_TM
-	bl	load_vr_state
-	mr	r4, r31
-	lwz	r7, VCPU_VRSAVE_TM(r4)
-	mtspr	SPRN_VRSAVE, r7
-
-	ld	r5, VCPU_LR_TM(r4)
-	lwz	r6, VCPU_CR_TM(r4)
-	ld	r7, VCPU_CTR_TM(r4)
-	ld	r8, VCPU_AMR_TM(r4)
-	ld	r9, VCPU_TAR_TM(r4)
-	mtlr	r5
-	mtcr	r6
-	mtctr	r7
-	mtspr	SPRN_AMR, r8
-	mtspr	SPRN_TAR, r9
-
-	/*
-	 * Load up PPR and DSCR values but don't put them in the actual SPRs
-	 * till the last moment to avoid running with userspace PPR and DSCR for
-	 * too long.
-	 */
-	ld	r29, VCPU_DSCR_TM(r4)
-	ld	r30, VCPU_PPR_TM(r4)
-
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* Load GPRs r0-r28 */
-	reg = 0
-	.rept	29
-	ld	reg, VCPU_GPRS_TM(reg)(r31)
-	reg = reg + 1
-	.endr
-
-	mtspr	SPRN_DSCR, r29
-	mtspr	SPRN_PPR, r30
-
-	/* Load final GPRs */
-	ld	29, VCPU_GPRS_TM(29)(r31)
-	ld	30, VCPU_GPRS_TM(30)(r31)
-	ld	31, VCPU_GPRS_TM(31)(r31)
-
-	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
-	TRECHKPT
-
-	/* Now let's get back the state we need. */
-	HMT_MEDIUM
-	GET_PACA(r13)
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATMSCRATCH(r13)
-
-	/* Set the MSR RI since we have our registers back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-skip_tm:
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Load guest PMU registers */
@@ -841,12 +754,6 @@ BEGIN_FTR_SECTION
 	/* Skip next section on POWER7 */
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
 	/* Load up POWER8-specific registers */
 	ld	r5, VCPU_IAMR(r4)
 	lwz	r6, VCPU_PSPB(r4)
@@ -1376,8 +1283,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	 */
 	li	r0, 0
 	mtspr	SPRN_IAMR, r0
-	mtspr	SPRN_CIABR, r0
-	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_TCSCR, r0
 	mtspr	SPRN_WORT, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
@@ -1393,6 +1299,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6,VCPU_UAMOR(r9)
 	li	r6,0
 	mtspr	SPRN_AMR,r6
+	mtspr	SPRN_UAMOR, r6
 
 	/* Switch DSCR back to host value */
 	mfspr	r8, SPRN_DSCR
@@ -1436,106 +1343,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	2f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-	/* Turn on TM. */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	ld	r5, VCPU_MSR(r9)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	1f	/* TM not active in guest. */
-
-	li	r3, TM_CAUSE_KVM_RESCHED
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* All GPRs are volatile at this point. */
-	TRECLAIM(R3)
-
-	/* Temporarily store r13 and r9 so we have some regs to play with */
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	std	r9, PACATMSCRATCH(r13)
-	ld	r9, HSTATE_KVM_VCPU(r13)
-
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
-	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
-	.rept	29
-	.if (reg != 9) && (reg != 13)
-	std	reg, VCPU_GPRS_TM(reg)(r9)
-	.endif
-	reg = reg + 1
-	.endr
-	/* ... now save r13 */
-	GET_SCRATCH0(r4)
-	std	r4, VCPU_GPRS_TM(13)(r9)
-	/* ... and save r9 */
-	ld	r4, PACATMSCRATCH(r13)
-	std	r4, VCPU_GPRS_TM(9)(r9)
-
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
-	mfcr	r6
-	mfctr	r7
-	mfspr	r8, SPRN_AMR
-	mfspr	r10, SPRN_TAR
-	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
-	std	r7, VCPU_CTR_TM(r9)
-	std	r8, VCPU_AMR_TM(r9)
-	std	r10, VCPU_TAR_TM(r9)
-
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
-	/* Save FP/VSX. */
-	addi	r3, r9, VCPU_FPRS_TM
-	bl	store_fp_state
-	addi	r3, r9, VCPU_VRS_TM
-	bl	store_vr_state
-	mfspr	r6, SPRN_VRSAVE
-	stw	r6, VCPU_VRSAVE_TM(r9)
-1:
-	/*
-	 * We need to save these SPRs after the treclaim so that the software
-	 * error code is recorded correctly in the TEXASR.  Also the user may
-	 * change these outside of a transaction, so they must always be
-	 * context switched.
-	 */
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-2:
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Increment yield count if they have a VPA */
@@ -1632,6 +1441,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	slbia
 	ptesync
 
+	/* Restore host values of some registers */
+BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_CIABR(r1)
+	ld	r6, STACK_SLOT_DAWR(r1)
+	ld	r7, STACK_SLOT_DAWRX(r1)
+	mtspr	SPRN_CIABR, r5
+	mtspr	SPRN_DAWR, r6
+	mtspr	SPRN_DAWRX, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
@@ -1741,8 +1560,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
-	ld	r0, 112+PPC_LR_STKOFF(r1)
-	addi	r1, r1, 112
+	ld	r0, SFS+PPC_LR_STKOFF(r1)
+	addi	r1, r1, SFS
 	mtlr	r0
 	blr
 
@@ -2245,6 +2064,13 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	/* save FP state */
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/*
 	 * Set DEC to the smaller of DEC and HDEC, so that we wake
 	 * no later than the end of our timeslice (HDEC interrupts
@@ -2321,6 +2147,12 @@ kvm_end_cede:
 	bl	kvmhv_accumulate_time
 #endif
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -2629,6 +2461,243 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r31
 	blr
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+kvmppc_save_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	std	r1, HSTATE_HOST_R1(r13)
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	mfxer	r11
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+	std	r11, VCPU_XER_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+kvmppc_restore_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	mfmsr	r5
+	li	r6, MSR_TM >> 32
+	sldi	r6, r6, 32
+	or	r5, r5, r6
+	ori	r5, r5, MSR_FP
+	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r5
+
+	/*
+	 * The user may change these outside of a transaction, so they must
+	 * always be context switched.
+	 */
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	ld	r5, VCPU_MSR(r4)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beqlr		/* TM not active in guest */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Make sure the failure summary is set, otherwise we'll program check
+	 * when we trechkpt.  It's possible that this might have been not set
+	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+	 * host.
+	 */
+	oris	r7, r7, (TEXASR_FS)@h
+	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * We need to load up the checkpointed state for the guest.
+	 * We need to do this early as it will blow away any GPRs, VSRs and
+	 * some SPRs.
+	 */
+
+	mr	r31, r4
+	addi	r3, r31, VCPU_FPRS_TM
+	bl	load_fp_state
+	addi	r3, r31, VCPU_VRS_TM
+	bl	load_vr_state
+	mr	r4, r31
+	lwz	r7, VCPU_VRSAVE_TM(r4)
+	mtspr	SPRN_VRSAVE, r7
+
+	ld	r5, VCPU_LR_TM(r4)
+	lwz	r6, VCPU_CR_TM(r4)
+	ld	r7, VCPU_CTR_TM(r4)
+	ld	r8, VCPU_AMR_TM(r4)
+	ld	r9, VCPU_TAR_TM(r4)
+	ld	r10, VCPU_XER_TM(r4)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+	mtxer	r10
+
+	/*
+	 * Load up PPR and DSCR values but don't put them in the actual SPRs
+	 * till the last moment to avoid running with userspace PPR and DSCR for
+	 * too long.
+	 */
+	ld	r29, VCPU_DSCR_TM(r4)
+	ld	r30, VCPU_PPR_TM(r4)
+
+	std	r2, PACATMSCRATCH(r13) /* Save TOC */
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* Load GPRs r0-r28 */
+	reg = 0
+	.rept	29
+	ld	reg, VCPU_GPRS_TM(reg)(r31)
+	reg = reg + 1
+	.endr
+
+	mtspr	SPRN_DSCR, r29
+	mtspr	SPRN_PPR, r30
+
+	/* Load final GPRs */
+	ld	29, VCPU_GPRS_TM(29)(r31)
+	ld	30, VCPU_GPRS_TM(30)(r31)
+	ld	31, VCPU_GPRS_TM(31)(r31)
+
+	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
+	TRECHKPT
+
+	/* Now let's get back the state we need. */
+	HMT_MEDIUM
+	GET_PACA(r13)
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATMSCRATCH(r13)
+
+	/* Set the MSR RI since we have our registers back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+#endif
+
 /*
  * We come here if we get any exception or interrupt while we are
  * executing host real mode code while in guest MMU context.
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index fd5875179e5c..6d63cd67b09b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -2033,7 +2033,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 		if (type == KVMPPC_DEBUG_NONE)
 			continue;
 
-		if (type & !(KVMPPC_DEBUG_WATCH_READ |
+		if (type & ~(KVMPPC_DEBUG_WATCH_READ |
 			     KVMPPC_DEBUG_WATCH_WRITE |
 			     KVMPPC_DEBUG_BREAKPOINT))
 			return -EINVAL;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 5cc2e7af3a7b..b379146de55b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -302,7 +302,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			advance = 0;
 			printk(KERN_ERR "Couldn't emulate instruction 0x%08x "
 			       "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst));
-			kvmppc_core_queue_program(vcpu, 0);
 		}
 	}
 
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index f09899e35991..7b22624f332c 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -359,6 +359,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	addi	r3,r3,8
 171:
 177:
+179:
 	addi	r3,r3,8
 370:
 372:
@@ -373,7 +374,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 173:
 174:
 175:
-179:
 181:
 184:
 186:
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index dc885b30f7a6..e37162d356d8 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -687,8 +687,10 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
 	case 19:
 		switch ((instr >> 1) & 0x3ff) {
 		case 0:		/* mcrf */
-			rd = (instr >> 21) & 0x1c;
-			ra = (instr >> 16) & 0x1c;
+			rd = 7 - ((instr >> 23) & 0x7);
+			ra = 7 - ((instr >> 18) & 0x7);
+			rd *= 4;
+			ra *= 4;
 			val = (regs->ccr >> ra) & 0xf;
 			regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd);
 			goto instr_done;
@@ -967,6 +969,19 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
 #endif
 
 		case 19:	/* mfcr */
+			if ((instr >> 20) & 1) {
+				imm = 0xf0000000UL;
+				for (sh = 0; sh < 8; ++sh) {
+					if (instr & (0x80000 >> sh)) {
+						regs->gpr[rd] = regs->ccr & imm;
+						break;
+					}
+					imm >>= 4;
+				}
+
+				goto instr_done;
+			}
+
 			regs->gpr[rd] = regs->ccr;
 			regs->gpr[rd] &= 0xffffffffUL;
 			goto instr_done;
@@ -1806,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case LARX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		err = -EFAULT;
@@ -1829,8 +1842,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case STCX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		err = -EFAULT;
@@ -1854,8 +1865,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case LOAD:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
 		if (!err) {
 			if (op.type & SIGNEXT)
@@ -1867,8 +1876,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
 		else
@@ -1877,15 +1884,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
@@ -1908,8 +1911,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case STORE:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if ((op.type & UPDATE) && size == sizeof(long) &&
 		    op.reg == 1 && op.update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
@@ -1922,8 +1923,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
 		else
@@ -1932,15 +1931,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 6527882ce05e..ddfd2740a1b5 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
 		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+		if (mm == NULL)
+			return 1;
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
 		vsid = get_vsid(mm->context.id, ea, ssize);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index c8822af10a58..19d9b2d2d212 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -645,6 +645,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;
+	unsigned int use_local;
+
+	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
 
 	local_irq_save(flags);
 
@@ -671,8 +675,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
-	    mmu_psize_defs[psize].tlbiel && local) {
+	if (use_local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
 			vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 9833fee493ec..807f1594701d 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
 {
 	struct hugepd_freelist **batchp;
 
-	batchp = this_cpu_ptr(&hugepd_freelist_cur);
+	batchp = &get_cpu_var(hugepd_freelist_cur);
 
 	if (atomic_read(&tlb->mm->mm_users) < 2 ||
 	    cpumask_equal(mm_cpumask(tlb->mm),
 			  cpumask_of(smp_processor_id()))) {
 		kmem_cache_free(hugepte_cache, hugepte);
-        put_cpu_var(hugepd_freelist_cur);
+		put_cpu_var(hugepd_freelist_cur);
 		return;
 	}
 
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 736d18b3cefd..0b48ce40d351 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -113,7 +113,12 @@ BEGIN_FTR_SECTION
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
-0:
+0:	/*
+	 * For userspace addresses, make sure this is region 0.
+	 */
+	cmpdi	r9, 0
+	bne	8f
+
 	/* when using slices, we extract the psize off the slice bitmaps
 	 * and then we need to get the sllp encoding off the mmu_psize_defs
 	 * array.
@@ -174,6 +179,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load
 
 8:	/* invalid EA */
+	/*
+	 * It's possible the bad EA is too large to fit in the SLB cache, which
+	 * would mean we'd fail to invalidate it on context switch. So mark the
+	 * SLB cache as full so we force a full flush. We also set cr7+eq to
+	 * mark the address as a kernel address, so slb_finish_load() skips
+	 * trying to insert it into the SLB cache.
+	 */
+	li	r9,SLB_CACHE_ENTRIES + 1
+	sth	r9,PACASLBCACHEPTR(r13)
+	crset	4*cr7+eq
 	li	r10,0			/* BAD_VSID */
 	li	r9,0			/* BAD_VSID */
 	li	r11,SLB_VSID_USER	/* flags don't much matter */
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 0f432a702870..6ad12b244770 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
 	if ((mm->task_size - len) < addr)
 		return 0;
 	vma = find_vma(mm, addr);
-	return (!vma || (addr + len) <= vma->vm_start);
+	return (!vma || (addr + len) <= vm_start_gap(vma));
 }
 
 static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 2ba602591a20..92736851c795 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -956,6 +956,11 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 		}
 
 		bus = eeh_pe_bus_get(pe);
+		if (!bus) {
+			pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+			       __func__, pe->phb->global_number, pe->addr);
+			return -EIO;
+		}
 		if (pci_is_root_bus(bus) ||
 			pci_is_root_bus(bus->parent))
 			ret = pnv_eeh_root_reset(hose, option);
@@ -1163,7 +1168,7 @@ static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose)
 		return;
 	}
 
-	switch (data->type) {
+	switch (be16_to_cpu(data->type)) {
 	case OPAL_P7IOC_DIAG_TYPE_RGC:
 		pr_info("P7IOC diag-data for RGC\n\n");
 		pnv_eeh_dump_hub_diag_common(data);
@@ -1395,7 +1400,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 
 				/* Try best to clear it */
 				opal_pci_eeh_freeze_clear(phb->opal_id,
-					frozen_pe_no,
+					be64_to_cpu(frozen_pe_no),
 					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
 				ret = EEH_NEXT_ERR_NONE;
 			} else if ((*pe)->state & EEH_PE_ISOLATED ||
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 2ee96431f736..4c827826c05e 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data)
 	uint32_t dump_id, dump_size, dump_type;
 	struct dump_obj *dump;
 	char name[22];
+	struct kobject *kobj;
 
 	rc = dump_read_info(&dump_id, &dump_size, &dump_type);
 	if (rc != OPAL_SUCCESS)
@@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(dump_kset, name))
+	kobj = kset_find_obj(dump_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return 0;
+	}
 
 	dump = create_dump_obj(dump_id, dump_size, dump_type);
 	if (!dump)
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 37f959bf392e..f2344cbd2f46 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data)
 	uint64_t elog_type;
 	int rc;
 	char name[2+16+1];
+	struct kobject *kobj;
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
@@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data)
 	 * that gracefully and not create two conflicting
 	 * entries.
 	 */
-	if (kset_find_obj(elog_kset, name))
+	kobj = kset_find_obj(elog_kset, name);
+	if (kobj) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(kobj);
 		return IRQ_HANDLED;
+	}
 
 	create_elog_obj(log_id, elog_size, elog_type);
 
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e45b88a5d7e0..ae877c7b3905 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -148,7 +148,7 @@ opal_tracepoint_entry:
 opal_tracepoint_return:
 	std	r3,STK_REG(R31)(r1)
 	mr	r4,r3
-	ld	r0,STK_REG(R23)(r1)
+	ld	r3,STK_REG(R23)(r1)
 	bl	__trace_opal_exit
 	ld	r3,STK_REG(R31)(r1)
 	addi	r1,r1,STACKFRAMESIZE
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index ad8c3f4a5e0b..dd5e0f3b1b5d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -197,8 +197,8 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
 			be64_to_cpu(data->dma1ErrorLog1));
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
+		if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 &&
+		    (be64_to_cpu(data->pestB[i]) >> 63) == 0)
 			continue;
 
 		pr_info("PE[%3d] A/B: %016llx %016llx\n",
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index f244dcb4f2cf..96536c969c9c 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -280,7 +280,6 @@ int dlpar_detach_node(struct device_node *dn)
 	if (rc)
 		return rc;
 
-	of_node_put(dn); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e059..405baaf96864 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;
 
 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;
 
-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
-	}
+	while (max_wait > 0) {
+		/* Use new configure-pe function, if supported */
+		if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else {
+			return -EFAULT;
+		}
 
-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
+	}
 
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index e9ff44cd5d86..e8b1027e1b5b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -110,6 +110,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}
 
@@ -553,6 +554,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index bd98ce2be17b..3e8865b187de 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -912,7 +912,8 @@ machine_arch_initcall(pseries, find_existing_ddw_windows);
 static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 			struct ddw_query_response *query)
 {
-	struct eeh_dev *edev;
+	struct device_node *dn;
+	struct pci_dn *pdn;
 	u32 cfg_addr;
 	u64 buid;
 	int ret;
@@ -923,11 +924,10 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	 * Retrieve them from the pci device, not the node with the
 	 * dma-window property
 	 */
-	edev = pci_dev_to_eeh_dev(dev);
-	cfg_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		cfg_addr = edev->pe_config_addr;
-	buid = edev->phb->buid;
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
 	ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
 		  cfg_addr, BUID_HI(buid), BUID_LO(buid));
@@ -941,7 +941,8 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 			struct ddw_create_response *create, int page_shift,
 			int window_shift)
 {
-	struct eeh_dev *edev;
+	struct device_node *dn;
+	struct pci_dn *pdn;
 	u32 cfg_addr;
 	u64 buid;
 	int ret;
@@ -952,11 +953,10 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	 * Retrieve them from the pci device, not the node with the
 	 * dma-window property
 	 */
-	edev = pci_dev_to_eeh_dev(dev);
-	cfg_addr = edev->config_addr;
-	if (edev->pe_config_addr)
-		cfg_addr = edev->pe_config_addr;
-	buid = edev->phb->buid;
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index b7a67e3d2201..3ae43282460e 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -406,7 +406,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
 					     unsigned long *vpn, int count,
 					     int psize, int ssize)
 {
-	unsigned long param[8];
+	unsigned long param[PLPAR_HCALL9_BUFSIZE];
 	int i = 0, pix = 0, rc;
 	unsigned long flags = 0;
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -523,7 +523,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 	unsigned long flags = 0;
 	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-	unsigned long param[9];
+	unsigned long param[PLPAR_HCALL9_BUFSIZE];
 	unsigned long hash, index, shift, hidx, slot;
 	real_pte_t pte;
 	int psize, ssize;
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 7c7fcc042549..fb695f142563 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -82,7 +82,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 
 	of_detach_node(np);
 	of_node_put(parent);
-	of_node_put(np); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 4da604ebf6fd..ca15613eaaa4 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -141,31 +141,34 @@ static void check_ipl_parmblock(void *start, unsigned long size)
 
 unsigned long decompress_kernel(void)
 {
-	unsigned long output_addr;
-	unsigned char *output;
+	void *output, *kernel_end;
 
-	output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
-	check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
-	memset(&_bss, 0, &_ebss - &_bss);
-	free_mem_ptr = (unsigned long)&_end;
-	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
-	output = (unsigned char *) output_addr;
+	output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE);
+	kernel_end = output + SZ__bss_start;
+	check_ipl_parmblock((void *) 0, (unsigned long) kernel_end);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/*
 	 * Move the initrd right behind the end of the decompressed
-	 * kernel image.
+	 * kernel image. This also prevents initrd corruption caused by
+	 * bss clearing since kernel_end will always be located behind the
+	 * current bss section..
 	 */
-	if (INITRD_START && INITRD_SIZE &&
-	    INITRD_START < (unsigned long) output + SZ__bss_start) {
-		check_ipl_parmblock(output + SZ__bss_start,
-				    INITRD_START + INITRD_SIZE);
-		memmove(output + SZ__bss_start,
-			(void *) INITRD_START, INITRD_SIZE);
-		INITRD_START = (unsigned long) output + SZ__bss_start;
+	if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
+		check_ipl_parmblock(kernel_end, INITRD_SIZE);
+		memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
+		INITRD_START = (unsigned long) kernel_end;
 	}
 #endif
 
+	/*
+	 * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
+	 * initialized afterwards since they reside in bss.
+	 */
+	memset(&_bss, 0, &_ebss - &_bss);
+	free_mem_ptr = (unsigned long) &_end;
+	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
 	puts("Uncompressing Linux... ");
 	__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
 	puts("Ok, booting the kernel.\n");
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index b8045b97f4fb..683a966b5b16 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -565,8 +565,10 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf,
 		prng_data->prngws.byte_counter += n;
 		prng_data->prngws.reseed_counter += n;
 
-		if (copy_to_user(ubuf, prng_data->buf, chunk))
-			return -EFAULT;
+		if (copy_to_user(ubuf, prng_data->buf, chunk)) {
+			ret = -EFAULT;
+			break;
+		}
 
 		nbytes -= chunk;
 		ret += chunk;
@@ -669,11 +671,13 @@ static const struct file_operations prng_tdes_fops = {
 static struct miscdevice prng_sha512_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_sha512_fops,
 };
 static struct miscdevice prng_tdes_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_tdes_fops,
 };
 
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 045035796ca7..b63b9a42af70 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -525,11 +525,11 @@ static int diag224(void *ptr)
 static int diag224_get_name_table(void)
 {
 	/* memory must be below 2GB */
-	diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+	diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA);
 	if (!diag224_cpu_names)
 		return -ENOMEM;
 	if (diag224(diag224_cpu_names)) {
-		kfree(diag224_cpu_names);
+		free_page((unsigned long) diag224_cpu_names);
 		return -EOPNOTSUPP;
 	}
 	EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
@@ -538,7 +538,7 @@ static int diag224_get_name_table(void)
 
 static void diag224_delete_name_table(void)
 {
-	kfree(diag224_cpu_names);
+	free_page((unsigned long) diag224_cpu_names);
 }
 
 static int diag224_idx2name(int index, char *name)
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab802f6..8e136b88cdf4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }
 
 #define __ctl_store(array, low, high) {					\
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bab6739a1154..b9eb7b1a49d2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -154,14 +154,13 @@ extern unsigned int vdso_enabled;
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk. 64-bit
-   tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_32bit_task() ? \
-				(STACK_TOP / 3 * 2) : \
-				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_compat_task() ? 0x000400000UL : \
+						    0x100000000UL)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 5e04f3cbd320..8ae236b0f80b 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc)
 		"	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "=d" (rc), "=d" (orig_fpc)
+		: "=d" (rc), "=&d" (orig_fpc)
 		: "d" (fpc), "0" (-EINVAL));
 	return rc;
 }
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index d29ad9545b41..081b2ad99d73 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -11,7 +11,7 @@ typedef struct {
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
 	struct list_head gmap_list;
-	unsigned long asce_bits;
+	unsigned long asce;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
 	/* The mmu context allocates 4K page tables. */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index e485817f7b1a..22877c9440ea 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 #endif
-	if (mm->context.asce_limit == 0) {
+	switch (mm->context.asce_limit) {
+	case 1UL << 42:
+		/*
+		 * forked 3-level task, fall through to set new asce with new
+		 * mm->pgd
+		 */
+	case 0:
 		/* context created by exec, set asce limit to 4TB */
-		mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-			_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
 		mm->context.asce_limit = STACK_TOP_MAX;
-	} else if (mm->context.asce_limit == (1UL << 31)) {
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+		break;
+	case 1UL << 53:
+		/* forked 4-level task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+		break;
+	case 1UL << 31:
+		/* forked 2-level compat task, set new asce with new mm->pgd */
+		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+		/* pgd_alloc() did not increase mm->nr_pmds */
 		mm_inc_nr_pmds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
@@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 static inline void set_user_asce(struct mm_struct *mm)
 {
-	S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+	S390_lowcore.user_asce = mm->context.asce;
 	if (current->thread.mm_segment.ar4)
 		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	set_cpu_flag(CIF_ASCE);
@@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
+	S390_lowcore.user_asce = next->context.asce;
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index c873e682b67f..6dafabb6ae1a 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -45,7 +45,8 @@ struct zpci_fmb {
 	u64 rpcit_ops;
 	u64 dma_rbytes;
 	u64 dma_wbytes;
-} __packed __aligned(16);
+	u64 pad[2];
+} __packed __aligned(128);
 
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 1aac41e83ea1..92df3eb8d14e 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -23,6 +23,8 @@ enum zpci_ioat_dtype {
 #define ZPCI_IOTA_FS_2G			2
 #define ZPCI_KEY			(PAGE_DEFAULT_KEY << 5)
 
+#define ZPCI_TABLE_SIZE_RT	(1UL << 42)
+
 #define ZPCI_IOTA_STO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
 #define ZPCI_IOTA_RTTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
 #define ZPCI_IOTA_RSTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index d7cc79fb6191..5991cdcb5b40 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -56,8 +56,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 	return _REGION2_ENTRY_EMPTY;
 }
 
-int crst_table_upgrade(struct mm_struct *, unsigned long limit);
-void crst_table_downgrade(struct mm_struct *, unsigned long limit);
+int crst_table_upgrade(struct mm_struct *);
+void crst_table_downgrade(struct mm_struct *);
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 024f85f947ae..e2c0e4eab037 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -829,6 +829,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 
+	if (pte_present(entry))
+		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index b16c3d0a1b9f..c61ed7890cef 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -74,7 +74,8 @@ extern void execve_tail(void);
  * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
  */
 
-#define TASK_SIZE_OF(tsk)	((tsk)->mm->context.asce_limit)
+#define TASK_SIZE_OF(tsk)	((tsk)->mm ? \
+				 (tsk)->mm->context.asce_limit : TASK_MAX_SIZE)
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
 					(1UL << 30) : (1UL << 41))
 #define TASK_SIZE		TASK_SIZE_OF(current)
@@ -163,7 +164,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS];
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_BA;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
 	regs->gprs[15]	= new_stackp;					\
-	crst_table_downgrade(current->mm, 1UL << 31);			\
+	crst_table_downgrade(current->mm);				\
 	execve_tail();							\
 } while (0)
 
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 6ba0bf928909..6bc941be6921 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -64,6 +64,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
 {
 	unsigned long mask = -1UL;
 
+	/*
+	 * No arguments for this syscall, there's nothing to do.
+	 */
+	if (!n)
+		return;
+
 	BUG_ON(i + n > 6);
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_31BIT))
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index ca148f7c3eaa..0a2031618f7f 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -81,7 +81,8 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
 }
 
 /*
- * Flush TLB entries for a specific ASCE on all CPUs.
+ * Flush TLB entries for a specific ASCE on all CPUs. Should never be used
+ * when more than one asce (e.g. gmap) ran on this mm.
  */
 static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 {
@@ -110,8 +111,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_idte((unsigned long) init_mm.pgd |
-				 init_mm.context.asce_bits);
+		__tlb_flush_idte(init_mm.context.asce);
 	else
 		__tlb_flush_global();
 }
@@ -133,8 +133,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 static inline void __tlb_flush_kernel(void)
 {
 	if (MACHINE_HAS_TLB_LC)
-		__tlb_flush_idte_local((unsigned long) init_mm.pgd |
-				       init_mm.context.asce_bits);
+		__tlb_flush_idte_local(init_mm.context.asce);
 	else
 		__tlb_flush_local();
 }
@@ -148,8 +147,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * only ran on the local cpu.
 	 */
 	if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
-		__tlb_flush_asce(mm, (unsigned long) mm->pgd |
-				 mm->context.asce_bits);
+		__tlb_flush_asce(mm, mm->context.asce);
 	else
 		__tlb_flush_full(mm);
 }
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 9dd4cc47ddc7..c8d837f0fbbc 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -150,7 +150,7 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
 		"	jg	2b\n"				\
 		".popsection\n"					\
 		EX_TABLE(0b,3b) EX_TABLE(1b,3b)			\
-		: "=d" (__rc), "=Q" (*(to))			\
+		: "=d" (__rc), "+Q" (*(to))			\
 		: "d" (size), "Q" (*(from)),			\
 		  "d" (__reg0), "K" (-EFAULT)			\
 		: "cc");					\
@@ -215,28 +215,28 @@ int __put_user_bad(void) __attribute__((noreturn));
 	__chk_user_ptr(ptr);					\
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
-		unsigned char __x;				\
+		unsigned char __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
-		unsigned short __x;				\
+		unsigned short __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
-		unsigned int __x;				\
+		unsigned int __x = 0;				\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
-		unsigned long long __x;				\
+		unsigned long long __x = 0;			\
 		__gu_err = __get_user_fn(&__x, ptr,		\
 					 sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 171e09bb8ea2..df4685905015 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -23,6 +23,8 @@
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
 #define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y))))
 
+#define LINUX_NOTE_NAME "LINUX"
+
 static struct memblock_region oldmem_region;
 
 static struct memblock_type oldmem_type = {
@@ -312,7 +314,7 @@ static void *nt_fpregset(void *ptr, struct save_area *sa)
 static void *nt_s390_timer(void *ptr, struct save_area *sa)
 {
 	return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer),
-			 KEXEC_CORE_NOTE_NAME);
+			 LINUX_NOTE_NAME);
 }
 
 /*
@@ -321,7 +323,7 @@ static void *nt_s390_timer(void *ptr, struct save_area *sa)
 static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa)
 {
 	return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp,
-		       sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME);
+		       sizeof(sa->clk_cmp), LINUX_NOTE_NAME);
 }
 
 /*
@@ -330,7 +332,7 @@ static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa)
 static void *nt_s390_tod_preg(void *ptr, struct save_area *sa)
 {
 	return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg,
-		       sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME);
+		       sizeof(sa->tod_reg), LINUX_NOTE_NAME);
 }
 
 /*
@@ -339,7 +341,7 @@ static void *nt_s390_tod_preg(void *ptr, struct save_area *sa)
 static void *nt_s390_ctrs(void *ptr, struct save_area *sa)
 {
 	return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs,
-		       sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME);
+		       sizeof(sa->ctrl_regs), LINUX_NOTE_NAME);
 }
 
 /*
@@ -348,7 +350,7 @@ static void *nt_s390_ctrs(void *ptr, struct save_area *sa)
 static void *nt_s390_prefix(void *ptr, struct save_area *sa)
 {
 	return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg,
-			 sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME);
+			 sizeof(sa->pref_reg), LINUX_NOTE_NAME);
 }
 
 /*
@@ -357,7 +359,7 @@ static void *nt_s390_prefix(void *ptr, struct save_area *sa)
 static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs)
 {
 	return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16],
-		       16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME);
+		       16 * sizeof(__vector128), LINUX_NOTE_NAME);
 }
 
 /*
@@ -370,12 +372,12 @@ static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
 	int i;
 
 	note = (Elf64_Nhdr *)ptr;
-	note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1;
+	note->n_namesz = strlen(LINUX_NOTE_NAME) + 1;
 	note->n_descsz = 16 * 8;
 	note->n_type = NT_S390_VXRS_LOW;
 	len = sizeof(Elf64_Nhdr);
 
-	memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz);
+	memcpy(ptr + len, LINUX_NOTE_NAME, note->n_namesz);
 	len = roundup(len + note->n_namesz, 4);
 
 	ptr += len;
@@ -462,6 +464,20 @@ static void *nt_vmcoreinfo(void *ptr)
 }
 
 /*
+ * Initialize final note (needed for /proc/vmcore code)
+ */
+static void *nt_final(void *ptr)
+{
+	Elf64_Nhdr *note;
+
+	note = (Elf64_Nhdr *) ptr;
+	note->n_namesz = 0;
+	note->n_descsz = 0;
+	note->n_type = 0;
+	return PTR_ADD(ptr, sizeof(Elf64_Nhdr));
+}
+
+/*
  * Initialize ELF header (new kernel)
  */
 static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
@@ -551,6 +567,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 		ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs);
 	}
 	ptr = nt_vmcoreinfo(ptr);
+	ptr = nt_final(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = notes_offset;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 857b6526d298..4612ed7ec2e5 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -229,12 +229,17 @@ ENTRY(sie64a)
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 .Lsie_done:
 # some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
+# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
+# Other instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
 # See also .Lcleanup_sie
-.Lrewind_pad:
-	nop	0
+.Lrewind_pad6:
+	nopr	7
+.Lrewind_pad4:
+	nopr	7
+.Lrewind_pad2:
+	nopr	7
 	.globl sie_exit
 sie_exit:
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
@@ -247,7 +252,9 @@ sie_exit:
 	stg	%r14,__SF_EMPTY+16(%r15)	# set exit reason code
 	j	sie_exit
 
-	EX_TABLE(.Lrewind_pad,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad6,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad4,.Lsie_fault)
+	EX_TABLE(.Lrewind_pad2,.Lsie_fault)
 	EX_TABLE(sie_exit,.Lsie_fault)
 #endif
 
@@ -308,6 +315,7 @@ ENTRY(system_call)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -593,6 +601,7 @@ ENTRY(io_int_handler)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -1118,15 +1127,23 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_sysc_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_sysc_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
@@ -1134,15 +1151,20 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_io_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_io_restore_insn)
-	je	0f
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_io_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_io_restore_insn:
+	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:
@@ -1197,114 +1219,12 @@ cleanup_critical:
 	.quad	.Lpsw_idle_lpsw
 
 .Lcleanup_save_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bor	%r14
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_done)
-	jhe	5f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_fp)
-	jhe	4f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_low)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_save_fpu_fpc_end)
-	jhe	1f
-	lg	%r2,__LC_CURRENT
-	aghi	%r2,__TASK_thread
-0:	# Store floating-point controls
-	stfpc	__THREAD_FPU_fpc(%r2)
-1:	# Load register save area and check if VX is active
-	lg	%r3,__THREAD_FPU_regs(%r2)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	jz	4f			  # no VX -> store FP regs
-2:	# Store vector registers (V0-V15)
-	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
-3:	# Store vector registers (V16-V31)
-	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
-	j	5f			  # -> done, set CIF_FPU flag
-4:	# Store floating-point registers
-	std	0,0(%r3)
-	std	1,8(%r3)
-	std	2,16(%r3)
-	std	3,24(%r3)
-	std	4,32(%r3)
-	std	5,40(%r3)
-	std	6,48(%r3)
-	std	7,56(%r3)
-	std	8,64(%r3)
-	std	9,72(%r3)
-	std	10,80(%r3)
-	std	11,88(%r3)
-	std	12,96(%r3)
-	std	13,104(%r3)
-	std	14,112(%r3)
-	std	15,120(%r3)
-5:	# Set CIF_FPU flag
-	oi	__LC_CPU_FLAGS+7,_CIF_FPU
-	lg	%r9,48(%r11)		# return from save_fpu_regs
+	larl	%r9,save_fpu_regs
 	br	%r14
-.Lcleanup_save_fpu_fpc_end:
-	.quad	.Lsave_fpu_regs_fpc_end
-.Lcleanup_save_fpu_regs_vx_low:
-	.quad	.Lsave_fpu_regs_vx_low
-.Lcleanup_save_fpu_regs_vx_high:
-	.quad	.Lsave_fpu_regs_vx_high
-.Lcleanup_save_fpu_regs_fp:
-	.quad	.Lsave_fpu_regs_fp
-.Lcleanup_save_fpu_regs_done:
-	.quad	.Lsave_fpu_regs_done
 
 .Lcleanup_load_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bnor	%r14
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_done)
-	jhe	1f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_fp)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx)
-	jhe	4f
-	lg	%r4,__LC_CURRENT
-	aghi	%r4,__TASK_thread
-	lfpc	__THREAD_FPU_fpc(%r4)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
-	jz	2f				# -> no VX, load FP regs
-4:	# Load V0 ..V15 registers
-	VLM	%v0,%v15,0,%r4
-3:	# Load V16..V31 registers
-	VLM	%v16,%v31,256,%r4
-	j	1f
-2:	# Load floating-point registers
-	ld	0,0(%r4)
-	ld	1,8(%r4)
-	ld	2,16(%r4)
-	ld	3,24(%r4)
-	ld	4,32(%r4)
-	ld	5,40(%r4)
-	ld	6,48(%r4)
-	ld	7,56(%r4)
-	ld	8,64(%r4)
-	ld	9,72(%r4)
-	ld	10,80(%r4)
-	ld	11,88(%r4)
-	ld	12,96(%r4)
-	ld	13,104(%r4)
-	ld	14,112(%r4)
-	ld	15,120(%r4)
-1:	# Clear CIF_FPU bit
-	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
-	lg	%r9,48(%r11)		# return from load_fpu_regs
+	larl	%r9,load_fpu_regs
 	br	%r14
-.Lcleanup_load_fpu_regs_vx:
-	.quad	.Lload_fpu_regs_vx
-.Lcleanup_load_fpu_regs_vx_high:
-	.quad	.Lload_fpu_regs_vx_high
-.Lcleanup_load_fpu_regs_fp:
-	.quad	.Lload_fpu_regs_fp
-.Lcleanup_load_fpu_regs_done:
-	.quad	.Lload_fpu_regs_done
 
 /*
  * Integer constants
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 58b719fa8067..1ad2407c7f75 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
 
 __HEAD
 ENTRY(startup_continue)
-	tm	__LC_STFL_FAC_LIST+6,0x80	# LPP available ?
+	tm	__LC_STFL_FAC_LIST+5,0x80	# LPP available ?
 	jz	0f
 	xc	__LC_LPP+1(7,0),__LC_LPP+1	# clear lpp and current_pid
 	mvi	__LC_LPP,0x80			#   and set LPP_MAGIC
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b1f0a90f933b..42570d8fb265 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2070,13 +2070,6 @@ void s390_reset_system(void (*fn_pre)(void),
 	S390_lowcore.program_new_psw.addr =
 		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
 
-	/*
-	 * Clear subchannel ID and number to signal new kernel that no CCW or
-	 * SCSI IPL has been done (for kexec and kdump)
-	 */
-	S390_lowcore.subchannel_id = 0;
-	S390_lowcore.subchannel_nr = 0;
-
 	/* Store status at absolute zero */
 	store_status();
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 01c37b36caf9..02bd587b610b 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+	else
+		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
 	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	for (i = 0; i < __NUM_VXRS_LOW; i++)
+		vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
 	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c837bcacf218..d097d71685df 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -329,6 +329,7 @@ static void __init setup_lowcore(void)
 		+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->current_task = (unsigned long) init_thread_union.thread_info.task;
 	lc->thread_info = (unsigned long) &init_thread_union;
+	lc->lpp = LPP_MAGIC;
 	lc->machine_flags = S390_lowcore.machine_flags;
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
@@ -804,10 +805,10 @@ static void __init setup_randomness(void)
 {
 	struct sysinfo_3_2_2 *vmms;
 
-	vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL);
-	if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count)
-		add_device_randomness(&vmms, vmms->count);
-	free_page((unsigned long) vmms);
+	vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
+		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
+	memblock_free((unsigned long) vmms, PAGE_SIZE);
 }
 
 /*
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 575dc123bda2..23e3f5d77a24 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -295,6 +295,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return -EINVAL;
+
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index c722400c7697..feff9caf89b5 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -89,7 +89,8 @@ void __init paging_init(void)
 		asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
 		pgd_type = _REGION3_ENTRY_EMPTY;
 	}
-	S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	S390_lowcore.kernel_asce = init_mm.context.asce;
 	clear_table((unsigned long *) init_mm.pgd, pgd_type,
 		    sizeof(unsigned long)*2048);
 	vmem_map_init();
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index ea01477b4aa6..126c4a9b9bf9 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -97,7 +97,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -135,7 +135,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
 	if (!(flags & MAP_FIXED))
 		addr = 0;
 	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm, 1UL << 53);
+		return crst_table_upgrade(current->mm);
 	return 0;
 }
 
@@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 		return area;
 	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area_topdown(filp, addr, len,
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 54ef3bc01b43..05ae254f84cf 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -49,81 +49,52 @@ static void __crst_table_upgrade(void *arg)
 	__tlb_flush_local();
 }
 
-int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+int crst_table_upgrade(struct mm_struct *mm)
 {
 	unsigned long *table, *pgd;
-	unsigned long entry;
-	int flush;
 
-	BUG_ON(limit > (1UL << 53));
-	flush = 0;
-repeat:
+	/* upgrade should only happen from 3 to 4 levels */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	table = crst_table_alloc(mm);
 	if (!table)
 		return -ENOMEM;
+
 	spin_lock_bh(&mm->page_table_lock);
-	if (mm->context.asce_limit < limit) {
-		pgd = (unsigned long *) mm->pgd;
-		if (mm->context.asce_limit <= (1UL << 31)) {
-			entry = _REGION3_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-		} else {
-			entry = _REGION2_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 53;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION2;
-		}
-		crst_table_init(table, entry);
-		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
-		mm->pgd = (pgd_t *) table;
-		mm->task_size = mm->context.asce_limit;
-		table = NULL;
-		flush = 1;
-	}
+	pgd = (unsigned long *) mm->pgd;
+	crst_table_init(table, _REGION2_ENTRY_EMPTY);
+	pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+	mm->pgd = (pgd_t *) table;
+	mm->context.asce_limit = 1UL << 53;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+	mm->task_size = mm->context.asce_limit;
 	spin_unlock_bh(&mm->page_table_lock);
-	if (table)
-		crst_table_free(mm, table);
-	if (mm->context.asce_limit < limit)
-		goto repeat;
-	if (flush)
-		on_each_cpu(__crst_table_upgrade, mm, 0);
+
+	on_each_cpu(__crst_table_upgrade, mm, 0);
 	return 0;
 }
 
-void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+void crst_table_downgrade(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 
+	/* downgrade should only happen from 3 to 2 levels (compat only) */
+	BUG_ON(mm->context.asce_limit != (1UL << 42));
+
 	if (current->active_mm == mm) {
 		clear_user_asce();
 		__tlb_flush_mm(mm);
 	}
-	while (mm->context.asce_limit > limit) {
-		pgd = mm->pgd;
-		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
-		case _REGION_ENTRY_TYPE_R2:
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-			break;
-		case _REGION_ENTRY_TYPE_R3:
-			mm->context.asce_limit = 1UL << 31;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_SEGMENT;
-			break;
-		default:
-			BUG();
-		}
-		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
-		mm->task_size = mm->context.asce_limit;
-		crst_table_free(mm, (unsigned long *) pgd);
-	}
+
+	pgd = mm->pgd;
+	mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+	mm->context.asce_limit = 1UL << 31;
+	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+			   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
+	mm->task_size = mm->context.asce_limit;
+	crst_table_free(mm, (unsigned long *) pgd);
+
 	if (current->active_mm == mm)
 		set_user_asce(mm);
 }
@@ -195,7 +166,7 @@ EXPORT_SYMBOL_GPL(gmap_alloc);
 static void gmap_flush_tlb(struct gmap *gmap)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 }
@@ -234,7 +205,7 @@ void gmap_free(struct gmap *gmap)
 
 	/* Flush tlb. */
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 
@@ -1266,11 +1237,28 @@ EXPORT_SYMBOL_GPL(s390_reset_cmma);
  */
 bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)
 {
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
 	pte_t *pte;
 	spinlock_t *ptl;
 	bool dirty = false;
 
-	pte = get_locked_pte(gmap->mm, address, &ptl);
+	pgd = pgd_offset(gmap->mm, address);
+	pud = pud_alloc(gmap->mm, pgd, address);
+	if (!pud)
+		return false;
+	pmd = pmd_alloc(gmap->mm, pud, address);
+	if (!pmd)
+		return false;
+	/* We can't run guests backed by huge pages, but userspace can
+	 * still set them up and then try to migrate them without any
+	 * migration support.
+	 */
+	if (pmd_large(*pmd))
+		return true;
+
+	pte = pte_alloc_map_lock(gmap->mm, pmd, address, &ptl);
 	if (unlikely(!pte))
 		return false;
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index ef7d6c8fea66..f354fd84adeb 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -372,7 +372,7 @@ void __init vmem_map_init(void)
 	ro_end = (unsigned long)&_eshared & PAGE_MASK;
 	for_each_memblock(memory, reg) {
 		start = reg->base;
-		end = reg->base + reg->size - 1;
+		end = reg->base + reg->size;
 		if (start >= ro_end || end <= ro_start)
 			vmem_add_mem(start, end - start, 0);
 		else if (start >= ro_start && end <= ro_end)
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f010c93a88b1..fda605dbc1b4 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |		      |     |
  *	      +---------------+     |
  *	      | 8 byte skbp   |     |
- * R15+170 -> +---------------+     |
+ * R15+176 -> +---------------+     |
  *	      | 8 byte hlen   |     |
  * R15+168 -> +---------------+     |
  *	      | 4 byte align  |     |
@@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 #define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	170	/* Offset of SKB pointer on stack */
+#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9a0c4c22e536..1395eeb6005f 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	0x7ffff	/* Max size for program (20 bit signed displ) */
+#define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
 #define SEEN_SKB	1	/* skb access */
 #define SEEN_MEM	2	/* use mem[] for temporary storage */
@@ -446,7 +446,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
 		emit_load_skb_data_hlen(jit);
 	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
+		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
 	/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
 	if (is_classic) {
@@ -1250,7 +1250,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
 			return -1;
-		jit->addrs[i + 1] = jit->prg; /* Next instruction address */
+		/* Next instruction address */
+		jit->addrs[i + insn_count] = jit->prg;
 	}
 	bpf_jit_epilogue(jit);
 
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 7ef12a3ace3a..f2f6720a3331 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev)
 		goto out;
 
 	zpci_map_resources(pdev);
-	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
-			   zdev->start_dma + zdev->iommu_size - 1,
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 			   (u64) zdev->dma_table);
 
 out:
@@ -871,8 +870,11 @@ static inline int barsize(u8 size)
 
 static int zpci_mem_init(void)
 {
+	BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
+		     __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb));
+
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
-				16, 0, NULL);
+					   __alignof__(struct zpci_fmb), 0, NULL);
 	if (!zdev_fmb_cache)
 		goto error_zdev;
 
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c09a1e..4004e03267cd 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -455,29 +455,42 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 	zdev->dma_table = dma_alloc_cpu_table();
 	if (!zdev->dma_table) {
 		rc = -ENOMEM;
-		goto out_clean;
+		goto out;
 	}
 
-	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	/*
+	 * Restrict the iommu bitmap size to the minimum of the following:
+	 * - main memory size
+	 * - 3-level pagetable address limit minus start_dma offset
+	 * - DMA address range allowed by the hardware (clp query pci fn)
+	 *
+	 * Also set zdev->end_dma to the actual end address of the usable
+	 * range, instead of the theoretical maximum as reported by hardware.
+	 */
+	zdev->iommu_size = min3((u64) high_memory,
+				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+				zdev->end_dma - zdev->start_dma + 1);
+	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
 		rc = -ENOMEM;
-		goto out_reg;
+		goto free_dma_table;
 	}
 
-	rc = zpci_register_ioat(zdev,
-				0,
-				zdev->start_dma + PAGE_OFFSET,
-				zdev->start_dma + zdev->iommu_size - 1,
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
-		goto out_reg;
-	return 0;
+		goto free_bitmap;
 
-out_reg:
+	return 0;
+free_bitmap:
+	vfree(zdev->iommu_bitmap);
+	zdev->iommu_bitmap = NULL;
+free_dma_table:
 	dma_free_cpu_table(zdev->dma_table);
-out_clean:
+	zdev->dma_table = NULL;
+out:
 	return rc;
 }
 
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index 20a3591225cc..01aec8ccde83 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -163,7 +163,7 @@ do {									\
 		__get_user_asm(val, "lw", ptr);				\
 		 break;							\
 	case 8: 							\
-		if ((copy_from_user((void *)&val, ptr, 8)) == 0)	\
+		if (__copy_from_user((void *)&val, ptr, 8) == 0)	\
 			__gu_err = 0;					\
 		else							\
 			__gu_err = -EFAULT;				\
@@ -188,6 +188,8 @@ do {									\
 									\
 	if (likely(access_ok(VERIFY_READ, __gu_ptr, size)))		\
 		__get_user_common((x), size, __gu_ptr);			\
+	else								\
+		(x) = 0;						\
 									\
 	__gu_err;							\
 })
@@ -201,6 +203,7 @@ do {									\
 		"2:\n"							\
 		".section .fixup,\"ax\"\n"				\
 		"3:li	%0, %4\n"					\
+		"li	%1, 0\n"					\
 		"j	2b\n"						\
 		".previous\n"						\
 		".section __ex_table,\"a\"\n"				\
@@ -298,35 +301,34 @@ extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
+	unsigned long res = len;
 
-	if (access_ok(VERIFY_READ, from, len))
-		return __copy_tofrom_user(to, from, len);
+	if (likely(access_ok(VERIFY_READ, from, len)))
+		res = __copy_tofrom_user(to, from, len);
 
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
-	return len;
+	if (unlikely(res))
+		memset(to + (len - res), 0, res);
+
+	return res;
 }
 
 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, len))
-		return __copy_tofrom_user(to, from, len);
+	if (likely(access_ok(VERIFY_WRITE, to, len)))
+		len = __copy_tofrom_user(to, from, len);
 
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
 	return len;
 }
 
-#define __copy_from_user(to, from, len)	\
-		__copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+	unsigned long left = __copy_tofrom_user(to, from, len);
+	if (unlikely(left))
+		memset(to + (len - left), 0, left);
+	return left;
+}
 
 #define __copy_to_user(to, from, len)		\
 		__copy_tofrom_user((to), (from), (len))
@@ -340,17 +342,17 @@ __copy_to_user_inatomic(void *to, const void *from, unsigned long len)
 static inline unsigned long
 __copy_from_user_inatomic(void *to, const void *from, unsigned long len)
 {
-	return __copy_from_user(to, from, len);
+	return __copy_tofrom_user(to, from, len);
 }
 
-#define __copy_in_user(to, from, len)	__copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len)	__copy_tofrom_user(to, from, len)
 
 static inline unsigned long
 copy_in_user(void *to, const void *from, unsigned long len)
 {
 	if (access_ok(VERIFY_READ, from, len) &&
 		      access_ok(VERFITY_WRITE, to, len))
-		return copy_from_user(to, from, len);
+		return __copy_tofrom_user(to, from, len);
 }
 
 /*
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index a49635c51266..92ade79ac427 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -151,7 +151,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 	__kernel_size_t __copy_size = (__kernel_size_t) n;
 
 	if (__copy_size && __access_ok(__copy_from, __copy_size))
-		return __copy_user(to, from, __copy_size);
+		__copy_size = __copy_user(to, from, __copy_size);
+
+	if (unlikely(__copy_size))
+		memset(to + (n - __copy_size), 0, __copy_size);
 
 	return __copy_size;
 }
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
index c01376c76b86..ca5073dd4596 100644
--- a/arch/sh/include/asm/uaccess_64.h
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -24,6 +24,7 @@
 #define __get_user_size(x,ptr,size,retval)			\
 do {								\
 	retval = 0;						\
+	x = 0;							\
 	switch (size) {						\
 	case 1:							\
 		retval = __get_user_asm_b((void *)&x,		\
diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c
index ec29e14ec5a8..bf25d7c79a2d 100644
--- a/arch/sh/mm/kmap.c
+++ b/arch/sh/mm/kmap.c
@@ -36,6 +36,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	BUG_ON(!test_bit(PG_dcache_clean, &page->flags));
 
+	preempt_disable();
 	pagefault_disable();
 
 	idx = FIX_CMAP_END -
@@ -64,4 +65,5 @@ void kunmap_coherent(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
index 6777177807c2..7df7d5944188 100644
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 56442d2d7bbc..eb9487470141 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -182,9 +182,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64
 
 source kernel/Kconfig.hz
 
diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dabc4c41..f0700cfeedd7 100644
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
 
 #define	PTREGS_OFF	(STACK_BIAS + STACKFRAME_SZ)
 
+#define	RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define	RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
 #define __CHEETAH_ID	0x003e0014
 #define __JALAPENO_ID	0x003e0016
 #define __SERRANO_ID	0x003e0022
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index 70067ce184b1..83b36a5371ff 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)
 
-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
@@ -92,7 +92,8 @@ struct tsb_config {
 typedef struct {
 	spinlock_t		lock;
 	unsigned long		sparc64_ctx_val;
-	unsigned long		huge_pte_count;
+	unsigned long		hugetlb_pte_count;
+	unsigned long		thp_pte_count;
 	struct tsb_config	tsb_block[MM_NUM_TSBS];
 	struct hv_tsb_descr	tsb_descr[MM_NUM_TSBS];
 } mm_context_t;
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be675e507..0cdeb2b483a0 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,22 +17,19 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
 void __tsb_context_switch(unsigned long pgd_pa,
 			  struct tsb_config *tsb_base,
 			  struct tsb_config *tsb_huge,
-			  unsigned long tsb_descr_pa);
+			  unsigned long tsb_descr_pa,
+			  unsigned long secondary_ctx);
 
-static inline void tsb_context_switch(struct mm_struct *mm)
+static inline void tsb_context_switch_ctx(struct mm_struct *mm,
+					  unsigned long ctx)
 {
 	__tsb_context_switch(__pa(mm->pgd),
 			     &mm->context.tsb_block[0],
@@ -43,9 +40,12 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[0]));
+			     , __pa(&mm->context.tsb_descr[0]),
+			     ctx);
 }
 
+#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0)
+
 void tsb_grow(struct mm_struct *mm,
 	      unsigned long tsb_index,
 	      unsigned long mm_rss);
@@ -74,8 +74,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;
 
@@ -114,14 +115,12 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * cpu0 to update it's TSB because at that point the cpu_vm_mask
 	 * only had cpu1 set in it.
 	 */
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 
 	/* Any time a processor runs a context on an address space
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -131,26 +130,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_MMU_CONTEXT_H) */
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 91b963a887b7..29c3b400f949 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -91,9 +91,9 @@ extern unsigned long pfn_base;
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 /*
  * In general all page table modifications should use the V8 atomic
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 131d36fcd07a..9d81579f3d54 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 #define pgprot_noncached pgprot_noncached
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline pte_t pte_mkhuge(pte_t pte)
+static inline unsigned long __pte_huge_mask(void)
 {
 	unsigned long mask;
 
@@ -390,8 +390,19 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	: "=r" (mask)
 	: "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V));
 
-	return __pte(pte_val(pte) | mask);
+	return mask;
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | __pte_huge_mask());
 }
+
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return !!(pte_val(pte) & __pte_huge_mask());
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@@ -403,6 +414,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 #endif
+#else
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return false;
+}
 #endif
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -652,26 +668,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return pte_pfn(pte);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_dirty(pte);
+	return pte_write(pte);
 }
 
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_dirty(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
@@ -865,6 +882,19 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);
 
+static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+				pte_t *ptep, pte_t orig, int fullmm)
+{
+	/* It is more efficient to let flush_tlb_kernel_range()
+	 * handle init_mm tlb flushes.
+	 *
+	 * 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(mm, orig))
+		tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+}
+
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr,
@@ -881,15 +911,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t orig = *ptep;
 
 	*ptep = pte;
-
-	/* It is more efficient to let flush_tlb_kernel_range()
-	 * handle init_mm tlb flushes.
-	 *
-	 * 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(mm, orig))
-		tlb_batch_add(mm, addr, ptep, orig, fullmm);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
 #define set_pte_at(mm,addr,ptep,pte)	\
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index 266937030546..522b43db2ed3 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 29d64b1758ed..be0cc1beed41 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -16,7 +16,7 @@ extern char reboot_command[];
  */
 extern unsigned char boot_cpu_id;
 
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 extern int serial_console;
 static inline int con_is_present(void)
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index dea1cfa2122b..a8e192e90700 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -8,6 +8,7 @@
 #define TLB_BATCH_NR	192
 
 struct tlb_batch {
+	bool huge;
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
 	unsigned long active;
@@ -16,7 +17,7 @@ struct tlb_batch {
 
 void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
 
 /* TLB flush operations. */
 
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ec9c04de3664..ff05992dae7a 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS];
 void init_cur_cpu_trap(struct thread_info *);
 void setup_tba(void);
 extern int ncpus_probed;
+extern u64 cpu_mondo_counter[NR_CPUS];
 
 unsigned long real_hard_smp_processor_id(void);
 
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 71b5a67522ab..781b9f1dbdc2 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop; nop;			\
 	nop; nop; nop; nop; nop;			\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
@@ -652,8 +652,8 @@ user_rtt_fill_32bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
 	nop; nop; nop;					\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 64ee103dc29d..dfb542c7cc71 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -328,8 +328,10 @@ static inline unsigned long copy_from_user(void *to, const void __user *from, un
 {
 	if (n && __access_ok((unsigned long) from, n))
 		return __copy_user((__force void __user *) to, from, n);
-	else
+	else {
+		memset(to, 0, n);
 		return n;
+	}
 }
 
 static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index ea6e9a20f3ff..f428512481f9 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -98,7 +98,6 @@ struct exception_table_entry {
         unsigned int insn, fixup;
 };
 
-void __ret_efault(void);
 void __retl_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
@@ -179,20 +178,6 @@ int __put_user_bad(void);
 	 __gu_ret;							     \
 })
 
-#define __get_user_nocheck_ret(data, addr, size, type, retval) ({	\
-	register unsigned long __gu_val __asm__ ("l1");			\
-	switch (size) {							\
-	case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break;	\
-	case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break;	\
-	case 4: __get_user_asm_ret(__gu_val, uw, addr, retval); break;	\
-	case 8: __get_user_asm_ret(__gu_val, x, addr, retval); break;	\
-	default:							\
-		if (__get_user_bad())					\
-			return retval;					\
-	}								\
-	data = (__force type) __gu_val;					\
-})
-
 #define __get_user_asm(x, size, addr, ret)				\
 __asm__ __volatile__(							\
 		"/* Get user asm, inline. */\n"				\
@@ -214,80 +199,35 @@ __asm__ __volatile__(							\
 	       : "=r" (ret), "=r" (x) : "r" (__m(addr)),		\
 		 "i" (-EFAULT))
 
-#define __get_user_asm_ret(x, size, addr, retval)			\
-if (__builtin_constant_p(retval) && retval == -EFAULT)			\
-	__asm__ __volatile__(						\
-		"/* Get user asm ret, inline. */\n"			\
-	"1:\t"	"ld"#size "a [%1] %%asi, %0\n\n\t"			\
-		".section __ex_table,\"a\"\n\t"				\
-		".align	4\n\t"						\
-		".word	1b,__ret_efault\n\n\t"				\
-		".previous\n\t"						\
-	       : "=r" (x) : "r" (__m(addr)));				\
-else									\
-	__asm__ __volatile__(						\
-		"/* Get user asm ret, inline. */\n"			\
-	"1:\t"	"ld"#size "a [%1] %%asi, %0\n\n\t"			\
-		".section .fixup,#alloc,#execinstr\n\t"			\
-		".align	4\n"						\
-	"3:\n\t"							\
-		"ret\n\t"						\
-		" restore %%g0, %2, %%o0\n\n\t"				\
-		".previous\n\t"						\
-		".section __ex_table,\"a\"\n\t"				\
-		".align	4\n\t"						\
-		".word	1b, 3b\n\n\t"					\
-		".previous\n\t"						\
-	       : "=r" (x) : "r" (__m(addr)), "i" (retval))
-
 int __get_user_bad(void);
 
 unsigned long __must_check ___copy_from_user(void *to,
 					     const void __user *from,
 					     unsigned long size);
-unsigned long copy_from_user_fixup(void *to, const void __user *from,
-				   unsigned long size);
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long ret = ___copy_from_user(to, from, size);
-
-	if (unlikely(ret))
-		ret = copy_from_user_fixup(to, from, size);
-
-	return ret;
+	return ___copy_from_user(to, from, size);
 }
 #define __copy_from_user copy_from_user
 
 unsigned long __must_check ___copy_to_user(void __user *to,
 					   const void *from,
 					   unsigned long size);
-unsigned long copy_to_user_fixup(void __user *to, const void *from,
-				 unsigned long size);
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long size)
 {
-	unsigned long ret = ___copy_to_user(to, from, size);
-
-	if (unlikely(ret))
-		ret = copy_to_user_fixup(to, from, size);
-	return ret;
+	return ___copy_to_user(to, from, size);
 }
 #define __copy_to_user copy_to_user
 
 unsigned long __must_check ___copy_in_user(void __user *to,
 					   const void __user *from,
 					   unsigned long size);
-unsigned long copy_in_user_fixup(void __user *to, void __user *from,
-				 unsigned long size);
 static inline unsigned long __must_check
 copy_in_user(void __user *to, void __user *from, unsigned long size)
 {
-	unsigned long ret = ___copy_in_user(to, from, size);
-
-	if (unlikely(ret))
-		ret = copy_in_user_fixup(to, from, size);
-	return ret;
+	return ___copy_in_user(to, from, size);
 }
 #define __copy_in_user copy_in_user
 
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 8174f6cdbbbb..9dca7a892978 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;
 
 	u64			dev_no;
+	u64			id;
 
 	unsigned long		channel_id;
 
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 7cf9c6ea3f1f..fdb13327fded 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
 CFLAGS_REMOVE_pcr.o := -pg
 endif
 
+obj-$(CONFIG_SPARC64)   += urtt_fill.o
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S
index 4ee1ad420862..655628def68e 100644
--- a/arch/sparc/kernel/cherrs.S
+++ b/arch/sparc/kernel/cherrs.S
@@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1		! Next cacheline
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_dcpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -224,8 +223,7 @@ do_dcpe_tl1_fatal:
 	mov		0x2, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_dcpe_tl1,.-do_dcpe_tl1
 
 	.globl		do_icpe_tl1
@@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_icpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -269,8 +266,7 @@ do_icpe_tl1_fatal:
 	mov		0x3, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_icpe_tl1,.-do_icpe_tl1
 	
 	.type		dcpe_icpe_tl1_common,#function
@@ -456,7 +452,7 @@ __cheetah_log_error:
 	 cmp		%g2, 0x63
 	be		c_cee
 	 nop
-	ba,pt		%xcc, c_deferred
+	ba,a,pt		%xcc, c_deferred
 	.size		__cheetah_log_error,.-__cheetah_log_error
 
 	/* Cheetah FECC trap handling, we get here from tl{0,1}_fecc
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index d668ca149e64..4087a62f96b0 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -25,13 +25,13 @@
 
 /* PROT ** ICACHE line 2: More real fault processing */
 	ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
+	srlx		%g5, PAGE_SHIFT, %g5
+	sllx		%g5, PAGE_SHIFT, %g5		! Clear context ID bits
 	bgu,pn		%xcc, winfix_trampoline		! Yes, perform winfixup
 	 mov		FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
 	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
 	 nop
 	nop
-	nop
-	nop
 
 /* PROT ** ICACHE line 3: Unused...	*/
 	nop
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 33c02b15f478..a83707c83be8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
 	cmp	%o0, 0
 	bne	3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ld	[%sp + STACKFRAME_SZ + PT_G1], %g1
+	sethi	%hi(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I0], %i0
+	or	%l7, %lo(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I1], %i1
+	ld	[%sp + STACKFRAME_SZ + PT_I2], %i2
+	ld	[%sp + STACKFRAME_SZ + PT_I3], %i3
+	ld	[%sp + STACKFRAME_SZ + PT_I4], %i4
+	ld	[%sp + STACKFRAME_SZ + PT_I5], %i5
+	cmp	%g1, NR_syscalls
+	bgeu	3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	ld	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S
index a6864826a4bd..336d2750fe78 100644
--- a/arch/sparc/kernel/fpu_traps.S
+++ b/arch/sparc/kernel/fpu_traps.S
@@ -100,8 +100,8 @@ do_fpdis:
 	fmuld		%f0, %f2, %f26
 	faddd		%f0, %f2, %f28
 	fmuld		%f0, %f2, %f30
-	b,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 2:	andcc		%g5, FPRS_DU, %g0
 	bne,pt		%icc, 3f
 	 fzero		%f32
@@ -144,8 +144,8 @@ do_fpdis:
 	fmuld		%f32, %f34, %f58
 	faddd		%f32, %f34, %f60
 	fmuld		%f32, %f34, %f62
-	ba,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 3:	mov		SECONDARY_CONTEXT, %g3
 	add		%g6, TI_FPREGS, %g1
 
@@ -197,8 +197,7 @@ fpdis_exit2:
 fp_other_bounce:
 	call		do_fpother
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		fp_other_bounce,.-fp_other_bounce
 
 	.align		32
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index f2d30cab5b3f..7eeeb1d5a410 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -461,9 +461,8 @@ sun4v_chip_type:
 	subcc	%g3, 1, %g3
 	bne,pt	%xcc, 41b
 	add	%g1, 1, %g1
-	mov	SUN4V_CHIP_SPARC64X, %g4
 	ba,pt	%xcc, 5f
-	nop
+	 mov	SUN4V_CHIP_SPARC64X, %g4
 
 49:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
@@ -548,8 +547,7 @@ sun4u_init:
 	stxa		%g0, [%g7] ASI_DMMU
 	membar	#Sync
 
-	ba,pt		%xcc, sun4u_continue
-	 nop
+	ba,a,pt		%xcc, sun4u_continue
 
 sun4v_init:
 	/* Set ctx 0 */
@@ -560,14 +558,12 @@ sun4v_init:
 	mov		SECONDARY_CONTEXT, %g7
 	stxa		%g0, [%g7] ASI_MMU
 	membar		#Sync
-	ba,pt		%xcc, niagara_tlb_fixup
-	 nop
+	ba,a,pt		%xcc, niagara_tlb_fixup
 
 sun4u_continue:
 	BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup)
 
-	ba,pt	%xcc, spitfire_tlb_fixup
-	 nop
+	ba,a,pt	%xcc, spitfire_tlb_fixup
 
 niagara_tlb_fixup:
 	mov	3, %g2		/* Set TLB type to hypervisor. */
@@ -639,8 +635,7 @@ niagara_patch:
 	call	hypervisor_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 cheetah_tlb_fixup:
 	mov	2, %g2		/* Set TLB type to cheetah+. */
@@ -659,8 +654,7 @@ cheetah_tlb_fixup:
 	call	cheetah_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 spitfire_tlb_fixup:
 	/* Set TLB type to spitfire. */
@@ -782,8 +776,7 @@ setup_trap_table:
 	call	%o1
 	 add	%sp, (2047 + 128), %o0
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 1:	sethi	%hi(sparc64_ttable_tl0), %o0
 	set	prom_set_trap_table_name, %g2
@@ -822,8 +815,7 @@ setup_trap_table:
 
 	BRANCH_IF_ANY_CHEETAH(o2, o3, 1f)
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 	/* Disable STICK_INT interrupts. */
 1:
@@ -930,47 +922,11 @@ prom_tba:	.xword	0
 tlb_type:	.word	0	/* Must NOT end up in BSS */
 	.section	".fixup",#alloc,#execinstr
 
-	.globl	__ret_efault, __retl_efault, __ret_one, __retl_one
-ENTRY(__ret_efault)
-	ret
-	 restore %g0, -EFAULT, %o0
-ENDPROC(__ret_efault)
-
 ENTRY(__retl_efault)
 	retl
 	 mov	-EFAULT, %o0
 ENDPROC(__retl_efault)
 
-ENTRY(__retl_one)
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one)
-
-ENTRY(__retl_one_fp)
-	VISExitHalf
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_fp)
-
-ENTRY(__ret_one_asi)
-	wr	%g0, ASI_AIUS, %asi
-	ret
-	 restore %g0, 1, %o0
-ENDPROC(__ret_one_asi)
-
-ENTRY(__retl_one_asi)
-	wr	%g0, ASI_AIUS, %asi
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_asi)
-
-ENTRY(__retl_one_asi_fp)
-	wr	%g0, ASI_AIUS, %asi
-	VISExitHalf
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_asi_fp)
-
 ENTRY(__retl_o1)
 	retl
 	 mov	%o1, %o0
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e22416ce56ea..bfbde8c4ffb2 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;
 
-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);
 
 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}
 
-	tb->cpu_mondo_block_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
+	tb->cpu_list_pa = __pa(page);
 #endif
 }
 
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 59bbeff55024..07933b9e9ce0 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -13,19 +13,30 @@
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	u32 val;
 	u32 *insn = (u32 *) (unsigned long) entry->code;
+	u32 val;
 
 	if (type == JUMP_LABEL_JMP) {
 		s32 off = (s32)entry->target - (s32)entry->code;
+		bool use_v9_branch = false;
+
+		BUG_ON(off & 3);
 
 #ifdef CONFIG_SPARC64
-		/* ba,pt %xcc, . + (off << 2) */
-		val = 0x10680000 | ((u32) off >> 2);
-#else
-		/* ba . + (off << 2) */
-		val = 0x10800000 | ((u32) off >> 2);
+		if (off <= 0xfffff && off >= -0x100000)
+			use_v9_branch = true;
 #endif
+		if (use_v9_branch) {
+			/* WDISP19 - target is . + immed << 2 */
+			/* ba,pt %xcc, . + off */
+			val = 0x10680000 | (((u32) off >> 2) & 0x7ffff);
+		} else {
+			/* WDISP22 - target is . + immed << 2 */
+			BUG_ON(off > 0x7fffff);
+			BUG_ON(off < -0x800000);
+			/* ba . + off */
+			val = 0x10800000 | (((u32) off >> 2) & 0x3fffff);
+		}
 	} else {
 		val = 0x01000000;
 	}
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index e7f652be9e61..44f32dd4477f 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
 
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index ef0d8e9e1210..f22bec0db645 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -20,6 +20,10 @@ kvmap_itlb:
 	mov		TLB_TAG_ACCESS, %g4
 	ldxa		[%g4] ASI_IMMU, %g4
 
+	/* The kernel executes in context zero, therefore we do not
+	 * need to clear the context ID bits out of %g4 here.
+	 */
+
 	/* sun4v_itlb_miss branches here with the missing virtual
 	 * address already loaded into %g4
 	 */
@@ -128,6 +132,10 @@ kvmap_dtlb:
 	mov		TLB_TAG_ACCESS, %g4
 	ldxa		[%g4] ASI_DMMU, %g4
 
+	/* The kernel executes in context zero, therefore we do not
+	 * need to clear the context ID bits out of %g4 here.
+	 */
+
 	/* sun4v_dtlb_miss branches here with the missing virtual
 	 * address already loaded into %g4
 	 */
@@ -251,6 +259,10 @@ kvmap_dtlb_longpath:
 	nop
 	.previous
 
+	/* The kernel executes in context zero, therefore we do not
+	 * need to clear the context ID bits out of %g5 here.
+	 */
+
 	be,pt	%xcc, sparc64_realfault_common
 	 mov	FAULT_CODE_DTLB, %g4
 	ba,pt	%xcc, winfix_trampoline
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 753b4f031bfb..34b4933900bf 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -18,8 +18,7 @@ __do_privact:
 109:	or		%g7, %lo(109b), %g7
 	call		do_privact
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__do_privact,.-__do_privact
 
 	.type		do_mna,#function
@@ -46,8 +45,7 @@ do_mna:
 	mov		%l5, %o2
 	call		mem_address_unaligned
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_mna,.-do_mna
 
 	.type		do_lddfmna,#function
@@ -65,8 +63,7 @@ do_lddfmna:
 	mov		%l5, %o2
 	call		handle_lddfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_lddfmna,.-do_lddfmna
 
 	.type		do_stdfmna,#function
@@ -84,8 +81,7 @@ do_stdfmna:
 	mov		%l5, %o2
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_stdfmna,.-do_stdfmna
 
 	.type		breakpoint_trap,#function
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index badf0951d73c..9f9614df9e1e 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev)
 	/* No special bus mastering setup handling */
 }
 
+#ifdef CONFIG_PCI_IOV
+int pcibios_add_device(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	/* Add sriov arch specific initialization here.
+	 * Copy dev_archdata from PF to VF
+	 */
+	if (dev->is_virtfn) {
+		pdev = dev->physfn;
+		memcpy(&dev->dev.archdata, &pdev->dev.archdata,
+		       sizeof(struct dev_archdata));
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int __init pcibios_init(void)
 {
 	pci_dfl_cache_line_size = 64 >> 2;
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 9ddc4928a089..c1566170964f 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -311,7 +311,7 @@ static int genregs64_set(struct task_struct *target,
 	}
 
 	if (!ret) {
-		unsigned long y;
+		unsigned long y = regs->y;
 
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					 &y,
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index d08bdaffdbfc..216948ca4382 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -14,10 +14,6 @@
 #include <asm/visasm.h>
 #include <asm/processor.h>
 
-#define		RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define		RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER schedule_user
 #else
@@ -242,52 +238,17 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit
 
-user_rtt_fill_fixup:
-		rdpr	%cwp, %g1
-		add	%g1, 1, %g1
-		wrpr	%g1, 0x0, %cwp
-
-		rdpr	%wstate, %g2
-		sll	%g2, 3, %g2
-		wrpr	%g2, 0x0, %wstate
-
-		/* We know %canrestore and %otherwin are both zero.  */
-
-		sethi	%hi(sparc64_kern_pri_context), %g2
-		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
-		mov	PRIMARY_CONTEXT, %g1
-
-661:		stxa	%g2, [%g1] ASI_DMMU
-		.section .sun4v_1insn_patch, "ax"
-		.word	661b
-		stxa	%g2, [%g1] ASI_MMU
-		.previous
-
-		sethi	%hi(KERNBASE), %g1
-		flush	%g1
+user_rtt_fill_fixup_dax:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	1, %g3
 
-		or	%g4, FAULT_CODE_WINFIXUP, %g4
-		stb	%g4, [%g6 + TI_FAULT_CODE]
-		stx	%g5, [%g6 + TI_FAULT_ADDR]
+user_rtt_fill_fixup_mna:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	2, %g3
 
-		mov	%g6, %l1
-		wrpr	%g0, 0x0, %tl
-
-661:		nop
-		.section		.sun4v_1insn_patch, "ax"
-		.word			661b
-		SET_GL(0)
-		.previous
-
-		wrpr	%g0, RTRAP_PSTATE, %pstate
-
-		mov	%l1, %g6
-		ldx	[%g6 + TI_TASK], %g4
-		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
-		call	do_sparc64_fault
-		 add	%sp, PTREGS_OFF, %o0
-		ba,pt	%xcc, rtrap
-		 nop
+user_rtt_fill_fixup:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 clr	%g3
 
 user_rtt_pre_restore:
 		add			%g1, 1, %g1
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 4eed773a7735..77655f0f0fc7 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return 0;
 }
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) ||
+	    ((unsigned long)fp) > 0x100000000ULL - fplen)
+		return true;
+	return false;
+}
+
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
-	unsigned int psr;
+	unsigned int psr, ufp;
 	unsigned pc, npc;
 	sigset_t set;
 	compat_sigset_t seta;
@@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
 	sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
-	if (get_user(pc, &sf->info.si_regs.pc) ||
+	if (__get_user(pc, &sf->info.si_regs.pc) ||
 	    __get_user(npc, &sf->info.si_regs.npc))
 		goto segv;
 
@@ -227,7 +244,7 @@ segv:
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
 	sigset_t set;
@@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
-	if (get_user(pc, &sf->regs.pc) || 
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
+		goto segv;
+
+	if (__get_user(pc, &sf->regs.pc) ||
 	    __get_user(npc, &sf->regs.npc))
 		goto segv;
 
@@ -307,14 +329,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
-		return 1;
-	return 0;
-}
-
 static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 52aa5e4ce5e7..9c0c8fd0b292 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -60,10 +60,22 @@ struct rt_signal_frame {
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+		return true;
+
+	return false;
+}
+
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
+	unsigned long up_psr, pc, npc, ufp;
 	struct signal_frame __user *sf;
-	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
@@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv_and_exit;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
 		goto segv_and_exit;
 
-	if (((unsigned long) sf) & 3)
+	if (ufp & 0x7)
 		goto segv_and_exit;
 
 	err = __get_user(pc,  &sf->info.si_regs.pc);
@@ -127,7 +142,7 @@ segv_and_exit:
 asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 0x03))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
 	err = __get_user(pc, &sf->regs.pc);
@@ -178,15 +198,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
-		return 1;
-
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP];
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d88beff47bab..5ee930c48f4c 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
 	unsigned char fenab;
 	int err;
 
-	flush_user_windows();
+	synchronize_user_stack();
 	if (get_thread_wsaved()					||
 	    (((unsigned long)ucp) & (sizeof(unsigned long)-1))	||
 	    (!__access_ok(ucp, sizeof(*ucp))))
@@ -234,6 +234,17 @@ do_sigsegv:
 	goto out;
 }
 
+/* Checks if the fp is valid.  We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+	if (((unsigned long) fp) & 15)
+		return true;
+	return false;
+}
+
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
 	siginfo_t		info;
@@ -246,8 +257,8 @@ struct rt_signal_frame {
 
 void do_rt_sigreturn(struct pt_regs *regs)
 {
+	unsigned long tpc, tnpc, tstate, ufp;
 	struct rt_signal_frame __user *sf;
-	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
 		(regs->u_regs [UREG_FP] + STACK_BIAS);
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (((unsigned long) sf) & 3)
+	if (invalid_frame_pointer(sf))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
 		goto segv;
 
-	err = get_user(tpc, &sf->regs.tpc);
+	if ((ufp + STACK_BIAS) & 0x7)
+		goto segv;
+
+	err = __get_user(tpc, &sf->regs.tpc);
 	err |= __get_user(tnpc, &sf->regs.tnpc);
 	if (test_thread_flag(TIF_32BIT)) {
 		tpc &= 0xffffffff;
@@ -308,14 +325,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
-	if (((unsigned long) fp) & 15)
-		return 1;
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
index 0f6eebe71e6c..e5fe8cef9a69 100644
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
 	int err;
+
+	if (((unsigned long) fpu) & 3)
+		return -EFAULT;
+
 #ifdef CONFIG_SMP
 	if (test_tsk_thread_flag(current, TIF_USEDFPU))
 		regs->psr &= ~PSR_EF;
@@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 3)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index 387834a9c56a..36aadcbeac69 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	unsigned long fprs;
 	int err;
 
-	err = __get_user(fprs, &fpu->si_fprs);
+	if (((unsigned long) fpu) & 7)
+		return -EFAULT;
+
+	err = get_user(fprs, &fpu->si_fprs);
 	fprs_write(0);
 	regs->tstate &= ~TSTATE_PEF;
 	if (fprs & FPRS_DL)
@@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 7)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 19cd08d18672..4511caa3b7e9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -617,22 +617,48 @@ retry:
 	}
 }
 
-/* Multi-cpu list version.  */
+#define	CPU_MONDO_COUNTER(cpuid)	(cpu_mondo_counter[cpuid])
+#define	MONDO_USEC_WAIT_MIN		2
+#define	MONDO_USEC_WAIT_MAX		100
+#define	MONDO_RETRY_LIMIT		500000
+
+/* Multi-cpu list version.
+ *
+ * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'.
+ * Sometimes not all cpus receive the mondo, requiring us to re-send
+ * the mondo until all cpus have received, or cpus are truly stuck
+ * unable to receive mondo, and we timeout.
+ * Occasionally a target cpu strand is borrowed briefly by hypervisor to
+ * perform guest service, such as PCIe error handling. Consider the
+ * service time, 1 second overall wait is reasonable for 1 cpu.
+ * Here two in-between mondo check wait time are defined: 2 usec for
+ * single cpu quick turn around and up to 100usec for large cpu count.
+ * Deliver mondo to large number of cpus could take longer, we adjusts
+ * the retry count as long as target cpus are making forward progress.
+ */
 static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 {
-	int retries, this_cpu, prev_sent, i, saw_cpu_error;
+	int this_cpu, tot_cpus, prev_sent, i, rem;
+	int usec_wait, retries, tot_retries;
+	u16 first_cpu = 0xffff;
+	unsigned long xc_rcvd = 0;
 	unsigned long status;
+	int ecpuerror_id = 0;
+	int enocpu_id = 0;
 	u16 *cpu_list;
+	u16 cpu;
 
 	this_cpu = smp_processor_id();
-
 	cpu_list = __va(tb->cpu_list_pa);
-
-	saw_cpu_error = 0;
-	retries = 0;
+	usec_wait = cnt * MONDO_USEC_WAIT_MIN;
+	if (usec_wait > MONDO_USEC_WAIT_MAX)
+		usec_wait = MONDO_USEC_WAIT_MAX;
+	retries = tot_retries = 0;
+	tot_cpus = cnt;
 	prev_sent = 0;
+
 	do {
-		int forward_progress, n_sent;
+		int n_sent, mondo_delivered, target_cpu_busy;
 
 		status = sun4v_cpu_mondo_send(cnt,
 					      tb->cpu_list_pa,
@@ -640,94 +666,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 
 		/* HV_EOK means all cpus received the xcall, we're done.  */
 		if (likely(status == HV_EOK))
-			break;
+			goto xcall_done;
+
+		/* If not these non-fatal errors, panic */
+		if (unlikely((status != HV_EWOULDBLOCK) &&
+			(status != HV_ECPUERROR) &&
+			(status != HV_ENOCPU)))
+			goto fatal_errors;
 
 		/* First, see if we made any forward progress.
 		 *
+		 * Go through the cpu_list, count the target cpus that have
+		 * received our mondo (n_sent), and those that did not (rem).
+		 * Re-pack cpu_list with the cpus remain to be retried in the
+		 * front - this simplifies tracking the truly stalled cpus.
+		 *
 		 * The hypervisor indicates successful sends by setting
 		 * cpu list entries to the value 0xffff.
+		 *
+		 * EWOULDBLOCK means some target cpus did not receive the
+		 * mondo and retry usually helps.
+		 *
+		 * ECPUERROR means at least one target cpu is in error state,
+		 * it's usually safe to skip the faulty cpu and retry.
+		 *
+		 * ENOCPU means one of the target cpu doesn't belong to the
+		 * domain, perhaps offlined which is unexpected, but not
+		 * fatal and it's okay to skip the offlined cpu.
 		 */
+		rem = 0;
 		n_sent = 0;
 		for (i = 0; i < cnt; i++) {
-			if (likely(cpu_list[i] == 0xffff))
+			cpu = cpu_list[i];
+			if (likely(cpu == 0xffff)) {
 				n_sent++;
+			} else if ((status == HV_ECPUERROR) &&
+				(sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) {
+				ecpuerror_id = cpu + 1;
+			} else if (status == HV_ENOCPU && !cpu_online(cpu)) {
+				enocpu_id = cpu + 1;
+			} else {
+				cpu_list[rem++] = cpu;
+			}
 		}
 
-		forward_progress = 0;
-		if (n_sent > prev_sent)
-			forward_progress = 1;
+		/* No cpu remained, we're done. */
+		if (rem == 0)
+			break;
 
-		prev_sent = n_sent;
+		/* Otherwise, update the cpu count for retry. */
+		cnt = rem;
 
-		/* If we get a HV_ECPUERROR, then one or more of the cpus
-		 * in the list are in error state.  Use the cpu_state()
-		 * hypervisor call to find out which cpus are in error state.
+		/* Record the overall number of mondos received by the
+		 * first of the remaining cpus.
 		 */
-		if (unlikely(status == HV_ECPUERROR)) {
-			for (i = 0; i < cnt; i++) {
-				long err;
-				u16 cpu;
+		if (first_cpu != cpu_list[0]) {
+			first_cpu = cpu_list[0];
+			xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
+		}
 
-				cpu = cpu_list[i];
-				if (cpu == 0xffff)
-					continue;
+		/* Was any mondo delivered successfully? */
+		mondo_delivered = (n_sent > prev_sent);
+		prev_sent = n_sent;
 
-				err = sun4v_cpu_state(cpu);
-				if (err == HV_CPU_STATE_ERROR) {
-					saw_cpu_error = (cpu + 1);
-					cpu_list[i] = 0xffff;
-				}
-			}
-		} else if (unlikely(status != HV_EWOULDBLOCK))
-			goto fatal_mondo_error;
+		/* or, was any target cpu busy processing other mondos? */
+		target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu));
+		xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
 
-		/* Don't bother rewriting the CPU list, just leave the
-		 * 0xffff and non-0xffff entries in there and the
-		 * hypervisor will do the right thing.
-		 *
-		 * Only advance timeout state if we didn't make any
-		 * forward progress.
+		/* Retry count is for no progress. If we're making progress,
+		 * reset the retry count.
 		 */
-		if (unlikely(!forward_progress)) {
-			if (unlikely(++retries > 10000))
-				goto fatal_mondo_timeout;
-
-			/* Delay a little bit to let other cpus catch up
-			 * on their cpu mondo queue work.
-			 */
-			udelay(2 * cnt);
+		if (likely(mondo_delivered || target_cpu_busy)) {
+			tot_retries += retries;
+			retries = 0;
+		} else if (unlikely(retries > MONDO_RETRY_LIMIT)) {
+			goto fatal_mondo_timeout;
 		}
-	} while (1);
 
-	if (unlikely(saw_cpu_error))
-		goto fatal_mondo_cpu_error;
+		/* Delay a little bit to let other cpus catch up on
+		 * their cpu mondo queue work.
+		 */
+		if (!mondo_delivered)
+			udelay(usec_wait);
 
-	return;
+		retries++;
+	} while (1);
 
-fatal_mondo_cpu_error:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus "
-	       "(including %d) were in error state\n",
-	       this_cpu, saw_cpu_error - 1);
+xcall_done:
+	if (unlikely(ecpuerror_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n",
+		       this_cpu, ecpuerror_id - 1);
+	} else if (unlikely(enocpu_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n",
+		       this_cpu, enocpu_id - 1);
+	}
 	return;
 
+fatal_errors:
+	/* fatal errors include bad alignment, etc */
+	pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n",
+	       this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
+	panic("Unexpected SUN4V mondo error %lu\n", status);
+
 fatal_mondo_timeout:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward "
-	       " progress after %d retries.\n",
-	       this_cpu, retries);
-	goto dump_cpu_list_and_out;
-
-fatal_mondo_error:
-	printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n",
-	       this_cpu, status);
-	printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) "
-	       "mondo_block_pa(%lx)\n",
-	       this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
-
-dump_cpu_list_and_out:
-	printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu);
-	for (i = 0; i < cnt; i++)
-		printk("%u ", cpu_list[i]);
-	printk("]\n");
+	/* some cpus being non-responsive to the cpu mondo */
+	pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n",
+	       this_cpu, first_cpu, (tot_retries + retries), tot_cpus);
+	panic("SUN4V mondo timeout panic\n");
 }
 
 static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
@@ -959,37 +1004,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }
 
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index a92d5d2c46a3..51b25325a961 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -27,7 +27,6 @@ EXPORT_SYMBOL(__flushw_user);
 EXPORT_SYMBOL_GPL(real_hard_smp_processor_id);
 
 /* from head_64.S */
-EXPORT_SYMBOL(__ret_efault);
 EXPORT_SYMBOL(tlb_type);
 EXPORT_SYMBOL(sun4v_chip_type);
 EXPORT_SYMBOL(prom_root_node);
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index c357e40ffd01..4a73009f66a5 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -85,8 +85,7 @@ __spitfire_cee_trap_continue:
 	ba,pt		%xcc, etraptl1
 	 rd		%pc, %g7
 
-	ba,pt		%xcc, 2f
-	 nop
+	ba,a,pt		%xcc, 2f
 
 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
@@ -100,8 +99,7 @@ __spitfire_cee_trap_continue:
 	mov		%l5, %o2
 	call		spitfire_access_error
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_access_error,.-__spitfire_access_error
 
 	/* This is the trap handler entry point for ECC correctable
@@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1
 
 	.type		__spitfire_data_access_exception,#function
@@ -200,8 +197,7 @@ __spitfire_data_access_exception:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception,.-__spitfire_data_access_exception
 
 	.type		__spitfire_insn_access_exception_tl1,#function
@@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1
 
 	.type		__spitfire_insn_access_exception,#function
@@ -240,6 +235,5 @@ __spitfire_insn_access_exception:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception,.-__spitfire_insn_access_exception
diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index 559bc5e9c199..34631995859a 100644
--- a/arch/sparc/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -26,6 +26,21 @@ sun4v_cpu_mondo:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g4
 	sub	%g4, TRAP_PER_CPU_FAULT_INFO, %g4
 
+	/* Get smp_processor_id() into %g3 */
+	sethi	%hi(trap_block), %g5
+	or	%g5, %lo(trap_block), %g5
+	sub	%g4, %g5, %g3
+	srlx	%g3, TRAP_BLOCK_SZ_SHIFT, %g3
+
+	/* Increment cpu_mondo_counter[smp_processor_id()] */
+	sethi	%hi(cpu_mondo_counter), %g5
+	or	%g5, %lo(cpu_mondo_counter), %g5
+	sllx	%g3, 3, %g3
+	add	%g5, %g3, %g5
+	ldx	[%g5], %g3
+	add	%g3, 1, %g3
+	stx	%g3, [%g5]
+
 	/* Get CPU mondo queue base phys address into %g7.  */
 	ldx	[%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7
 
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c690c8e16a96..7f0f7c01b297 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index bb0008927598..c4a1b5c40e4e 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	srl	%i0, 0, %o0
+	lduw	[%l7 + %l4], %l7
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	lduw	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index d21cd625c0de..d883c5951e8b 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -85,7 +85,7 @@ static void dump_tl1_traplog(struct tl1_traplog *p)
 
 void bad_trap(struct pt_regs *regs, long lvl)
 {
-	char buffer[32];
+	char buffer[36];
 	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "bad trap", regs,
@@ -116,7 +116,7 @@ void bad_trap(struct pt_regs *regs, long lvl)
 
 void bad_trap_tl1(struct pt_regs *regs, long lvl)
 {
-	char buffer[32];
+	char buffer[36];
 	
 	if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs,
 		       0, lvl, SIGTRAP) == NOTIFY_STOP)
@@ -2659,6 +2659,7 @@ void do_getpsr(struct pt_regs *regs)
 	}
 }
 
+u64 cpu_mondo_counter[NR_CPUS] = {0};
 struct trap_per_cpu trap_block[NR_CPUS];
 EXPORT_SYMBOL(trap_block);
 
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index be98685c14c6..7d961f6e3907 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -29,13 +29,17 @@
 	 */
 tsb_miss_dtlb:
 	mov		TLB_TAG_ACCESS, %g4
+	ldxa		[%g4] ASI_DMMU, %g4
+	srlx		%g4, PAGE_SHIFT, %g4
 	ba,pt		%xcc, tsb_miss_page_table_walk
-	 ldxa		[%g4] ASI_DMMU, %g4
+	 sllx		%g4, PAGE_SHIFT, %g4
 
 tsb_miss_itlb:
 	mov		TLB_TAG_ACCESS, %g4
+	ldxa		[%g4] ASI_IMMU, %g4
+	srlx		%g4, PAGE_SHIFT, %g4
 	ba,pt		%xcc, tsb_miss_page_table_walk
-	 ldxa		[%g4] ASI_IMMU, %g4
+	 sllx		%g4, PAGE_SHIFT, %g4
 
 	/* At this point we have:
 	 * %g1 --	PAGE_SIZE TSB entry address
@@ -284,6 +288,10 @@ tsb_do_dtlb_fault:
 	nop
 	.previous
 
+	/* Clear context ID bits.  */
+	srlx		%g5, PAGE_SHIFT, %g5
+	sllx		%g5, PAGE_SHIFT, %g5
+
 	be,pt	%xcc, sparc64_realfault_common
 	 mov	FAULT_CODE_DTLB, %g4
 	ba,pt	%xcc, winfix_trampoline
@@ -367,6 +375,7 @@ tsb_flush:
 	 * %o1:	TSB base config pointer
 	 * %o2:	TSB huge config pointer, or NULL if none
 	 * %o3:	Hypervisor TSB descriptor physical address
+	 * %o4: Secondary context to load, if non-zero
 	 *
 	 * We have to run this whole thing with interrupts
 	 * disabled so that the current cpu doesn't change
@@ -379,6 +388,17 @@ __tsb_context_switch:
 	rdpr	%pstate, %g1
 	wrpr	%g1, PSTATE_IE, %pstate
 
+	brz,pn	%o4, 1f
+	 mov	SECONDARY_CONTEXT, %o5
+
+661:	stxa	%o4, [%o5] ASI_DMMU
+	.section .sun4v_1insn_patch, "ax"
+	.word	661b
+	stxa	%o4, [%o5] ASI_MMU
+	.previous
+	flush	%g6
+
+1:
 	TRAP_LOAD_TRAP_BLOCK(%g2, %g3)
 
 	stx	%o0, [%g2 + TRAP_PER_CPU_PGD_PADDR]
@@ -462,13 +482,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */
 
+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -493,9 +516,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -503,7 +526,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */
 
 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop
 
diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S
index c6dfdaa29e20..170ead662f2a 100644
--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 000000000000..5604a2b051d4
--- /dev/null
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+		.text
+		.align	8
+		.globl	user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+		rdpr	%cwp, %g1
+		add	%g1, 1, %g1
+		wrpr	%g1, 0x0, %cwp
+
+		rdpr	%wstate, %g2
+		sll	%g2, 3, %g2
+		wrpr	%g2, 0x0, %wstate
+
+		/* We know %canrestore and %otherwin are both zero.  */
+
+		sethi	%hi(sparc64_kern_pri_context), %g2
+		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
+		mov	PRIMARY_CONTEXT, %g1
+
+661:		stxa	%g2, [%g1] ASI_DMMU
+		.section .sun4v_1insn_patch, "ax"
+		.word	661b
+		stxa	%g2, [%g1] ASI_MMU
+		.previous
+
+		sethi	%hi(KERNBASE), %g1
+		flush	%g1
+
+		mov	%g4, %l4
+		mov	%g5, %l5
+		brnz,pn	%g3, 1f
+		 mov	%g3, %l3
+
+		or	%g4, FAULT_CODE_WINFIXUP, %g4
+		stb	%g4, [%g6 + TI_FAULT_CODE]
+		stx	%g5, [%g6 + TI_FAULT_ADDR]
+1:
+		mov	%g6, %l1
+		wrpr	%g0, 0x0, %tl
+
+661:		nop
+		.section		.sun4v_1insn_patch, "ax"
+		.word			661b
+		SET_GL(0)
+		.previous
+
+		wrpr	%g0, RTRAP_PSTATE, %pstate
+
+		mov	%l1, %g6
+		ldx	[%g6 + TI_TASK], %g4
+		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+		brnz,pn	%l3, 1f
+		 nop
+
+		call	do_sparc64_fault
+		 add	%sp, PTREGS_OFF, %o0
+		ba,pt	%xcc, rtrap
+		 nop
+
+1:		cmp	%g3, 2
+		bne,pn	%xcc, 2f
+		 nop
+
+		sethi	%hi(tlb_type), %g1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		mov	%l4, %o2
+		call	sun4v_do_mna
+		 mov	%l5, %o1
+		ba,a,pt	%xcc, rtrap
+1:		mov	%l4, %o1
+		mov	%l5, %o2
+		call	mem_address_unaligned
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+2:		sethi	%hi(tlb_type), %g1
+		mov	%l4, %o1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		mov	%l5, %o2
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		call	sun4v_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+1:		call	spitfire_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S
index b7f0f3f3a909..c731e8023d3e 100644
--- a/arch/sparc/kernel/utrap.S
+++ b/arch/sparc/kernel/utrap.S
@@ -11,8 +11,7 @@ utrap_trap:		/* %g3=handler,%g4=level */
 	mov		%l4, %o1
         call		bad_trap
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 
 invoke_utrap:
 	sllx		%g3, 3, %g3
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index cb5789c9f961..34824ca396f0 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -284,13 +284,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}
 
 	vdev->dev.parent = parent;
@@ -333,27 +336,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }
 
+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);
 
-	if (vdev->mp == (u64) arg)
-		return 1;
+	if (vdev->dev_no != query->dev_no)
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;
 
-	return 0;
+	return 1;
 }
 
 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;
 
-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
 
 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }
 
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f1a2f688b28a..4a41d412dd3d 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -33,6 +33,10 @@ ENTRY(_start)
 jiffies = jiffies_64;
 #endif
 
+#ifdef CONFIG_SPARC64
+ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large")
+#endif
+
 SECTIONS
 {
 #ifdef CONFIG_SPARC64
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 1e67ce958369..855019a8590e 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -32,8 +32,7 @@ fill_fixup:
 	 rd	%pc, %g7
 	call	do_sparc64_fault
 	 add	%sp, PTREGS_OFF, %o0
-	ba,pt	%xcc, rtrap
-	 nop
+	ba,a,pt	%xcc, rtrap
 
 	/* Be very careful about usage of the trap globals here.
 	 * You cannot touch %g5 as that has the fault information.
diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S
index b7d0bd6b1406..69a439fa2fc1 100644
--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S
index 780550e1afc7..9947427ce354 100644
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S
index 89358ee94851..059ea24ad73d 100644
--- a/arch/sparc/lib/GENmemcpy.S
+++ b/arch/sparc/lib/GENmemcpy.S
@@ -4,21 +4,18 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #define GLOBAL_SPARE	%g7
 #else
 #define GLOBAL_SPARE	%g5
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -45,6 +42,29 @@
 	.register	%g3,#scratch
 
 	.text
+
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+ENTRY(GEN_retl_o4_1)
+	add	%o4, %o2, %o4
+	retl
+	 add	%o4, 1, %o0
+ENDPROC(GEN_retl_o4_1)
+ENTRY(GEN_retl_g1_8)
+	add	%g1, %o2, %g1
+	retl
+	 add	%g1, 8, %o0
+ENDPROC(GEN_retl_g1_8)
+ENTRY(GEN_retl_o2_4)
+	retl
+	 add	%o2, 4, %o0
+ENDPROC(GEN_retl_o2_4)
+ENTRY(GEN_retl_o2_1)
+	retl
+	 add	%o2, 1, %o0
+ENDPROC(GEN_retl_o2_1)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -73,8 +93,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%g0, %o4, %o4
 	sub		%o2, %o4, %o2
 1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1)
+	EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1)
 	add		%o1, 1, %o1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -82,8 +102,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	andn		%o2, 0x7, %g1
 	sub		%o2, %g1, %o2
 1:	subcc		%g1, 0x8, %g1
-	EX_LD(LOAD(ldx, %o1, %g2))
-	EX_ST(STORE(stx, %g2, %o0))
+	EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8)
+	EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8)
 	add		%o1, 0x8, %o1
 	bne,pt		%XCC, 1b
 	 add		%o0, 0x8, %o0
@@ -100,8 +120,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4)
+	EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -111,8 +131,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1)
+	EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 3269b0234093..4f2384a4286a 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -38,7 +38,7 @@ lib-$(CONFIG_SPARC64) +=  NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 
-lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
+lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o
 lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
 obj-$(CONFIG_SPARC64) += iomap.o
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index d5242b8c4f94..b79a6998d87c 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 4e962d993b10..dcec55f254ab 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index d5f585df2f3f..c629dbd121b6 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -32,21 +33,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -140,45 +137,110 @@
 	fsrc2		%x6, %f12; \
 	fsrc2		%x7, %f14;
 #define FREG_LOAD_1(base, x0) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1)
 #define FREG_LOAD_2(base, x0, x1) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_3(base, x0, x1, x2) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_4(base, x0, x1, x2, x3) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
-	EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1);
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_fp:
+	VISExitHalf
+__restore_asi:
+	retl
+	 wr	%g0, ASI_AIUS, %asi
+ENTRY(NG2_retl_o2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%o2, %o0
+ENDPROC(NG2_retl_o2)
+ENTRY(NG2_retl_o2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 1, %o0
+ENDPROC(NG2_retl_o2_plus_1)
+ENTRY(NG2_retl_o2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 4, %o0
+ENDPROC(NG2_retl_o2_plus_4)
+ENTRY(NG2_retl_o2_plus_8)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 8, %o0
+ENDPROC(NG2_retl_o2_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_1)
+	add	%o4, 1, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_1)
+ENTRY(NG2_retl_o2_plus_o4_plus_8)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_16)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_16)
+ENTRY(NG2_retl_o2_plus_g1_fp)
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_64_fp)
+	add	%g1, 64, %g1
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_1)
+ENTRY(NG2_retl_o2_and_7_plus_o4)
+	and	%o2, 7, %o2
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4)
+ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8)
+	and	%o2, 7, %o2
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -230,8 +292,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%g0, %o4, %o4	! bytes to align dst
 	sub		%o2, %o4, %o2
 1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1)
+	EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1)
 	add		%o1, 1, %o1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -281,11 +343,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	/* fall through for 0 < low bits < 8 */
 110:	sub		%o4, 64, %g2
-	EX_LD_FP(LOAD_BLK(%g2, %f0))
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+	EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1)
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -296,10 +358,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 120:	sub		%o4, 56, %g2
 	FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -310,10 +372,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 130:	sub		%o4, 48, %g2
 	FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -324,10 +386,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 140:	sub		%o4, 40, %g2
 	FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_5(f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -338,10 +400,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 150:	sub		%o4, 32, %g2
 	FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_4(f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -352,10 +414,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 160:	sub		%o4, 24, %g2
 	FREG_LOAD_3(%g2, f0, f2, f4)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_3(f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -366,10 +428,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 170:	sub		%o4, 16, %g2
 	FREG_LOAD_2(%g2, f0, f2)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_2(f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -380,10 +442,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 180:	sub		%o4, 8, %g2
 	FREG_LOAD_1(%g2, f0)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_1(f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -393,10 +455,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 
 190:
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	subcc		%g1, 64, %g1
-	EX_LD_FP(LOAD_BLK(%o4, %f0))
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64)
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64)
 	add		%o4, 64, %o4
 	bne,pt		%xcc, 1b
 	 LOAD(prefetch, %o4 + 64, #one_read)
@@ -423,28 +485,28 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	andn		%o2, 0xf, %o4
 	and		%o2, 0xf, %o2
 1:	subcc		%o4, 0x10, %o4
-	EX_LD(LOAD(ldx, %o1, %o5))
+	EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16)
 	add		%o1, 0x08, %o1
-	EX_LD(LOAD(ldx, %o1, %g1))
+	EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16)
 	sub		%o1, 0x08, %o1
-	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE))
+	EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x8, %o2
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8)
+	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4)
+	EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -460,8 +522,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%o2, %g1, %o2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %o1, %o5))
-	EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -477,16 +539,16 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 8:	mov		64, GLOBAL_SPARE
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2)
 	sub		GLOBAL_SPARE, %g1, GLOBAL_SPARE
 	andn		%o2, 0x7, %o4
 	sllx		%g2, %g1, %g2
 1:	add		%o1, 0x8, %o1
-	EX_LD(LOAD(ldx, %o1, %g3))
+	EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4)
 	subcc		%o4, 0x8, %o4
 	srlx		%g3, GLOBAL_SPARE, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -506,8 +568,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4)
+	EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -517,8 +579,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1)
+	EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index 2e8ee7ad07a9..16a286c1a528 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x, y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index be0bf4590df8..6b0276ffc858 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 8e13ee1f4454..75bb93b1437f 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -46,22 +47,19 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
-#endif
 
 #ifndef LOAD
 #define LOAD(type,addr,dest)	type [addr], dest
@@ -94,6 +92,158 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi_fp:
+	VISExitHalf
+__restore_asi:
+	retl
+	 wr	%g0, ASI_AIUS, %asi
+
+ENTRY(NG4_retl_o2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%o2, %o0
+ENDPROC(NG4_retl_o2)
+ENTRY(NG4_retl_o2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 1, %o0
+ENDPROC(NG4_retl_o2_plus_1)
+ENTRY(NG4_retl_o2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 4, %o0
+ENDPROC(NG4_retl_o2_plus_4)
+ENTRY(NG4_retl_o2_plus_o5)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5)
+ENTRY(NG4_retl_o2_plus_o5_plus_4)
+	add	%o5, 4, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_4)
+ENTRY(NG4_retl_o2_plus_o5_plus_8)
+	add	%o5, 8, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_8)
+ENTRY(NG4_retl_o2_plus_o5_plus_16)
+	add	%o5, 16, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_16)
+ENTRY(NG4_retl_o2_plus_o5_plus_24)
+	add	%o5, 24, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_24)
+ENTRY(NG4_retl_o2_plus_o5_plus_32)
+	add	%o5, 32, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_32)
+ENTRY(NG4_retl_o2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1)
+ENTRY(NG4_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_1)
+ENTRY(NG4_retl_o2_plus_g1_plus_8)
+	add	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_8)
+ENTRY(NG4_retl_o2_plus_o4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4)
+ENTRY(NG4_retl_o2_plus_o4_plus_8)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8)
+ENTRY(NG4_retl_o2_plus_o4_plus_16)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16)
+ENTRY(NG4_retl_o2_plus_o4_plus_24)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24)
+ENTRY(NG4_retl_o2_plus_o4_plus_32)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32)
+ENTRY(NG4_retl_o2_plus_o4_plus_40)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40)
+ENTRY(NG4_retl_o2_plus_o4_plus_48)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48)
+ENTRY(NG4_retl_o2_plus_o4_plus_56)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56)
+ENTRY(NG4_retl_o2_plus_o4_plus_64)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64)
+ENTRY(NG4_retl_o2_plus_o4_fp)
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_8_fp)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_16_fp)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_24_fp)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_32_fp)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_40_fp)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_48_fp)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_56_fp)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_64_fp)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp)
+#endif
 	.align		64
 
 	.globl	FUNC_NAME
@@ -124,12 +274,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	brz,pt		%g1, 51f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 
 51:	LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
 	LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
@@ -154,43 +305,43 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	brz,pt		%g1, .Llarge_aligned
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 8, %o1
 	subcc		%g1, 8, %g1
 	add		%o0, 8, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g2, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8)
 
 .Llarge_aligned:
 	/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4)
 	add		%o1, 0x40, %o1
-	EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
+	EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
-	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
-	EX_ST(STORE_INIT(%g1, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
-	EX_ST(STORE_INIT(%o5, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
@@ -216,17 +367,17 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%o2, %o4, %o2
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
-	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
-1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4)
+1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f2, %f4, %f18
 	add		%g1, 0x40, %g1
 	faligndata	%f4, %f6, %f20
@@ -235,14 +386,14 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
-	EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
-	EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
-	EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
-	EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
-	EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
-	EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
-	EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
+	EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56)
+	EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24)
+	EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16)
+	EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
@@ -270,37 +421,38 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	andncc		%o2, 0x20 - 1, %o5
 	be,pn		%icc, 2f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
-	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5)
 	add		%o1, 0x20, %o1
 	subcc		%o5, 0x20, %o5
-	EX_ST(STORE(stx, %g1, %o0 + 0x00))
-	EX_ST(STORE(stx, %g2, %o0 + 0x08))
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
-	EX_ST(STORE(stx, %o4, %o0 + 0x18))
+	EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32)
+	EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x20, %o0
 2:	andcc		%o2, 0x18, %o5
 	be,pt		%icc, 3f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	add		%o0, 0x08, %o0
 	subcc		%o5, 0x08, %o5
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g1, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8)
 3:	brz,pt		%o2, .Lexit
 	 cmp		%o2, 0x04
 	bl,pn		%icc, .Ltiny
 	 nop
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 0x04, %o1
 	add		%o0, 0x04, %o0
 	subcc		%o2, 0x04, %o2
 	bne,pn		%icc, .Ltiny
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4)
 	ba,a,pt		%icc, .Lexit
 .Lmedium_unaligned:
 	/* First get dest 8 byte aligned.  */
@@ -309,12 +461,12 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	brz,pt		%g1, 2f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 2:
 	and		%o1, 0x7, %g1
 	brz,pn		%g1, .Lmedium_noprefetch
@@ -322,16 +474,16 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	mov		64, %g2
 	sub		%g2, %g1, %g2
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
+	EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2)
 	sllx		%o4, %g1, %o4
 	andn		%o2, 0x08 - 1, %o5
 	sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	subcc		%o5, 0x08, %o5
 	srlx		%g3, %g2, GLOBAL_SPARE
 	or		GLOBAL_SPARE, %o4, GLOBAL_SPARE
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 sllx		%g3, %g1, %o4
@@ -342,17 +494,17 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	ba,pt		%icc, .Lsmall_unaligned
 
 .Ltiny:
-	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x00))
-	EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x01))
-	EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2)
 	ba,pt		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x02))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2)
 
 .Lsmall:
 	andcc		%g2, 0x3, %g0
@@ -360,22 +512,22 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 andn		%o2, 0x4 - 1, %o5
 	sub		%o2, %o5, %o2
 1:
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x04, %o1
 	subcc		%o5, 0x04, %o5
 	add		%o0, 0x04, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4)
 	brz,pt		%o2, .Lexit
 	 nop
 	ba,a,pt		%icc, .Ltiny
 
 .Lsmall_unaligned:
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 1, %o1
 	add		%o0, 1, %o0
 	subcc		%o2, 1, %o2
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g1, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
 	ba,a,pt		%icc, .Lexit
 	.size		FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S
index 5d1e4d1ac21e..9cd42fcbc781 100644
--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S
index ff630dcb273c..5c358afd464e 100644
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index 96a14caf6966..d88c4ed50a00 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/asi.h>
 #include <asm/thread_info.h>
 #define GLOBAL_SPARE	%g7
@@ -27,15 +28,11 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -79,6 +76,92 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi:
+	ret
+	wr	%g0, ASI_AIUS, %asi
+	 restore
+ENTRY(NG_ret_i2_plus_i4_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i5, %i0
+ENDPROC(NG_ret_i2_plus_i4_plus_1)
+ENTRY(NG_ret_i2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1)
+ENTRY(NG_ret_i2_plus_g1_minus_8)
+	sub	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_8)
+ENTRY(NG_ret_i2_plus_g1_minus_16)
+	sub	%g1, 16, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_16)
+ENTRY(NG_ret_i2_plus_g1_minus_24)
+	sub	%g1, 24, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_24)
+ENTRY(NG_ret_i2_plus_g1_minus_32)
+	sub	%g1, 32, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_32)
+ENTRY(NG_ret_i2_plus_g1_minus_40)
+	sub	%g1, 40, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_40)
+ENTRY(NG_ret_i2_plus_g1_minus_48)
+	sub	%g1, 48, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_48)
+ENTRY(NG_ret_i2_plus_g1_minus_56)
+	sub	%g1, 56, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_56)
+ENTRY(NG_ret_i2_plus_i4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_minus_8)
+	sub	%i4, 8, %i4
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENTRY(NG_ret_i2_plus_8)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 8, %i0
+ENDPROC(NG_ret_i2_plus_8)
+ENTRY(NG_ret_i2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 4, %i0
+ENDPROC(NG_ret_i2_plus_4)
+ENTRY(NG_ret_i2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 1, %i0
+ENDPROC(NG_ret_i2_plus_1)
+ENTRY(NG_ret_i2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_plus_1)
+ENTRY(NG_ret_i2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%i2, %i0
+ENDPROC(NG_ret_i2)
+ENTRY(NG_ret_i2_and_7_plus_i4)
+	and	%i2, 7, %i2
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -126,8 +209,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	sub		%g0, %i4, %i4	! bytes to align dst
 	sub		%i2, %i4, %i2
 1:	subcc		%i4, 1, %i4
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
+	EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
 	add		%i1, 1, %i1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -160,7 +243,7 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	and		%i4, 0x7, GLOBAL_SPARE
 	sll		GLOBAL_SPARE, 3, GLOBAL_SPARE
 	mov		64, %i5
-	EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
 	sub		%i5, GLOBAL_SPARE, %i5
 	mov		16, %o4
 	mov		32, %o5
@@ -178,31 +261,31 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	srlx		WORD3, PRE_SHIFT, TMP; \
 	or		WORD2, TMP, WORD2;
 
-8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x00))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x20))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 8b
@@ -211,31 +294,31 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	ba,pt		%XCC, 60f
 	 add		%i1, %i4, %i1
 
-9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x00))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 9b
@@ -249,25 +332,25 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	 * one twin load ahead, then add 8 back into source when
 	 * we finish the loop.
 	 */
-	EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+	EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
 	mov	16, %o7
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o5, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
-	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+	EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 1b
 	 add		%o0, 64, %o0
@@ -282,20 +365,20 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o4, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o5, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	add	%i1, 64, %i1
-	EX_ST(STORE_INIT(%o4, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x28))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc	%g1, 64, %g1
 	bne,pt	%XCC, 1b
 	 add	%o0, 64, %o0
@@ -321,28 +404,28 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	andn		%i2, 0xf, %i4
 	and		%i2, 0xf, %i2
 1:	subcc		%i4, 0x10, %i4
-	EX_LD(LOAD(ldx, %i1, %o4))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
 	add		%i1, 0x08, %i1
-	EX_LD(LOAD(ldx, %i1, %g1))
+	EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
 	sub		%i1, 0x08, %i1
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
 	add		%i1, 0x8, %i1
-	EX_ST(STORE(stx, %g1, %i1 + %i3))
+	EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 0x8, %i1
 73:	andcc		%i2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x8, %i2
-	EX_LD(LOAD(ldx, %i1, %o4))
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
 	add		%i1, 0x8, %i1
 1:	andcc		%i2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x4, %i2
-	EX_LD(LOAD(lduw, %i1, %i5))
-	EX_ST(STORE(stw, %i5, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
 	add		%i1, 0x4, %i1
 1:	cmp		%i2, 0
 	be,pt		%XCC, 85f
@@ -358,8 +441,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	sub		%i2, %g1, %i2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %i1, %i5))
-	EX_ST(STORE(stb, %i5, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%i1, 1, %i1
 
@@ -375,16 +458,16 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 
 8:	mov		64, %i3
 	andn		%i1, 0x7, %i1
-	EX_LD(LOAD(ldx, %i1, %g2))
+	EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
 	sub		%i3, %g1, %i3
 	andn		%i2, 0x7, %i4
 	sllx		%g2, %g1, %g2
 1:	add		%i1, 0x8, %i1
-	EX_LD(LOAD(ldx, %i1, %g3))
+	EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
 	subcc		%i4, 0x8, %i4
 	srlx		%g3, %i3, %i5
 	or		%i5, %g2, %i5
-	EX_ST(STORE(stx, %i5, %o0))
+	EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -404,8 +487,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 
 1:
 	subcc		%i2, 4, %i2
-	EX_LD(LOAD(lduw, %i1, %g1))
-	EX_ST(STORE(stw, %g1, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 4, %i1
 
@@ -415,8 +498,8 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	.align		32
 90:
 	subcc		%i2, 1, %i2
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
+	EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%i1, 1, %i1
 	ret
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index ecc5692fa2b4..bb6ff73229e3 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index 9eea392e44d4..ed92ce739558 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index 3e6209ebb7d7..f30d2ab2c371 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -5,6 +5,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	g7
@@ -23,21 +24,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -78,53 +75,169 @@
 	faligndata		%f7, %f8, %f60;			\
 	faligndata		%f8, %f9, %f62;
 
-#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt)	\
-	EX_LD_FP(LOAD_BLK(%src, %fdest));				\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));				\
-	add			%src, 0x40, %src;		\
-	subcc			%len, 0x40, %len;		\
-	be,pn			%xcc, jmptgt;			\
-	 add			%dest, 0x40, %dest;		\
-
-#define LOOP_CHUNK1(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f0,  f48, len, branch_dest)
-#define LOOP_CHUNK2(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
-#define LOOP_CHUNK3(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
+#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt)			\
+	EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp);			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp);			\
+	add			%src, 0x40, %src;			\
+	subcc			%GLOBAL_SPARE, 0x40, %GLOBAL_SPARE;	\
+	be,pn			%xcc, jmptgt;				\
+	 add			%dest, 0x40, %dest;			\
+
+#define LOOP_CHUNK1(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f0,  f48, branch_dest)
+#define LOOP_CHUNK2(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest)
+#define LOOP_CHUNK3(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest)
 
 #define DO_SYNC			membar	#Sync;
 #define STORE_SYNC(dest, fsrc)				\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp);	\
 	add			%dest, 0x40, %dest;	\
 	DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)			\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp);	\
 	add			%dest, 0x40, %dest;	\
 	ba,pt			%xcc, target;		\
 	 nop;
 
-#define FINISH_VISCHUNK(dest, f0, f1, left)	\
-	subcc			%left, 8, %left;\
-	bl,pn			%xcc, 95f;	\
-	 faligndata		%f0, %f1, %f48;	\
-	EX_ST_FP(STORE(std, %f48, %dest));		\
+#define FINISH_VISCHUNK(dest, f0, f1)			\
+	subcc			%g3, 8, %g3;		\
+	bl,pn			%xcc, 95f;		\
+	 faligndata		%f0, %f1, %f48;		\
+	EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp);	\
 	add			%dest, 8, %dest;
 
-#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
-	subcc			%left, 8, %left;	\
-	bl,pn			%xcc, 95f;		\
+#define UNEVEN_VISCHUNK_LAST(dest, f0, f1)	\
+	subcc			%g3, 8, %g3;	\
+	bl,pn			%xcc, 95f;	\
 	 fsrc2			%f0, %f1;
 
-#define UNEVEN_VISCHUNK(dest, f0, f1, left)		\
-	UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
+#define UNEVEN_VISCHUNK(dest, f0, f1)		\
+	UNEVEN_VISCHUNK_LAST(dest, f0, f1)	\
 	ba,a,pt			%xcc, 93f;
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+ENTRY(U1_g1_1_fp)
+	VISExitHalf
+	add		%g1, 1, %g1
+	add		%g1, %g2, %g1
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_1_fp)
+ENTRY(U1_g2_0_fp)
+	VISExitHalf
+	retl
+	 add		%g2, %o2, %o0
+ENDPROC(U1_g2_0_fp)
+ENTRY(U1_g2_8_fp)
+	VISExitHalf
+	add		%g2, 8, %g2
+	retl
+	 add		%g2, %o2, %o0
+ENDPROC(U1_g2_8_fp)
+ENTRY(U1_gs_0_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_0_fp)
+ENTRY(U1_gs_80_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_80_fp)
+ENTRY(U1_gs_40_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, 0x40, %GLOBAL_SPARE
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_40_fp)
+ENTRY(U1_g3_0_fp)
+	VISExitHalf
+	retl
+	 add		%g3, %o2, %o0
+ENDPROC(U1_g3_0_fp)
+ENTRY(U1_g3_8_fp)
+	VISExitHalf
+	add		%g3, 8, %g3
+	retl
+	 add		%g3, %o2, %o0
+ENDPROC(U1_g3_8_fp)
+ENTRY(U1_o2_0_fp)
+	VISExitHalf
+	retl
+	 mov		%o2, %o0
+ENDPROC(U1_o2_0_fp)
+ENTRY(U1_o2_1_fp)
+	VISExitHalf
+	retl
+	 add		%o2, 1, %o0
+ENDPROC(U1_o2_1_fp)
+ENTRY(U1_gs_0)
+	VISExitHalf
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0)
+ENTRY(U1_gs_8)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, 0x8, %o0
+ENDPROC(U1_gs_8)
+ENTRY(U1_gs_10)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, 0x10, %o0
+ENDPROC(U1_gs_10)
+ENTRY(U1_o2_0)
+	retl
+	 mov		%o2, %o0
+ENDPROC(U1_o2_0)
+ENTRY(U1_o2_8)
+	retl
+	 add		%o2, 8, %o0
+ENDPROC(U1_o2_8)
+ENTRY(U1_o2_4)
+	retl
+	 add		%o2, 4, %o0
+ENDPROC(U1_o2_4)
+ENTRY(U1_o2_1)
+	retl
+	 add		%o2, 1, %o0
+ENDPROC(U1_o2_1)
+ENTRY(U1_g1_0)
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_0)
+ENTRY(U1_g1_1)
+	add		%g1, 1, %g1
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_1)
+ENTRY(U1_gs_0_o2_adj)
+	and		%o2, 7, %o2
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0_o2_adj)
+ENTRY(U1_gs_8_o2_adj)
+	and		%o2, 7, %o2
+	add		%GLOBAL_SPARE, 8, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_8_o2_adj)
+#endif
+
 	.align		64
 
 	.globl		FUNC_NAME
@@ -166,8 +279,8 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp)
+	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -178,20 +291,20 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD_FP(LOAD(ldd, %o1, %f4))
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp)
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -214,13 +327,13 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	add		%g1, %GLOBAL_SPARE, %g1
 	subcc		%o2, %g3, %o2
 
-	EX_LD_FP(LOAD_BLK(%o1, %f0))
+	EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp)
 	add		%o1, 0x40, %o1
 	add		%g1, %g3, %g1
-	EX_LD_FP(LOAD_BLK(%o1, %f16))
+	EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp)
 	add		%o1, 0x40, %o1
 	sub		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
-	EX_LD_FP(LOAD_BLK(%o1, %f32))
+	EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp)
 	add		%o1, 0x40, %o1
 
 	/* There are 8 instances of the unrolled loop,
@@ -240,11 +353,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 	.align		64
 1:	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f0, %f2, %f48
 1:	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
@@ -261,11 +374,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 56f)
 
 1:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f2, %f4, %f48
 1:	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
@@ -282,11 +395,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 57f)
 
 1:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f4, %f6, %f48
 1:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
@@ -303,11 +416,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 58f)
 
 1:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) 
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f6, %f8, %f48
 1:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
@@ -324,11 +437,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 59f)
 
 1:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f8, %f10, %f48
 1:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
@@ -345,11 +458,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 60f)
 
 1:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f10, %f12, %f48
 1:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
@@ -366,11 +479,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 61f)
 
 1:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f12, %f14, %f48
 1:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
@@ -387,11 +500,11 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	STORE_JUMP(o0, f48, 62f)
 
 1:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f14, %f16, %f48
 1:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
@@ -407,53 +520,53 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
 	STORE_JUMP(o0, f48, 63f)
 
-40:	FINISH_VISCHUNK(o0, f0,  f2,  g3)
-41:	FINISH_VISCHUNK(o0, f2,  f4,  g3)
-42:	FINISH_VISCHUNK(o0, f4,  f6,  g3)
-43:	FINISH_VISCHUNK(o0, f6,  f8,  g3)
-44:	FINISH_VISCHUNK(o0, f8,  f10, g3)
-45:	FINISH_VISCHUNK(o0, f10, f12, g3)
-46:	FINISH_VISCHUNK(o0, f12, f14, g3)
-47:	UNEVEN_VISCHUNK(o0, f14, f0,  g3)
-48:	FINISH_VISCHUNK(o0, f16, f18, g3)
-49:	FINISH_VISCHUNK(o0, f18, f20, g3)
-50:	FINISH_VISCHUNK(o0, f20, f22, g3)
-51:	FINISH_VISCHUNK(o0, f22, f24, g3)
-52:	FINISH_VISCHUNK(o0, f24, f26, g3)
-53:	FINISH_VISCHUNK(o0, f26, f28, g3)
-54:	FINISH_VISCHUNK(o0, f28, f30, g3)
-55:	UNEVEN_VISCHUNK(o0, f30, f0,  g3)
-56:	FINISH_VISCHUNK(o0, f32, f34, g3)
-57:	FINISH_VISCHUNK(o0, f34, f36, g3)
-58:	FINISH_VISCHUNK(o0, f36, f38, g3)
-59:	FINISH_VISCHUNK(o0, f38, f40, g3)
-60:	FINISH_VISCHUNK(o0, f40, f42, g3)
-61:	FINISH_VISCHUNK(o0, f42, f44, g3)
-62:	FINISH_VISCHUNK(o0, f44, f46, g3)
-63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0,  g3)
-
-93:	EX_LD_FP(LOAD(ldd, %o1, %f2))
+40:	FINISH_VISCHUNK(o0, f0,  f2)
+41:	FINISH_VISCHUNK(o0, f2,  f4)
+42:	FINISH_VISCHUNK(o0, f4,  f6)
+43:	FINISH_VISCHUNK(o0, f6,  f8)
+44:	FINISH_VISCHUNK(o0, f8,  f10)
+45:	FINISH_VISCHUNK(o0, f10, f12)
+46:	FINISH_VISCHUNK(o0, f12, f14)
+47:	UNEVEN_VISCHUNK(o0, f14, f0)
+48:	FINISH_VISCHUNK(o0, f16, f18)
+49:	FINISH_VISCHUNK(o0, f18, f20)
+50:	FINISH_VISCHUNK(o0, f20, f22)
+51:	FINISH_VISCHUNK(o0, f22, f24)
+52:	FINISH_VISCHUNK(o0, f24, f26)
+53:	FINISH_VISCHUNK(o0, f26, f28)
+54:	FINISH_VISCHUNK(o0, f28, f30)
+55:	UNEVEN_VISCHUNK(o0, f30, f0)
+56:	FINISH_VISCHUNK(o0, f32, f34)
+57:	FINISH_VISCHUNK(o0, f34, f36)
+58:	FINISH_VISCHUNK(o0, f36, f38)
+59:	FINISH_VISCHUNK(o0, f38, f40)
+60:	FINISH_VISCHUNK(o0, f40, f42)
+61:	FINISH_VISCHUNK(o0, f42, f44)
+62:	FINISH_VISCHUNK(o0, f44, f46)
+63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0)
+
+93:	EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f0, %f2, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
 	bl,pn		%xcc, 95f
 	 add		%o0, 8, %o0
-	EX_LD_FP(LOAD(ldd, %o1, %f0))
+	EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f2, %f0, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
 	bge,pt		%xcc, 93b
 	 add		%o0, 8, %o0
 
 95:	brz,pt		%o2, 2f
 	 mov		%g1, %o1
 
-1:	EX_LD_FP(LOAD(ldub, %o1, %o3))
+1:	EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp)
 	add		%o1, 1, %o1
 	subcc		%o2, 1, %o2
-	EX_ST_FP(STORE(stb, %o3, %o0))
+	EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp)
 	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 
@@ -469,27 +582,27 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 72:	andn		%o2, 0xf, %GLOBAL_SPARE
 	and		%o2, 0xf, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0)
 	subcc		%GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + %o3))
+	EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
-	EX_LD(LOAD(ldx, %o1, %o5))
+	EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0)
 	sub		%o2, 0x8, %o2
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
-	EX_LD(LOAD(lduw, %o1, %o5))
+	EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0)
 	sub		%o2, 0x4, %o2
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -503,9 +616,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	 sub		%g0, %g1, %g1
 	sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1, %o5))
+1:	EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0)
 	subcc		%g1, 1, %g1
-	EX_ST(STORE(stb, %o5, %o1 + %o3))
+	EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -521,16 +634,16 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 8:	mov		64, %o3
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0)
 	sub		%o3, %g1, %o3
 	andn		%o2, 0x7, %GLOBAL_SPARE
 	sllx		%g2, %g1, %g2
-1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj)
 	subcc		%GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
 	add		%o1, 0x8, %o1
 	srlx		%g3, %o3, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -548,9 +661,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	bne,pn		%XCC, 90f
 	 sub		%o0, %o1, %o3
 
-1:	EX_LD(LOAD(lduw, %o1, %g1))
+1:	EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0)
 	subcc		%o2, 4, %o2
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -558,9 +671,9 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	 mov		EX_RETVAL(%o4), %o0
 
 	.align		32
-90:	EX_LD(LOAD(ldub, %o1, %g1))
+90:	EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0)
 	subcc		%o2, 1, %o2
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index 88ad73d86fe4..db73010a1af8 100644
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index 845139d75537..c4ee858e352a 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 491ee69e4995..54f98706b03b 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -22,21 +23,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -77,6 +74,87 @@
 	 */
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_fp:
+	VISExitHalf
+	retl
+	 nop
+ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+	add	%g1, 1, %g1
+	add	%g2, %g1, %g2
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ENTRY(U3_retl_o2_plus_g2_fp)
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_fp)
+ENTRY(U3_retl_o2_plus_g2_plus_8_fp)
+	add	%g2, 8, %g2
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_8_fp)
+ENTRY(U3_retl_o2)
+	retl
+	 mov	%o2, %o0
+ENDPROC(U3_retl_o2)
+ENTRY(U3_retl_o2_plus_1)
+	retl
+	 add	%o2, 1, %o0
+ENDPROC(U3_retl_o2_plus_1)
+ENTRY(U3_retl_o2_plus_4)
+	retl
+	 add	%o2, 4, %o0
+ENDPROC(U3_retl_o2_plus_4)
+ENTRY(U3_retl_o2_plus_8)
+	retl
+	 add	%o2, 8, %o0
+ENDPROC(U3_retl_o2_plus_8)
+ENTRY(U3_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	retl
+	 add	%o2, %g1, %o0
+ENDPROC(U3_retl_o2_plus_g1_plus_1)
+ENTRY(U3_retl_o2_fp)
+	ba,pt	%xcc, __restore_fp
+	 mov	%o2, %o0
+ENDPROC(U3_retl_o2_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+	sll	%o3, 6, %o3
+	add	%o3, 0x80, %o3
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+	sll	%o3, 6, %o3
+	add	%o3, 0x40, %o3
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ENTRY(U3_retl_o2_plus_GS_plus_0x10)
+	add	GLOBAL_SPARE, 0x10, GLOBAL_SPARE
+	retl
+	 add	%o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x10)
+ENTRY(U3_retl_o2_plus_GS_plus_0x08)
+	add	GLOBAL_SPARE, 0x08, GLOBAL_SPARE
+	retl
+	 add	%o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
+ENTRY(U3_retl_o2_and_7_plus_GS)
+	and	%o2, 7, %o2
+	retl
+	 add	%o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS)
+ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
+	add	GLOBAL_SPARE, 8, GLOBAL_SPARE
+	and	%o2, 7, %o2
+	retl
+	 add	%o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
+#endif
+
 	.align		64
 
 	/* The cheetah's flexible spine, oversized liver, enlarged heart,
@@ -126,8 +204,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1)
+	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -138,20 +216,20 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD_FP(LOAD(ldd, %o1, %f4))
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2)
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8)
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f2
-	EX_ST_FP(STORE(std, %f2, %o0))
+	EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -161,25 +239,25 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	LOAD(prefetch, %o1 + 0x080, #one_read)
 	LOAD(prefetch, %o1 + 0x0c0, #one_read)
 	LOAD(prefetch, %o1 + 0x100, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x140, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x180, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2)
 	faligndata	%f6, %f8, %f22
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2)
 	faligndata	%f8, %f10, %f24
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2)
 	faligndata	%f10, %f12, %f26
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2)
 
 	subcc		GLOBAL_SPARE, 0x80, GLOBAL_SPARE
 	add		%o1, 0x40, %o1
@@ -190,26 +268,26 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	.align		64
 1:
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f12, %f14, %f28
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f0, %f2, %f16
 	add		%o0, 0x40, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	subcc		%o3, 0x01, %o3
 	faligndata	%f6, %f8, %f22
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 
 	faligndata	%f8, %f10, %f24
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f10, %f12, %f26
 	bg,pt		%XCC, 1b
@@ -217,29 +295,29 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	/* Finally we copy the last full 64-byte block. */
 2:
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f12, %f14, %f28
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f6, %f8, %f22
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f8, %f10, %f24
 	cmp		%g1, 0
 	be,pt		%XCC, 1f
 	 add		%o0, 0x40, %o0
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 1:	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	add		%o0, 0x40, %o0
 	add		%o1, 0x40, %o1
 	membar		#Sync
@@ -259,20 +337,20 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 	sub		%o2, %g2, %o2
 	be,a,pt		%XCC, 1f
-	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
+	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2)
 
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f0, %f2, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
 	be,pn		%XCC, 2f
 	 add		%o0, 0x8, %o0
-	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f2, %f0, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
 	bne,pn		%XCC, 1b
 	 add		%o0, 0x8, %o0
 
@@ -292,30 +370,33 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 andcc		%o2, 0x8, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x8, %o1
+	sub		%o2, 8, %o2
 
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x4, %o1
+	sub		%o2, 4, %o2
 
 1:	andcc		%o2, 0x2, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(lduh, %o1, %o5))
-	EX_ST(STORE(sth, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x2, %o1
+	sub		%o2, 2, %o2
 
 1:	andcc		%o2, 0x1, %g0
 	be,pt		%icc, 85f
 	 nop
-	EX_LD(LOAD(ldub, %o1, %o5))
+	EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2)
 	ba,pt		%xcc, 85f
-	 EX_ST(STORE(stb, %o5, %o1 + %o3))
+	 EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2)
 
 	.align		64
 70: /* 16 < len <= 64 */
@@ -326,26 +407,26 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	andn		%o2, 0xf, GLOBAL_SPARE
 	and		%o2, 0xf, %o2
 1:	subcc		GLOBAL_SPARE, 0x10, GLOBAL_SPARE
-	EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + %o3))
+	EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x8, %o2
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4)
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -361,8 +442,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%o2, %g1, %o2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %o1, %o5))
-	EX_ST(STORE(stb, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -378,16 +459,16 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 8:	mov		64, %o3
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2)
 	sub		%o3, %g1, %o3
 	andn		%o2, 0x7, GLOBAL_SPARE
 	sllx		%g2, %g1, %g2
-1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS)
 	subcc		GLOBAL_SPARE, 0x8, GLOBAL_SPARE
 	add		%o1, 0x8, %o1
 	srlx		%g3, %o3, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -407,8 +488,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4)
+	EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -418,8 +499,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1)
+	EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S
index 302c0e60dc2c..4c89b486fa0d 100644
--- a/arch/sparc/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
@@ -8,18 +8,33 @@
 
 #define XCC xcc
 
-#define EX(x,y)			\
+#define EX(x,y,z)		\
 98:	x,y;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, z;		\
 	.text;			\
 	.align 4;
 
+#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8)
+#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4)
+#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1)
+
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+__retl_o4_plus_8:
+	add	%o4, %o2, %o4
+	retl
+	 add	%o4, 8, %o0
+__retl_o2_plus_4:
+	retl
+	 add	%o2, 4, %o0
+__retl_o2_plus_1:
+	retl
+	 add	%o2, 1, %o0
+
 	.align	32
 
 	/* Don't try to get too fancy here, just nice and
@@ -44,8 +59,8 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 	andn		%o2, 0x7, %o4
 	and		%o2, 0x7, %o2
 1:	subcc		%o4, 0x8, %o4
-	EX(ldxa [%o1] %asi, %o5)
-	EX(stxa %o5, [%o0] %asi)
+	EX_O4(ldxa [%o1] %asi, %o5)
+	EX_O4(stxa %o5, [%o0] %asi)
 	add		%o1, 0x8, %o1
 	bgu,pt		%XCC, 1b
 	 add		%o0, 0x8, %o0
@@ -53,8 +68,8 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX(lduwa [%o1] %asi, %o5)
-	EX(stwa %o5, [%o0] %asi)
+	EX_O2_4(lduwa [%o1] %asi, %o5)
+	EX_O2_4(stwa %o5, [%o0] %asi)
 	add		%o1, 0x4, %o1
 	add		%o0, 0x4, %o0
 1:	cmp		%o2, 0
@@ -70,8 +85,8 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 
 82:
 	subcc		%o2, 4, %o2
-	EX(lduwa [%o1] %asi, %g1)
-	EX(stwa %g1, [%o0] %asi)
+	EX_O2_4(lduwa [%o1] %asi, %g1)
+	EX_O2_4(stwa %g1, [%o0] %asi)
 	add		%o1, 4, %o1
 	bgu,pt		%XCC, 82b
 	 add		%o0, 4, %o0
@@ -82,8 +97,8 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 	.align	32
 90:
 	subcc		%o2, 1, %o2
-	EX(lduba [%o1] %asi, %g1)
-	EX(stba %g1, [%o0] %asi)
+	EX_O2_1(lduba [%o1] %asi, %g1)
+	EX_O2_1(stba %g1, [%o0] %asi)
 	add		%o1, 1, %o1
 	bgu,pt		%XCC, 90b
 	 add		%o0, 1, %o0
diff --git a/arch/sparc/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c
deleted file mode 100644
index ac96ae236709..000000000000
--- a/arch/sparc/lib/user_fixup.c
+++ /dev/null
@@ -1,71 +0,0 @@
-/* user_fixup.c: Fix up user copy faults.
- *
- * Copyright (C) 2004 David S. Miller <davem@redhat.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/module.h>
-
-#include <asm/uaccess.h>
-
-/* Calculating the exact fault address when using
- * block loads and stores can be very complicated.
- *
- * Instead of trying to be clever and handling all
- * of the cases, just fix things up simply here.
- */
-
-static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset)
-{
-	unsigned long fault_addr = current_thread_info()->fault_address;
-	unsigned long end = start + size;
-
-	if (fault_addr < start || fault_addr >= end) {
-		*offset = 0;
-	} else {
-		*offset = fault_addr - start;
-		size = end - fault_addr;
-	}
-	return size;
-}
-
-unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size)
-{
-	unsigned long offset;
-
-	size = compute_size((unsigned long) from, size, &offset);
-	if (likely(size))
-		memset(to + offset, 0, size);
-
-	return size;
-}
-EXPORT_SYMBOL(copy_from_user_fixup);
-
-unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size)
-{
-	unsigned long offset;
-
-	return compute_size((unsigned long) to, size, &offset);
-}
-EXPORT_SYMBOL(copy_to_user_fixup);
-
-unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size)
-{
-	unsigned long fault_addr = current_thread_info()->fault_address;
-	unsigned long start = (unsigned long) to;
-	unsigned long end = start + size;
-
-	if (fault_addr >= start && fault_addr < end)
-		return end - fault_addr;
-
-	start = (unsigned long) from;
-	end = start + size;
-	if (fault_addr >= start && fault_addr < end)
-		return end - fault_addr;
-
-	return size;
-}
-EXPORT_SYMBOL(copy_in_user_fixup);
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index dbabe5713a15..e15f33715103 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -479,14 +479,14 @@ good_area:
 	up_read(&mm->mmap_sem);
 
 	mm_rss = get_mm_rss(mm);
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
 #endif
 	if (unlikely(mm_rss >
 		     mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
 		tsb_grow(mm, MM_TSB_BASE, mm_rss);
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	mm_rss = mm->context.huge_pte_count;
+	mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
 	if (unlikely(mm_rss >
 		     mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
 		if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 131eaf4ad7f5..ffa842b4d7d4 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, HPAGE_SIZE);
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (mm->get_unmapped_area == arch_get_unmapped_area)
@@ -176,17 +176,31 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	int i;
+	pte_t orig[2];
+	unsigned long nptes;
 
 	if (!pte_present(*ptep) && pte_present(entry))
-		mm->context.huge_pte_count++;
+		mm->context.hugetlb_pte_count++;
 
 	addr &= HPAGE_MASK;
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, ptep, entry);
+
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	orig[0] = *ptep;
+	orig[1] = *(ptep + nptes / 2);
+	for (i = 0; i < nptes; i++) {
+		*ptep = entry;
 		ptep++;
 		addr += PAGE_SIZE;
 		pte_val(entry) += PAGE_SIZE;
 	}
+
+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
@@ -194,19 +208,28 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 {
 	pte_t entry;
 	int i;
+	unsigned long nptes;
 
 	entry = *ptep;
 	if (pte_present(entry))
-		mm->context.huge_pte_count--;
+		mm->context.hugetlb_pte_count--;
 
 	addr &= HPAGE_MASK;
-
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		pte_clear(mm, addr, ptep);
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	for (i = 0; i < nptes; i++) {
+		*ptep = __pte(0UL);
 		addr += PAGE_SIZE;
 		ptep++;
 	}
 
+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+
 	return entry;
 }
 
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index eb8287155279..3b7092d9ea8f 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -301,7 +301,7 @@ void __init mem_init(void)
 
 
 	/* Saves us work later. */
-	memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
 	i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
 	i += 1;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3025bd57f7ab..384aba109d7c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -324,18 +324,6 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 	tsb_insert(tsb, tag, tte);
 }
 
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline bool is_hugetlb_pte(pte_t pte)
-{
-	if ((tlb_type == hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
-	    (tlb_type != hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U))
-		return true;
-	return false;
-}
-#endif
-
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	struct mm_struct *mm;
@@ -358,7 +346,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+	if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
+	    is_hugetlb_pte(pte))
 		__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
 					address, pte_val(pte));
 	else
@@ -667,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}
 
 /* Caller does TLB context flushing on local CPU if necessary.
  * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -686,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;
 
 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
+			mmu_context_wrap();
+			goto retry;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }
 
 static int numa_enabled = 1;
@@ -811,8 +830,10 @@ struct mdesc_mblock {
 };
 static struct mdesc_mblock *mblocks;
 static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask);
 
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
 {
 	int i;
 
@@ -828,8 +849,11 @@ static unsigned long ra_to_pa(unsigned long addr)
 	return addr;
 }
 
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
 {
+	static bool search_mdesc = true;
+	static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+	static int last_index;
 	int i;
 
 	addr = ra_to_pa(addr);
@@ -839,13 +863,30 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	/* The following condition has been observed on LDOM guests.*/
-	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
-		" rule. Some physical memory will be owned by node 0.");
-	return 0;
+	/* The following condition has been observed on LDOM guests because
+	 * node_masks only contains the best latency mask and value.
+	 * LDOM guest's mdesc can contain a single latency group to
+	 * cover multiple address range. Print warning message only if the
+	 * address cannot be found in node_masks nor mdesc.
+	 */
+	if ((search_mdesc) &&
+	    ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+		/* find the available node in the mdesc */
+		last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+		numadbg("find_node: latency group for address 0x%lx is %d\n",
+			addr, last_index);
+		if ((last_index < 0) || (last_index >= num_node_masks)) {
+			/* WARN_ONCE() and use default group 0 */
+			WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+			search_mdesc = false;
+			last_index = 0;
+		}
+	}
+
+	return last_index;
 }
 
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -1169,6 +1210,41 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask)
+{
+	struct mdesc_handle *md = mdesc_grab();
+	u64 node, arc;
+	int i = 0;
+
+	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+	if (node == MDESC_NODE_NULL)
+		goto out;
+
+	mdesc_for_each_node_by_name(md, node, "group") {
+		mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+			u64 target = mdesc_arc_target(md, arc);
+			struct mdesc_mlgroup *m = find_mlgroup(target);
+
+			if (!m)
+				continue;
+			if ((pa & m->mask) == m->match) {
+				if (pnode_mask) {
+					pnode_mask->mask = m->mask;
+					pnode_mask->val = m->match;
+				}
+				mdesc_release(md);
+				return i;
+			}
+		}
+		i++;
+	}
+
+out:
+	mdesc_release(md);
+	return -1;
+}
+
 static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;
@@ -1267,13 +1343,6 @@ static int __init numa_parse_mdesc(void)
 	int i, j, err, count;
 	u64 node;
 
-	/* Some sane defaults for numa latency values */
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		for (j = 0; j < MAX_NUMNODES; j++)
-			numa_latency[i][j] = (i == j) ?
-				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	}
-
 	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
 	if (node == MDESC_NODE_NULL) {
 		mdesc_release(md);
@@ -1369,10 +1438,18 @@ static int __init numa_parse_sun4u(void)
 
 static int __init bootmem_init_numa(void)
 {
+	int i, j;
 	int err = -1;
 
 	numadbg("bootmem_init_numa()\n");
 
+	/* Some sane defaults for numa latency values */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		for (j = 0; j < MAX_NUMNODES; j++)
+			numa_latency[i][j] = (i == j) ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	}
+
 	if (numa_enabled) {
 		if (tlb_type == hypervisor)
 			err = numa_parse_mdesc();
@@ -1446,7 +1523,7 @@ bool kern_addr_valid(unsigned long addr)
 	if ((long)addr < 0L) {
 		unsigned long pa = __pa(addr);
 
-		if ((addr >> max_phys_bits) != 0UL)
+		if ((pa >> max_phys_bits) != 0UL)
 			return false;
 
 		return pfn_valid(pa >> PAGE_SHIFT);
@@ -2832,9 +2909,10 @@ void hugetlb_setup(struct pt_regs *regs)
 	 * the Data-TLB for huge pages.
 	 */
 	if (tlb_type == cheetah_plus) {
+		bool need_context_reload = false;
 		unsigned long ctx;
 
-		spin_lock(&ctx_alloc_lock);
+		spin_lock_irq(&ctx_alloc_lock);
 		ctx = mm->context.sparc64_ctx_val;
 		ctx &= ~CTX_PGSZ_MASK;
 		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2853,9 +2931,12 @@ void hugetlb_setup(struct pt_regs *regs)
 			 * also executing in this address space.
 			 */
 			mm->context.sparc64_ctx_val = ctx;
-			on_each_cpu(context_reload, mm, 0);
+			need_context_reload = true;
 		}
-		spin_unlock(&ctx_alloc_lock);
+		spin_unlock_irq(&ctx_alloc_lock);
+
+		if (need_context_reload)
+			on_each_cpu(context_reload, mm, 0);
 	}
 }
 #endif
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 9df2190c097e..3659d37b4d81 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void)
 }
 
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
-			      bool exec)
+			      bool exec, bool huge)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
 	unsigned long nr;
@@ -84,13 +84,21 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}
 
 	if (!tb->active) {
-		flush_tsb_user_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr, huge);
 		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}
 
-	if (nr == 0)
+	if (nr == 0) {
 		tb->mm = mm;
+		tb->huge = huge;
+	}
+
+	if (tb->huge != huge) {
+		flush_tlb_pending();
+		tb->huge = huge;
+		nr = 0;
+	}
 
 	tb->vaddrs[nr] = vaddr;
 	tb->tlb_nr = ++nr;
@@ -104,6 +112,8 @@ out:
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
+	bool huge = is_hugetlb_pte(orig);
+
 	if (tlb_type != hypervisor &&
 	    pte_dirty(orig)) {
 		unsigned long paddr, pfn = pte_pfn(orig);
@@ -129,7 +139,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 
 no_cache_flush:
 	if (!fullmm)
-		tlb_batch_add_one(mm, vaddr, pte_exec(orig));
+		tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -145,7 +155,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 		if (pte_val(*pte) & _PAGE_VALID) {
 			bool exec = pte_exec(*pte);
 
-			tlb_batch_add_one(mm, vaddr, exec);
+			tlb_batch_add_one(mm, vaddr, exec, false);
 		}
 		pte++;
 		vaddr += PAGE_SIZE;
@@ -165,9 +175,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 
 	if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
 		if (pmd_val(pmd) & _PAGE_PMD_HUGE)
-			mm->context.huge_pte_count++;
+			mm->context.thp_pte_count++;
 		else
-			mm->context.huge_pte_count--;
+			mm->context.thp_pte_count--;
 
 		/* Do not try to allocate the TSB hash table if we
 		 * don't have one already.  We have various locks held
@@ -185,8 +195,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			pte_t orig_pte = __pte(pmd_val(orig));
 			bool exec = pte_exec(orig_pte);
 
-			tlb_batch_add_one(mm, addr, exec);
-			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
+			tlb_batch_add_one(mm, addr, exec, true);
+			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
+					true);
 		} else {
 			tlb_batch_pmd_scan(mm, addr, orig);
 		}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a06576683c38..266411291634 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr)
 	return (tag == (vaddr >> 22));
 }
 
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+	unsigned long idx;
+
+	for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+		struct tsb *ent = &swapper_tsb[idx];
+		unsigned long match = idx << 13;
+
+		match |= (ent->tag << 22);
+		if (match >= start && match < end)
+			ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+	}
+}
+
 /* TSB flushes need only occur on the processor initiating the address
  * space modification, not on each cpu the address space has run on.
  * Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long v;
 
+	if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+		return flush_tsb_kernel_range_scan(start, end);
+
 	for (v = start; v < end; v += PAGE_SIZE) {
 		unsigned long hash = tsb_hash(v, PAGE_SHIFT,
 					      KERNEL_TSB_NENTRIES);
@@ -76,14 +93,15 @@ void flush_tsb_user(struct tlb_batch *tb)
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
-	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
-	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
-		base = __pa(base);
-	__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
-
+	if (!tb->huge) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
+	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@@ -94,20 +112,21 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
 {
 	unsigned long nentries, base, flags;
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
-	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
-	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
-		base = __pa(base);
-	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
-
+	if (!huge) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@@ -432,7 +451,8 @@ retry_tsb_alloc:
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;
 
@@ -440,7 +460,9 @@ retry_tsb_alloc:
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}
 
 	mm->context.tsb_block[tsb_index].tsb = new_tsb;
@@ -468,7 +490,7 @@ retry_tsb_alloc:
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	unsigned long huge_pte_count;
+	unsigned long total_huge_pte_count;
 #endif
 	unsigned int i;
 
@@ -477,12 +499,14 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm->context.sparc64_ctx_val = 0UL;
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	/* We reset it to zero because the fork() page copying
+	/* We reset them to zero because the fork() page copying
 	 * will re-increment the counters as the parent PTEs are
 	 * copied into the child address space.
 	 */
-	huge_pte_count = mm->context.huge_pte_count;
-	mm->context.huge_pte_count = 0;
+	total_huge_pte_count = mm->context.hugetlb_pte_count +
+			 mm->context.thp_pte_count;
+	mm->context.hugetlb_pte_count = 0;
+	mm->context.thp_pte_count = 0;
 #endif
 
 	/* copy_mm() copies over the parent's mm_struct before calling
@@ -498,8 +522,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (unlikely(huge_pte_count))
-		tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
+	if (unlikely(total_huge_pte_count))
+		tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
 #endif
 
 	if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index b4f4733abc6e..fcf4d27a38fb 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
 	.text
 	.align		32
 	.globl		__flush_tlb_mm
-__flush_tlb_mm:		/* 18 insns */
+__flush_tlb_mm:		/* 19 insns */
 	/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
 	ldxa		[%o1] ASI_DMMU, %g2
 	cmp		%g2, %o0
@@ -81,7 +81,7 @@ __flush_tlb_page:	/* 22 insns */
 
 	.align		32
 	.globl		__flush_tlb_pending
-__flush_tlb_pending:	/* 26 insns */
+__flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
 	sllx		%o1, 3, %o1
@@ -113,12 +113,14 @@ __flush_tlb_pending:	/* 26 insns */
 
 	.align		32
 	.globl		__flush_tlb_kernel_range
-__flush_tlb_kernel_range:	/* 16 insns */
+__flush_tlb_kernel_range:	/* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, __spitfire_flush_tlb_kernel_range_slow
 	 sethi		%hi(PAGE_SIZE), %o4
-	sub		%o1, %o0, %o3
 	sub		%o3, %o4, %o3
 	or		%o0, 0x20, %o0		! Nucleus
 1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -131,6 +133,41 @@ __flush_tlb_kernel_range:	/* 16 insns */
 	retl
 	 nop
 	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+	mov		63 * 8, %o4
+1:	ldxa		[%o4] ASI_ITLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_IMMU
+	stxa		%g0, [%o4] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%o4] ASI_DTLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_DMMU
+	stxa		%g0, [%o4] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%o4, 8, %o4
+	brgez,pt	%o4, 1b
+	 nop
+	retl
+	 nop
 
 __spitfire_flush_tlb_mm_slow:
 	rdpr		%pstate, %g1
@@ -285,6 +322,40 @@ __cheetah_flush_tlb_pending:	/* 27 insns */
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_kernel_range:	/* 31 insns */
+	/* %o0=start, %o1=end */
+	cmp		%o0, %o1
+	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, 3f
+	 sethi		%hi(PAGE_SIZE), %o4
+	sub		%o3, %o4, %o3
+	or		%o0, 0x20, %o0		! Nucleus
+1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
+	stxa		%g0, [%o0 + %o3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%o3, 1b
+	 sub		%o3, %o4, %o3
+2:	sethi		%hi(KERNBASE), %o3
+	flush		%o3
+	retl
+	 nop
+3:	mov		0x80, %o4
+	stxa		%g0, [%o4] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%o4] ASI_IMMU_DEMAP
+	membar		#Sync
+	retl
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 __cheetah_flush_dcache_page: /* 11 insns */
 	sethi		%hi(PAGE_OFFSET), %g1
@@ -309,19 +380,28 @@ __hypervisor_tlb_tl0_error:
 	ret
 	 restore
 
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
 	mov		%o0, %o2	/* ARG2: mmu context */
 	mov		0, %o0		/* ARG0: CPU lists unimplemented */
 	mov		0, %o1		/* ARG1: CPU lists unimplemented */
 	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
 	mov		HV_FAST_MMU_DEMAP_CTX, %o5
 	ta		HV_FAST_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o5
+	jmpl		%o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
 	/* %o0 = context, %o1 = vaddr */
 	mov		%o0, %g2
 	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
@@ -330,12 +410,23 @@ __hypervisor_flush_tlb_page: /* 11 insns */
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_pending: /* 16 insns */
+__hypervisor_flush_tlb_pending: /* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
 	mov		%o2, %g2
@@ -347,31 +438,57 @@ __hypervisor_flush_tlb_pending: /* 16 insns */
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g1, 1b
 	 nop
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
-	 sethi		%hi(PAGE_SIZE), %g3
-	mov		%o0, %g1
-	sub		%o1, %g1, %g2
+	 sub		%o1, %o0, %g2
+	srlx		%g2, 18, %g3
+	brnz,pn		%g3, 4f
+	 mov		%o0, %g1
+	sethi		%hi(PAGE_SIZE), %g3
 	sub		%g2, %g3, %g2
 1:	add		%g1, %g2, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 3f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g2, 1b
 	 sub		%g2, %g3, %g2
 2:	retl
 	 nop
+3:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+4:	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	brnz,pn		%o0, 3b
+	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
+	retl
+	 nop
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -394,43 +511,6 @@ tlb_patch_one:
 	retl
 	 nop
 
-	.globl		cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
-	save		%sp, -128, %sp
-
-	sethi		%hi(__flush_tlb_mm), %o0
-	or		%o0, %lo(__flush_tlb_mm), %o0
-	sethi		%hi(__cheetah_flush_tlb_mm), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
-	call		tlb_patch_one
-	 mov		19, %o2
-
-	sethi		%hi(__flush_tlb_page), %o0
-	or		%o0, %lo(__flush_tlb_page), %o0
-	sethi		%hi(__cheetah_flush_tlb_page), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
-	call		tlb_patch_one
-	 mov		22, %o2
-
-	sethi		%hi(__flush_tlb_pending), %o0
-	or		%o0, %lo(__flush_tlb_pending), %o0
-	sethi		%hi(__cheetah_flush_tlb_pending), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
-	call		tlb_patch_one
-	 mov		27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
-	sethi		%hi(__flush_dcache_page), %o0
-	or		%o0, %lo(__flush_dcache_page), %o0
-	sethi		%hi(__cheetah_flush_dcache_page), %o1
-	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
-	call		tlb_patch_one
-	 mov		11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
-	ret
-	 restore
-
 #ifdef CONFIG_SMP
 	/* These are all called by the slaves of a cross call, at
 	 * trap level 1, with interrupts fully disabled.
@@ -447,7 +527,7 @@ cheetah_patch_cachetlbops:
 	 */
 	.align		32
 	.globl		xcall_flush_tlb_mm
-xcall_flush_tlb_mm:	/* 21 insns */
+xcall_flush_tlb_mm:	/* 24 insns */
 	mov		PRIMARY_CONTEXT, %g2
 	ldxa		[%g2] ASI_DMMU, %g3
 	srlx		%g3, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -469,9 +549,12 @@ xcall_flush_tlb_mm:	/* 21 insns */
 	nop
 	nop
 	nop
+	nop
+	nop
+	nop
 
 	.globl		xcall_flush_tlb_page
-xcall_flush_tlb_page:	/* 17 insns */
+xcall_flush_tlb_page:	/* 20 insns */
 	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
@@ -490,15 +573,20 @@ xcall_flush_tlb_page:	/* 17 insns */
 	retry
 	nop
 	nop
+	nop
+	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range:	/* 25 insns */
+xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
-	add		%g2, 1, %g2
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -507,8 +595,25 @@ xcall_flush_tlb_kernel_range:	/* 25 insns */
 	brnz,pt		%g3, 1b
 	 sub		%g3, %g2, %g3
 	retry
-	nop
-	nop
+2:	mov		63 * 8, %g1
+1:	ldxa		[%g1] ASI_ITLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_IMMU
+	stxa		%g0, [%g1] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%g1] ASI_DTLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_DMMU
+	stxa		%g0, [%g1] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%g1, 8, %g1
+	brgez,pt	%g1, 1b
+	 nop
+	retry
 	nop
 	nop
 	nop
@@ -637,6 +742,52 @@ xcall_fetch_glob_pmu_n4:
 
 	retry
 
+__cheetah_xcall_flush_tlb_kernel_range:	/* 44 insns */
+	sethi		%hi(PAGE_SIZE - 1), %g2
+	or		%g2, %lo(PAGE_SIZE - 1), %g2
+	andn		%g1, %g2, %g1
+	andn		%g7, %g2, %g7
+	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
+	sub		%g3, %g2, %g3
+	or		%g1, 0x20, %g1		! Nucleus
+1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
+	stxa		%g0, [%g1 + %g3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%g3, 1b
+	 sub		%g3, %g2, %g3
+	retry
+2:	mov		0x80, %g2
+	stxa		%g0, [%g2] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%g2] ASI_IMMU_DEMAP
+	membar		#Sync
+	retry
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 	.align		32
 	.globl		xcall_flush_dcache_page_cheetah
@@ -700,7 +851,7 @@ __hypervisor_tlb_xcall_error:
 	ba,a,pt	%xcc, rtrap
 
 	.globl		__hypervisor_xcall_flush_tlb_mm
-__hypervisor_xcall_flush_tlb_mm: /* 21 insns */
+__hypervisor_xcall_flush_tlb_mm: /* 24 insns */
 	/* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */
 	mov		%o0, %g2
 	mov		%o1, %g3
@@ -714,7 +865,7 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	mov		HV_FAST_MMU_DEMAP_CTX, %o5
 	ta		HV_FAST_TRAP
 	mov		HV_FAST_MMU_DEMAP_CTX, %g6
-	brnz,pn		%o0, __hypervisor_tlb_xcall_error
+	brnz,pn		%o0, 1f
 	 mov		%o0, %g5
 	mov		%g2, %o0
 	mov		%g3, %o1
@@ -723,9 +874,12 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	mov		%g7, %o5
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
 
 	.globl		__hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+__hypervisor_xcall_flush_tlb_page: /* 20 insns */
 	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
@@ -737,42 +891,64 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
-	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
+	brnz,a,pn	%o0, 1f
 	 mov		%o0, %g5
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
 
 	.globl		__hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
 	/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g7
 	add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	mov		%o0, %g2
 	mov		%o1, %g4
-	mov		%o2, %g7
+	brnz,pn		%g7, 2f
+	 mov		%o2, %g7
 1:	add		%g1, %g3, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
 	ta		HV_MMU_UNMAP_ADDR_TRAP
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
-	brnz,pn		%o0, __hypervisor_tlb_xcall_error
+	brnz,pn		%o0, 1f
 	 mov		%o0, %g5
 	sethi		%hi(PAGE_SIZE), %o2
 	brnz,pt		%g3, 1b
 	 sub		%g3, %o2, %g3
-	mov		%g2, %o0
+5:	mov		%g2, %o0
 	mov		%g4, %o1
 	mov		%g7, %o2
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
+2:	mov		%o3, %g1
+	mov		%o5, %g3
+	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	mov		%g1, %o3
+	brz,pt		%o0, 5b
+	 mov		%g3, %o5
+	mov		HV_FAST_MMU_DEMAP_CTX, %g6
+	ba,pt		%xcc, 1b
+	 clr		%g5
 
 	/* These just get rescheduled to PIL vectors. */
 	.globl		xcall_call_function
@@ -795,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry
 
-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture:
@@ -809,6 +980,58 @@ xcall_kgdb_capture:
 
 #endif /* CONFIG_SMP */
 
+	.globl		cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+	save		%sp, -128, %sp
+
+	sethi		%hi(__flush_tlb_mm), %o0
+	or		%o0, %lo(__flush_tlb_mm), %o0
+	sethi		%hi(__cheetah_flush_tlb_mm), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
+	call		tlb_patch_one
+	 mov		19, %o2
+
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
+	sethi		%hi(__flush_tlb_pending), %o0
+	or		%o0, %lo(__flush_tlb_pending), %o0
+	sethi		%hi(__cheetah_flush_tlb_pending), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
+	call		tlb_patch_one
+	 mov		27, %o2
+
+	sethi		%hi(__flush_tlb_kernel_range), %o0
+	or		%o0, %lo(__flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+	sethi		%hi(__flush_dcache_page), %o0
+	or		%o0, %lo(__flush_dcache_page), %o0
+	sethi		%hi(__cheetah_flush_dcache_page), %o1
+	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
+	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		44, %o2
+#endif /* CONFIG_SMP */
+
+	ret
+	 restore
 
 	.globl		hypervisor_patch_cachetlbops
 hypervisor_patch_cachetlbops:
@@ -819,28 +1042,28 @@ hypervisor_patch_cachetlbops:
 	sethi		%hi(__hypervisor_flush_tlb_mm), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_mm), %o1
 	call		tlb_patch_one
-	 mov		10, %o2
+	 mov		19, %o2
 
 	sethi		%hi(__flush_tlb_page), %o0
 	or		%o0, %lo(__flush_tlb_page), %o0
 	sethi		%hi(__hypervisor_flush_tlb_page), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		11, %o2
+	 mov		22, %o2
 
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_pending), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		27, %o2
 
 	sethi		%hi(__flush_tlb_kernel_range), %o0
 	or		%o0, %lo(__flush_tlb_kernel_range), %o0
 	sethi		%hi(__hypervisor_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		31, %o2
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	sethi		%hi(__flush_dcache_page), %o0
@@ -857,21 +1080,21 @@ hypervisor_patch_cachetlbops:
 	sethi		%hi(__hypervisor_xcall_flush_tlb_mm), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		24, %o2
 
 	sethi		%hi(xcall_flush_tlb_page), %o0
 	or		%o0, %lo(xcall_flush_tlb_page), %o0
 	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		17, %o2
+	 mov		20, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
 	sethi		%hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		25, %o2
+	 mov		44, %o2
 #endif /* CONFIG_SMP */
 
 	ret
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 17bd2e167e07..df707a8ad311 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -35,6 +35,5 @@ void restore_processor_state(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 }
diff --git a/arch/tile/include/asm/elf.h b/arch/tile/include/asm/elf.h
index c505d77e4d06..e9d54a06736f 100644
--- a/arch/tile/include/asm/elf.h
+++ b/arch/tile/include/asm/elf.h
@@ -129,6 +129,7 @@ extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int executable_stack);
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO \
 do { \
 	NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \
diff --git a/arch/tile/include/uapi/asm/auxvec.h b/arch/tile/include/uapi/asm/auxvec.h
index c93e92709f14..f497123ed980 100644
--- a/arch/tile/include/uapi/asm/auxvec.h
+++ b/arch/tile/include/uapi/asm/auxvec.h
@@ -18,4 +18,6 @@
 /* The vDSO location. */
 #define AT_SYSINFO_EHDR         33
 
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif /* _ASM_TILE_AUXVEC_H */
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index bdc126faf741..6239aa155f6d 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target,
 			  const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs regs;
+	struct pt_regs regs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0,
 				 sizeof(regs));
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 178989e6d3e3..ea960d660917 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -218,8 +218,8 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
  */
 unsigned long long sched_clock(void)
 {
-	return clocksource_cyc2ns(get_cycles(),
-				  sched_clock_mult, SCHED_CLOCK_SHIFT);
+	return mult_frac(get_cycles(),
+			 sched_clock_mult, 1ULL << SCHED_CLOCK_SHIFT);
 }
 
 int setup_profiling_timer(unsigned int multiplier)
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index c034dc3fe2d4..c97ee6c7f949 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -232,7 +232,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (current->mm->get_unmapped_area == arch_get_unmapped_area)
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 29880c9b324e..e22e57298522 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req)
 	ptr += strlen("proc");
 	ptr = skip_spaces(ptr);
 
-	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
+	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
 		printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file));
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 1dd5bd8a8c59..133055311dce 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -81,7 +81,7 @@
   .altinstr_replacement : { *(.altinstr_replacement) }
   /* .exit.text is discard at runtime, not link time, to deal with references
      from .altinstructions and .eh_frame */
-  .exit.text : { *(.exit.text) }
+  .exit.text : { EXIT_TEXT }
   .exit.data : { *(.exit.data) }
 
   .preinit_array : {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f7c69436accc..9d5e3a27bef2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1129,22 +1129,23 @@ config MICROCODE
 	bool "CPU microcode loading support"
 	default y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
-	depends on BLK_DEV_INITRD
 	select FW_LOADER
 	---help---
-
 	  If you say Y here, you will be able to update the microcode on
-	  certain Intel and AMD processors. The Intel support is for the
-	  IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4,
-	  Xeon etc. The AMD support is for families 0x10 and later. You will
-	  obviously need the actual microcode binary data itself which is not
-	  shipped with the Linux kernel.
-
-	  This option selects the general module only, you need to select
-	  at least one vendor specific module as well.
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called microcode.
+	  Intel and AMD processors. The Intel support is for the IA32 family,
+	  e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The
+	  AMD support is for families 0x10 and later. You will obviously need
+	  the actual microcode binary data itself which is not shipped with
+	  the Linux kernel.
+
+	  The preferred method to load microcode from a detached initrd is described
+	  in Documentation/x86/early-microcode.txt. For that you need to enable
+	  CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the
+	  initrd for microcode blobs.
+
+	  In addition, you can build-in the microcode into the kernel. For that you
+	  need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode
+	  to the CONFIG_EXTRA_FIRMWARE config option.
 
 config MICROCODE_INTEL
 	bool "Intel microcode loading support"
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 2ee62dba0373..c0cc2a6be0bf 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage
 	for i in lib lib64 share end ; do \
 		if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
 			cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+			if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \
+				cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \
+			fi ; \
 			break ; \
 		fi ; \
 		if [ $$i = end ] ; then exit 1 ; fi ; \
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9011a88353de..ed1e9206f830 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -16,7 +16,7 @@
 #ifndef BOOT_BOOT_H
 #define BOOT_BOOT_H
 
-#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+#define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 0a291cdfaf77..efa6073ffa7e 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -22,7 +22,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -35,6 +35,18 @@ KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
+ifeq ($(CONFIG_RELOCATABLE),y)
+# If kernel is relocatable, build compressed kernel as PIE.
+ifeq ($(CONFIG_X86_32),y)
+LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
+else
+# To build 64-bit compressed kernel as PIE, we disable relocation
+# overflow check to avoid relocation overflow error with a new linker
+# command-line option, -z noreloc-overflow.
+LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
+	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
+endif
+endif
 LDFLAGS_vmlinux := -T
 
 hostprogs-y	:= mkpiggy
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 8ef964ddc18e..0256064da8da 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -31,6 +31,34 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
+ * relocation to get the symbol address in PIC.  When the compressed x86
+ * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
+ * relocations to their fixed symbol addresses.  However, when the
+ * compressed x86 kernel is loaded at a different address, it leads
+ * to the following load failure:
+ *
+ *   Failed to allocate space for phdrs
+ *
+ * during the decompression stage.
+ *
+ * If the compressed x86 kernel is relocatable at run-time, it should be
+ * compiled with -fPIE, instead of -fPIC, if possible and should be built as
+ * Position Independent Executable (PIE) so that linker won't optimize
+ * R_386_GOT32X relocation to its fixed symbol address.  Older
+ * linkers generate R_386_32 relocations against locally defined symbols,
+ * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
+ * R_386_32 relocations when relocating the kernel.  To generate
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index b0c0d16ef58d..86558a199139 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * Locally defined symbols should be marked hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 	.code32
 ENTRY(startup_32)
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b8465d302..06ceddb3a22e 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include "ctype.h"
+#include "string.h"
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 725e820602b1..113588ddb43f 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len);
 #define memset(d,c,l) __builtin_memset(d,c,l)
 #define memcmp	__builtin_memcmp
 
+extern int strcmp(const char *str1, const char *str2);
+extern int strncmp(const char *cs, const char *ct, size_t count);
+extern size_t strlen(const char *s);
+extern char *strstr(const char *s1, const char *s2);
+extern size_t strnlen(const char *s, size_t maxlen);
+extern unsigned int atou(const char *s);
+extern unsigned long long simple_strtoull(const char *cp, char **endp,
+					  unsigned int base);
+
 #endif /* BOOT_STRING_H */
diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config
index 4e2ecfa23c15..4b429df40d7a 100644
--- a/arch/x86/configs/tiny.config
+++ b/arch/x86/configs/tiny.config
@@ -1 +1,3 @@
 CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 440df0c7a2ee..a69321a77783 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req)
 	}
 }
 
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	ghash_async_init(req);
+	memcpy(dctx, in, sizeof(*dctx));
+	return 0;
+
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memcpy(out, dctx, sizeof(*dctx));
+	return 0;
+
+}
+
 static int ghash_async_digest(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -288,8 +311,11 @@ static struct ahash_alg ghash_async_alg = {
 	.final		= ghash_async_final,
 	.setkey		= ghash_async_setkey,
 	.digest		= ghash_async_digest,
+	.export		= ghash_async_export,
+	.import		= ghash_async_import,
 	.halg = {
 		.digestsize	= GHASH_DIGEST_SIZE,
+		.statesize = sizeof(struct ghash_desc_ctx),
 		.base = {
 			.cra_name		= "ghash",
 			.cra_driver_name	= "ghash-clmulni",
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index a841e9765bd6..8381c09d2870 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 03663740c866..1a4477cedc49 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -268,6 +268,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 /* Called with IRQs disabled. */
 __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 {
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	u32 cached_flags;
 
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
@@ -275,12 +276,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 
 	lockdep_sys_exit();
 
-	cached_flags =
-		READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+	cached_flags = READ_ONCE(ti->flags);
 
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 		exit_to_usermode_loop(regs, cached_flags);
 
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
+	 * returning to user mode.  We need to clear it *after* signal
+	 * handling, because syscall restart has a fixup for compat
+	 * syscalls.  The fixup is exercised by the ptrace_syscall_32
+	 * selftest.
+	 */
+	ti->status &= ~TS_COMPAT;
+#endif
+
 	user_enter();
 }
 
@@ -332,14 +343,6 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 	if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
 		syscall_slow_exit_work(regs, cached_flags);
 
-#ifdef CONFIG_COMPAT
-	/*
-	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
-	 * returning to user mode.
-	 */
-	ti->status &= ~TS_COMPAT;
-#endif
-
 	local_irq_disable();
 	prepare_exit_to_usermode(regs);
 }
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index f3b6d54e0042..ae678ad128a9 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -766,8 +766,8 @@ ftrace_graph_call:
 	jmp	ftrace_stub
 #endif
 
-.globl ftrace_stub
-ftrace_stub:
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
 	ret
 END(ftrace_caller)
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a55697d19824..cc0f2f5da19b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1190,6 +1190,8 @@ ENTRY(nmi)
 	 * other IST entries.
 	 */
 
+	ASM_CLAC
+
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f17705e1332c..e62f4401e792 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -294,7 +294,7 @@
 # 285 sys_setaltroot
 286	i386	add_key			sys_add_key
 287	i386	request_key		sys_request_key
-288	i386	keyctl			sys_keyctl
+288	i386	keyctl			sys_keyctl			compat_sys_keyctl
 289	i386	ioprio_set		sys_ioprio_set
 290	i386	ioprio_get		sys_ioprio_get
 291	i386	inotify_init		sys_inotify_init
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 08a317a9ae4b..a7508d7e20b7 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -31,8 +31,10 @@ static int __init vdso32_setup(char *s)
 {
 	vdso32_enabled = simple_strtoul(s, NULL, 0);
 
-	if (vdso32_enabled > 1)
+	if (vdso32_enabled > 1) {
 		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+		vdso32_enabled = 0;
+	}
 
 	return 1;
 }
@@ -63,13 +65,18 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
+static const int zero;
+static const int one = 1;
+
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (int *)&zero,
+		.extra2		= (int *)&one,
 	},
 	{}
 };
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a30316bf801a..163769d82475 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -638,8 +638,8 @@ static inline void entering_irq(void)
 
 static inline void entering_ack_irq(void)
 {
-	ack_APIC_irq();
 	entering_irq();
+	ack_APIC_irq();
 }
 
 static inline void ipi_entering_ack_irq(void)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..bcd3d6199464 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -245,12 +245,13 @@ extern int force_personality32;
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
@@ -278,7 +279,7 @@ struct task_struct;
 
 #define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso32_enabled) {						\
+	if (VDSO_CURRENT_BASE) {					\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index f8a29d2c97b0..e6a8613fbfb0 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#define hugepages_supported() cpu_has_pse
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 1e3408e88604..59caa55fb9b5 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -136,6 +136,7 @@ struct irq_alloc_info {
 struct irq_cfg {
 	unsigned int		dest_apicid;
 	u8			vector;
+	u8			old_vector;
 };
 
 extern struct irq_cfg *irq_cfg(unsigned int irq);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad07853..9016b4b70375 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -304,13 +304,13 @@ static inline unsigned type in##bwl##_p(int port)			\
 static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 {									\
 	asm volatile("rep; outs" #bwl					\
-		     : "+S"(addr), "+c"(count) : "d"(port));		\
+		     : "+S"(addr), "+c"(count) : "d"(port) : "memory");	\
 }									\
 									\
 static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 {									\
 	asm volatile("rep; ins" #bwl					\
-		     : "+D"(addr), "+c"(count) : "d"(port));		\
+		     : "+D"(addr), "+c"(count) : "d"(port) : "memory");	\
 }
 
 BUILDIO(b, b, char)
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e9cd7befcb76..19d14ac23ef9 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -221,6 +221,9 @@ struct x86_emulate_ops {
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+
+	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -290,7 +293,6 @@ struct x86_emulate_ctxt {
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
-	int emul_flags;
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 30cfd64295a0..9d2abb2a41d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -41,7 +41,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 400000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 34e62b1dcfce..712b24ed3a64 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_MICROCODE_H
 
 #include <linux/earlycpio.h>
+#include <linux/initrd.h>
 
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
@@ -168,4 +169,29 @@ static inline void reload_early_microcode(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
+
+static inline unsigned long get_initrd_start(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	return initrd_start;
+#else
+	return 0;
+#endif
+}
+
+static inline unsigned long get_initrd_start_addr(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+#ifdef CONFIG_X86_32
+	unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+
+	return (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+	return get_initrd_start();
+#endif
+#else /* CONFIG_BLK_DEV_INITRD */
+	return 0;
+#endif
+}
+
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 690b4027e17c..37db36fddc88 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -405,6 +405,8 @@
 #define MSR_IA32_TSC_ADJUST             0x0000003b
 #define MSR_IA32_BNDCFGS		0x00000d90
 
+#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
+
 #define MSR_IA32_XSS			0x00000da0
 
 #define FEATURE_CONTROL_LOCKED				(1<<0)
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
 #define _ASM_X86_MTRR_H
 
 #include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
 
 
 /*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
+static inline void mtrr_bp_init(void)
+{
+	pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
 
 #define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
 #define set_mtrr_aps_delayed_init() do {} while (0)
 #define mtrr_aps_init() do {} while (0)
 #define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..fffb2794dd89 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,9 @@
 #include <asm/pgtable_types.h>
 
 bool pat_enabled(void);
+void pat_disable(const char *reason);
 extern void pat_init(void);
-void pat_init_cache_modes(u64);
+extern void init_cache_modes(void);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195dae425..164e3f8d3c3d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7bcb861a04e5..5a2ed3ed2f26 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -165,6 +165,7 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
 #define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
  * IBS cpuid feature detection
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d8ce3ec816ab..6503526d7b24 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 {
@@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(vaddr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
-		__arch_wb_cache_pmem(vaddr, bytes);
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				__arch_wb_cache_pmem(addr, bytes);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				__arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				__arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
+		__arch_wb_cache_pmem(addr, bytes);
 
 	return len;
 }
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7a6bed5c08bc..baad72e4c100 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	u8 ret_flags;
 
 	version = src->version;
+	/* Make the latest version visible */
+	smp_rmb();
 
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6df2029405a3..6433e28dc9c8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -32,7 +32,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
-	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+	this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe());
 }
 
 /* Set in this cpu's CR4. */
@@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }
 
 static inline void __native_flush_tlb_global_irq_disabled(void)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 09b1b0ab94b7..b8c75f3aade8 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -332,7 +332,7 @@ do {									\
 #define __get_user_asm_u64(x, ptr, retval, errret) \
 	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
 #define __get_user_asm_ex_u64(x, ptr) \
-	 __get_user_asm_ex(x, ptr, "q", "", "=r")
+	 __get_user_asm_ex(x, ptr, "q", "", "=&r")
 #endif
 
 #define __get_user_size(x, ptr, size, retval, errret)			\
@@ -375,13 +375,13 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm_ex(x, ptr, "b", "b", "=q");		\
+		__get_user_asm_ex(x, ptr, "b", "b", "=&q");		\
 		break;							\
 	case 2:								\
-		__get_user_asm_ex(x, ptr, "w", "w", "=r");		\
+		__get_user_asm_ex(x, ptr, "w", "w", "=&r");		\
 		break;							\
 	case 4:								\
-		__get_user_asm_ex(x, ptr, "l", "k", "=r");		\
+		__get_user_asm_ex(x, ptr, "l", "k", "=&r");		\
 		break;							\
 	case 8:								\
 		__get_user_asm_ex_u64(x, ptr);				\
@@ -395,7 +395,7 @@ do {									\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
 		     _ASM_EXTABLE_EX(1b, 2b)				\
-		     : ltype(x) : "m" (__m(addr)))
+		     : ltype(x) : "m" (__m(addr)), "0" (0))
 
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 4c20dd333412..85133b2b8e99 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -43,6 +43,7 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/smap.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -213,10 +214,12 @@ privcmd_call(unsigned call,
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
+	stac();
 	asm volatile("call *%[call]"
 		     : __HYPERCALL_5PARAM
 		     : [call] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
+	clac();
 
 	return (long)__res;
 }
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 8b2d4bea9962..39171b3646bb 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);
 #endif
 
+extern void xen_set_iopl_mask(unsigned mask);
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e75907601a41..1e5eb9f2ff5f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -329,6 +329,14 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 	struct mpc_intsrc mp_irq;
 
 	/*
+	 * Check bus_irq boundary.
+	 */
+	if (bus_irq >= NR_IRQS_LEGACY) {
+		pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq);
+		return;
+	}
+
+	/*
 	 * Convert 'gsi' to 'ioapic.pin'.
 	 */
 	ioapic = mp_find_ioapic(gsi);
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 29fa475ec518..c986d0b3bc35 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
 	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
 		i++;
 
-	if (i == 0)
-		return 0;
+	if (!i)
+		return -ENODEV;
 
 	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2f69e3b184f6..a3e1f8497f8c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1587,6 +1587,9 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	int ret, ir_stat;
 
+	if (skip_ioapic_setup)
+		return;
+
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
 		return;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fdb0fbfb1197..fc91c98bee01 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2113,8 +2115,9 @@ static inline void __init check_timer(void)
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_ioapic_irq(irq_get_chip_data(0));
+				unmask_ioapic_irq(irq_get_irq_data(0));
 		}
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
@@ -2136,6 +2139,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index a35f6b5473f4..0988e204f1e3 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -211,6 +211,7 @@ update:
 	 */
 	cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
 	d->move_in_progress = !cpumask_empty(d->old_domain);
+	d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0;
 	d->cfg.vector = vector;
 	cpumask_copy(d->domain, vector_cpumask);
 success:
@@ -253,7 +254,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	struct irq_desc *desc;
 	int cpu, vector;
 
-	BUG_ON(!data->cfg.vector);
+	if (!data->cfg.vector)
+		return;
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
@@ -653,46 +655,114 @@ void irq_complete_move(struct irq_cfg *cfg)
 }
 
 /*
- * Called with @desc->lock held and interrupts disabled.
+ * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
  */
 void irq_force_complete_move(struct irq_desc *desc)
 {
-	struct irq_data *irqdata = irq_desc_get_irq_data(desc);
-	struct apic_chip_data *data = apic_chip_data(irqdata);
-	struct irq_cfg *cfg = data ? &data->cfg : NULL;
+	struct irq_data *irqdata;
+	struct apic_chip_data *data;
+	struct irq_cfg *cfg;
+	unsigned int cpu;
 
-	if (!cfg)
+	/*
+	 * The function is called for all descriptors regardless of which
+	 * irqdomain they belong to. For example if an IRQ is provided by
+	 * an irq_chip as part of a GPIO driver, the chip data for that
+	 * descriptor is specific to the irq_chip in question.
+	 *
+	 * Check first that the chip_data is what we expect
+	 * (apic_chip_data) before touching it any further.
+	 */
+	irqdata = irq_domain_get_irq_data(x86_vector_domain,
+					  irq_desc_get_irq(desc));
+	if (!irqdata)
 		return;
 
-	__irq_complete_move(cfg, cfg->vector);
+	data = apic_chip_data(irqdata);
+	cfg = data ? &data->cfg : NULL;
+
+	if (!cfg)
+		return;
 
 	/*
 	 * This is tricky. If the cleanup of @data->old_domain has not been
 	 * done yet, then the following setaffinity call will fail with
 	 * -EBUSY. This can leave the interrupt in a stale state.
 	 *
-	 * The cleanup cannot make progress because we hold @desc->lock. So in
-	 * case @data->old_domain is not yet cleaned up, we need to drop the
-	 * lock and acquire it again. @desc cannot go away, because the
-	 * hotplug code holds the sparse irq lock.
+	 * All CPUs are stuck in stop machine with interrupts disabled so
+	 * calling __irq_complete_move() would be completely pointless.
 	 */
 	raw_spin_lock(&vector_lock);
-	/* Clean out all offline cpus (including ourself) first. */
+	/*
+	 * Clean out all offline cpus (including the outgoing one) from the
+	 * old_domain mask.
+	 */
 	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
-	while (!cpumask_empty(data->old_domain)) {
+
+	/*
+	 * If move_in_progress is cleared and the old_domain mask is empty,
+	 * then there is nothing to cleanup. fixup_irqs() will take care of
+	 * the stale vectors on the outgoing cpu.
+	 */
+	if (!data->move_in_progress && cpumask_empty(data->old_domain)) {
 		raw_spin_unlock(&vector_lock);
-		raw_spin_unlock(&desc->lock);
-		cpu_relax();
-		raw_spin_lock(&desc->lock);
+		return;
+	}
+
+	/*
+	 * 1) The interrupt is in move_in_progress state. That means that we
+	 *    have not seen an interrupt since the io_apic was reprogrammed to
+	 *    the new vector.
+	 *
+	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
+	 *    have not been processed yet.
+	 */
+	if (data->move_in_progress) {
 		/*
-		 * Reevaluate apic_chip_data. It might have been cleared after
-		 * we dropped @desc->lock.
+		 * In theory there is a race:
+		 *
+		 * set_ioapic(new_vector) <-- Interrupt is raised before update
+		 *			      is effective, i.e. it's raised on
+		 *			      the old vector.
+		 *
+		 * So if the target cpu cannot handle that interrupt before
+		 * the old vector is cleaned up, we get a spurious interrupt
+		 * and in the worst case the ioapic irq line becomes stale.
+		 *
+		 * But in case of cpu hotplug this should be a non issue
+		 * because if the affinity update happens right before all
+		 * cpus rendevouz in stop machine, there is no way that the
+		 * interrupt can be blocked on the target cpu because all cpus
+		 * loops first with interrupts enabled in stop machine, so the
+		 * old vector is not yet cleaned up when the interrupt fires.
+		 *
+		 * So the only way to run into this issue is if the delivery
+		 * of the interrupt on the apic/system bus would be delayed
+		 * beyond the point where the target cpu disables interrupts
+		 * in stop machine. I doubt that it can happen, but at least
+		 * there is a theroretical chance. Virtualization might be
+		 * able to expose this, but AFAICT the IOAPIC emulation is not
+		 * as stupid as the real hardware.
+		 *
+		 * Anyway, there is nothing we can do about that at this point
+		 * w/o refactoring the whole fixup_irq() business completely.
+		 * We print at least the irq number and the old vector number,
+		 * so we have the necessary information when a problem in that
+		 * area arises.
 		 */
-		data = apic_chip_data(irqdata);
-		if (!data)
-			return;
-		raw_spin_lock(&vector_lock);
+		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
+			irqdata->irq, cfg->old_vector);
 	}
+	/*
+	 * If old_domain is not empty, then other cpus still have the irq
+	 * descriptor set in their vector array. Clean it up.
+	 */
+	for_each_cpu(cpu, data->old_domain)
+		per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED;
+
+	/* Cleanup the left overs of the (half finished) move */
+	cpumask_clear(data->old_domain);
+	data->move_in_progress = 0;
 	raw_spin_unlock(&vector_lock);
 }
 #endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a8816b325162..e2defc7593a4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -352,7 +352,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
-	unsigned int socket_id, core_complex_id;
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
@@ -370,10 +369,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	 if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
 		return;
 
-	socket_id	= (c->apicid >> bits) - 1;
-	core_complex_id	= (c->apicid & ((1 << bits) - 1)) >> 3;
-
-	per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+	per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
 #endif
 }
 
@@ -656,6 +652,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
 }
 
+#define MSR_AMD64_DE_CFG	0xC0011029
+
+static void init_amd_ln(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Apply erratum 665 fix unconditionally so machines without a BIOS
+	 * fix work.
+	 */
+	msr_set_bit(MSR_AMD64_DE_CFG, 31);
+}
+
 static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
@@ -713,6 +720,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 6:	   init_amd_k7(c); break;
 	case 0xf:  init_amd_k8(c); break;
 	case 0x10: init_amd_gh(c); break;
+	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	}
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c2b7522cbf35..637ca414d431 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -737,21 +737,20 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		identify_cpu_without_cpuid(c);
 
 	/* cyrix could have cpuid enabled via c_identify()*/
-	if (!have_cpuid_p())
-		return;
+	if (have_cpuid_p()) {
+		cpu_detect(c);
+		get_cpu_vendor(c);
+		get_cpu_cap(c);
 
-	cpu_detect(c);
-	get_cpu_vendor(c);
-	get_cpu_cap(c);
-
-	if (this_cpu->c_early_init)
-		this_cpu->c_early_init(c);
+		if (this_cpu->c_early_init)
+			this_cpu->c_early_init(c);
 
-	c->cpu_index = 0;
-	filter_cpuid_features(c, false);
+		c->cpu_index = 0;
+		filter_cpuid_features(c, false);
 
-	if (this_cpu->c_bsp_init)
-		this_cpu->c_bsp_init(c);
+		if (this_cpu->c_bsp_init)
+			this_cpu->c_bsp_init(c);
+	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 	fpu__init_system(c);
@@ -1130,7 +1129,7 @@ static __init int setup_disablecpuid(char *arg)
 {
 	int bit;
 
-	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+	if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
 		setup_clear_cpu_cap(bit);
 	else
 		return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 0a850100c594..2658e2af74ec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ];
 void mce_gen_pool_process(void)
 {
 	struct llist_node *head;
-	struct mce_evt_llist *node;
+	struct mce_evt_llist *node, *tmp;
 	struct mce *mce;
 
 	head = llist_del_all(&mce_event_llist);
@@ -37,7 +37,7 @@ void mce_gen_pool_process(void)
 		return;
 
 	head = llist_reverse_order(head);
-	llist_for_each_entry(node, head, llnode) {
+	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		mce = &node->mce;
 		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index e99b15077e94..2116176c1721 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -53,7 +53,7 @@ static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
 	"combined_unit",
-	"",
+	"decode_unit",
 	"northbridge",
 	"execution_unit",
 };
@@ -682,6 +682,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	const char *name = th_names[bank];
 	int err = 0;
 
+	if (!dev)
+		return -ENODEV;
+
 	if (is_shared_bank(bank)) {
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 2c5aaf8c2e2f..05538582a809 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
 
+	if (static_cpu_has(X86_FEATURE_HWP))
+		wrmsrl_safe(MSR_HWP_STATUS, 0);
+
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
 	/* Check for violation of core thermal thresholds*/
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ce47402eb2f9..ac8975a65280 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -555,10 +555,14 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 	cd.data = NULL;
 	cd.size = 0;
 
-	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data) {
+	/* try built-in microcode if no initrd */
+	if (!size) {
 		if (!load_builtin_intel_microcode(&cd))
 			return UCODE_ERROR;
+	} else {
+		cd = find_cpio_data(p, (void *)start, size, &offset);
+		if (!cd.data)
+			return UCODE_ERROR;
 	}
 
 	return get_matching_model_microcode(0, start, cd.data, cd.size,
@@ -694,7 +698,7 @@ int __init save_microcode_in_initrd_intel(void)
 	if (count == 0)
 		return ret;
 
-	copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count);
+	copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, get_initrd_start(), count);
 	ret = save_microcode(&mc_saved_data, mc_saved, count);
 	if (ret)
 		pr_err("Cannot save microcode patches from initrd.\n");
@@ -732,16 +736,20 @@ void __init load_ucode_intel_bsp(void)
 	struct boot_params *p;
 
 	p	= (struct boot_params *)__pa_nodebug(&boot_params);
-	start	= p->hdr.ramdisk_image;
 	size	= p->hdr.ramdisk_size;
 
-	_load_ucode_intel_bsp(
-			(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
-			(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
-			start, size);
+	/*
+	 * Set start only if we have an initrd image. We cannot use initrd_start
+	 * because it is not set that early yet.
+	 */
+	start	= (size ? p->hdr.ramdisk_image : 0);
+
+	_load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+			      (unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
+			      start, size);
 #else
-	start	= boot_params.hdr.ramdisk_image + PAGE_OFFSET;
 	size	= boot_params.hdr.ramdisk_size;
+	start	= (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0);
 
 	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size);
 #endif
@@ -752,20 +760,14 @@ void load_ucode_intel_ap(void)
 	struct mc_saved_data *mc_saved_data_p;
 	struct ucode_cpu_info uci;
 	unsigned long *mc_saved_in_initrd_p;
-	unsigned long initrd_start_addr;
 	enum ucode_state ret;
 #ifdef CONFIG_X86_32
-	unsigned long *initrd_start_p;
 
-	mc_saved_in_initrd_p =
-		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+	mc_saved_in_initrd_p = (unsigned long *)__pa_nodebug(mc_saved_in_initrd);
 	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
-	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
-	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
 #else
-	mc_saved_data_p = &mc_saved_data;
 	mc_saved_in_initrd_p = mc_saved_in_initrd;
-	initrd_start_addr = initrd_start;
+	mc_saved_data_p = &mc_saved_data;
 #endif
 
 	/*
@@ -777,7 +779,7 @@ void load_ucode_intel_ap(void)
 
 	collect_cpu_info_early(&uci);
 	ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
-			     initrd_start_addr, &uci);
+			     get_initrd_start_addr(), &uci);
 
 	if (ret != UCODE_OK)
 		return;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1bc4..83b5f7a323a9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,6 +30,7 @@
 #include <asm/apic.h>
 #include <asm/timer.h>
 #include <asm/reboot.h>
+#include <asm/nmi.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -152,6 +153,31 @@ static struct clocksource hyperv_cs = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static unsigned char hv_get_nmi_reason(void)
+{
+	return 0;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
+ * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * unknown NMI on the first CPU which gets it.
+ */
+static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
+{
+	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+
+	if (!unknown_nmi_panic)
+		return NMI_DONE;
+
+	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+		return NMI_HANDLED;
+
+	return NMI_DONE;
+}
+#endif
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -177,6 +203,9 @@ static void __init ms_hyperv_init_platform(void)
 		printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n",
 				lapic_timer_frequency);
 	}
+
+	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
+			     "hv_nmi_unknown");
 #endif
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
@@ -191,6 +220,13 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	mark_tsc_unstable("running on Hyper-V");
+
+	/*
+	 * Generation 2 instances don't support reading the NMI status from
+	 * 0x61 port.
+	 */
+	if (efi_enabled(EFI_BOOT))
+		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 3b533cf37c74..b5624fafa44a 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
 		pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
 }
 
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	prepare_set();
+
+	pat_init();
+
+	post_set();
+	local_irq_restore(flags);
+}
+
 /* Grab all of the MTRR state for this CPU into *state */
 bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
-	unsigned long flags;
 	unsigned lo, dummy;
 	unsigned int i;
 
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
 
 	mtrr_state_set = 1;
 
-	/* PAT setup for BP. We need to go through sync steps here */
-	local_irq_save(flags);
-	prepare_set();
-
-	pat_init();
-
-	post_set();
-	local_irq_restore(flags);
-
 	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f891b4750f04..fa77ac8291f0 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
 			/* BIOS may override */
 			__mtrr_enabled = get_mtrr_state();
 
+			if (mtrr_enabled())
+				mtrr_bp_pat_init();
+
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
 				mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
 		}
 	}
 
-	if (!mtrr_enabled())
+	if (!mtrr_enabled()) {
 		pr_info("MTRR: Disabled\n");
+
+		/*
+		 * PAT initialization relies on MTRR's rendezvous handler.
+		 * Skip PAT init until the handler can initialize both
+		 * features independently.
+		 */
+		pat_disable("MTRRs disabled, skipping PAT initialization too.");
+	}
 }
 
 void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884dcc433..6c7ced07d16d 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7c97df..5b2f2306fbcc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -67,7 +67,7 @@ u64 x86_perf_event_update(struct perf_event *event)
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
 	int idx = hwc->idx;
-	s64 delta;
+	u64 delta;
 
 	if (idx == INTEL_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -593,6 +593,19 @@ void x86_pmu_disable_all(void)
 	}
 }
 
+/*
+ * There may be PMI landing after enabled=0. The PMI hitting could be before or
+ * after disable_all.
+ *
+ * If PMI hits before disable_all, the PMU will be disabled in the NMI handler.
+ * It will not be re-enabled in the NMI handler again, because enabled=0. After
+ * handling the NMI, disable_all will be called, which will not change the
+ * state either. If PMI hits after disable_all, the PMU is already disabled
+ * before entering NMI handler. The NMI handler will not change the state
+ * either.
+ *
+ * So either situation is harmless.
+ */
 static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1983,8 +1996,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->mm)
-		load_mm_cr4(current->mm);
+	if (current->active_mm)
+		load_mm_cr4(current->active_mm);
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d0e35ebb2adb..ee70445fbb1f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -591,6 +591,7 @@ struct x86_pmu {
 			pebs_active	:1,
 			pebs_broken	:1;
 	int		pebs_record_size;
+	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
@@ -907,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void);
 
 void intel_pmu_lbr_init_skl(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e2a430021e46..5cc2242d77c6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cache_event_ids
 };
 
 /*
- * Use from PMIs where the LBRs are already disabled.
+ * Used from PMIs where the LBRs are already disabled.
+ *
+ * This function could be called consecutively. It is required to remain in
+ * disabled state if called consecutively.
+ *
+ * During consecutive calls, the same disable value will be written to related
+ * registers, so the PMU state remains unchanged. hw.state in
+ * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
+ * calls.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1840,6 +1848,16 @@ again:
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
 		handled++;
 		x86_pmu.drain_pebs(regs);
+		/*
+		 * There are cases where, even though, the PEBS ovfl bit is set
+		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their
+		 * overflow bits set for their counters. We must clear them
+		 * here because they have been processed as exact samples in
+		 * the drain_pebs() routine. They must not be processed again
+		 * in the for_each_bit_set() loop for regular samples below.
+		 */
+		status &= ~cpuc->pebs_enabled;
+		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 	}
 
 	/*
@@ -1885,7 +1903,10 @@ again:
 		goto again;
 
 done:
-	__intel_pmu_enable_all(0, true);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		__intel_pmu_enable_all(0, true);
+
 	/*
 	 * Only unmask the NMI after the overflow counters
 	 * have been reset. This avoids spurious NMIs on
@@ -3315,6 +3336,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
 
 		pr_cont("Nehalem events, ");
@@ -3377,6 +3399,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		pr_cont("Westmere events, ");
 		break;
 
@@ -3578,7 +3601,7 @@ __init int intel_pmu_init(void)
 				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
 			c->idxmsk64 &=
-				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+				~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
 			c->weight = hweight64(c->idxmsk64);
 		}
 	}
@@ -3613,7 +3636,7 @@ __init int intel_pmu_init(void)
 
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
-		x86_pmu.max_period = x86_pmu.cntval_mask;
+		x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
 		x86_pmu.perfctr = MSR_IA32_PMC0;
 		pr_cont("full-width counters, ");
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index a316ca96f1b6..fc704ed587e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid)
 	list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
 }
 
+static void cqm_cleanup(void)
+{
+	int i;
+
+	if (!cqm_rmid_ptrs)
+		return;
+
+	for (i = 0; i < cqm_max_rmid; i++)
+		kfree(cqm_rmid_ptrs[i]);
+
+	kfree(cqm_rmid_ptrs);
+	cqm_rmid_ptrs = NULL;
+}
+
 static int intel_cqm_setup_rmid_cache(void)
 {
 	struct cqm_rmid_entry *entry;
@@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void)
 	int r = 0;
 
 	nr_rmids = cqm_max_rmid + 1;
-	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+	cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
 				nr_rmids, GFP_KERNEL);
 	if (!cqm_rmid_ptrs)
 		return -ENOMEM;
@@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void)
 	mutex_unlock(&cache_mutex);
 
 	return 0;
-fail:
-	while (r--)
-		kfree(cqm_rmid_ptrs[r]);
 
-	kfree(cqm_rmid_ptrs);
+fail:
+	cqm_cleanup();
 	return -ENOMEM;
 }
 
@@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 
 	/*
 	 * Events that target same task are placed into the same cache group.
+	 * Mark it as a multi event group, so that we update ->count
+	 * for every event rather than just the group leader later.
 	 */
-	if (a->hw.target == b->hw.target)
+	if (a->hw.target == b->hw.target) {
+		b->hw.is_group_event = true;
 		return true;
+	}
 
 	/*
 	 * Are we an inherited event?
@@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 	bool conflict = false;
 	u32 rmid;
 
+	event->hw.is_group_event = false;
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
 
@@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 		return __perf_event_count(event);
 
 	/*
-	 * Only the group leader gets to report values. This stops us
+	 * Only the group leader gets to report values except in case of
+	 * multiple events in the same group, we still need to read the
+	 * other events.This stops us
 	 * reporting duplicate values to userspace, and gives us a clear
 	 * rule for which task gets to report the values.
 	 *
@@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 	 * specific packages - we forfeit that ability when we create
 	 * task events.
 	 */
-	if (!cqm_group_leader(event))
+	if (!cqm_group_leader(event) && !event->hw.is_group_event)
 		return 0;
 
 	/*
@@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = {
 
 static int __init intel_cqm_init(void)
 {
-	char *str, scale[20];
+	char *str = NULL, scale[20];
 	int i, cpu, ret;
 
 	if (!x86_match_cpu(intel_cqm_match))
@@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void)
 		cqm_pick_event_reader(i);
 	}
 
-	__perf_cpu_notifier(intel_cqm_cpu_notifier);
-
 	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
-	if (ret)
+	if (ret) {
 		pr_err("Intel CQM perf registration failed: %d\n", ret);
-	else
-		pr_info("Intel CQM monitoring enabled\n");
+		goto out;
+	}
+
+	pr_info("Intel CQM monitoring enabled\n");
 
+	/*
+	 * Register the hot cpu notifier once we are sure cqm
+	 * is enabled to avoid notifier leak.
+	 */
+	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 out:
 	cpu_notifier_register_done();
+	if (ret) {
+		kfree(str);
+		cqm_cleanup();
+	}
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5db1c7755548..1e7de3cefc9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu)
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
 
-	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
 
 	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
 	ds->pebs_index = ds->pebs_buffer_base;
@@ -1101,6 +1110,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	void *at;
 	u64 pebs_status;
 
+	/*
+	 * fmt0 does not have a status bitfield (does not use
+	 * perf_record_nhm format)
+	 */
+	if (x86_pmu.intel_cap.pebs_format < 1)
+		return base;
+
 	if (base == NULL)
 		return NULL;
 
@@ -1186,7 +1202,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	if (!event->attr.precise_ip)
 		return;
 
-	n = (top - at) / x86_pmu.pebs_record_size;
+	n = top - at;
 	if (n <= 0)
 		return;
 
@@ -1296,6 +1312,7 @@ void __init intel_ds_init(void)
 
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;
@@ -1304,6 +1321,14 @@ void __init intel_ds_init(void)
 		case 0:
 			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			/*
+			 * Using >PAGE_SIZE buffers makes the WRMSR to
+			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+			 * mysteriously hang on Core2.
+			 *
+			 * As a workaround, we don't do this.
+			 */
+			x86_pmu.pebs_buffer_size = PAGE_SIZE;
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 659f01e165d5..2cdae69d7e0b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -153,7 +153,7 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	 */
 	if (cpuc->lbr_sel)
 		lbr_select = cpuc->lbr_sel->config;
-	if (!pmi)
+	if (!pmi && cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, lbr_select);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
@@ -410,6 +410,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
 		cpuc->lbr_entries[i].mispred	= 0;
 		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].in_tx	= 0;
+		cpuc->lbr_entries[i].abort	= 0;
+		cpuc->lbr_entries[i].cycles	= 0;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
@@ -429,8 +432,10 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	int out = 0;
 	int num = x86_pmu.lbr_nr;
 
-	if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-		num = tos;
+	if (cpuc->lbr_sel) {
+		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
+			num = tos;
+	}
 
 	for (i = 0; i < num; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 868e1194337f..49e35d003b74 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -694,6 +694,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 
 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
 	/* how many pages till the STOP marker */
@@ -718,6 +719,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 5b0c232d1ee6..b931095e86d4 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -263,7 +263,9 @@ again:
 		goto again;
 
 done:
-	knc_pmu_enable_all(0);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		knc_pmu_enable_all(0);
 
 	return handled;
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 569c1e4f96fe..52a2526c3fbe 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -753,7 +753,7 @@ u64 __init early_reserve_e820(u64 size, u64 align)
 /*
  * Find the highest page frame number we have available
  */
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 {
 	int i;
 	unsigned long last_pfn = 0;
@@ -764,11 +764,7 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
 		unsigned long start_pfn;
 		unsigned long end_pfn;
 
-		/*
-		 * Persistent memory is accounted as ram for purposes of
-		 * establishing max_pfn and mem_map.
-		 */
-		if (ei->type != E820_RAM && ei->type != E820_PRAM)
+		if (ei->type != type)
 			continue;
 
 		start_pfn = ei->addr >> PAGE_SHIFT;
@@ -793,12 +789,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
 }
 unsigned long __init e820_end_of_ram_pfn(void)
 {
-	return e820_end_pfn(MAX_ARCH_PFN);
+	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
 }
 
 unsigned long __init e820_end_of_low_ram_pfn(void)
 {
-	return e820_end_pfn(1UL << (32-PAGE_SHIFT));
+	return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM);
 }
 
 static void early_panic(char *msg)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index db9a675e751b..a257d6077d1b 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -11,7 +11,11 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/pci_ids.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_regs.h>
 #include <drm/i915_drm.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
@@ -21,6 +25,9 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/irq_remapping.h>
+#include <asm/early_ioremap.h>
+
+#define dev_err(msg)  pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func)
 #ifdef CONFIG_ACPI
 #ifdef CONFIG_X86_IO_APIC
 	/*
+	 * Only applies to Nvidia root ports (bus 0) and not to
+	 * Nvidia graphics cards with PCI ports on secondary buses.
+	 */
+	if (num)
+		return;
+
+	/*
 	 * All timer overrides on Nvidia are
 	 * wrong unless HPET is enabled.
 	 * Unfortunately that's not true on many Asus boards.
@@ -317,12 +331,11 @@ static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_si
 
 static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size)
 {
-	/*
-	 * FIXME is the graphics stolen memory region
-	 * always at TOUD? Ie. is it always the last
-	 * one to be allocated by the BIOS?
-	 */
-	return read_pci_config_16(0, 0, 0, I865_TOUD) << 16;
+	u16 toud = 0;
+
+	toud = read_pci_config_16(0, 0, 0, I865_TOUD);
+
+	return (phys_addr_t)(toud << 16) + i845_tseg_size();
 }
 
 static size_t __init i830_stolen_size(int num, int slot, int func)
@@ -589,6 +602,61 @@ static void __init force_disable_hpet(int num, int slot, int func)
 #endif
 }
 
+#define BCM4331_MMIO_SIZE	16384
+#define BCM4331_PM_CAP		0x40
+#define bcma_aread32(reg)	ioread32(mmio + 1 * BCMA_CORE_SIZE + reg)
+#define bcma_awrite32(reg, val)	iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg)
+
+static void __init apple_airport_reset(int bus, int slot, int func)
+{
+	void __iomem *mmio;
+	u16 pmcsr;
+	u64 addr;
+	int i;
+
+	if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc."))
+		return;
+
+	/* Card may have been put into PCI_D3hot by grub quirk */
+	pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+
+	if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+		write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr);
+		mdelay(10);
+
+		pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+			dev_err("Cannot power up Apple AirPort card\n");
+			return;
+		}
+	}
+
+	addr  =      read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+	addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32;
+	addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+	mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
+	if (!mmio) {
+		dev_err("Cannot iomap Apple AirPort card\n");
+		return;
+	}
+
+	pr_info("Resetting Apple AirPort card (left enabled by EFI)\n");
+
+	for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++)
+		udelay(10);
+
+	bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET);
+	bcma_aread32(BCMA_RESET_CTL);
+	udelay(1);
+
+	bcma_awrite32(BCMA_RESET_CTL, 0);
+	bcma_aread32(BCMA_RESET_CTL);
+	udelay(10);
+
+	early_iounmap(mmio, BCM4331_MMIO_SIZE);
+}
 
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
@@ -602,12 +670,6 @@ struct chipset {
 	void (*f)(int num, int slot, int func);
 };
 
-/*
- * Only works for devices on the root bus. If you add any devices
- * not on bus 0 readd another loop level in early_quirks(). But
- * be careful because at least the Nvidia quirk here relies on
- * only matching on bus 0.
- */
 static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -637,9 +699,13 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
+	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
 };
 
+static void __init early_pci_scan_bus(int bus);
+
 /**
  * check_dev_quirk - apply early quirks to a given PCI device
  * @num: bus number
@@ -648,7 +714,7 @@ static struct chipset early_qrk[] __initdata = {
  *
  * Check the vendor & device ID against the early quirks table.
  *
- * If the device is single function, let early_quirks() know so we don't
+ * If the device is single function, let early_pci_scan_bus() know so we don't
  * poke at this device again.
  */
 static int __init check_dev_quirk(int num, int slot, int func)
@@ -657,6 +723,7 @@ static int __init check_dev_quirk(int num, int slot, int func)
 	u16 vendor;
 	u16 device;
 	u8 type;
+	u8 sec;
 	int i;
 
 	class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
@@ -684,25 +751,36 @@ static int __init check_dev_quirk(int num, int slot, int func)
 
 	type = read_pci_config_byte(num, slot, func,
 				    PCI_HEADER_TYPE);
+
+	if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+		sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
+		if (sec > num)
+			early_pci_scan_bus(sec);
+	}
+
 	if (!(type & 0x80))
 		return -1;
 
 	return 0;
 }
 
-void __init early_quirks(void)
+static void __init early_pci_scan_bus(int bus)
 {
 	int slot, func;
 
-	if (!early_pci_allowed())
-		return;
-
 	/* Poor man's PCI discovery */
-	/* Only scan the root bus */
 	for (slot = 0; slot < 32; slot++)
 		for (func = 0; func < 8; func++) {
 			/* Only probe function 0 on single fn devices */
-			if (check_dev_quirk(0, slot, func))
+			if (check_dev_quirk(bus, slot, func))
 				break;
 		}
 }
+
+void __init early_quirks(void)
+{
+	if (!early_pci_allowed())
+		return;
+
+	early_pci_scan_bus(0);
+}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index be39b5fde4b9..1011c05b1bd5 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -96,6 +96,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index eb6bd34582c6..1b96bfe09d42 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -977,6 +977,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	/*
+	 * When resuming from suspend-to-ram, this function can be indirectly
+	 * called from early CPU startup code while the CPU is in real mode,
+	 * which would fail miserably.  Make sure the stack pointer is a
+	 * virtual address.
+	 *
+	 * This check isn't as accurate as virt_addr_valid(), but it should be
+	 * good enough for this purpose, and it's fast.
+	 */
+	if (unlikely((long)__builtin_frame_address(0) >= 0))
+		return;
+
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index f129a9af6357..b6b0077da1af 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 6bc9ae24b6d2..8f1a3f443f7d 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -571,7 +571,7 @@ early_idt_handler_common:
 	movl %eax,%ds
 	movl %eax,%es
 
-	cmpl $(__KERNEL_CS),32(%esp)
+	cmpw $(__KERNEL_CS),32(%esp)
 	jne 10f
 
 	leal 28(%esp),%eax	# Pointer to %eip
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b8e6ff5cd5d0..acc9b8f19ca8 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -351,6 +351,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 	} else {
 		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
 
+		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 		disable_irq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 37dae792dbbe..589b3193f102 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 SYSCALL_DEFINE1(iopl, unsigned int, level)
 {
 	struct pt_regs *regs = current_pt_regs();
-	unsigned int old = (regs->flags >> 12) & 3;
 	struct thread_struct *t = &current->thread;
 
+	/*
+	 * Careful: the IOPL bits in regs->flags are undefined under Xen PV
+	 * and changing them has no effect.
+	 */
+	unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT;
+
 	if (level > 3)
 		return -EINVAL;
 	/* Trying to gain more privileges? */
@@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level)
 		if (!capable(CAP_SYS_RAWIO))
 			return -EPERM;
 	}
-	regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12);
-	t->iopl = level << 12;
+	regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
+		(level << X86_EFLAGS_IOPL_BIT);
+	t->iopl = level << X86_EFLAGS_IOPL_BIT;
 	set_iopl_mask(t->iopl);
 
 	return 0;
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..d688826e5736 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6cc873..99d293ea2b49 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -163,12 +163,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -413,7 +413,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
@@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * normal page fault.
 		 */
 		regs->ip = (unsigned long)cur->addr;
+		/*
+		 * Trap flag (TF) has been set here because this fault
+		 * happened where the single stepping will be done.
+		 * So clear it by resetting the current kprobe:
+		 */
+		regs->flags &= ~X86_EFLAGS_TF;
+
+		/*
+		 * If the TF flag was set before the kprobe hit,
+		 * don't touch it:
+		 */
 		regs->flags |= kcb->kprobe_old_flags;
+
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7b3b9d15c47a..c9d488f3e4cd 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -177,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 47190bd399e7..32187f8a49b4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_wait(&n.wq, &wait);
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 87e1762e2bca..5d9afbcb6074 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -180,7 +180,8 @@ GLOBAL(ftrace_graph_call)
 	jmp ftrace_stub
 #endif
 
-GLOBAL(ftrace_stub)
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
 	retq
 END(ftrace_caller)
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c2130aef3f9d..f534a0e3af53 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -55,12 +55,12 @@ asm (".pushsection .entry.text, \"ax\"\n"
      ".popsection");
 
 /* identity function, which can be inlined */
-u32 _paravirt_ident_32(u32 x)
+u32 notrace _paravirt_ident_32(u32 x)
 {
 	return x;
 }
 
-u64 _paravirt_ident_64(u64 x)
+u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 0497f719977d..c055e9a4e547 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 	/* were we called with bad_dma_address? */
 	badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) {
+	if (unlikely(dma_addr < badend)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e835d263a33b..4cbb60fbff3e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -48,6 +48,7 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
+#include <asm/xen/hypervisor.h>
 
 asmlinkage extern void ret_from_fork(void);
 
@@ -411,6 +412,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
 		__switch_to_xtra(prev_p, next_p, tss);
 
+#ifdef CONFIG_XEN
+	/*
+	 * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
+	 * current_pt_regs()->flags may not match the current task's
+	 * intended IOPL.  We need to switch it manually.
+	 */
+	if (unlikely(static_cpu_has(X86_FEATURE_XENPV) &&
+		     prev->iopl != next->iopl))
+		xen_set_iopl_mask(next->iopl);
+#endif
+
 	if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
 		/*
 		 * AMD CPUs have a misfeature: SYSRET sets the SS selector but
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 558f50edebca..479a409ddac8 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -188,8 +188,8 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs)
 		return sp;
 
 	prev_esp = (u32 *)(context);
-	if (prev_esp)
-		return (unsigned long)prev_esp;
+	if (*prev_esp)
+		return (unsigned long)*prev_esp;
 
 	return (unsigned long)regs;
 }
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d229a58..bf0ce75735b0 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -66,6 +66,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 
 	do {
 		version = __pvclock_read_cycles(src, &ret, &flags);
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	return flags & valid_flags;
@@ -80,6 +82,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 
 	do {
 		version = __pvclock_read_cycles(src, &ret, &flags);
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d2bbe343fda7..e67b834279b2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1048,6 +1048,13 @@ void __init setup_arch(char **cmdline_p)
 	if (mtrr_trim_uncached_memory(max_pfn))
 		max_pfn = e820_end_of_ram_pfn();
 
+	/*
+	 * This call is required when the CPU does not support PAT. If
+	 * mtrr_bp_init() invoked it already via pat_init() the call has no
+	 * effect.
+	 */
+	init_cache_modes();
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 10e0272d789a..136ad7c1ce7b 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -143,7 +143,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (end - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -186,7 +186,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index b285d4e8c68e..5da924bbf0a0 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id)
 					continue;
 				for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 					resource_size_t start, end;
+					unsigned long flags;
+
+					flags = pci_resource_flags(dev, i);
+					if (!(flags & IORESOURCE_MEM))
+						continue;
+
+					if (flags & IORESOURCE_UNSET)
+						continue;
+
+					if (pci_resource_len(dev, i) == 0)
+						continue;
 
 					start = pci_resource_start(dev, i);
-					if (start == 0)
-						break;
 					end = pci_resource_end(dev, i);
 					if (screen_info.lfb_base >= start &&
 					    screen_info.lfb_base < end) {
 						found_bar = 1;
+						break;
 					}
 				}
 			}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ade185a46b1d..679302c312f8 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -109,6 +109,12 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 	preempt_count_dec();
 }
 
+/*
+ * In IST context, we explicitly disable preemption.  This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
 void ist_enter(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
@@ -123,13 +129,7 @@ void ist_enter(struct pt_regs *regs)
 		rcu_nmi_enter();
 	}
 
-	/*
-	 * We are atomic because we're on the IST stack; or we're on
-	 * x86_32, in which case we still shouldn't schedule; or we're
-	 * on x86_64 and entered from user mode, in which case we're
-	 * still atomic unless ist_begin_non_atomic is called.
-	 */
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 
 	/* This code is a bit fragile.  Test it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -137,7 +137,7 @@ void ist_enter(struct pt_regs *regs)
 
 void ist_exit(struct pt_regs *regs)
 {
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 
 	if (!user_mode(regs))
 		rcu_nmi_exit();
@@ -168,7 +168,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	BUG_ON((unsigned long)(current_top_of_stack() -
 			       current_stack_pointer()) >= THREAD_SIZE);
 
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 }
 
 /**
@@ -178,7 +178,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
  */
 void ist_end_non_atomic(void)
 {
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 }
 
 static nokprobe_inline int
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 92ae6acac8a7..6aa0f4d9eea6 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void)
 
 	if (freq_desc_tables[cpu_index].msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
-		ratio = (lo >> 8) & 0x1f;
+		ratio = (lo >> 8) & 0xff;
 	} else {
 		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 		ratio = (hi >> 8) & 0x1f;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index bf4db6eaec8f..c6aace2bbe08 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 		*cursor &= 0xfe;
 	}
 	/*
-	 * Similar treatment for VEX3 prefix.
-	 * TODO: add XOP/EVEX treatment when insn decoder supports them
+	 * Similar treatment for VEX3/EVEX prefix.
+	 * TODO: add XOP treatment when insn decoder supports them
 	 */
-	if (insn->vex_prefix.nbytes == 3) {
+	if (insn->vex_prefix.nbytes >= 3) {
 		/*
 		 * vex2:     c5    rvvvvLpp   (has no b bit)
 		 * vex3/xop: c4/8f rxbmmmmm wvvvvLpp
 		 * evex:     62    rxbR00mm wvvvv1pp zllBVaaa
-		 *   (evex will need setting of both b and x since
-		 *   in non-sib encoding evex.x is 4th bit of MODRM.rm)
-		 * Setting VEX3.b (setting because it has inverted meaning):
+		 * Setting VEX3.b (setting because it has inverted meaning).
+		 * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+		 * is the 4th bit of MODRM.rm, and needs the same treatment.
+		 * For VEX3-encoded insns, VEX3.x value has no effect in
+		 * non-SIB encoding, the change is superfluous but harmless.
 		 */
 		cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
-		*cursor |= 0x20;
+		*cursor |= 0x60;
 	}
 
 	/*
@@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 
 	reg = MODRM_REG(insn);	/* Fetch modrm.reg */
 	reg2 = 0xff;		/* Fetch vex.vvvv */
-	if (insn->vex_prefix.nbytes == 2)
-		reg2 = insn->vex_prefix.bytes[1];
-	else if (insn->vex_prefix.nbytes == 3)
+	if (insn->vex_prefix.nbytes)
 		reg2 = insn->vex_prefix.bytes[2];
 	/*
-	 * TODO: add XOP, EXEV vvvv reading.
+	 * TODO: add XOP vvvv reading.
 	 *
 	 * vex.vvvv field is in bits 6-3, bits are inverted.
 	 * But in 32-bit mode, high-order bit may be ignored.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6525e926f566..83d6369c45f5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -46,11 +46,18 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 	return ret;
 }
 
+bool kvm_mpx_supported(void)
+{
+	return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
+		 && kvm_x86_ops->mpx_supported());
+}
+EXPORT_SYMBOL_GPL(kvm_mpx_supported);
+
 u64 kvm_supported_xcr0(void)
 {
 	u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0;
 
-	if (!kvm_x86_ops->mpx_supported())
+	if (!kvm_mpx_supported())
 		xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
 
 	return xcr0;
@@ -97,7 +104,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+	vcpu->arch.eager_fpu = use_eager_fpu();
 	if (vcpu->arch.eager_fpu)
 		kvm_x86_ops->fpu_activate(vcpu);
 
@@ -295,7 +302,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
 	unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
-	unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0;
+	unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
 	unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
 
 	/* cpuid 1.edx */
@@ -509,6 +516,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			do_cpuid_1_ent(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_supported_word10_x86_features;
+				cpuid_mask(&entry[i].eax, 10);
 				entry[i].ebx = 0;
 				if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
 					entry[i].ebx =
@@ -736,18 +744,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that
@@ -817,12 +827,6 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 	if (!best)
 		best = check_cpuid_limit(vcpu, function, index);
 
-	/*
-	 * Perfmon not yet supported for L2 guest.
-	 */
-	if (is_guest_mode(vcpu) && function == 0xa)
-		best = NULL;
-
 	if (best) {
 		*eax = best->eax;
 		*ebx = best->ebx;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 3f5c48ddba45..d1534feefcfe 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -4,6 +4,7 @@
 #include "x86.h"
 
 int kvm_update_cpuid(struct kvm_vcpu *vcpu);
+bool kvm_mpx_supported(void);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
 int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
@@ -134,20 +135,20 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
 
-static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
-	return best && (best->ebx & bit(X86_FEATURE_MPX));
+	return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
 }
 
-static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
-	return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
+	return best && (best->ebx & bit(X86_FEATURE_MPX));
 }
 
 static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b9b09fec173b..04b2f3cad7ba 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -172,6 +172,7 @@
 #define NearBranch  ((u64)1 << 52)  /* Near branches */
 #define No16	    ((u64)1 << 53)  /* No 16 bit operand */
 #define IncSP       ((u64)1 << 54)  /* SP is incremented before ModRM calc */
+#define Aligned16   ((u64)1 << 55)  /* Aligned to 16 byte boundary (e.g. FXSAVE) */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -434,6 +435,26 @@ FOP_END;
 FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
 FOP_END;
 
+/*
+ * XXX: inoutclob user must know where the argument is being expanded.
+ *      Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault.
+ */
+#define asm_safe(insn, inoutclob...) \
+({ \
+	int _fault = 0; \
+ \
+	asm volatile("1:" insn "\n" \
+	             "2:\n" \
+	             ".pushsection .fixup, \"ax\"\n" \
+	             "3: movl $1, %[_fault]\n" \
+	             "   jmp  2b\n" \
+	             ".popsection\n" \
+	             _ASM_EXTABLE(1b, 3b) \
+	             : [_fault] "+qm"(_fault) inoutclob ); \
+ \
+	_fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
+})
+
 static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
 				    enum x86_intercept intercept,
 				    enum x86_intercept_stage stage)
@@ -620,21 +641,24 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
  * depending on whether they're AVX encoded or not.
  *
  * Also included is CMPXCHG16B which is not a vector instruction, yet it is
- * subject to the same check.
+ * subject to the same check.  FXSAVE and FXRSTOR are checked here too as their
+ * 512 bytes of data must be aligned to a 16 byte boundary.
  */
-static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
 {
 	if (likely(size < 16))
-		return false;
+		return 1;
 
 	if (ctxt->d & Aligned)
-		return true;
+		return size;
 	else if (ctxt->d & Unaligned)
-		return false;
+		return 1;
 	else if (ctxt->d & Avx)
-		return false;
+		return 1;
+	else if (ctxt->d & Aligned16)
+		return 16;
 	else
-		return true;
+		return size;
 }
 
 static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
@@ -692,7 +716,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 		}
 		break;
 	}
-	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+	if (la & (insn_alignment(ctxt, size) - 1))
 		return emulate_gp(ctxt, 0);
 	return X86EMUL_CONTINUE;
 bad:
@@ -779,6 +803,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
 }
 
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+			       struct segmented_address addr,
+			       void *data,
+			       unsigned int size)
+{
+	int rc;
+	ulong linear;
+
+	rc = linearize(ctxt, addr, size, true, &linear);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
 /*
  * Prefetch the remaining bytes of the instruction without crossing page
  * boundary if they are not in fetch_cache yet.
@@ -1532,7 +1570,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				    &ctxt->exception);
 }
 
-/* Does not support long mode */
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, int seg, u8 cpl,
 				     enum x86_transfer_type transfer,
@@ -1569,20 +1606,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 	rpl = selector & 3;
 
-	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
-	if ((seg == VCPU_SREG_CS
-	     || (seg == VCPU_SREG_SS
-		 && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
-	     || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
-
 	/* TR should be in GDT only */
 	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
 		goto exception;
 
-	if (null_selector) /* for NULL selector skip all following checks */
+	/* NULL selector is not valid for TR, CS and (except for long mode) SS */
+	if (null_selector) {
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+			goto exception;
+
+		if (seg == VCPU_SREG_SS) {
+			if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+				goto exception;
+
+			/*
+			 * ctxt->ops->set_segment expects the CPL to be in
+			 * SS.DPL, so fake an expand-up 32-bit data segment.
+			 */
+			seg_desc.type = 3;
+			seg_desc.p = 1;
+			seg_desc.s = 1;
+			seg_desc.dpl = cpl;
+			seg_desc.d = 1;
+			seg_desc.g = 1;
+		}
+
+		/* Skip all following checks */
 		goto load;
+	}
 
 	ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
 	if (ret != X86EMUL_CONTINUE)
@@ -1698,6 +1749,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				   u16 selector, int seg)
 {
 	u8 cpl = ctxt->ops->cpl(ctxt);
+
+	/*
+	 * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+	 * they can load it at CPL<3 (Intel's manual says only LSS can,
+	 * but it's wrong).
+	 *
+	 * However, the Intel manual says that putting IST=1/DPL=3 in
+	 * an interrupt gate will result in SS=3 (the AMD manual instead
+	 * says it doesn't), so allow SS=3 in __load_segment_descriptor
+	 * and only forbid it here.
+	 */
+	if (seg == VCPU_SREG_SS && selector == 3 &&
+	    ctxt->mode == X86EMUL_MODE_PROT64)
+		return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
 	return __load_segment_descriptor(ctxt, selector, seg, cpl,
 					 X86_TRANSFER_NONE, NULL);
 }
@@ -2093,16 +2159,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
 static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
-	unsigned short sel, old_sel;
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
+	unsigned short sel;
+	struct desc_struct new_desc;
 	u8 cpl = ctxt->ops->cpl(ctxt);
 
-	/* Assignment of RIP may only fail in 64-bit mode */
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
-				 VCPU_SREG_CS);
-
 	memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
 
 	rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
@@ -2112,12 +2172,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 		return rc;
 
 	rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		/* assigning eip failed; restore the old cs */
-		ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
-		return rc;
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 
@@ -2177,14 +2235,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long eip, cs;
-	u16 old_cs;
 	int cpl = ctxt->ops->cpl(ctxt);
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
-
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
-				 VCPU_SREG_CS);
+	struct desc_struct new_desc;
 
 	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2201,10 +2253,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = assign_eip_far(ctxt, eip, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 
@@ -2479,7 +2531,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	u64 smbase;
 	int ret;
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
 	/*
@@ -2528,11 +2580,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
 		ctxt->ops->set_nmi_mask(ctxt, false);
 
-	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
-	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3660,8 +3712,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt,
 	}
 	/* Disable writeback. */
 	ctxt->dst.type = OP_NONE;
-	return segmented_write(ctxt, ctxt->dst.addr.mem,
-			       &desc_ptr, 2 + ctxt->op_bytes);
+	return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+				   &desc_ptr, 2 + ctxt->op_bytes);
 }
 
 static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3844,6 +3896,131 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int check_fxsr(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax = 1, ebx, ecx = 0, edx;
+
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	if (!(edx & FFL(FXSR)))
+		return emulate_ud(ctxt);
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	/*
+	 * Don't emulate a case that should never be hit, instead of working
+	 * around a lack of fxsave64/fxrstor64 on old compilers.
+	 */
+	if (ctxt->mode >= X86EMUL_MODE_PROT64)
+		return X86EMUL_UNHANDLEABLE;
+
+	return X86EMUL_CONTINUE;
+}
+
+/*
+ * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
+ *  1) 16 bit mode
+ *  2) 32 bit mode
+ *     - like (1), but FIP and FDP (foo) are only 16 bit.  At least Intel CPUs
+ *       preserve whole 32 bit values, though, so (1) and (2) are the same wrt.
+ *       save and restore
+ *  3) 64-bit mode with REX.W prefix
+ *     - like (2), but XMM 8-15 are being saved and restored
+ *  4) 64-bit mode without REX.W prefix
+ *     - like (3), but FIP and FDP are 64 bit
+ *
+ * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the
+ * desired result.  (4) is not emulated.
+ *
+ * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS
+ * and FPU DS) should match.
+ */
+static int em_fxsave(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	size_t size;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	ctxt->ops->get_fpu(ctxt);
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
+		size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
+	else
+		size = offsetof(struct fxregs_state, xmm_space[0]);
+
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+}
+
+static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
+		struct fxregs_state *new)
+{
+	int rc = X86EMUL_CONTINUE;
+	struct fxregs_state old;
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	/*
+	 * 64 bit host will restore XMM 8-15, which is not correct on non-64
+	 * bit guests.  Load the current values in order to preserve 64 bit
+	 * XMMs after fxrstor.
+	 */
+#ifdef CONFIG_X86_64
+	/* XXX: accessing XMM 8-15 very awkwardly */
+	memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
+#endif
+
+	/*
+	 * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
+	 * does save and restore MXCSR.
+	 */
+	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
+		memcpy(new->xmm_space, old.xmm_space, 8 * 16);
+
+	return rc;
+}
+
+static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (fx_state.mxcsr >> 16)
+		return emulate_gp(ctxt, 0);
+
+	ctxt->ops->get_fpu(ctxt);
+
+	if (ctxt->mode < X86EMUL_MODE_PROT64)
+		rc = fxrstor_fixup(ctxt, &fx_state);
+
+	if (rc == X86EMUL_CONTINUE)
+		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	return rc;
+}
+
 static bool valid_cr(int nr)
 {
 	switch (nr) {
@@ -4196,7 +4373,9 @@ static const struct gprefix pfx_0f_ae_7 = {
 };
 
 static const struct group_dual group15 = { {
-	N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7),
+	I(ModRM | Aligned16, em_fxsave),
+	I(ModRM | Aligned16, em_fxrstor),
+	N, N, N, N, N, GP(0, &pfx_0f_ae_7),
 }, {
 	N, N, N, N, N, N, N, N,
 } };
@@ -5033,7 +5212,7 @@ done_prefixes:
 	/* Decode and fetch the destination operand: register or memory. */
 	rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
 
-	if (ctxt->rip_relative)
+	if (ctxt->rip_relative && likely(ctxt->memopp))
 		ctxt->memopp->addr.mem.ea = address_mask(ctxt,
 					ctxt->memopp->addr.mem.ea + ctxt->_eip);
 
@@ -5068,21 +5247,13 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 
 static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
-	bool fault = false;
+	int rc;
 
 	ctxt->ops->get_fpu(ctxt);
-	asm volatile("1: fwait \n\t"
-		     "2: \n\t"
-		     ".pushsection .fixup,\"ax\" \n\t"
-		     "3: \n\t"
-		     "movb $1, %[fault] \n\t"
-		     "jmp 2b \n\t"
-		     ".popsection \n\t"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [fault]"+qm"(fault));
+	rc = asm_safe("fwait");
 	ctxt->ops->put_fpu(ctxt);
 
-	if (unlikely(fault))
+	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
 
 	return X86EMUL_CONTINUE;
@@ -5125,6 +5296,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	int rc = X86EMUL_CONTINUE;
 	int saved_dst_type = ctxt->dst.type;
+	unsigned emul_flags;
 
 	ctxt->mem_read.pos = 0;
 
@@ -5139,6 +5311,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		goto done;
 	}
 
+	emul_flags = ctxt->ops->get_hflags(ctxt);
 	if (unlikely(ctxt->d &
 		     (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
 		if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
@@ -5172,7 +5345,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5201,7 +5374,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5255,7 +5428,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 special_insn:
 
-	if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+	if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index b0ea42b78ccd..ab5318727579 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 		 * PIC is being reset.  Handle it gracefully here
 		 */
 		atomic_inc(&ps->pending);
-	else if (value > 0)
+	else if (value > 0 && ps->reinject)
 		/* in this case, we had multiple outstanding pit interrupts
 		 * that we needed to inject.  Reinject
 		 */
@@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work)
 	 * last one has been acked.
 	 */
 	spin_lock(&ps->inject_lock);
-	if (ps->irq_ack) {
+	if (!ps->reinject)
+		inject = 1;
+	else if (ps->irq_ack) {
 		ps->irq_ack = 0;
 		inject = 1;
 	}
@@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
 	struct kvm_pit *pt = ps->kvm->arch.vpit;
 
-	if (ps->reinject || !atomic_read(&ps->pending)) {
+	if (ps->reinject)
 		atomic_inc(&ps->pending);
-		queue_kthread_work(&pt->worker, &pt->expired);
-	}
+
+	queue_kthread_work(&pt->worker, &pt->expired);
 
 	if (ps->is_periodic) {
 		hrtimer_add_expires_ns(&ps->timer, ps->period);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 88d0a92d3f94..3aab53f8cad2 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -580,7 +580,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->irr = 0;
 	ioapic->irr_delivered = 0;
 	ioapic->id = 0;
-	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+	memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi));
 	rtc_irq_eoi_tracking_reset(ioapic);
 }
 
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 84b96d319909..d09544e826f6 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -38,6 +38,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   bool line_status)
 {
 	struct kvm_pic *pic = pic_irqchip(kvm);
+
+	/*
+	 * XXX: rejecting pic routes when pic isn't in use would be better,
+	 * but the default routing table is installed while kvm->arch.vpic is
+	 * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE.
+	 */
+	if (!pic)
+		return -1;
+
 	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
 }
 
@@ -46,6 +55,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 			      bool line_status)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	if (!ioapic)
+		return -1;
+
 	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
 				line_status);
 }
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4d30b865be30..1c96f09367ae 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2187,3 +2187,9 @@ void kvm_lapic_init(void)
 	jump_label_rate_limit(&apic_hw_disabled, HZ);
 	jump_label_rate_limit(&apic_sw_disabled, HZ);
 }
+
+void kvm_lapic_exit(void)
+{
+	static_key_deferred_flush(&apic_hw_disabled);
+	static_key_deferred_flush(&apic_sw_disabled);
+}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index fde8e35d5850..eb418fd670ff 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -95,6 +95,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
 void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
 
 static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
 {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8eb8a934b531..1049c3c9b877 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3433,12 +3433,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3454,7 +3457,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 55ffb7b0f95e..e60fc80f8a9c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -74,6 +74,7 @@ enum {
 int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 3f8c732117ec..0149ac59c273 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr)
 	case MSR_MTRRdefType:
 	case MSR_IA32_CR_PAT:
 		return true;
-	case 0x2f8:
-		return true;
 	}
 	return false;
 }
@@ -541,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
 
 	iter->fixed = false;
 	iter->start_max = iter->start;
+	iter->range = NULL;
 	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
 
 	__mtrr_lookup_var_next(iter);
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index ab38af4f4947..23a7c7ba377a 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
-	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0958fa2b7cb7..b12391119ce8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -408,6 +408,7 @@ struct nested_vmx {
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
+	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 	/*
@@ -862,7 +863,6 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
-static bool vmx_mpx_supported(void);
 static bool vmx_xsaves_supported(void);
 static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
@@ -1246,10 +1246,10 @@ static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
 }
 
-static inline bool is_exception(u32 intr_info)
+static inline bool is_nmi(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
+		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
 }
 
 static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
@@ -2263,7 +2263,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
@@ -2540,7 +2540,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
 
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
 	/* We support free control of debug control saving. */
@@ -2561,7 +2561,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_ENTRY_LOAD_IA32_PAT;
 	vmx->nested.nested_vmx_entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
@@ -2637,8 +2637,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	/*
+	 * Old versions of KVM use the single-context version without
+	 * checking for support, so declare that it is supported even
+	 * though it is treated as global context.  The alternative is
+	 * not failing the single-context invvpid, and it is worse.
+	 */
 	if (enable_vpid)
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+				VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
 				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 	else
 		vmx->nested.nested_vmx_vpid_caps = 0;
@@ -2805,7 +2812,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -2882,7 +2890,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported() ||
+		    (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
+			return 1;
+		if (is_noncanonical_address(data & PAGE_MASK) ||
+		    (data & MSR_IA32_BNDCFGS_RSVD))
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
@@ -3355,7 +3367,7 @@ static void init_vmcs_shadow_fields(void)
 	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
 		switch (shadow_read_write_fields[i]) {
 		case GUEST_BNDCFGS:
-			if (!vmx_mpx_supported())
+			if (!kvm_mpx_supported())
 				continue;
 			break;
 		default:
@@ -3491,7 +3503,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save)
 	}
 
 	vmcs_write16(sf->selector, var.selector);
-	vmcs_write32(sf->base, var.base);
+	vmcs_writel(sf->base, var.base);
 	vmcs_write32(sf->limit, var.limit);
 	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var));
 }
@@ -4859,6 +4871,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
+	if (enable_pml) {
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	return 0;
 }
 
@@ -4947,8 +4965,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 
 	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
-	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx->vcpu.arch.cr0 = cr0;
+	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx_set_cr4(vcpu, 0);
 	vmx_set_efer(vcpu, 0);
 	vmx_fpu_activate(vcpu);
@@ -5226,7 +5244,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	if (is_machine_check(intr_info))
 		return handle_machine_check(vcpu);
 
-	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
+	if (is_nmi(intr_info))
 		return 1;  /* already handled by vmx_vcpu_run() */
 
 	if (is_no_device(intr_info)) {
@@ -6239,7 +6257,6 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
 
 	memcpy(vmx_msr_bitmap_legacy_x2apic,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
@@ -6572,7 +6589,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
 	/* Checks for #GP/#SS exceptions. */
 	exn = false;
-	if (is_protmode(vcpu)) {
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is the only check on the memory
+		 * destination for long mode!
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
 		/* Protected mode: apply checks for segment validity in the
 		 * following order:
 		 * - segment type check (#GP(0) may be thrown)
@@ -6589,17 +6612,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 			 * execute-only code segment
 			 */
 			exn = ((s.type & 0xa) == 8);
-	}
-	if (exn) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-		return 1;
-	}
-	if (is_long_mode(vcpu)) {
-		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
-		 * non-canonical form. This is an only check for long mode.
-		 */
-		exn = is_noncanonical_address(*ret);
-	} else if (is_protmode(vcpu)) {
+		if (exn) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
@@ -6665,14 +6681,20 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		}
 
 		page = nested_get_page(vcpu, vmptr);
-		if (page == NULL ||
-		    *(u32 *)kmap(page) != VMCS12_REVISION) {
+		if (page == NULL) {
 			nested_vmx_failInvalid(vcpu);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		if (*(u32 *)kmap(page) != VMCS12_REVISION) {
 			kunmap(page);
+			nested_release_page_clean(page);
+			nested_vmx_failInvalid(vcpu);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		}
 		kunmap(page);
+		nested_release_page_clean(page);
 		vmx->nested.vmxon_ptr = vmptr;
 		break;
 	case EXIT_REASON_VMCLEAR:
@@ -7340,6 +7362,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	if (!(types & (1UL << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		skip_emulated_instruction(vcpu);
 		return 1;
 	}
 
@@ -7398,6 +7421,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	if (!(types & (1UL << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		skip_emulated_instruction(vcpu);
 		return 1;
 	}
 
@@ -7414,12 +7438,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	}
 
 	switch (type) {
+	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+		/*
+		 * Old versions of KVM use the single-context version so we
+		 * have to support it; just treat it the same as all-context.
+		 */
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
 		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap single context invalidation invvpid calls */
+		/* Trap individual address invalidation invvpid calls */
 		BUG_ON(1);
 		break;
 	}
@@ -7708,7 +7737,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 
 	switch (exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
-		if (!is_exception(intr_info))
+		if (is_nmi(intr_info))
 			return false;
 		else if (is_page_fault(intr_info))
 			return enable_ept;
@@ -7728,8 +7757,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_TASK_SWITCH:
 		return true;
 	case EXIT_REASON_CPUID:
-		if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
-			return false;
 		return true;
 	case EXIT_REASON_HLT:
 		return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
@@ -7814,6 +7841,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
 	case EXIT_REASON_PCOMMIT:
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
+	case EXIT_REASON_PML_FULL:
+		/* We don't expose PML support to L1. */
+		return false;
 	default:
 		return true;
 	}
@@ -7825,22 +7855,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
-	struct page *pml_pg;
-
-	pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!pml_pg)
-		return -ENOMEM;
-
-	vmx->pml_pg = pml_pg;
-
-	vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
-	return 0;
-}
-
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
 	if (vmx->pml_pg) {
@@ -7901,7 +7915,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm)
 static void vmx_dump_sel(char *name, uint32_t sel)
 {
 	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
-	       name, vmcs_read32(sel),
+	       name, vmcs_read16(sel),
 	       vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
 	       vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
 	       vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
@@ -8111,6 +8125,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8170,6 +8185,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 {
 	u32 sec_exec_control;
 
+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		return;
+	}
+
 	/*
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
@@ -8308,8 +8329,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 		kvm_machine_check();
 
 	/* We need to handle NMIs before interrupts are enabled */
-	if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
-	    (exit_intr_info & INTR_INFO_VALID_MASK)) {
+	if (is_nmi(exit_intr_info)) {
 		kvm_before_handle_nmi(&vmx->vcpu);
 		asm("int $2");
 		kvm_after_handle_nmi(&vmx->vcpu);
@@ -8723,6 +8743,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8731,8 +8767,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
@@ -8754,14 +8789,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	err = -ENOMEM;
+
+	/*
+	 * If PML is turned on, failure on enabling PML just results in failure
+	 * of creating the vcpu, therefore we can simplify PML logic (by
+	 * avoiding dealing with cases, such as enabling PML partially on vcpus
+	 * for the guest, etc.
+	 */
+	if (enable_pml) {
+		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vmx->pml_pg)
+			goto uninit_vcpu;
+	}
+
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
 		     > PAGE_SIZE);
 
-	err = -ENOMEM;
-	if (!vmx->guest_msrs) {
-		goto uninit_vcpu;
-	}
+	if (!vmx->guest_msrs)
+		goto free_pml;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
@@ -8805,18 +8852,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.current_vmptr = -1ull;
 	vmx->nested.current_vmcs12 = NULL;
 
-	/*
-	 * If PML is turned on, failure on enabling PML just results in failure
-	 * of creating the vcpu, therefore we can simplify PML logic (by
-	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
-	 */
-	if (enable_pml) {
-		err = vmx_create_pml_buffer(vmx);
-		if (err)
-			goto free_vmcs;
-	}
-
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -8824,6 +8859,8 @@ free_vmcs:
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
+free_pml:
+	vmx_destroy_pml_buffer(vmx);
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:
@@ -9726,6 +9763,18 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	}
 
+	if (enable_pml) {
+		/*
+		 * Conceptually we want to copy the PML address and index from
+		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+		 * since we always flush the log on each vmexit, this happens
+		 * to be equivalent to simply resetting the fields in vmcs02.
+		 */
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
@@ -10219,7 +10268,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 	if (nested_cpu_has_xsaves(vmcs12))
 		vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
@@ -10454,6 +10503,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	/* Update TSC_OFFSET if TSC was changed while L2 ran */
 	vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
 
+	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+		vmx_set_virtual_x2apic_mode(vcpu,
+				vcpu->arch.apic_base & X2APIC_ENABLE);
+	}
+
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d2945024ed33..8e526c6fd784 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -199,7 +199,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;
 
+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -207,8 +218,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }
 
 static void shared_msr_update(unsigned slot, u32 msr)
@@ -697,7 +706,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
 			return 1;
 	}
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -2941,6 +2949,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
@@ -2950,6 +2960,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	/* INITs are latched while in SMM */
+	if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
+	    (events->smi.smm || events->smi.pending) &&
+	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -2973,10 +2989,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+		u32 hflags = vcpu->arch.hflags;
 		if (events->smi.smm)
-			vcpu->arch.hflags |= HF_SMM_MASK;
+			hflags |= HF_SMM_MASK;
 		else
-			vcpu->arch.hflags &= ~HF_SMM_MASK;
+			hflags &= ~HF_SMM_MASK;
+		kvm_set_hflags(vcpu, hflags);
+
 		vcpu->arch.smi_pending = events->smi.pending;
 		if (events->smi.smm_inside_nmi)
 			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
@@ -3014,6 +3033,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	if (dbgregs->flags)
 		return -EINVAL;
 
+	if (dbgregs->dr6 & ~0xffffffffull)
+		return -EINVAL;
+	if (dbgregs->dr7 & ~0xffffffffull)
+		return -EINVAL;
+
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
@@ -3039,6 +3063,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV */
+	xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
 	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
 
 	/*
@@ -3115,11 +3140,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (cpu_has_xsave) {
 		/*
@@ -3127,11 +3155,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
-		if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
@@ -3313,6 +3343,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;
 
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
@@ -3320,7 +3351,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4575,16 +4608,20 @@ emul_write:
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
-	/* TODO: String I/O for in kernel device */
-	int r;
+	int r = 0, i;
 
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+	for (i = 0; i < vcpu->arch.pio.count; i++) {
+		if (vcpu->arch.pio.in)
+			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+					    vcpu->arch.pio.size, pd);
+		else
+			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+					     vcpu->arch.pio.port, vcpu->arch.pio.size,
+					     pd);
+		if (r)
+			break;
+		pd += vcpu->arch.pio.size;
+	}
 	return r;
 }
 
@@ -4622,6 +4659,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
+	memset(vcpu->arch.pio_data, 0, size * count);
+
 	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
 	if (ret) {
 data_avail:
@@ -4805,6 +4844,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 
 	if (var.unusable) {
 		memset(desc, 0, sizeof(*desc));
+		if (base3)
+			*base3 = 0;
 		return false;
 	}
 
@@ -4960,6 +5001,16 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
 	kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked);
 }
 
+static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+{
+	return emul_to_vcpu(ctxt)->arch.hflags;
+}
+
+static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
+{
+	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.read_gpr            = emulator_read_gpr,
 	.write_gpr           = emulator_write_gpr,
@@ -4999,6 +5050,8 @@ static const struct x86_emulate_ops emulate_ops = {
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
+	.get_hflags          = emulator_get_hflags,
+	.set_hflags          = emulator_set_hflags,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -5051,7 +5104,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
-	ctxt->emul_flags = vcpu->arch.hflags;
 
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
@@ -5447,8 +5499,6 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		if (vcpu->arch.hflags != ctxt->emul_flags)
-			kvm_set_hflags(vcpu, ctxt->emul_flags);
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
 			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
@@ -5821,6 +5871,7 @@ out:
 
 void kvm_arch_exit(void)
 {
+	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -5934,7 +5985,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
 
-	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+	return emulator_write_emulated(ctxt, rip, instruction, 3,
+		&ctxt->exception);
 }
 
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
@@ -6023,12 +6075,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending) {
-		if (kvm_x86_ops->nmi_allowed(vcpu)) {
-			--vcpu->arch.nmi_pending;
-			vcpu->arch.nmi_injected = true;
-			kvm_x86_ops->set_nmi(vcpu);
-		}
+	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+		--vcpu->arch.nmi_pending;
+		vcpu->arch.nmi_injected = true;
+		kvm_x86_ops->set_nmi(vcpu);
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		/*
 		 * Because interrupts can be injected asynchronously, we are
@@ -6473,10 +6523,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		else if (vcpu->arch.nmi_pending)
-			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			kvm_x86_ops->enable_irq_window(vcpu);
+		else {
+			if (vcpu->arch.nmi_pending)
+				kvm_x86_ops->enable_nmi_window(vcpu);
+			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+				kvm_x86_ops->enable_irq_window(vcpu);
+		}
 
 		if (kvm_lapic_enabled(vcpu)) {
 			update_cr8_intercept(vcpu);
@@ -6494,8 +6546,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
-	kvm_load_guest_xcr0(vcpu);
-
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6518,6 +6568,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6567,6 +6619,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
+	kvm_put_guest_xcr0(vcpu);
+
 	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
@@ -6968,6 +7022,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		return -EINVAL;
 
+	/* INITs are latched while in SMM */
+	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
+	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
+		return -EINVAL;
+
 	if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
 		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 		set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
@@ -7214,7 +7274,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 * and assume host would use all available bits.
 	 * Guest xcr0 would be loaded later.
 	 */
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7223,8 +7282,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	kvm_put_guest_xcr0(vcpu);
-
 	if (!vcpu->guest_fpu_loaded) {
 		vcpu->fpu_counter = 0;
 		return;
@@ -7249,10 +7306,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
 	kvmclock_reset(vcpu);
 
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	kvm_x86_ops->vcpu_free(vcpu);
+	free_cpumask_var(wbinvd_dirty_mask);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
@@ -8198,8 +8257,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 27f89c79a44b..423644c230e7 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -80,7 +80,7 @@ ENTRY(copy_user_generic_unrolled)
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_copy_short_string
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -101,7 +101,8 @@ ENTRY(copy_user_generic_unrolled)
 	leaq 64(%rdi),%rdi
 	decl %ecx
 	jnz 1b
-17:	movl %edx,%ecx
+.L_copy_short_string:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
 	jz 20f
@@ -215,6 +216,8 @@ ENDPROC(copy_user_generic_string)
  */
 ENTRY(copy_user_enhanced_fast_string)
 	ASM_STAC
+	cmpl $64,%edx
+	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
 	movl %edx,%ecx
 1:	rep
 	movsb
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 42982b26e32b..39bdaf3ac44a 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (mm->get_unmapped_area == arch_get_unmapped_area)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 493f54172b4a..3aebbd6c6f5f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -628,21 +628,40 @@ void __init init_mem_mapping(void)
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
  */
 int devmem_is_allowed(unsigned long pagenr)
 {
-	if (pagenr < 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+	if (page_is_ram(pagenr)) {
+		/*
+		 * For disallowed memory regions in the low 1MB range,
+		 * request that the page be shown as all zeros.
+		 */
+		if (pagenr < 256)
+			return 2;
+
+		return 0;
+	}
+
+	/*
+	 * This must follow RAM test, since System RAM is considered a
+	 * restricted resource under CONFIG_STRICT_IOMEM.
+	 */
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+		/* Low 1MB bypasses iomem restrictions. */
+		if (pagenr < 256)
+			return 1;
+
 		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
-	return 0;
+	}
+
+	return 1;
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index d470cf219a2d..4e5ac46adc9d 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 637ab34ed632..ddb2244b06a1 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -33,7 +33,7 @@
 struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
-	unsigned long page; /* location of the fault page */
+	unsigned long addr; /* the requested address */
 	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
@@ -70,9 +70,16 @@ unsigned int kmmio_count;
 static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
 static LIST_HEAD(kmmio_probes);
 
-static struct list_head *kmmio_page_list(unsigned long page)
+static struct list_head *kmmio_page_list(unsigned long addr)
 {
-	return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)];
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+
+	return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)];
 }
 
 /* Accessed per-cpu */
@@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 }
 
 /* You must be holding RCU read lock. */
-static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 {
 	struct list_head *head;
 	struct kmmio_fault_page *f;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
 
-	page &= PAGE_MASK;
-	head = kmmio_page_list(page);
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+	head = kmmio_page_list(addr);
 	list_for_each_entry_rcu(f, head, list) {
-		if (f->page == page)
+		if (f->addr == addr)
 			return f;
 	}
 	return NULL;
@@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(f->page, &level);
+	pte_t *pte = lookup_address(f->addr, &level);
 
 	if (!pte) {
-		pr_err("no pte for page 0x%08lx\n", f->page);
+		pr_err("no pte for addr 0x%08lx\n", f->addr);
 		return -1;
 	}
 
@@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 		return -1;
 	}
 
-	__flush_tlb_one(f->page);
+	__flush_tlb_one(f->addr);
 	return 0;
 }
 
@@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n",
-			   f->page, f->count, !!f->old_presence);
+		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			   f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
-	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"),
-		  f->page);
+	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
+		  f->addr);
 	f->armed = true;
 	return ret;
 }
@@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
 	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
-			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+			KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr);
 	f->armed = false;
 }
 
@@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	struct kmmio_context *ctx;
 	struct kmmio_fault_page *faultpage;
 	int ret = 0; /* default to fault not handled */
+	unsigned long page_base = addr;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+	if (!pte)
+		return -EINVAL;
+	page_base &= page_level_mask(l);
 
 	/*
 	 * Preemption is now disabled to prevent process switch during
@@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	preempt_disable();
 	rcu_read_lock();
 
-	faultpage = get_kmmio_fault_page(addr);
+	faultpage = get_kmmio_fault_page(page_base);
 	if (!faultpage) {
 		/*
 		 * Either this page fault is not caused by kmmio, or
@@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 
 	ctx = &get_cpu_var(kmmio_ctx);
 	if (ctx->active) {
-		if (addr == ctx->addr) {
+		if (page_base == ctx->addr) {
 			/*
 			 * A second fault on the same page means some other
 			 * condition needs handling by do_page_fault(), the
@@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	ctx->active++;
 
 	ctx->fpage = faultpage;
-	ctx->probe = get_kmmio_probe(addr);
+	ctx->probe = get_kmmio_probe(page_base);
 	ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	ctx->addr = addr;
+	ctx->addr = page_base;
 
 	if (ctx->probe && ctx->probe->pre_handler)
 		ctx->probe->pre_handler(ctx->probe, regs, addr);
@@ -354,12 +371,11 @@ out:
 }
 
 /* You must be holding kmmio_lock. */
-static int add_kmmio_fault_page(unsigned long page)
+static int add_kmmio_fault_page(unsigned long addr)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (f) {
 		if (!f->count)
 			arm_kmmio_fault_page(f);
@@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page)
 		return -1;
 
 	f->count = 1;
-	f->page = page;
+	f->addr = addr;
 
 	if (arm_kmmio_fault_page(f)) {
 		kfree(f);
 		return -1;
 	}
 
-	list_add_rcu(&f->list, kmmio_page_list(f->page));
+	list_add_rcu(&f->list, kmmio_page_list(f->addr));
 
 	return 0;
 }
 
 /* You must be holding kmmio_lock. */
-static void release_kmmio_fault_page(unsigned long page,
+static void release_kmmio_fault_page(unsigned long addr,
 				struct kmmio_fault_page **release_list)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (!f)
 		return;
 
@@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	int ret = 0;
 	unsigned long size = 0;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+	unsigned int l;
+	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	if (get_kmmio_probe(p->addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
 		if (add_kmmio_fault_page(p->addr + size))
 			pr_err("Unable to set page fault.\n");
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 out:
 	spin_unlock_irqrestore(&kmmio_lock, flags);
@@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
+	unsigned int l;
+	pte_t *pte;
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte)
+		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
 		release_kmmio_fault_page(p->addr + size, &release_list);
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
 	kmmio_count--;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 844b06d67df4..307f60ecfc6d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd)
 }
 
 /*
- * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
- * does, but not when emulating X86_32
- */
-static unsigned long mmap_legacy_base(unsigned long rnd)
-{
-	if (mmap_is_ia32())
-		return TASK_UNMAPPED_BASE;
-	else
-		return TASK_UNMAPPED_BASE + rnd;
-}
-
-/*
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
@@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (current->flags & PF_RANDOMIZE)
 		random_factor = arch_mmap_rnd();
 
-	mm->mmap_legacy_base = mmap_legacy_base(random_factor);
+	mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mm->mmap_legacy_base;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index ef05755a1900..7ed47b1e6f42 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}
@@ -525,15 +525,7 @@ int mpx_handle_bd_fault(void)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault()) {
-		force_sig(SIGSEGV, current);
-		/*
-		 * The force_sig() is essentially "handling" this
-		 * exception, so we do not pass up the error
-		 * from do_mpx_bt_fault().
-		 */
-	}
-	return 0;
+	return do_mpx_bt_fault();
 }
 
 /*
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 47b6436e41c2..3686a1db25b2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -100,5 +100,6 @@ void __init initmem_init(void)
 	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(highstart_pfn));
 
+	__vmalloc_start_set = true;
 	setup_bootmem_allocator();
 }
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 188e3e07eeeb..3f1bb4f93a5a 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -36,13 +36,22 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "" fmt
 
-static bool boot_cpu_done;
+static bool __read_mostly boot_cpu_done;
+static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __read_mostly pat_initialized;
+static bool __read_mostly init_cm_done;
 
-static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
-
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
 {
-	__pat_enabled = 0;
+	if (pat_disabled)
+		return;
+
+	if (boot_cpu_done) {
+		WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+		return;
+	}
+
+	pat_disabled = true;
 	pr_info("x86/PAT: %s\n", reason);
 }
 
@@ -55,7 +64,7 @@ early_param("nopat", nopat);
 
 bool pat_enabled(void)
 {
-	return !!__pat_enabled;
+	return pat_initialized;
 }
 EXPORT_SYMBOL_GPL(pat_enabled);
 
@@ -180,7 +189,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
  * configuration.
  * Using lower indices is preferred, so we start with highest index.
  */
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
 {
 	enum page_cache_mode cache;
 	char pat_msg[33];
@@ -193,6 +202,8 @@ void pat_init_cache_modes(u64 pat)
 		update_cache_mode_entry(i, cache);
 	}
 	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
+
+	init_cm_done = true;
 }
 
 #define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
@@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat)
 {
 	u64 tmp_pat;
 
-	if (!cpu_has_pat) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		pat_disable("PAT not supported by CPU.");
 		return;
 	}
 
-	if (!pat_enabled())
-		goto done;
-
 	rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
 	if (!tmp_pat) {
 		pat_disable("PAT MSR is 0, disabled.");
@@ -216,17 +224,14 @@ static void pat_bsp_init(u64 pat)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
+	pat_initialized = true;
 
-done:
-	pat_init_cache_modes(pat);
+	__init_cache_modes(pat);
 }
 
 static void pat_ap_init(u64 pat)
 {
-	if (!pat_enabled())
-		return;
-
-	if (!cpu_has_pat) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		/*
 		 * If this happens we are on a secondary CPU, but switched to
 		 * PAT on the boot CPU. We have no way to undo PAT.
@@ -237,18 +242,31 @@ static void pat_ap_init(u64 pat)
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 }
 
-void pat_init(void)
+void init_cache_modes(void)
 {
-	u64 pat;
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u64 pat = 0;
 
-	if (!pat_enabled()) {
+	if (init_cm_done)
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_PAT)) {
+		/*
+		 * CPU supports PAT. Set PAT table to be consistent with
+		 * PAT MSR. This case supports "nopat" boot option, and
+		 * virtual machine environments which support PAT without
+		 * MTRRs. In specific, Xen has unique setup to PAT MSR.
+		 *
+		 * If PAT MSR returns 0, it is considered invalid and emulates
+		 * as No PAT.
+		 */
+		rdmsrl(MSR_IA32_CR_PAT, pat);
+	}
+
+	if (!pat) {
 		/*
 		 * No PAT. Emulate the PAT table that corresponds to the two
-		 * cache bits, PWT (Write Through) and PCD (Cache Disable). This
-		 * setup is the same as the BIOS default setup when the system
-		 * has PAT but the "nopat" boot option has been specified. This
-		 * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+		 * cache bits, PWT (Write Through) and PCD (Cache Disable).
+		 * This setup is also the same as the BIOS default setup.
 		 *
 		 * PTE encoding:
 		 *
@@ -265,10 +283,32 @@ void pat_init(void)
 		 */
 		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
 		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+	}
 
-	} else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
-		   (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
-		    ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+	__init_cache_modes(pat);
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+	u64 pat;
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (pat_disabled)
+		return;
+
+	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+	     ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
 		/*
 		 * PAT support with the lower four entries. Intel Pentium 2,
 		 * 3, M, and 4 are affected by PAT errata, which makes the
@@ -733,25 +773,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	if (file->f_flags & O_DSYNC)
 		pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
-#ifdef CONFIG_X86_32
-	/*
-	 * On the PPro and successors, the MTRRs are used to set
-	 * memory types for physical addresses outside main memory,
-	 * so blindly setting UC or PWT on those pages is wrong.
-	 * For Pentiums and earlier, the surround logic should disable
-	 * caching for the high addresses through the KEN pin, but
-	 * we maintain the tradition of paranoia in this code.
-	 */
-	if (!pat_enabled() &&
-	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
-	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
-	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
-	      boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
-	    (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
-		pcm = _PAGE_CACHE_MODE_UC;
-	}
-#endif
-
 	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
 			     cachemode2protval(pcm));
 	return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 8f4cc3dfac32..5a760fd66bec 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -106,8 +106,6 @@ static void flush_tlb_func(void *info)
 
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
-	if (!f->flush_end)
-		f->flush_end = f->flush_start + PAGE_SIZE;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
@@ -135,12 +133,18 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 				 unsigned long end)
 {
 	struct flush_tlb_info info;
+
 	info.flush_mm = mm;
 	info.flush_start = start;
 	info.flush_end = end;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start);
+	if (end == TLB_FLUSH_ALL)
+		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
+	else
+		trace_tlb_flush(TLB_REMOTE_SEND_IPI,
+				(end - start) >> PAGE_SHIFT);
+
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -258,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
 
 	preempt_enable();
 }
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 3cd69832d7f4..3961103e9176 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -114,6 +114,16 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
 		},
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+	{
+		.callback = set_nouse_crs,
+		.ident = "Supermicro X8DTH",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+			DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+		},
+	},
 
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
 	{
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index eccd4d99e6a4..8fd6f44aee83 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -673,28 +673,22 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-int pcibios_alloc_irq(struct pci_dev *dev)
+int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	/*
-	 * If the PCI device was already claimed by core code and has
-	 * MSI enabled, probing of the pcibios IRQ will overwrite
-	 * dev->irq.  So bail out if MSI is already enabled.
-	 */
-	if (pci_dev_msi_enabled(dev))
-		return -EBUSY;
+	int err;
 
-	return pcibios_enable_irq(dev);
-}
+	if ((err = pci_enable_resources(dev, mask)) < 0)
+		return err;
 
-void pcibios_free_irq(struct pci_dev *dev)
-{
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
+	if (!pci_dev_msi_enabled(dev))
+		return pcibios_enable_irq(dev);
+	return 0;
 }
 
-int pcibios_enable_device(struct pci_dev *dev, int mask)
+void pcibios_disable_device (struct pci_dev *dev)
 {
-	return pci_enable_resources(dev, mask);
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
 }
 
 int pci_ext_cfg_avail(void)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index e58565556703..0ae7e9fa348d 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -540,3 +540,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
         }
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
+
+static void pci_bdwep_bar(struct pci_dev *dev)
+{
+	dev->non_compliant_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 0d24e7c10145..ae97f24a4371 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -37,6 +37,7 @@
 
 /* Quirks for the listed devices */
 #define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+#define PCI_DEVICE_ID_INTEL_MRFL_HSU	0x1191
 
 /* Fixed BAR fields */
 #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
@@ -215,7 +216,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	int polarity;
 	int ret;
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	switch (intel_mid_identify_cpu()) {
@@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 		/* Special treatment for IRQ0 */
 		if (dev->irq == 0) {
 			/*
+			 * Skip HS UART common registers device since it has
+			 * IRQ0 assigned and not used by the kernel.
+			 */
+			if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU)
+				return -EBUSY;
+			/*
 			 * TNG has IRQ0 assigned to eMMC controller. But there
 			 * are also other devices with bogus PCI configuration
 			 * that have IRQ0 assigned. This check ensures that
-			 * eMMC gets it.
+			 * eMMC gets it. The rest of devices still could be
+			 * enabled without interrupt line being allocated.
 			 */
 			if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
-				return -EBUSY;
+				return 0;
 		}
 		break;
 	default:
@@ -256,13 +264,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (pci_has_managed_irq(dev)) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		/*
-		 * Don't reset dev->irq here, otherwise
-		 * intel_mid_pci_irq_enable() will fail on next call.
-		 */
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 32e70343e6fd..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			struct pci_dev *temp_dev;
 			int irq;
 
-			if (pci_has_managed_irq(dev))
+			if (dev->irq_managed && dev->irq > 0)
 				return 0;
 
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
@@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				pci_set_managed_irq(dev, irq);
+				dev->irq_managed = 1;
+				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
 				return 0;
@@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
-		pci_reset_managed_irq(dev);
+		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ff31ab464213..7575f0798194 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -231,23 +231,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return 1;
 
 	for_each_pci_msi_entry(msidesc, dev) {
-		__pci_read_msi_msg(msidesc, &msg);
-		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
-			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (msg.data != XEN_PIRQ_MSI_DATA ||
-		    xen_irq_from_pirq(pirq) < 0) {
-			pirq = xen_allocate_pirq_msi(dev, msidesc);
-			if (pirq < 0) {
-				irq = -ENODEV;
-				goto error;
-			}
-			xen_msi_compose_msg(dev, pirq, &msg);
-			__pci_write_msi_msg(msidesc, &msg);
-			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
-		} else {
-			dev_dbg(&dev->dev,
-				"xen: msi already bound to pirq=%d\n", pirq);
+		pirq = xen_allocate_pirq_msi(dev, msidesc);
+		if (pirq < 0) {
+			irq = -ENODEV;
+			goto error;
 		}
+		xen_msi_compose_msg(dev, pirq, &msg);
+		__pci_write_msi_msg(msidesc, &msg);
+		dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
@@ -488,8 +479,11 @@ int __init pci_xen_initial_domain(void)
 #endif
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	__acpi_unregister_gsi = NULL;
-	/* Pre-allocate legacy irqs */
-	for (irq = 0; irq < nr_legacy_irqs(); irq++) {
+	/*
+	 * Pre-allocate the legacy IRQs.  Use NR_LEGACY_IRQS here
+	 * because we don't have a PIC and thus nr_legacy_irqs() is zero.
+	 */
+	for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
 		int trigger, polarity;
 
 		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
diff --git a/arch/x86/platform/goldfish/goldfish.c b/arch/x86/platform/goldfish/goldfish.c
index 1693107a518e..0d17c0aafeb1 100644
--- a/arch/x86/platform/goldfish/goldfish.c
+++ b/arch/x86/platform/goldfish/goldfish.c
@@ -42,10 +42,22 @@ static struct resource goldfish_pdev_bus_resources[] = {
 	}
 };
 
+static bool goldfish_enable __initdata;
+
+static int __init goldfish_setup(char *str)
+{
+	goldfish_enable = true;
+	return 0;
+}
+__setup("goldfish", goldfish_setup);
+
 static int __init goldfish_init(void)
 {
+	if (!goldfish_enable)
+		return -ENODEV;
+
 	platform_device_register_simple("goldfish_pdev_bus", -1,
-						goldfish_pdev_bus_resources, 2);
+					goldfish_pdev_bus_resources, 2);
 	return 0;
 }
 device_initcall(goldfish_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index de734134bc8d..40c616495da7 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -17,7 +17,7 @@
 #include <asm/intel-mid.h>
 #include <asm/io_apic.h>
 
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
 
 static struct platform_device wdt_dev = {
 	.name = "intel_mid_wdt",
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2c835e356349..d445c5f1aeb1 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -12,6 +12,7 @@ targets += purgatory.ro
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
 KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 0c2fae8d929d..73eb7fd4aec4 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode)
 		die("Segment relocations found but --realmode not specified\n");
 
 	/* Order the relocations for more efficient processing */
-	sort_relocs(&relocs16);
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
 	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
+#else
+	sort_relocs(&relocs16);
 #endif
 
 	/* Print the relocations */
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index a629694ee750..e14c43a2d187 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -121,7 +121,7 @@ int poke_user(struct task_struct *child, long addr, long data)
 	else if ((addr >= offsetof(struct user, u_debugreg[0])) &&
 		(addr <= offsetof(struct user, u_debugreg[7]))) {
 		addr -= offsetof(struct user, u_debugreg[0]);
-		addr = addr >> 2;
+		addr = addr >> 3;
 		if ((addr == 4) || (addr == 5))
 			return -EIO;
 		child->thread.arch.debugregs[addr] = data;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b7de78bdc09c..ffa41591bff9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -74,7 +74,6 @@
 #include <asm/mach_traps.h>
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
-#include <asm/pat.h>
 #include <asm/cpu.h>
 
 #ifdef CONFIG_ACPI
@@ -961,7 +960,7 @@ static void xen_load_sp0(struct tss_struct *tss,
 	tss->x86_tss.sp0 = thread->sp0;
 }
 
-static void xen_set_iopl_mask(unsigned mask)
+void xen_set_iopl_mask(unsigned mask)
 {
 	struct physdev_set_iopl set_iopl;
 
@@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	unsigned long initrd_start = 0;
-	u64 pat;
 	int rc;
 
 	if (!xen_start_info)
@@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 				   xen_start_info->nr_pages);
 	xen_reserve_special_pages();
 
-	/*
-	 * Modify the cache mode translation tables to match Xen's PAT
-	 * configuration.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	pat_init_cache_modes(pat);
-
 	/* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index cb5e266a8bf7..63146c378f1e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
 
 	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
 	 * We include the PMD passed in on _both_ boundaries. */
-	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
 			pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -2038,7 +2038,8 @@ static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
 
 /*
  * Translate a virtual address to a physical one without relying on mapped
- * page tables.
+ * page tables. Don't rely on big pages being aligned in (guest) physical
+ * space!
  */
 static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 {
@@ -2059,7 +2060,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pud)));
 	if (!pud_present(pud))
 		return 0;
-	pa = pud_pfn(pud) << PAGE_SHIFT;
+	pa = pud_val(pud) & PTE_PFN_MASK;
 	if (pud_large(pud))
 		return pa + (vaddr & ~PUD_MASK);
 
@@ -2067,7 +2068,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
 						       sizeof(pmd)));
 	if (!pmd_present(pmd))
 		return 0;
-	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	pa = pmd_val(pmd) & PTE_PFN_MASK;
 	if (pmd_large(pmd))
 		return pa + (vaddr & ~PMD_MASK);
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 7ab29518a3b9..df8844a1853a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -393,6 +393,9 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 	unsigned long i = 0;
 	unsigned long n = end_pfn - start_pfn;
 
+	if (remap_pfn == 0)
+		remap_pfn = nr_pages;
+
 	while (i < n) {
 		unsigned long cur_pfn = start_pfn + i;
 		unsigned long left = n - i;
@@ -438,17 +441,29 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 	return remap_pfn;
 }
 
-static void __init xen_set_identity_and_remap(unsigned long nr_pages)
+static unsigned long __init xen_count_remap_pages(
+	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+	unsigned long remap_pages)
+{
+	if (start_pfn >= nr_pages)
+		return remap_pages;
+
+	return remap_pages + min(end_pfn, nr_pages) - start_pfn;
+}
+
+static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
+	unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn,
+			      unsigned long nr_pages, unsigned long last_val))
 {
 	phys_addr_t start = 0;
-	unsigned long last_pfn = nr_pages;
+	unsigned long ret_val = 0;
 	const struct e820entry *entry = xen_e820_map;
 	int i;
 
 	/*
 	 * Combine non-RAM regions and gaps until a RAM region (or the
-	 * end of the map) is reached, then set the 1:1 map and
-	 * remap the memory in those non-RAM regions.
+	 * end of the map) is reached, then call the provided function
+	 * to perform its duty on the non-RAM region.
 	 *
 	 * The combined non-RAM regions are rounded to a whole number
 	 * of pages so any partial pages are accessible via the 1:1
@@ -466,14 +481,13 @@ static void __init xen_set_identity_and_remap(unsigned long nr_pages)
 				end_pfn = PFN_UP(entry->addr);
 
 			if (start_pfn < end_pfn)
-				last_pfn = xen_set_identity_and_remap_chunk(
-						start_pfn, end_pfn, nr_pages,
-						last_pfn);
+				ret_val = func(start_pfn, end_pfn, nr_pages,
+					       ret_val);
 			start = end;
 		}
 	}
 
-	pr_info("Released %ld page(s)\n", xen_released_pages);
+	return ret_val;
 }
 
 /*
@@ -596,35 +610,6 @@ static void __init xen_ignore_unusable(void)
 	}
 }
 
-static unsigned long __init xen_count_remap_pages(unsigned long max_pfn)
-{
-	unsigned long extra = 0;
-	unsigned long start_pfn, end_pfn;
-	const struct e820entry *entry = xen_e820_map;
-	int i;
-
-	end_pfn = 0;
-	for (i = 0; i < xen_e820_map_entries; i++, entry++) {
-		start_pfn = PFN_DOWN(entry->addr);
-		/* Adjacent regions on non-page boundaries handling! */
-		end_pfn = min(end_pfn, start_pfn);
-
-		if (start_pfn >= max_pfn)
-			return extra + max_pfn - end_pfn;
-
-		/* Add any holes in map to result. */
-		extra += start_pfn - end_pfn;
-
-		end_pfn = PFN_UP(entry->addr + entry->size);
-		end_pfn = min(end_pfn, max_pfn);
-
-		if (entry->type != E820_RAM)
-			extra += end_pfn - start_pfn;
-	}
-
-	return extra;
-}
-
 bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
 {
 	struct e820entry *entry;
@@ -728,10 +713,9 @@ static void __init xen_reserve_xen_mfnlist(void)
 		size = PFN_PHYS(xen_start_info->nr_p2m_frames);
 	}
 
-	if (!xen_is_e820_reserved(start, size)) {
-		memblock_reserve(start, size);
+	memblock_reserve(start, size);
+	if (!xen_is_e820_reserved(start, size))
 		return;
-	}
 
 #ifdef CONFIG_X86_32
 	/*
@@ -742,6 +726,7 @@ static void __init xen_reserve_xen_mfnlist(void)
 	BUG();
 #else
 	xen_relocate_p2m();
+	memblock_free(start, size);
 #endif
 }
 
@@ -804,7 +789,7 @@ char * __init xen_memory_setup(void)
 	max_pages = xen_get_max_pages();
 
 	/* How many extra pages do we need due to remapping? */
-	max_pages += xen_count_remap_pages(max_pfn);
+	max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages);
 
 	if (max_pages > max_pfn)
 		extra_pages += max_pages - max_pfn;
@@ -922,7 +907,9 @@ char * __init xen_memory_setup(void)
 	 * Set identity map on non-RAM pages and prepare remapping the
 	 * underlying RAM.
 	 */
-	xen_set_identity_and_remap(max_pfn);
+	xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk);
+
+	pr_info("Released %ld page(s)\n", xen_released_pages);
 
 	return "Xen";
 }
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 9e2ba5c6e1dd..f42e78de1e10 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -27,6 +27,12 @@ static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
 {
+	int irq = per_cpu(lock_kicker_irq, cpu);
+
+	/* Don't kick if the target's kicker interrupt is not initialized. */
+	if (irq == -1)
+		return;
+
 	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 }
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index f1ba6a092854..8846257d8792 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -343,11 +343,11 @@ static int xen_vcpuop_set_next_event(unsigned long delta,
 	WARN_ON(!clockevent_state_oneshot(evt));
 
 	single.timeout_abs_ns = get_abs_timeout(delta);
-	single.flags = VCPU_SSHOTTMR_future;
+	/* Get an event anyway, even if the timeout is already expired */
+	single.flags = 0;
 
 	ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single);
-
-	BUG_ON(ret != 0 && ret != -ETIME);
+	BUG_ON(ret != 0);
 
 	return ret;
 }
diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h
index f71f88ea7646..19707db966f1 100644
--- a/arch/xtensa/include/asm/irq.h
+++ b/arch/xtensa/include/asm/irq.h
@@ -29,7 +29,8 @@ static inline void variant_irq_disable(unsigned int irq) { }
 # define PLATFORM_NR_IRQS 0
 #endif
 #define XTENSA_NR_IRQS XCHAL_NUM_INTERRUPTS
-#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS)
+#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS + 1)
+#define XTENSA_PIC_LINUX_IRQ(hwirq) ((hwirq) + 1)
 
 #if VARIANT_NR_IRQS == 0
 static inline void variant_init_irq(void) { }
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 9ed55649ac8e..05e1df943856 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -128,7 +128,7 @@ ENTRY(_startup)
 	wsr	a0, icountlevel
 
 	.set	_index, 0
-	.rept	XCHAL_NUM_DBREAK - 1
+	.rept	XCHAL_NUM_DBREAK
 	wsr	a0, SREG_DBREAKC + _index
 	.set	_index, _index + 1
 	.endr
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 4ac3d23161cf..441694464b1e 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -34,11 +34,6 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
 {
 	int irq = irq_find_mapping(NULL, hwirq);
 
-	if (hwirq >= NR_IRQS) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-				__func__, hwirq);
-	}
-
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	/* Debugging check for stack overflow: is there less than 1KB free? */
 	{
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 9735691f37f1..49ccbd9022f6 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -133,6 +133,8 @@ static int __init parse_tag_initrd(const bp_tag_t* tag)
 
 __tagtable(BP_TAG_INITRD, parse_tag_initrd);
 
+#endif /* CONFIG_BLK_DEV_INITRD */
+
 #ifdef CONFIG_OF
 
 static int __init parse_tag_fdt(const bp_tag_t *tag)
@@ -145,8 +147,6 @@ __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
 #endif /* CONFIG_OF */
 
-#endif /* CONFIG_BLK_DEV_INITRD */
-
 static int __init parse_tag_cmdline(const bp_tag_t* tag)
 {
 	strlcpy(command_line, (char *)(tag->data), COMMAND_LINE_SIZE);
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index 83cf49685373..3aaaae18417c 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -87,7 +87,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		/* At this point:  (!vmm || addr < vmm->vm_end). */
 		if (TASK_SIZE - len < addr)
 			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
+		if (!vmm || addr + len <= vm_start_gap(vmm))
 			return addr;
 		addr = vmm->vm_end;
 		if (flags & MAP_SHARED)
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index d75aa1476da7..1a804a2f9a5b 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr)
 	unsigned long paddr;
 	void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr);
 
-	pagefault_disable();
+	preempt_disable();
 	kmap_invalidate_coherent(page, vaddr);
 	set_bit(PG_arch_1, &page->flags);
 	clear_page_alias(kvaddr, paddr);
-	pagefault_enable();
+	preempt_enable();
 }
 
 void copy_user_highpage(struct page *dst, struct page *src,
@@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src,
 	void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr,
 					  &src_paddr);
 
-	pagefault_disable();
+	preempt_disable();
 	kmap_invalidate_coherent(dst, vaddr);
 	set_bit(PG_arch_1, &dst->flags);
 	copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr);
-	pagefault_enable();
+	preempt_enable();
 }
 
 #endif /* DCACHE_WAY_SIZE > PAGE_SIZE */
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 70cb408bc20d..92d785fefb6d 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv)
 {
 	struct tty_port *port = (struct tty_port *)priv;
 	int i = 0;
+	int rd = 1;
 	unsigned char c;
 
 	spin_lock(&timer_lock);
 
 	while (simc_poll(0)) {
-		simc_read(0, &c, 1);
+		rd = simc_read(0, &c, 1);
+		if (rd <= 0)
+			break;
 		tty_insert_flip_char(port, c, TTY_NORMAL);
 		i++;
 	}
 
 	if (i)
 		tty_flip_buffer_push(port);
-
-
-	mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE);
+	if (rd)
+		mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE);
 	spin_unlock(&timer_lock);
 }
 
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
index dbeea2b440a1..1fda7e20dfcb 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
@@ -24,16 +24,18 @@
 
 /* Interrupt configuration. */
 
-#define PLATFORM_NR_IRQS	10
+#define PLATFORM_NR_IRQS	0
 
 /* Default assignment of LX60 devices to external interrupts. */
 
 #ifdef CONFIG_XTENSA_MX
 #define DUART16552_INTNUM	XCHAL_EXTINT3_NUM
 #define OETH_IRQ		XCHAL_EXTINT4_NUM
+#define C67X00_IRQ		XCHAL_EXTINT8_NUM
 #else
 #define DUART16552_INTNUM	XCHAL_EXTINT0_NUM
 #define OETH_IRQ		XCHAL_EXTINT1_NUM
+#define C67X00_IRQ		XCHAL_EXTINT5_NUM
 #endif
 
 /*
@@ -63,5 +65,5 @@
 
 #define C67X00_PADDR		(XCHAL_KIO_PADDR + 0x0D0D0000)
 #define C67X00_SIZE		0x10
-#define C67X00_IRQ		5
+
 #endif /* __XTENSA_XTAVNET_HARDWARE_H */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index e9f65f79cf2e..d1e9439fad45 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -209,8 +209,8 @@ static struct resource ethoc_res[] = {
 		.flags = IORESOURCE_MEM,
 	},
 	[2] = { /* IRQ number */
-		.start = OETH_IRQ,
-		.end   = OETH_IRQ,
+		.start = XTENSA_PIC_LINUX_IRQ(OETH_IRQ),
+		.end   = XTENSA_PIC_LINUX_IRQ(OETH_IRQ),
 		.flags = IORESOURCE_IRQ,
 	},
 };
@@ -246,8 +246,8 @@ static struct resource c67x00_res[] = {
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = { /* IRQ number */
-		.start = C67X00_IRQ,
-		.end   = C67X00_IRQ,
+		.start = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ),
+		.end   = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ),
 		.flags = IORESOURCE_IRQ,
 	},
 };
@@ -280,7 +280,7 @@ static struct resource serial_resource = {
 static struct plat_serial8250_port serial_platform_data[] = {
 	[0] = {
 		.mapbase	= DUART16552_PADDR,
-		.irq		= DUART16552_INTNUM,
+		.irq		= XTENSA_PIC_LINUX_IRQ(DUART16552_INTNUM),
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
 				  UPF_IOREMAP,
 		.iotype		= UPIO_MEM32,
diff --git a/block/bio.c b/block/bio.c
index d4d144363250..14263fab94d3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -373,10 +373,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	bio_list_init(&punt);
 	bio_list_init(&nopunt);
 
-	while ((bio = bio_list_pop(current->bio_list)))
+	while ((bio = bio_list_pop(&current->bio_list[0])))
 		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[0] = nopunt;
 
-	*current->bio_list = nopunt;
+	bio_list_init(&nopunt);
+	while ((bio = bio_list_pop(&current->bio_list[1])))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[1] = nopunt;
 
 	spin_lock(&bs->rescue_lock);
 	bio_list_merge(&bs->rescue_list, &punt);
@@ -464,7 +468,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * we retry with the original gfp_flags.
 		 */
 
-		if (current->bio_list && !bio_list_empty(current->bio_list))
+		if (current->bio_list &&
+		    (!bio_list_empty(&current->bio_list[0]) ||
+		     !bio_list_empty(&current->bio_list[1])))
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -584,6 +590,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_rw = bio_src->bi_rw;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
+
+	bio_clone_blkcg_association(bio, bio_src);
 }
 EXPORT_SYMBOL(__bio_clone_fast);
 
@@ -689,6 +697,8 @@ integrity_clone:
 		}
 	}
 
+	bio_clone_blkcg_association(bio, bio_src);
+
 	return bio;
 }
 EXPORT_SYMBOL(bio_clone_bioset);
@@ -2014,6 +2024,17 @@ void bio_disassociate_task(struct bio *bio)
 	}
 }
 
+/**
+ * bio_clone_blkcg_association - clone blkcg association from src to dst bio
+ * @dst: destination bio
+ * @src: source bio
+ */
+void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
+{
+	if (src->bi_css)
+		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
+}
+
 #endif /* CONFIG_BLK_CGROUP */
 
 static void __init biovec_init_slabs(void)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5a37188b559f..8161090a1970 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
@@ -1331,10 +1340,8 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 			struct blkcg_policy_data *cpd;
 
 			cpd = pol->cpd_alloc_fn(GFP_KERNEL);
-			if (!cpd) {
-				mutex_unlock(&blkcg_pol_mutex);
+			if (!cpd)
 				goto err_free_cpds;
-			}
 
 			blkcg->cpd[pol->plid] = cpd;
 			cpd->blkcg = blkcg;
diff --git a/block/blk-core.c b/block/blk-core.c
index 33e2f62d5062..ef083e7a37c5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
 
 void blk_set_queue_dying(struct request_queue *q)
 {
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
+	spin_unlock_irq(q->queue_lock);
 
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);
@@ -2019,7 +2021,14 @@ end_io:
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
-	struct bio_list bio_list_on_stack;
+	/*
+	 * bio_list_on_stack[0] contains bios submitted by the current
+	 * make_request_fn.
+	 * bio_list_on_stack[1] contains bios that were submitted before
+	 * the current make_request_fn, but that haven't been processed
+	 * yet.
+	 */
+	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
@@ -2036,7 +2045,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * should be added at the tail
 	 */
 	if (current->bio_list) {
-		bio_list_add(current->bio_list, bio);
+		bio_list_add(&current->bio_list[0], bio);
 		goto out;
 	}
 
@@ -2055,24 +2064,39 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * bio_list, and call into ->make_request() again.
 	 */
 	BUG_ON(bio->bi_next);
-	bio_list_init(&bio_list_on_stack);
-	current->bio_list = &bio_list_on_stack;
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) {
+			struct bio_list lower, same;
+
+			/* Create a fresh bio_list for all subordinate requests */
+			bio_list_on_stack[1] = bio_list_on_stack[0];
+			bio_list_init(&bio_list_on_stack[0]);
 
 			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
-
-			bio = bio_list_pop(current->bio_list);
+			/* sort new bios into those for a lower level
+			 * and those for the same level
+			 */
+			bio_list_init(&lower);
+			bio_list_init(&same);
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+				if (q == bdev_get_queue(bio->bi_bdev))
+					bio_list_add(&same, bio);
+				else
+					bio_list_add(&lower, bio);
+			/* now assemble so we handle the lowest level first */
+			bio_list_merge(&bio_list_on_stack[0], &lower);
+			bio_list_merge(&bio_list_on_stack[0], &same);
+			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
-			struct bio *bio_next = bio_list_pop(current->bio_list);
-
 			bio_io_error(bio);
-			bio = bio_next;
 		}
+		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 
@@ -2189,7 +2213,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, true);
+		blk_mq_insert_request(rq, false, true, false);
 		return 0;
 	}
 
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d69c5c79f98e..478f572cb1e7 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -412,12 +412,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 
 	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
 		template->flags;
-	bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+	bi->interval_exp = template->interval_exp ? :
+		ilog2(queue_logical_block_size(disk->queue));
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
 }
 EXPORT_SYMBOL(blk_integrity_register);
 
@@ -430,26 +431,11 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES;
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 
-void blk_integrity_revalidate(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!(disk->flags & GENHD_FL_UP))
-		return;
-
-	if (bi->profile)
-		disk->queue->backing_dev_info.capabilities |=
-			BDI_CAP_STABLE_WRITES;
-	else
-		disk->queue->backing_dev_info.capabilities &=
-			~BDI_CAP_STABLE_WRITES;
-}
-
 void blk_integrity_add(struct gendisk *disk)
 {
 	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
diff --git a/block/blk-map.c b/block/blk-map.c
index f565e11f465a..69953bd97e65 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -90,6 +90,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	if (!iter || !iter->count)
 		return -EINVAL;
 
+	if (!iter_is_iovec(iter))
+		return -EINVAL;
+
 	iov_for_each(iov, i, *iter) {
 		unsigned long uaddr = (unsigned long) iov.iov_base;
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b966db8f3556..7225511cf0b4 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -92,9 +92,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
+	unsigned bvecs = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
 		/*
+		 * With arbitrary bio size, the incoming bio may be very
+		 * big. We have to split the bio into small bios so that
+		 * each holds at most BIO_MAX_PAGES bvecs because
+		 * bio_clone() can fail to allocate big bvecs.
+		 *
+		 * It should have been better to apply the limit per
+		 * request queue in which bio_clone() is involved,
+		 * instead of globally. The biggest blocker is the
+		 * bio_clone() in bio bounce.
+		 *
+		 * If bio is splitted by this reason, we should have
+		 * allowed to continue bios merging, but don't do
+		 * that now for making the change simple.
+		 *
+		 * TODO: deal with bio bounce's bio_clone() gracefully
+		 * and convert the global limit into per-queue limit.
+		 */
+		if (bvecs++ >= BIO_MAX_PAGES)
+			goto split;
+
+		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6d6f8feb48c0..0d1af3e44efb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -601,8 +601,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 	if (rq->cmd_flags & REQ_NO_TIMEOUT)
@@ -778,7 +780,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
-			continue;
+			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
 			list_add(&rq->queuelist, &rq_list);
 			__blk_mq_requeue_request(rq);
@@ -840,7 +842,7 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int cpu = hctx->next_cpu, next_cpu;
+		int next_cpu;
 
 		next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
 		if (next_cpu >= nr_cpu_ids)
@@ -848,8 +850,6 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 
 		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
-
-		return cpu;
 	}
 
 	return hctx->next_cpu;
@@ -1259,12 +1259,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-		if (blk_attempt_plug_merge(q, bio, &request_count,
-					   &same_queue_rq))
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return BLK_QC_T_NONE;
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1311,9 +1308,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		if (!old_rq)
 			goto done;
-		if (!blk_mq_direct_issue_request(old_rq, &cookie))
-			goto done;
-		blk_mq_insert_request(old_rq, false, true, true);
+		if (test_bit(BLK_MQ_S_STOPPED, &data.hctx->state) ||
+		    blk_mq_direct_issue_request(old_rq, &cookie) != 0)
+			blk_mq_insert_request(old_rq, false, true, true);
 		goto done;
 	}
 
@@ -1355,9 +1352,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return BLK_QC_T_NONE;
+	if (!is_flush_fua && !blk_queue_nomerges(q)) {
+		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+			return BLK_QC_T_NONE;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1471,7 +1470,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&tags->page_list);
 
 	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
-				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 set->numa_node);
 	if (!tags->rqs) {
 		blk_mq_free_tags(tags);
@@ -1497,7 +1496,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 
 		do {
 			page = alloc_pages_node(set->numa_node,
-				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
+				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
 				this_order);
 			if (page)
 				break;
@@ -1518,7 +1517,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		 * Allow kmemleak to scan these pages as they contain pointers
 		 * to additional allocations like via ops->init_request().
 		 */
-		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL);
+		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
 		entries_per_page = order_to_size(this_order) / rq_size;
 		to_do = min(entries_per_page, set->queue_depth - i);
 		left -= to_do * rq_size;
diff --git a/block/bsg.c b/block/bsg.c
index d214e929ce18..b9a53615bdef 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -655,6 +655,9 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 
 	dprintk("%s: write %Zd bytes\n", bd->name, count);
 
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EINVAL;
+
 	bsg_set_block(bd, file);
 
 	bytes_written = 0;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1f9093e901da..e04a7b8492cf 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1572,7 +1572,7 @@ static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp)
 {
 	struct cfq_group_data *cgd;
 
-	cgd = kzalloc(sizeof(*cgd), GFP_KERNEL);
+	cgd = kzalloc(sizeof(*cgd), gfp);
 	if (!cgd)
 		return NULL;
 	return &cgd->cpd;
@@ -3003,7 +3003,6 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	if (time_before(jiffies, rq->fifo_time))
 		rq = NULL;
 
-	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }
 
@@ -3377,6 +3376,9 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;
 
+	if (cfq_cfqq_must_dispatch(cfqq))
+		return true;
+
 	/*
 	 * Drain async requests before we start sync IO
 	 */
@@ -3468,15 +3470,20 @@ static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
 
+	rq = cfq_check_fifo(cfqq);
+	if (rq)
+		cfq_mark_cfqq_must_dispatch(cfqq);
+
 	if (!cfq_may_dispatch(cfqd, cfqq))
 		return false;
 
 	/*
 	 * follow expired path, else get first next available
 	 */
-	rq = cfq_check_fifo(cfqq);
 	if (!rq)
 		rq = cfqq->next_rq;
+	else
+		cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 
 	/*
 	 * insert request into driver dispatch list
@@ -3944,7 +3951,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if the new request is sync, but the currently running queue is
 	 * not, let the sync request have priority.
 	 */
-	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
+	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
 		return true;
 
 	if (new_cfqq->cfqg != cfqq->cfqg)
diff --git a/block/genhd.c b/block/genhd.c
index e5cafa51567c..3032453a89e6 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -612,7 +612,7 @@ void add_disk(struct gendisk *disk)
 
 	/* Register BDI before referencing it from bdev */
 	bdi = &disk->queue->backing_dev_info;
-	bdi_register_dev(bdi, disk_devt(disk));
+	bdi_register_owner(bdi, disk_to_dev(disk));
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
@@ -664,7 +664,6 @@ void del_gendisk(struct gendisk *disk)
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
-	disk->driverfs_dev = NULL;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -831,6 +830,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v)
 	if (iter) {
 		class_dev_iter_exit(iter);
 		kfree(iter);
+		seqf->private = NULL;
 	}
 }
 
diff --git a/block/ioprio.c b/block/ioprio.c
index cc7800e9eb44..01b8116298a1 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p)
 	if (ret)
 		goto out;
 	ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+	task_lock(p);
 	if (p->io_context)
 		ret = p->io_context->ioprio;
+	task_unlock(p);
 out:
 	return ret;
 }
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 746935a5973c..3c062699f28b 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -349,15 +349,20 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_del;
 	}
 
+	err = hd_ref_init(p);
+	if (err) {
+		if (flags & ADDPART_FLAG_WHOLEDISK)
+			goto out_remove_file;
+		goto out_del;
+	}
+
 	/* everything is up and running, commence */
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
-
-	if (!hd_ref_init(p))
-		return p;
+	return p;
 
 out_free_info:
 	free_part_info(p);
@@ -366,6 +371,8 @@ out_free_stats:
 out_free:
 	kfree(p);
 	return ERR_PTR(err);
+out_remove_file:
+	device_remove_file(pdev, &dev_attr_whole_disk);
 out_del:
 	kobject_put(p->holder_dir);
 	device_del(pdev);
@@ -428,7 +435,6 @@ rescan:
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	check_disk_size_change(disk, bdev);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c
index 93e7c1b32edd..5610cd537da7 100644
--- a/block/partitions/msdos.c
+++ b/block/partitions/msdos.c
@@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state,
 			continue;
 		bsd_start = le32_to_cpu(p->p_offset);
 		bsd_size = le32_to_cpu(p->p_size);
+		if (memcmp(flavour, "bsd\0", 4) == 0)
+			bsd_start += offset;
 		if (offset == bsd_start && size == bsd_size)
 			/* full parent partition, we have it already */
 			continue;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 0774799942e0..c6fee7437be4 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(WRITE_16, filter->write_ok);
 	__set_bit(WRITE_LONG, filter->write_ok);
 	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(WRITE_SAME, filter->write_ok);
+	__set_bit(WRITE_SAME_16, filter->write_ok);
+	__set_bit(WRITE_SAME_32, filter->write_ok);
 	__set_bit(ERASE, filter->write_ok);
 	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
 	__set_bit(MODE_SELECT, filter->write_ok);
diff --git a/crypto/Makefile b/crypto/Makefile
index f7aba923458d..03e66097eb0c 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
 
 $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h
 $(obj)/rsaprivkey-asn1.o: $(obj)/rsaprivkey-asn1.c $(obj)/rsaprivkey-asn1.h
+$(obj)/rsa_helper.o: $(obj)/rsapubkey-asn1.h $(obj)/rsaprivkey-asn1.h
 clean-files += rsapubkey-asn1.c rsapubkey-asn1.h
 clean-files += rsaprivkey-asn1.c rsaprivkey-asn1.h
 
@@ -61,6 +62,7 @@ obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o
 obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o
 obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
+CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
 obj-$(CONFIG_CRYPTO_ECB) += ecb.o
@@ -84,6 +86,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH_COMMON) += blowfish_common.o
 obj-$(CONFIG_CRYPTO_TWOFISH) += twofish_generic.o
 obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
 obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
+CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o
 obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o
diff --git a/crypto/ahash.c b/crypto/ahash.c
index d19b52324cf5..f9caf0f74199 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -31,6 +31,7 @@ struct ahash_request_priv {
 	crypto_completion_t complete;
 	void *data;
 	u8 *result;
+	u32 flags;
 	void *ubuf[] CRYPTO_MINALIGN_ATTR;
 };
 
@@ -69,8 +70,9 @@ static int hash_walk_new_entry(struct crypto_hash_walk *walk)
 	struct scatterlist *sg;
 
 	sg = walk->sg;
-	walk->pg = sg_page(sg);
 	walk->offset = sg->offset;
+	walk->pg = sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT);
+	walk->offset = offset_in_page(walk->offset);
 	walk->entrylen = sg->length;
 
 	if (walk->entrylen > walk->total)
@@ -269,6 +271,8 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
 	priv->result = req->result;
 	priv->complete = req->base.complete;
 	priv->data = req->base.data;
+	priv->flags = req->base.flags;
+
 	/*
 	 * WARNING: We do not backup req->priv here! The req->priv
 	 *          is for internal use of the Crypto API and the
@@ -283,38 +287,44 @@ static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
 	return 0;
 }
 
-static void ahash_restore_req(struct ahash_request *req)
+static void ahash_restore_req(struct ahash_request *req, int err)
 {
 	struct ahash_request_priv *priv = req->priv;
 
+	if (!err)
+		memcpy(priv->result, req->result,
+		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+
 	/* Restore the original crypto request. */
 	req->result = priv->result;
-	req->base.complete = priv->complete;
-	req->base.data = priv->data;
+
+	ahash_request_set_callback(req, priv->flags,
+				   priv->complete, priv->data);
 	req->priv = NULL;
 
 	/* Free the req->priv.priv from the ADJUSTED request. */
 	kzfree(priv);
 }
 
-static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
+static void ahash_notify_einprogress(struct ahash_request *req)
 {
 	struct ahash_request_priv *priv = req->priv;
+	struct crypto_async_request oreq;
 
-	if (err == -EINPROGRESS)
-		return;
-
-	if (!err)
-		memcpy(priv->result, req->result,
-		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+	oreq.data = priv->data;
 
-	ahash_restore_req(req);
+	priv->complete(&oreq, -EINPROGRESS);
 }
 
 static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
 
+	if (err == -EINPROGRESS) {
+		ahash_notify_einprogress(areq);
+		return;
+	}
+
 	/*
 	 * Restore the original request, see ahash_op_unaligned() for what
 	 * goes where.
@@ -325,7 +335,7 @@ static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
 	 */
 
 	/* First copy req->result into req->priv.result */
-	ahash_op_unaligned_finish(areq, err);
+	ahash_restore_req(areq, err);
 
 	/* Complete the ORIGINAL request. */
 	areq->base.complete(&areq->base, err);
@@ -341,7 +351,12 @@ static int ahash_op_unaligned(struct ahash_request *req,
 		return err;
 
 	err = op(req);
-	ahash_op_unaligned_finish(req, err);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
+
+	ahash_restore_req(req, err);
 
 	return err;
 }
@@ -376,25 +391,14 @@ int crypto_ahash_digest(struct ahash_request *req)
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_digest);
 
-static void ahash_def_finup_finish2(struct ahash_request *req, int err)
+static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
 {
-	struct ahash_request_priv *priv = req->priv;
+	struct ahash_request *areq = req->data;
 
 	if (err == -EINPROGRESS)
 		return;
 
-	if (!err)
-		memcpy(priv->result, req->result,
-		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
-
-	ahash_restore_req(req);
-}
-
-static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
-{
-	struct ahash_request *areq = req->data;
-
-	ahash_def_finup_finish2(areq, err);
+	ahash_restore_req(areq, err);
 
 	areq->base.complete(&areq->base, err);
 }
@@ -405,11 +409,15 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err)
 		goto out;
 
 	req->base.complete = ahash_def_finup_done2;
-	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
 	err = crypto_ahash_reqtfm(req)->final(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
 
 out:
-	ahash_def_finup_finish2(req, err);
+	ahash_restore_req(req, err);
 	return err;
 }
 
@@ -417,7 +425,16 @@ static void ahash_def_finup_done1(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
 
+	if (err == -EINPROGRESS) {
+		ahash_notify_einprogress(areq);
+		return;
+	}
+
+	areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
 	err = ahash_def_finup_finish1(areq, err);
+	if (areq->priv)
+		return;
 
 	areq->base.complete(&areq->base, err);
 }
@@ -432,6 +449,11 @@ static int ahash_def_finup(struct ahash_request *req)
 		return err;
 
 	err = tfm->update(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && (ahash_request_flags(req) &
+			       CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		return err;
+
 	return ahash_def_finup_finish1(req, err);
 }
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 59bf491fe3d8..43f5bdb6b570 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -357,6 +357,7 @@ int crypto_register_alg(struct crypto_alg *alg)
 	struct crypto_larval *larval;
 	int err;
 
+	alg->cra_flags &= ~CRYPTO_ALG_DEAD;
 	err = crypto_check_alg(alg);
 	if (err)
 		return err;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 6d4d4569447e..faea9d728fd2 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -29,6 +29,11 @@ struct aead_sg_list {
 	struct scatterlist sg[ALG_MAX_PAGES];
 };
 
+struct aead_tfm {
+	struct crypto_aead *aead;
+	bool has_key;
+};
+
 struct aead_ctx {
 	struct aead_sg_list tsgl;
 	/*
@@ -513,24 +518,146 @@ static struct proto_ops algif_aead_ops = {
 	.poll		=	aead_poll,
 };
 
+static int aead_check_key(struct socket *sock)
+{
+	int err = 0;
+	struct sock *psk;
+	struct alg_sock *pask;
+	struct aead_tfm *tfm;
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+
+	lock_sock(sk);
+	if (ask->refcnt)
+		goto unlock_child;
+
+	psk = ask->parent;
+	pask = alg_sk(ask->parent);
+	tfm = pask->private;
+
+	err = -ENOKEY;
+	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
+	if (!tfm->has_key)
+		goto unlock;
+
+	if (!pask->refcnt++)
+		sock_hold(psk);
+
+	ask->refcnt = 1;
+	sock_put(psk);
+
+	err = 0;
+
+unlock:
+	release_sock(psk);
+unlock_child:
+	release_sock(sk);
+
+	return err;
+}
+
+static int aead_sendmsg_nokey(struct socket *sock, struct msghdr *msg,
+				  size_t size)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_sendmsg(sock, msg, size);
+}
+
+static ssize_t aead_sendpage_nokey(struct socket *sock, struct page *page,
+				       int offset, size_t size, int flags)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_sendpage(sock, page, offset, size, flags);
+}
+
+static int aead_recvmsg_nokey(struct socket *sock, struct msghdr *msg,
+				  size_t ignored, int flags)
+{
+	int err;
+
+	err = aead_check_key(sock);
+	if (err)
+		return err;
+
+	return aead_recvmsg(sock, msg, ignored, flags);
+}
+
+static struct proto_ops algif_aead_ops_nokey = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.accept		=	sock_no_accept,
+	.setsockopt	=	sock_no_setsockopt,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	aead_sendmsg_nokey,
+	.sendpage	=	aead_sendpage_nokey,
+	.recvmsg	=	aead_recvmsg_nokey,
+	.poll		=	aead_poll,
+};
+
 static void *aead_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_aead(name, type, mask);
+	struct aead_tfm *tfm;
+	struct crypto_aead *aead;
+
+	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
+	if (!tfm)
+		return ERR_PTR(-ENOMEM);
+
+	aead = crypto_alloc_aead(name, type, mask);
+	if (IS_ERR(aead)) {
+		kfree(tfm);
+		return ERR_CAST(aead);
+	}
+
+	tfm->aead = aead;
+
+	return tfm;
 }
 
 static void aead_release(void *private)
 {
-	crypto_free_aead(private);
+	struct aead_tfm *tfm = private;
+
+	crypto_free_aead(tfm->aead);
+	kfree(tfm);
 }
 
 static int aead_setauthsize(void *private, unsigned int authsize)
 {
-	return crypto_aead_setauthsize(private, authsize);
+	struct aead_tfm *tfm = private;
+
+	return crypto_aead_setauthsize(tfm->aead, authsize);
 }
 
 static int aead_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	return crypto_aead_setkey(private, key, keylen);
+	struct aead_tfm *tfm = private;
+	int err;
+
+	err = crypto_aead_setkey(tfm->aead, key, keylen);
+	tfm->has_key = !err;
+
+	return err;
 }
 
 static void aead_sock_destruct(struct sock *sk)
@@ -546,12 +673,14 @@ static void aead_sock_destruct(struct sock *sk)
 	af_alg_release_parent(sk);
 }
 
-static int aead_accept_parent(void *private, struct sock *sk)
+static int aead_accept_parent_nokey(void *private, struct sock *sk)
 {
 	struct aead_ctx *ctx;
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(private);
-	unsigned int ivlen = crypto_aead_ivsize(private);
+	struct aead_tfm *tfm = private;
+	struct crypto_aead *aead = tfm->aead;
+	unsigned int len = sizeof(*ctx) + crypto_aead_reqsize(aead);
+	unsigned int ivlen = crypto_aead_ivsize(aead);
 
 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
@@ -577,7 +706,7 @@ static int aead_accept_parent(void *private, struct sock *sk)
 
 	ask->private = ctx;
 
-	aead_request_set_tfm(&ctx->aead_req, private);
+	aead_request_set_tfm(&ctx->aead_req, aead);
 	aead_request_set_callback(&ctx->aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  af_alg_complete, &ctx->completion);
 
@@ -586,13 +715,25 @@ static int aead_accept_parent(void *private, struct sock *sk)
 	return 0;
 }
 
+static int aead_accept_parent(void *private, struct sock *sk)
+{
+	struct aead_tfm *tfm = private;
+
+	if (!tfm->has_key)
+		return -ENOKEY;
+
+	return aead_accept_parent_nokey(private, sk);
+}
+
 static const struct af_alg_type algif_type_aead = {
 	.bind		=	aead_bind,
 	.release	=	aead_release,
 	.setkey		=	aead_setkey,
 	.setauthsize	=	aead_setauthsize,
 	.accept		=	aead_accept_parent,
+	.accept_nokey	=	aead_accept_parent_nokey,
 	.ops		=	&algif_aead_ops,
+	.ops_nokey	=	&algif_aead_ops_nokey,
 	.name		=	"aead",
 	.owner		=	THIS_MODULE
 };
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 68a5ceaa04c8..8d8b3eeba725 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -184,7 +184,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
 	struct ahash_request *req = &ctx->req;
-	char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req))];
+	char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req)) ? : 1];
 	struct sock *sk2;
 	struct alg_sock *ask2;
 	struct hash_ctx *ctx2;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index f5e9f9310b48..b3b0004ea8ac 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -86,8 +86,13 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq)
 	}
 	sgl = sreq->tsg;
 	n = sg_nents(sgl);
-	for_each_sg(sgl, sg, n, i)
-		put_page(sg_page(sg));
+	for_each_sg(sgl, sg, n, i) {
+		struct page *page = sg_page(sg);
+
+		/* some SGs may not have a page mapped */
+		if (page && atomic_read(&page->_count))
+			put_page(page);
+	}
 
 	kfree(sreq->tsg);
 }
diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig
index 4870f28403f5..05bfe568cd30 100644
--- a/crypto/asymmetric_keys/Kconfig
+++ b/crypto/asymmetric_keys/Kconfig
@@ -14,6 +14,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
 	select MPILIB
 	select PUBLIC_KEY_ALGO_RSA
 	select CRYPTO_HASH_INFO
+	select CRYPTO_AKCIPHER
 	help
 	  This option provides support for asymmetric public key type handling.
 	  If signature generation and/or verification are to be used,
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index 758acabf2d81..8f3056cd0399 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -547,9 +547,7 @@ int pkcs7_sig_note_set_of_authattrs(void *context, size_t hdrlen,
 	struct pkcs7_signed_info *sinfo = ctx->sinfo;
 
 	if (!test_bit(sinfo_has_content_type, &sinfo->aa_set) ||
-	    !test_bit(sinfo_has_message_digest, &sinfo->aa_set) ||
-	    (ctx->msg->data_type == OID_msIndirectData &&
-	     !test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))) {
+	    !test_bit(sinfo_has_message_digest, &sinfo->aa_set)) {
 		pr_warn("Missing required AuthAttr\n");
 		return -EBADMSG;
 	}
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index 90d6d47965b0..ecdb5a2ce085 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -178,6 +178,8 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7,
 	int cached_ret = -ENOKEY;
 	int ret;
 
+	*_trusted = false;
+
 	for (p = pkcs7->certs; p; p = p->next)
 		p->seen = false;
 
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 021d39c0ba75..13c4e5a5fe8c 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -494,7 +494,7 @@ int x509_decode_time(time64_t *_t,  size_t hdrlen,
 		     unsigned char tag,
 		     const unsigned char *value, size_t vlen)
 {
-	static const unsigned char month_lengths[] = { 31, 29, 31, 30, 31, 30,
+	static const unsigned char month_lengths[] = { 31, 28, 31, 30, 31, 30,
 						       31, 31, 30, 31, 30, 31 };
 	const unsigned char *p = value;
 	unsigned year, mon, day, hour, min, sec, mon_len;
@@ -540,9 +540,9 @@ int x509_decode_time(time64_t *_t,  size_t hdrlen,
 		if (year % 4 == 0) {
 			mon_len = 29;
 			if (year % 100 == 0) {
-				year /= 100;
-				if (year % 4 != 0)
-					mon_len = 28;
+				mon_len = 28;
+				if (year % 400 == 0)
+					mon_len = 29;
 			}
 		}
 	}
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index c0748bbd4c08..84f8d4d8b6bc 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -368,8 +368,6 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 
 		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
-
-		return tx;
 	} else {
 		struct page *p_src = P(blocks, disks);
 		struct page *q_src = Q(blocks, disks);
@@ -424,9 +422,11 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		submit->cb_param = cb_param_orig;
 		submit->flags = flags_orig;
 		async_tx_sync_epilog(submit);
-
-		return NULL;
+		tx = NULL;
 	}
+	dmaengine_unmap_put(unmap);
+
+	return tx;
 }
 EXPORT_SYMBOL_GPL(async_syndrome_val);
 
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 0c0468869e25..52154ef21b5e 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -245,6 +245,9 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	u8 *ihash = ohash + crypto_ahash_digestsize(auth);
 	u32 tmp[2];
 
+	if (!authsize)
+		goto decrypt;
+
 	/* Move high-order bits of sequence number back. */
 	scatterwalk_map_and_copy(tmp, dst, 4, 4, 0);
 	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0);
@@ -253,6 +256,8 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	if (crypto_memneq(ihash, ohash, authsize))
 		return -EBADMSG;
 
+decrypt:
+
 	sg_init_table(areq_ctx->dst, 2);
 	dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen);
 
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 8cc1622b2ee0..dca7bc87dad9 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -234,6 +234,8 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
+	bsize = min(walk->walk_blocksize, n);
+
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
 	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
@@ -246,7 +248,6 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index c81861b1350b..26a504db3f53 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -594,9 +594,14 @@ static int cryptd_hash_export(struct ahash_request *req, void *out)
 
 static int cryptd_hash_import(struct ahash_request *req, const void *in)
 {
-	struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct shash_desc *desc = cryptd_shash_desc(req);
+
+	desc->tfm = ctx->child;
+	desc->flags = req->base.flags;
 
-	return crypto_shash_import(&rctx->desc, in);
+	return crypto_shash_import(desc, in);
 }
 
 static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
@@ -637,6 +642,7 @@ static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = cryptd_hash_init_tfm;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 43fe85f20d57..7097a3395b25 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = {
 	[CRYPTO_MSG_NEWALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_UPDATEALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = 0,
 };
 
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index b96a84560b67..343a74e96e2a 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -1,8 +1,8 @@
 /*
  * echainiv: Encrypted Chain IV Generator
  *
- * This generator generates an IV based on a sequence number by xoring it
- * with a salt and then encrypting it with the same key as used to encrypt
+ * This generator generates an IV based on a sequence number by multiplying
+ * it with a salt and then encrypting it with the same key as used to encrypt
  * the plain text.  This algorithm requires that the block size be equal
  * to the IV size.  It is mainly useful for CBC.
  *
@@ -23,81 +23,17 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
-#define MAX_IV_SIZE 16
-
-static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
-
-/* We don't care if we get preempted and read/write IVs from the next CPU. */
-static void echainiv_read_iv(u8 *dst, unsigned size)
-{
-	u32 *a = (u32 *)dst;
-	u32 __percpu *b = echainiv_iv;
-
-	for (; size >= 4; size -= 4) {
-		*a++ = this_cpu_read(*b);
-		b++;
-	}
-}
-
-static void echainiv_write_iv(const u8 *src, unsigned size)
-{
-	const u32 *a = (const u32 *)src;
-	u32 __percpu *b = echainiv_iv;
-
-	for (; size >= 4; size -= 4) {
-		this_cpu_write(*b, *a);
-		a++;
-		b++;
-	}
-}
-
-static void echainiv_encrypt_complete2(struct aead_request *req, int err)
-{
-	struct aead_request *subreq = aead_request_ctx(req);
-	struct crypto_aead *geniv;
-	unsigned int ivsize;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	if (err)
-		goto out;
-
-	geniv = crypto_aead_reqtfm(req);
-	ivsize = crypto_aead_ivsize(geniv);
-
-	echainiv_write_iv(subreq->iv, ivsize);
-
-	if (req->iv != subreq->iv)
-		memcpy(req->iv, subreq->iv, ivsize);
-
-out:
-	if (req->iv != subreq->iv)
-		kzfree(subreq->iv);
-}
-
-static void echainiv_encrypt_complete(struct crypto_async_request *base,
-					 int err)
-{
-	struct aead_request *req = base->data;
-
-	echainiv_encrypt_complete2(req, err);
-	aead_request_complete(req, err);
-}
-
 static int echainiv_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
 	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *subreq = aead_request_ctx(req);
-	crypto_completion_t compl;
-	void *data;
+	__be64 nseqno;
+	u64 seqno;
 	u8 *info;
 	unsigned int ivsize = crypto_aead_ivsize(geniv);
 	int err;
@@ -107,8 +43,6 @@ static int echainiv_encrypt(struct aead_request *req)
 
 	aead_request_set_tfm(subreq, ctx->child);
 
-	compl = echainiv_encrypt_complete;
-	data = req;
 	info = req->iv;
 
 	if (req->src != req->dst) {
@@ -123,29 +57,30 @@ static int echainiv_encrypt(struct aead_request *req)
 			return err;
 	}
 
-	if (unlikely(!IS_ALIGNED((unsigned long)info,
-				 crypto_aead_alignmask(geniv) + 1))) {
-		info = kmalloc(ivsize, req->base.flags &
-				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
-								  GFP_ATOMIC);
-		if (!info)
-			return -ENOMEM;
-
-		memcpy(info, req->iv, ivsize);
-	}
-
-	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
 	aead_request_set_crypt(subreq, req->dst, req->dst,
 			       req->cryptlen, info);
 	aead_request_set_ad(subreq, req->assoclen);
 
-	crypto_xor(info, ctx->salt, ivsize);
+	memcpy(&nseqno, info + ivsize - 8, 8);
+	seqno = be64_to_cpu(nseqno);
+	memset(info, 0, ivsize);
+
 	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
-	echainiv_read_iv(info, ivsize);
 
-	err = crypto_aead_encrypt(subreq);
-	echainiv_encrypt_complete2(req, err);
-	return err;
+	do {
+		u64 a;
+
+		memcpy(&a, ctx->salt + ivsize - 8, 8);
+
+		a |= 1;
+		a *= seqno;
+
+		memcpy(info + ivsize - 8, &a, 8);
+	} while ((ivsize -= 8));
+
+	return crypto_aead_encrypt(subreq);
 }
 
 static int echainiv_decrypt(struct aead_request *req)
@@ -192,8 +127,7 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
-	if (inst->alg.ivsize & (sizeof(u32) - 1) ||
-	    inst->alg.ivsize > MAX_IV_SIZE)
+	if (inst->alg.ivsize & (sizeof(u64) - 1) || !inst->alg.ivsize)
 		goto free_inst;
 
 	inst->alg.encrypt = echainiv_encrypt;
@@ -202,7 +136,6 @@ static int echainiv_aead_create(struct crypto_template *tmpl,
 	inst->alg.init = aead_init_geniv;
 	inst->alg.exit = aead_exit_geniv;
 
-	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
 	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
 	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
 
diff --git a/crypto/gcm.c b/crypto/gcm.c
index bec329b3de8d..0a12c09d7cb2 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -117,7 +117,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	struct crypto_ablkcipher *ctr = ctx->ctr;
 	struct {
 		be128 hash;
-		u8 iv[8];
+		u8 iv[16];
 
 		struct crypto_gcm_setkey_result result;
 
@@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	err = crypto_ablkcipher_encrypt(&data->req);
 	if (err == -EINPROGRESS || err == -EBUSY) {
-		err = wait_for_completion_interruptible(
-			&data->result.completion);
-		if (!err)
-			err = data->result.err;
+		wait_for_completion(&data->result.completion);
+		err = data->result.err;
 	}
 
 	if (err)
@@ -639,7 +637,9 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
-				    CRYPTO_ALG_TYPE_AHASH_MASK);
+				    CRYPTO_ALG_TYPE_AHASH_MASK |
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (IS_ERR(ghash_alg))
 		return PTR_ERR(ghash_alg);
 
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index bac70995e064..12ad3e3a84e3 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -14,24 +14,13 @@
 
 #include <crypto/algapi.h>
 #include <crypto/gf128mul.h>
+#include <crypto/ghash.h>
 #include <crypto/internal/hash.h>
 #include <linux/crypto.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-#define GHASH_BLOCK_SIZE	16
-#define GHASH_DIGEST_SIZE	16
-
-struct ghash_ctx {
-	struct gf128mul_4k *gf128;
-};
-
-struct ghash_desc_ctx {
-	u8 buffer[GHASH_BLOCK_SIZE];
-	u32 bytes;
-};
-
 static int ghash_init(struct shash_desc *desc)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
diff --git a/crypto/keywrap.c b/crypto/keywrap.c
index b1d106ce55f3..72014f963ba7 100644
--- a/crypto/keywrap.c
+++ b/crypto/keywrap.c
@@ -212,7 +212,7 @@ static int crypto_kw_decrypt(struct blkcipher_desc *desc,
 			  SEMIBSIZE))
 		ret = -EBADMSG;
 
-	memzero_explicit(&block, sizeof(struct crypto_kw_block));
+	memzero_explicit(block, sizeof(struct crypto_kw_block));
 
 	return ret;
 }
@@ -297,7 +297,7 @@ static int crypto_kw_encrypt(struct blkcipher_desc *desc,
 	/* establish the IV for the caller to pick up */
 	memcpy(desc->info, block->A, SEMIBSIZE);
 
-	memzero_explicit(&block, sizeof(struct crypto_kw_block));
+	memzero_explicit(block, sizeof(struct crypto_kw_block));
 
 	return 0;
 }
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index fe5b495a434d..b4f3930266b1 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -258,18 +258,22 @@ out_free_inst:
 	goto out;
 }
 
-static inline void mcryptd_check_internal(struct rtattr **tb, u32 *type,
+static inline bool mcryptd_check_internal(struct rtattr **tb, u32 *type,
 					  u32 *mask)
 {
 	struct crypto_attr_type *algt;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return;
-	if ((algt->type & CRYPTO_ALG_INTERNAL))
-		*type |= CRYPTO_ALG_INTERNAL;
-	if ((algt->mask & CRYPTO_ALG_INTERNAL))
-		*mask |= CRYPTO_ALG_INTERNAL;
+		return false;
+
+	*type |= algt->type & CRYPTO_ALG_INTERNAL;
+	*mask |= algt->mask & CRYPTO_ALG_INTERNAL;
+
+	if (*type & *mask & CRYPTO_ALG_INTERNAL)
+		return true;
+	else
+		return false;
 }
 
 static int mcryptd_hash_init_tfm(struct crypto_tfm *tfm)
@@ -498,7 +502,8 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	u32 mask = 0;
 	int err;
 
-	mcryptd_check_internal(tb, &type, &mask);
+	if (!mcryptd_check_internal(tb, &type, &mask))
+		return -EINVAL;
 
 	salg = shash_attr_alg(tb[1], type, mask);
 	if (IS_ERR(salg))
@@ -526,6 +531,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index ea5815c5e128..bc769c448d4a 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -72,7 +72,8 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
 
 void scatterwalk_done(struct scatter_walk *walk, int out, int more)
 {
-	if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more)
+	if (!more || walk->offset >= walk->sg->offset + walk->sg->length ||
+	    !(walk->offset & (PAGE_SIZE - 1)))
 		scatterwalk_pagedone(walk, out, more);
 }
 EXPORT_SYMBOL_GPL(scatterwalk_done);
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index ae8c57fd8bc7..5f15f45fcc9f 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -488,6 +488,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  tcrypt_complete, &result);
 
+	iv_len = crypto_aead_ivsize(tfm);
+
 	for (i = 0, j = 0; i < tcount; i++) {
 		if (template[i].np)
 			continue;
@@ -508,7 +510,6 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 		memcpy(input, template[i].input, template[i].ilen);
 		memcpy(assoc, template[i].assoc, template[i].alen);
-		iv_len = crypto_aead_ivsize(tfm);
 		if (template[i].iv)
 			memcpy(iv, template[i].iv, iv_len);
 		else
@@ -617,7 +618,7 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		j++;
 
 		if (template[i].iv)
-			memcpy(iv, template[i].iv, MAX_IVLEN);
+			memcpy(iv, template[i].iv, iv_len);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
@@ -1849,6 +1850,7 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 static int do_test_rsa(struct crypto_akcipher *tfm,
 		       struct akcipher_testvec *vecs)
 {
+	char *xbuf[XBUFSIZE];
 	struct akcipher_request *req;
 	void *outbuf_enc = NULL;
 	void *outbuf_dec = NULL;
@@ -1857,9 +1859,12 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 	int err = -ENOMEM;
 	struct scatterlist src, dst, src_tab[2];
 
+	if (testmgr_alloc_buf(xbuf))
+		return err;
+
 	req = akcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req)
-		return err;
+		goto free_xbuf;
 
 	init_completion(&result.completion);
 
@@ -1877,9 +1882,14 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 	if (!outbuf_enc)
 		goto free_req;
 
+	if (WARN_ON(vecs->m_size > PAGE_SIZE))
+		goto free_all;
+
+	memcpy(xbuf[0], vecs->m, vecs->m_size);
+
 	sg_init_table(src_tab, 2);
-	sg_set_buf(&src_tab[0], vecs->m, 8);
-	sg_set_buf(&src_tab[1], vecs->m + 8, vecs->m_size - 8);
+	sg_set_buf(&src_tab[0], xbuf[0], 8);
+	sg_set_buf(&src_tab[1], xbuf[0] + 8, vecs->m_size - 8);
 	sg_init_one(&dst, outbuf_enc, out_len_max);
 	akcipher_request_set_crypt(req, src_tab, &dst, vecs->m_size,
 				   out_len_max);
@@ -1898,7 +1908,7 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 		goto free_all;
 	}
 	/* verify that encrypted message is equal to expected */
-	if (memcmp(vecs->c, sg_virt(req->dst), vecs->c_size)) {
+	if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) {
 		pr_err("alg: rsa: encrypt test failed. Invalid output\n");
 		err = -EINVAL;
 		goto free_all;
@@ -1913,7 +1923,13 @@ static int do_test_rsa(struct crypto_akcipher *tfm,
 		err = -ENOMEM;
 		goto free_all;
 	}
-	sg_init_one(&src, vecs->c, vecs->c_size);
+
+	if (WARN_ON(vecs->c_size > PAGE_SIZE))
+		goto free_all;
+
+	memcpy(xbuf[0], vecs->c, vecs->c_size);
+
+	sg_init_one(&src, xbuf[0], vecs->c_size);
 	sg_init_one(&dst, outbuf_dec, out_len_max);
 	init_completion(&result.completion);
 	akcipher_request_set_crypt(req, &src, &dst, vecs->c_size, out_len_max);
@@ -1940,6 +1956,8 @@ free_all:
 	kfree(outbuf_enc);
 free_req:
 	akcipher_request_free(req);
+free_xbuf:
+	testmgr_free_buf(xbuf);
 	return err;
 }
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index da0a8fd765f4..0e02c60a57b6 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -21778,7 +21778,7 @@ static struct aead_testvec aes_ccm_enc_tv_template[] = {
 			  "\x09\x75\x9a\x9b\x3c\x9b\x27\x39",
 		.klen	= 32,
 		.iv	= "\x03\xf9\xd9\x4e\x63\xb5\x3d\x9d"
-			  "\x43\xf6\x1e\x50",
+			  "\x43\xf6\x1e\x50\0\0\0\0",
 		.assoc	= "\x57\xf5\x6b\x8b\x57\x5c\x3d\x3b"
 			  "\x13\x02\x01\x0c\x83\x4c\x96\x35"
 			  "\x8e\xd6\x39\xcf\x7d\x14\x9b\x94"
diff --git a/drivers/Makefile b/drivers/Makefile
index e694c0c2735d..a2a1fbd53bbe 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -98,6 +98,7 @@ obj-$(CONFIG_USB_PHY)		+= usb/
 obj-$(CONFIG_USB)		+= usb/
 obj-$(CONFIG_PCI)		+= usb/
 obj-$(CONFIG_USB_GADGET)	+= usb/
+obj-$(CONFIG_OF)		+= usb/
 obj-$(CONFIG_SERIO)		+= input/serio/
 obj-$(CONFIG_GAMEPORT)		+= input/gameport/
 obj-$(CONFIG_INPUT)		+= input/
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 675eaf337178..b9cebca376f9 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the Linux ACPI interpreter
 #
 
-ccflags-y			:= -Os
 ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
 
 #
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 296b7a14893a..5365ff6e69c1 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -24,9 +24,11 @@
 ACPI_MODULE_NAME("platform");
 
 static const struct acpi_device_id forbidden_id_list[] = {
-	{"PNP0000", 0},	/* PIC */
-	{"PNP0100", 0},	/* Timer */
-	{"PNP0200", 0},	/* AT DMA Controller */
+	{"PNP0000",  0},	/* PIC */
+	{"PNP0100",  0},	/* Timer */
+	{"PNP0200",  0},	/* AT DMA Controller */
+	{"ACPI0009", 0},	/* IOxAPIC */
+	{"ACPI000A", 0},	/* IOAPIC */
 	{"", 0},
 };
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 6979186dbd4b..9f77943653fb 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -491,6 +491,58 @@ static void acpi_processor_remove(struct acpi_device *device)
 }
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+#ifdef CONFIG_X86
+static bool acpi_hwp_native_thermal_lvt_set;
+static acpi_status __init acpi_hwp_native_thermal_lvt_osc(acpi_handle handle,
+							  u32 lvl,
+							  void *context,
+							  void **rv)
+{
+	u8 sb_uuid_str[] = "4077A616-290C-47BE-9EBD-D87058713953";
+	u32 capbuf[2];
+	struct acpi_osc_context osc_context = {
+		.uuid_str = sb_uuid_str,
+		.rev = 1,
+		.cap.length = 8,
+		.cap.pointer = capbuf,
+	};
+
+	if (acpi_hwp_native_thermal_lvt_set)
+		return AE_CTRL_TERMINATE;
+
+	capbuf[0] = 0x0000;
+	capbuf[1] = 0x1000; /* set bit 12 */
+
+	if (ACPI_SUCCESS(acpi_run_osc(handle, &osc_context))) {
+		if (osc_context.ret.pointer && osc_context.ret.length > 1) {
+			u32 *capbuf_ret = osc_context.ret.pointer;
+
+			if (capbuf_ret[1] & 0x1000) {
+				acpi_handle_info(handle,
+					"_OSC native thermal LVT Acked\n");
+				acpi_hwp_native_thermal_lvt_set = true;
+			}
+		}
+		kfree(osc_context.ret.pointer);
+	}
+
+	return AE_OK;
+}
+
+void __init acpi_early_processor_osc(void)
+{
+	if (boot_cpu_has(X86_FEATURE_HWP)) {
+		acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
+				    ACPI_UINT32_MAX,
+				    acpi_hwp_native_thermal_lvt_osc,
+				    NULL, NULL, NULL);
+		acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID,
+				 acpi_hwp_native_thermal_lvt_osc,
+				 NULL, NULL);
+	}
+}
+#endif
+
 /*
  * The following ACPI IDs are known to be suitable for representing as
  * processor devices.
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 5fdac394207a..549cdbed7b0e 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -1211,6 +1211,9 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video)
 	union acpi_object *dod = NULL;
 	union acpi_object *obj;
 
+	if (!video->cap._DOD)
+		return AE_NOT_EXIST;
+
 	status = acpi_evaluate_object(video->device->handle, "_DOD", NULL, &buffer);
 	if (!ACPI_SUCCESS(status)) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _DOD"));
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index bc32f3194afe..28c50c6b5f45 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -417,6 +417,9 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node,
 				obj_desc->method.mutex->mutex.
 				    original_sync_level =
 				    obj_desc->method.mutex->mutex.sync_level;
+
+				obj_desc->method.mutex->mutex.thread_id =
+				    acpi_os_get_thread_id();
 			}
 		}
 
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 5f97468df8ff..b2e50d8007fe 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -504,11 +504,20 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 *sleep_type_a, u8 *sleep_type_b)
 	 * Evaluate the \_Sx namespace object containing the register values
 	 * for this state
 	 */
-	info->relative_pathname =
-	    ACPI_CAST_PTR(char, acpi_gbl_sleep_state_names[sleep_state]);
+	info->relative_pathname = ACPI_CAST_PTR(char,
+						acpi_gbl_sleep_state_names
+						[sleep_state]);
+
 	status = acpi_ns_evaluate(info);
 	if (ACPI_FAILURE(status)) {
-		goto cleanup;
+		if (status == AE_NOT_FOUND) {
+
+			/* The _Sx states are optional, ignore NOT_FOUND */
+
+			goto final_cleanup;
+		}
+
+		goto warning_cleanup;
 	}
 
 	/* Must have a return object */
@@ -517,7 +526,7 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 *sleep_type_a, u8 *sleep_type_b)
 		ACPI_ERROR((AE_INFO, "No Sleep State object returned from [%s]",
 			    info->relative_pathname));
 		status = AE_AML_NO_RETURN_VALUE;
-		goto cleanup;
+		goto warning_cleanup;
 	}
 
 	/* Return object must be of type Package */
@@ -526,7 +535,7 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 *sleep_type_a, u8 *sleep_type_b)
 		ACPI_ERROR((AE_INFO,
 			    "Sleep State return object is not a Package"));
 		status = AE_AML_OPERAND_TYPE;
-		goto cleanup1;
+		goto return_value_cleanup;
 	}
 
 	/*
@@ -570,16 +579,17 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 *sleep_type_a, u8 *sleep_type_b)
 		break;
 	}
 
-cleanup1:
+return_value_cleanup:
 	acpi_ut_remove_reference(info->return_object);
 
-cleanup:
+warning_cleanup:
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status,
 				"While evaluating Sleep State [%s]",
 				info->relative_pathname));
 	}
 
+final_cleanup:
 	ACPI_FREE(info);
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3dd9c462d22a..bb81cd05f0bc 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -657,7 +657,7 @@ static int ghes_proc(struct ghes *ghes)
 	ghes_do_proc(ghes, ghes->estatus);
 out:
 	ghes_clear_estatus(ghes);
-	return 0;
+	return rc;
 }
 
 static void ghes_add_timer(struct ghes *ghes)
@@ -847,6 +847,8 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		if (ghes_read_estatus(ghes, 1)) {
 			ghes_clear_estatus(ghes);
 			continue;
+		} else {
+			ret = NMI_HANDLED;
 		}
 
 		sev = ghes_severity(ghes->estatus->error_severity);
@@ -858,12 +860,11 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 
 		__process_error(ghes);
 		ghes_clear_estatus(ghes);
-
-		ret = NMI_HANDLED;
 	}
 
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-	irq_work_queue(&ghes_proc_irq_work);
+	if (ret == NMI_HANDLED)
+		irq_work_queue(&ghes_proc_irq_work);
 #endif
 	atomic_dec(&ghes_in_nmi);
 	return ret;
@@ -1066,6 +1067,7 @@ static int ghes_remove(struct platform_device *ghes_dev)
 		if (list_empty(&ghes_sci))
 			unregister_acpi_hed_notifier(&ghes_notifier_sci);
 		mutex_unlock(&ghes_list_mutex);
+		synchronize_rcu();
 		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 96809cd99ace..2f24b578bcaf 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -346,6 +346,34 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		      DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343"),
 		},
 	},
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Precision 5520",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Precision 5520"),
+		},
+	},
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Precision 3520",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3520"),
+		},
+	},
+	/*
+	 * Resolves a quirk with the Dell Latitude 3350 that
+	 * causes the ethernet adapter to not function.
+	 */
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Latitude 3350",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3350"),
+		},
+	},
 #endif
 	{}
 };
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index a212cefae524..ca4f28432d87 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1004,6 +1004,9 @@ static int __init acpi_bus_init(void)
 		goto error1;
 	}
 
+	/* Set capability bits for _OSC under processor scope */
+	acpi_early_processor_osc();
+
 	/*
 	 * _OSC method may exist in module level code,
 	 * so it must be run after ACPI_FULL_INITIALIZATION
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 6730f965b379..0afd1981e350 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -216,8 +216,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 			continue;
 
 		cpc_ptr = per_cpu(cpc_desc_ptr, i);
-		if (!cpc_ptr)
-			continue;
+		if (!cpc_ptr) {
+			retval = -EFAULT;
+			goto err_ret;
+		}
 
 		pdomain = &(cpc_ptr->domain_info);
 		cpumask_set_cpu(i, pr->shared_cpu_map);
@@ -239,8 +241,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 				continue;
 
 			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
-			if (!match_cpc_ptr)
-				continue;
+			if (!match_cpc_ptr) {
+				retval = -EFAULT;
+				goto err_ret;
+			}
 
 			match_pdomain = &(match_cpc_ptr->domain_info);
 			if (match_pdomain->domain != pdomain->domain)
@@ -270,8 +274,10 @@ int acpi_get_psd_map(struct cpudata **all_cpu_data)
 				continue;
 
 			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
-			if (!match_cpc_ptr)
-				continue;
+			if (!match_cpc_ptr) {
+				retval = -EFAULT;
+				goto err_ret;
+			}
 
 			match_pdomain = &(match_cpc_ptr->domain_info);
 			if (match_pdomain->domain != pdomain->domain)
@@ -502,9 +508,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	/* Store CPU Logical ID */
 	cpc_ptr->cpu_id = pr->id;
 
-	/* Plug it into this CPUs CPC descriptor. */
-	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
-
 	/* Parse PSD data for this CPU */
 	ret = acpi_get_psd(cpc_ptr, handle);
 	if (ret)
@@ -517,6 +520,9 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 			goto out_free;
 	}
 
+	/* Plug PSD data into this CPUs CPC descriptor. */
+	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
+
 	/* Everything looks okay */
 	pr_debug("Parsed CPC struct for CPU: %d\n", pr->id);
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index b420fb46669d..43f20328f830 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -101,6 +101,7 @@ enum ec_command {
 #define ACPI_EC_UDELAY_POLL	550	/* Wait 1ms for EC transaction polling */
 #define ACPI_EC_CLEAR_MAX	100	/* Maximum number of events to query
 					 * when trying to clear the EC */
+#define ACPI_EC_MAX_QUERIES	16	/* Maximum number of parallel queries */
 
 enum {
 	EC_FLAGS_QUERY_PENDING,		/* Query is pending */
@@ -121,6 +122,10 @@ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY;
 module_param(ec_delay, uint, 0644);
 MODULE_PARM_DESC(ec_delay, "Timeout(ms) waited until an EC command completes");
 
+static unsigned int ec_max_queries __read_mostly = ACPI_EC_MAX_QUERIES;
+module_param(ec_max_queries, uint, 0644);
+MODULE_PARM_DESC(ec_max_queries, "Maximum parallel _Qxx evaluations");
+
 static bool ec_busy_polling __read_mostly;
 module_param(ec_busy_polling, bool, 0644);
 MODULE_PARM_DESC(ec_busy_polling, "Use busy polling to advance EC transaction");
@@ -174,6 +179,7 @@ static void acpi_ec_event_processor(struct work_struct *work);
 
 struct acpi_ec *boot_ec, *first_ec;
 EXPORT_SYMBOL(first_ec);
+static struct workqueue_struct *ec_query_wq;
 
 static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
 static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
@@ -1097,7 +1103,7 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
 	 * work queue execution.
 	 */
 	ec_dbg_evt("Query(0x%02x) scheduled", value);
-	if (!schedule_work(&q->work)) {
+	if (!queue_work(ec_query_wq, &q->work)) {
 		ec_dbg_evt("Query(0x%02x) overlapped", value);
 		result = -EBUSY;
 	}
@@ -1657,15 +1663,41 @@ static struct acpi_driver acpi_ec_driver = {
 		},
 };
 
+static inline int acpi_ec_query_init(void)
+{
+	if (!ec_query_wq) {
+		ec_query_wq = alloc_workqueue("kec_query", 0,
+					      ec_max_queries);
+		if (!ec_query_wq)
+			return -ENODEV;
+	}
+	return 0;
+}
+
+static inline void acpi_ec_query_exit(void)
+{
+	if (ec_query_wq) {
+		destroy_workqueue(ec_query_wq);
+		ec_query_wq = NULL;
+	}
+}
+
 int __init acpi_ec_init(void)
 {
-	int result = 0;
+	int result;
 
+	/* register workqueue for _Qxx evaluations */
+	result = acpi_ec_query_init();
+	if (result)
+		goto err_exit;
 	/* Now register the driver for the EC */
 	result = acpi_bus_register_driver(&acpi_ec_driver);
-	if (result < 0)
-		return -ENODEV;
+	if (result)
+		goto err_exit;
 
+err_exit:
+	if (result)
+		acpi_ec_query_exit();
 	return result;
 }
 
@@ -1675,5 +1707,6 @@ static void __exit acpi_ec_exit(void)
 {
 
 	acpi_bus_unregister_driver(&acpi_ec_driver);
+	acpi_ec_query_exit();
 }
 #endif	/* 0 */
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 5ea5dc219f56..73c9c7fa9001 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -98,7 +98,15 @@ static int find_child_checks(struct acpi_device *adev, bool check_children)
 	if (check_children && list_empty(&adev->children))
 		return -ENODEV;
 
-	return sta_present ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
+	/*
+	 * If the device has a _HID (or _CID) returning a valid ACPI/PNP
+	 * device ID, it is better to make it look less attractive here, so that
+	 * the other device with the same _ADR value (that may not have a valid
+	 * device ID) can be matched going forward.  [This means a second spec
+	 * violation in a row, so whatever we do here is best effort anyway.]
+	 */
+	return sta_present && list_empty(&adev->pnp.ids) ?
+			FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
 }
 
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 11d87bf67e73..0f3f41c13b38 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -130,6 +130,12 @@ void acpi_early_processor_set_pdc(void);
 static inline void acpi_early_processor_set_pdc(void) {}
 #endif
 
+#ifdef CONFIG_X86
+void acpi_early_processor_osc(void);
+#else
+static inline void acpi_early_processor_osc(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c
index ccdc8db16bb8..fa2cf2dc4e33 100644
--- a/drivers/acpi/ioapic.c
+++ b/drivers/acpi/ioapic.c
@@ -45,6 +45,12 @@ static acpi_status setup_res(struct acpi_resource *acpi_res, void *data)
 	struct resource *res = data;
 	struct resource_win win;
 
+	/*
+	 * We might assign this to 'res' later, make sure all pointers are
+	 * cleared before the resource is added to the global list
+	 */
+	memset(&win, 0, sizeof(win));
+
 	res->flags = 0;
 	if (acpi_dev_filter_resource_type(acpi_res, IORESOURCE_MEM) == 0)
 		return AE_OK;
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 11d8209e6e5d..67d7489ced01 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -965,7 +965,7 @@ static size_t sizeof_nfit_set_info(int num_mappings)
 		+ num_mappings * sizeof(struct nfit_set_info_map);
 }
 
-static int cmp_map(const void *m0, const void *m1)
+static int cmp_map_compat(const void *m0, const void *m1)
 {
 	const struct nfit_set_info_map *map0 = m0;
 	const struct nfit_set_info_map *map1 = m1;
@@ -974,6 +974,18 @@ static int cmp_map(const void *m0, const void *m1)
 			sizeof(u64));
 }
 
+static int cmp_map(const void *m0, const void *m1)
+{
+	const struct nfit_set_info_map *map0 = m0;
+	const struct nfit_set_info_map *map1 = m1;
+
+	if (map0->region_offset < map1->region_offset)
+		return -1;
+	else if (map0->region_offset > map1->region_offset)
+		return 1;
+	return 0;
+}
+
 /* Retrieve the nth entry referencing this spa */
 static struct acpi_nfit_memory_map *memdev_from_spa(
 		struct acpi_nfit_desc *acpi_desc, u16 range_index, int n)
@@ -1029,6 +1041,12 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
 			cmp_map, NULL);
 	nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+
+	/* support namespaces created with the wrong sort order */
+	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
+			cmp_map_compat, NULL);
+	nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+
 	ndr_desc->nd_set = nd_set;
 	devm_kfree(dev, info);
 
@@ -1072,11 +1090,12 @@ static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 {
 	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
 	u64 offset = nfit_blk->stat_offset + mmio->size * bw;
+	const u32 STATUS_MASK = 0x80000037;
 
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	return readl(mmio->addr.base + offset);
+	return readl(mmio->addr.base + offset) & STATUS_MASK;
 }
 
 static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
@@ -1805,6 +1824,9 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 
 	dev_dbg(dev, "%s: event: %d\n", __func__, event);
 
+	if (event != NFIT_NOTIFY_UPDATE)
+		return;
+
 	device_lock(dev);
 	if (!dev->driver) {
 		/* dev->driver may be null if we're being removed */
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 3d549a383659..13d6ec1ff055 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -45,6 +45,10 @@ enum {
 	ND_BLK_DCR_LATCH = 2,
 };
 
+enum nfit_root_notifiers {
+	NFIT_NOTIFY_UPDATE = 0x80,
+};
+
 struct nfit_spa {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 72b6e9ef0ae9..d176e0ece470 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -327,10 +327,18 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-				     acpi_parse_x2apic_affinity, 0);
-		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-				     acpi_parse_processor_affinity, 0);
+		struct acpi_subtable_proc srat_proc[2];
+
+		memset(srat_proc, 0, sizeof(srat_proc));
+		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
+		srat_proc[0].handler = acpi_parse_processor_affinity;
+		srat_proc[1].id = ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY;
+		srat_proc[1].handler = acpi_parse_x2apic_affinity;
+
+		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
+					sizeof(struct acpi_table_srat),
+					srat_proc, ARRAY_SIZE(srat_proc), 0);
+
 		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 					    acpi_parse_memory_affinity,
 					    NR_NODE_MEMBLKS);
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 32d684af0ec7..a000ecb995e6 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -135,7 +135,7 @@ static struct osi_linux {
 	unsigned int	enable:1;
 	unsigned int	dmi:1;
 	unsigned int	cmdline:1;
-	unsigned int	default_disabling:1;
+	u8		default_disabling;
 } osi_linux = {0, 0, 0, 0};
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
@@ -1444,10 +1444,13 @@ void __init acpi_osi_setup(char *str)
 	if (*str == '!') {
 		str++;
 		if (*str == '\0') {
-			osi_linux.default_disabling = 1;
+			/* Do not override acpi_osi=!* */
+			if (!osi_linux.default_disabling)
+				osi_linux.default_disabling =
+					ACPI_DISABLE_ALL_VENDOR_STRINGS;
 			return;
 		} else if (*str == '*') {
-			acpi_update_interfaces(ACPI_DISABLE_ALL_STRINGS);
+			osi_linux.default_disabling = ACPI_DISABLE_ALL_STRINGS;
 			for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) {
 				osi = &osi_setup_entries[i];
 				osi->enable = false;
@@ -1520,10 +1523,13 @@ static void __init acpi_osi_setup_late(void)
 	acpi_status status;
 
 	if (osi_linux.default_disabling) {
-		status = acpi_update_interfaces(ACPI_DISABLE_ALL_VENDOR_STRINGS);
+		status = acpi_update_interfaces(osi_linux.default_disabling);
 
 		if (ACPI_SUCCESS(status))
-			printk(KERN_INFO PREFIX "Disabled all _OSI OS vendors\n");
+			printk(KERN_INFO PREFIX "Disabled all _OSI OS vendors%s\n",
+				osi_linux.default_disabling ==
+				ACPI_DISABLE_ALL_STRINGS ?
+				" and feature groups" : "");
 	}
 
 	for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) {
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index c9336751e5e3..8a10a7ae6a8a 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -409,7 +409,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	entry = acpi_pci_irq_lookup(dev, pin);
@@ -454,7 +454,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		kfree(entry);
 		return rc;
 	}
-	pci_set_managed_irq(dev, rc);
+	dev->irq = rc;
+	dev->irq_managed = 1;
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);
@@ -477,9 +478,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin || !pci_has_managed_irq(dev))
+	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
+	/* Keep IOAPIC pin configuration when suspending */
+	if (dev->dev.power.is_prepared)
+		return;
+#ifdef	CONFIG_PM
+	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
+		return;
+#endif
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
 		return;
@@ -499,6 +508,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
-		pci_reset_managed_irq(dev);
+		dev->irq_managed = 0;
 	}
 }
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index fcd4ce6f78d5..1c2b846c5776 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state)
 		return -EINVAL;
 
 	/* The state of the list is 'on' IFF all resources are 'on'. */
+	cur_state = 0;
 	list_for_each_entry(entry, list, node) {
 		struct acpi_power_resource *resource = entry->resource;
 		acpi_handle handle = resource->device.handle;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index cdc5c2599beb..627f8fbb5e9a 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -26,8 +26,20 @@
 
 #ifdef CONFIG_X86
 #define valid_IRQ(i) (((i) != 0) && ((i) != 2))
+static inline bool acpi_iospace_resource_valid(struct resource *res)
+{
+	/* On X86 IO space is limited to the [0 - 64K] IO port range */
+	return res->end < 0x10003;
+}
 #else
 #define valid_IRQ(i) (true)
+/*
+ * ACPI IO descriptors on arches other than X86 contain MMIO CPU physical
+ * addresses mapping IO space in CPU physical address space, IO space
+ * resources can be placed anywhere in the 64-bit physical address space.
+ */
+static inline bool
+acpi_iospace_resource_valid(struct resource *res) { return true; }
 #endif
 
 static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io)
@@ -126,7 +138,7 @@ static void acpi_dev_ioresource_flags(struct resource *res, u64 len,
 	if (!acpi_dev_resource_len_valid(res->start, res->end, len, true))
 		res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET;
 
-	if (res->end >= 0x10003)
+	if (!acpi_iospace_resource_valid(res))
 		res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET;
 
 	if (io_decode == ACPI_DECODE_16)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 78d5f02a073b..dcb3d6245ca5 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1958,7 +1958,7 @@ int __init acpi_scan_init(void)
 
 static struct acpi_probe_entry *ape;
 static int acpi_probe_count;
-static DEFINE_SPINLOCK(acpi_probe_lock);
+static DEFINE_MUTEX(acpi_probe_mutex);
 
 static int __init acpi_match_madt(struct acpi_subtable_header *header,
 				  const unsigned long end)
@@ -1977,7 +1977,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 	if (acpi_disabled)
 		return 0;
 
-	spin_lock(&acpi_probe_lock);
+	mutex_lock(&acpi_probe_mutex);
 	for (ape = ap_head; nr; ape++, nr--) {
 		if (ACPI_COMPARE_NAME(ACPI_SIG_MADT, ape->id)) {
 			acpi_probe_count = 0;
@@ -1990,7 +1990,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 				count++;
 		}
 	}
-	spin_unlock(&acpi_probe_lock);
+	mutex_unlock(&acpi_probe_mutex);
 
 	return count;
 }
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 0d94621dc856..e3322adaaae0 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -714,6 +714,7 @@ static int acpi_hibernation_enter(void)
 
 static void acpi_hibernation_leave(void)
 {
+	pm_set_resume_via_firmware();
 	/*
 	 * If ACPI is not enabled by the BIOS and the boot kernel, we need to
 	 * enable it here.
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 0243d375c6fd..4b3a9e27f1b6 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -555,23 +555,22 @@ static void acpi_global_event_handler(u32 event_type, acpi_handle device,
 static int get_status(u32 index, acpi_event_status *status,
 		      acpi_handle *handle)
 {
-	int result = 0;
+	int result;
 
 	if (index >= num_gpes + ACPI_NUM_FIXED_EVENTS)
-		goto end;
+		return -EINVAL;
 
 	if (index < num_gpes) {
 		result = acpi_get_gpe_device(index, handle);
 		if (result) {
 			ACPI_EXCEPTION((AE_INFO, AE_NOT_FOUND,
 					"Invalid GPE 0x%x", index));
-			goto end;
+			return result;
 		}
 		result = acpi_get_gpe_status(*handle, index, status);
 	} else if (index < (num_gpes + ACPI_NUM_FIXED_EVENTS))
 		result = acpi_get_event_status(index - num_gpes, status);
 
-end:
 	return result;
 }
 
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 80e55cb0827b..b48ecbfc4498 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -271,6 +271,26 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro12,1"),
 		},
 	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1123661 */
+	 .callback = video_detect_force_native,
+	 .ident = "Dell XPS 17 L702X",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"),
+		},
+	},
+	{
+	/* https://bugzilla.redhat.com/show_bug.cgi?id=1204476 */
+	/* https://bugs.launchpad.net/ubuntu/+source/linux-lts-trusty/+bug/1416940 */
+	.callback = video_detect_force_native,
+	.ident = "HP Pavilion dv6",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv6 Notebook PC"),
+		},
+	},
+
 	{ },
 };
 
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 7d00b7a015ea..5531f020e561 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1003,7 +1003,7 @@ static int binder_dec_node(struct binder_node *node, int strong, int internal)
 
 
 static struct binder_ref *binder_get_ref(struct binder_proc *proc,
-					 uint32_t desc)
+					 u32 desc, bool need_strong_ref)
 {
 	struct rb_node *n = proc->refs_by_desc.rb_node;
 	struct binder_ref *ref;
@@ -1011,12 +1011,16 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc,
 	while (n) {
 		ref = rb_entry(n, struct binder_ref, rb_node_desc);
 
-		if (desc < ref->desc)
+		if (desc < ref->desc) {
 			n = n->rb_left;
-		else if (desc > ref->desc)
+		} else if (desc > ref->desc) {
 			n = n->rb_right;
-		else
+		} else if (need_strong_ref && !ref->strong) {
+			binder_user_error("tried to use weak ref as strong ref\n");
+			return NULL;
+		} else {
 			return ref;
+		}
 	}
 	return NULL;
 }
@@ -1286,7 +1290,10 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 		} break;
 		case BINDER_TYPE_HANDLE:
 		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+			struct binder_ref *ref;
+
+			ref = binder_get_ref(proc, fp->handle,
+					     fp->type == BINDER_TYPE_HANDLE);
 
 			if (ref == NULL) {
 				pr_err("transaction release %d bad handle %d\n",
@@ -1380,7 +1387,7 @@ static void binder_transaction(struct binder_proc *proc,
 		if (tr->target.handle) {
 			struct binder_ref *ref;
 
-			ref = binder_get_ref(proc, tr->target.handle);
+			ref = binder_get_ref(proc, tr->target.handle, true);
 			if (ref == NULL) {
 				binder_user_error("%d:%d got transaction to invalid handle\n",
 					proc->pid, thread->pid);
@@ -1571,7 +1578,9 @@ static void binder_transaction(struct binder_proc *proc,
 				fp->type = BINDER_TYPE_HANDLE;
 			else
 				fp->type = BINDER_TYPE_WEAK_HANDLE;
+			fp->binder = 0;
 			fp->handle = ref->desc;
+			fp->cookie = 0;
 			binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
 				       &thread->todo);
 
@@ -1583,7 +1592,10 @@ static void binder_transaction(struct binder_proc *proc,
 		} break;
 		case BINDER_TYPE_HANDLE:
 		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+			struct binder_ref *ref;
+
+			ref = binder_get_ref(proc, fp->handle,
+					     fp->type == BINDER_TYPE_HANDLE);
 
 			if (ref == NULL) {
 				binder_user_error("%d:%d got transaction with invalid handle, %d\n",
@@ -1618,7 +1630,9 @@ static void binder_transaction(struct binder_proc *proc,
 					return_error = BR_FAILED_REPLY;
 					goto err_binder_get_ref_for_node_failed;
 				}
+				fp->binder = 0;
 				fp->handle = new_ref->desc;
+				fp->cookie = 0;
 				binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
 				trace_binder_transaction_ref_to_ref(t, ref,
 								    new_ref);
@@ -1672,6 +1686,7 @@ static void binder_transaction(struct binder_proc *proc,
 			binder_debug(BINDER_DEBUG_TRANSACTION,
 				     "        fd %d -> %d\n", fp->handle, target_fd);
 			/* TODO: fput? */
+			fp->binder = 0;
 			fp->handle = target_fd;
 		} break;
 
@@ -1703,8 +1718,12 @@ static void binder_transaction(struct binder_proc *proc,
 	list_add_tail(&t->work.entry, target_list);
 	tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
 	list_add_tail(&tcomplete->entry, &thread->todo);
-	if (target_wait)
-		wake_up_interruptible(target_wait);
+	if (target_wait) {
+		if (reply || !(t->flags & TF_ONE_WAY))
+			wake_up_interruptible_sync(target_wait);
+		else
+			wake_up_interruptible(target_wait);
+	}
 	return;
 
 err_get_unused_fd_failed:
@@ -1794,7 +1813,9 @@ static int binder_thread_write(struct binder_proc *proc,
 						ref->desc);
 				}
 			} else
-				ref = binder_get_ref(proc, target);
+				ref = binder_get_ref(proc, target,
+						     cmd == BC_ACQUIRE ||
+						     cmd == BC_RELEASE);
 			if (ref == NULL) {
 				binder_user_error("%d:%d refcount change on invalid ref %d\n",
 					proc->pid, thread->pid, target);
@@ -1990,7 +2011,7 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
 				return -EFAULT;
 			ptr += sizeof(binder_uintptr_t);
-			ref = binder_get_ref(proc, target);
+			ref = binder_get_ref(proc, target, false);
 			if (ref == NULL) {
 				binder_user_error("%d:%d %s invalid ref %d\n",
 					proc->pid, thread->pid,
@@ -2848,7 +2869,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	const char *failure_string;
 	struct binder_buffer *buffer;
 
-	if (proc->tsk != current)
+	if (proc->tsk != current->group_leader)
 		return -EINVAL;
 
 	if ((vma->vm_end - vma->vm_start) > SZ_4M)
@@ -2949,8 +2970,8 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
 	if (proc == NULL)
 		return -ENOMEM;
-	get_task_struct(current);
-	proc->tsk = current;
+	get_task_struct(current->group_leader);
+	proc->tsk = current->group_leader;
 	INIT_LIST_HEAD(&proc->todo);
 	init_waitqueue_head(&proc->wait);
 	proc->default_priority = task_nice(current);
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 04975b851c23..639adb1f8abd 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -51,6 +51,9 @@ static int ahci_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
+	of_property_read_u32(dev->of_node,
+			     "ports-implemented", &hpriv->force_port_map);
+
 	if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci"))
 		hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ;
 
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index e2c6d9e0c5ac..e916bff6cee8 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -739,9 +739,9 @@ static int xgene_ahci_probe(struct platform_device *pdev)
 				dev_warn(&pdev->dev, "%s: Error reading device info. Assume version1\n",
 					__func__);
 				version = XGENE_AHCI_V1;
-			}
-			if (info->valid & ACPI_VALID_CID)
+			} else if (info->valid & ACPI_VALID_CID) {
 				version = XGENE_AHCI_V2;
+			}
 		}
 	}
 #endif
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 998c6a85ad89..9628fa131757 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -467,6 +467,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		dev_info(dev, "forcing port_map 0x%x -> 0x%x\n",
 			 port_map, hpriv->force_port_map);
 		port_map = hpriv->force_port_map;
+		hpriv->saved_port_map = port_map;
 	}
 
 	if (hpriv->mask_port_map) {
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b79cb10e289e..b0b77b61c40c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4138,6 +4138,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	 */
 	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
 
+	/*
+	 * These devices time out with higher max sects.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
+	 */
+	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+
 	/* Devices we expect to fail diagnostics */
 
 	/* Devices where NCQ should be avoided */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 961acc788f44..91a9e6af2ec4 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 	ata_scsi_port_error_handler(host, ap);
 
 	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+	WARN_ON(!list_empty(&eh_work_q));
 
 	DPRINTK("EXIT\n");
 }
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index e417e1a1d02c..5b2aee83d776 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2832,10 +2832,12 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 static struct ata_device *ata_find_dev(struct ata_port *ap, int devno)
 {
 	if (!sata_pmp_attached(ap)) {
-		if (likely(devno < ata_link_max_devices(&ap->link)))
+		if (likely(devno >= 0 &&
+			   devno < ata_link_max_devices(&ap->link)))
 			return &ap->link.device[devno];
 	} else {
-		if (likely(devno < ap->nr_pmp_links))
+		if (likely(devno >= 0 &&
+			   devno < ap->nr_pmp_links))
 			return &ap->pmp_link[devno].device[0];
 	}
 
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index 8d4d959a821c..8706533db57b 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -616,6 +616,7 @@ static const struct pci_device_id amd[] = {
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE),	8 },
 	{ PCI_VDEVICE(NVIDIA,	PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE),	8 },
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE),		9 },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE),	9 },
 
 	{ },
 };
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index 6c15a554efbe..dc1255294628 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -289,6 +289,7 @@ static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 
 static const struct pci_device_id cs5536[] = {
 	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE), },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE), },
 	{ },
 };
 
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bd74ee555278..729f26322095 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4121,6 +4121,9 @@ static int mv_platform_probe(struct platform_device *pdev)
 	host->iomap = NULL;
 	hpriv->base = devm_ioremap(&pdev->dev, res->start,
 				   resource_size(res));
+	if (!hpriv->base)
+		return -ENOMEM;
+
 	hpriv->base -= SATAHC0_REG_BASE;
 
 	hpriv->clk = clk_get(&pdev->dev, NULL);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 500592486e88..0346e46e2871 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -737,7 +737,7 @@ int bus_add_driver(struct device_driver *drv)
 
 out_unregister:
 	kobject_put(&priv->kobj);
-	kfree(drv->p);
+	/* drv->p is freed in driver_release()  */
 	drv->p = NULL;
 out_put_bus:
 	bus_put(bus);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b7d56c5ea3c6..afe045792796 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -836,11 +836,29 @@ static struct kobject *get_device_parent(struct device *dev,
 	return NULL;
 }
 
+static inline bool live_in_glue_dir(struct kobject *kobj,
+				    struct device *dev)
+{
+	if (!kobj || !dev->class ||
+	    kobj->kset != &dev->class->p->glue_dirs)
+		return false;
+	return true;
+}
+
+static inline struct kobject *get_glue_dir(struct device *dev)
+{
+	return dev->kobj.parent;
+}
+
+/*
+ * make sure cleaning up dir as the last step, we need to make
+ * sure .release handler of kobject is run with holding the
+ * global lock
+ */
 static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 {
 	/* see if we live in a "glue" directory */
-	if (!glue_dir || !dev->class ||
-	    glue_dir->kset != &dev->class->p->glue_dirs)
+	if (!live_in_glue_dir(glue_dir, dev))
 		return;
 
 	mutex_lock(&gdp_mutex);
@@ -848,11 +866,6 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 	mutex_unlock(&gdp_mutex);
 }
 
-static void cleanup_device_parent(struct device *dev)
-{
-	cleanup_glue_dir(dev, dev->kobj.parent);
-}
-
 static int device_add_class_symlinks(struct device *dev)
 {
 	struct device_node *of_node = dev_of_node(dev);
@@ -1028,6 +1041,7 @@ int device_add(struct device *dev)
 	struct kobject *kobj;
 	struct class_interface *class_intf;
 	int error = -EINVAL;
+	struct kobject *glue_dir = NULL;
 
 	dev = get_device(dev);
 	if (!dev)
@@ -1072,8 +1086,10 @@ int device_add(struct device *dev)
 	/* first, register with generic layer. */
 	/* we require the name to be set before, and pass NULL */
 	error = kobject_add(&dev->kobj, dev->kobj.parent, NULL);
-	if (error)
+	if (error) {
+		glue_dir = get_glue_dir(dev);
 		goto Error;
+	}
 
 	/* notify platform of device entry */
 	if (platform_notify)
@@ -1154,9 +1170,10 @@ done:
 	device_remove_file(dev, &dev_attr_uevent);
  attrError:
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
  Error:
-	cleanup_device_parent(dev);
+	cleanup_glue_dir(dev, glue_dir);
 	put_device(parent);
 name_error:
 	kfree(dev->p);
@@ -1232,6 +1249,7 @@ EXPORT_SYMBOL_GPL(put_device);
 void device_del(struct device *dev)
 {
 	struct device *parent = dev->parent;
+	struct kobject *glue_dir = NULL;
 	struct class_interface *class_intf;
 
 	/* Notify clients of device removal.  This call must come
@@ -1276,8 +1294,9 @@ void device_del(struct device *dev)
 		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
 					     BUS_NOTIFY_REMOVED_DEVICE, dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
-	cleanup_device_parent(dev);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
+	cleanup_glue_dir(dev, glue_dir);
 	put_device(parent);
 }
 EXPORT_SYMBOL_GPL(device_del);
@@ -2075,7 +2094,11 @@ void device_shutdown(void)
 		pm_runtime_get_noresume(dev);
 		pm_runtime_barrier(dev);
 
-		if (dev->bus && dev->bus->shutdown) {
+		if (dev->class && dev->class->shutdown) {
+			if (initcall_debug)
+				dev_info(dev, "shutdown\n");
+			dev->class->shutdown(dev);
+		} else if (dev->bus && dev->bus->shutdown) {
 			if (initcall_debug)
 				dev_info(dev, "shutdown\n");
 			dev->bus->shutdown(dev);
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index d95c5971c225..a00f7b79202b 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -335,7 +335,7 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
 		return;
 	}
 
-	unmap_kernel_range((unsigned long)cpu_addr, size);
+	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
 	vunmap(cpu_addr);
 }
 #endif
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8524450e75bd..ccfd268148a8 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -942,13 +942,14 @@ static int _request_firmware_load(struct firmware_priv *fw_priv,
 		timeout = MAX_JIFFY_OFFSET;
 	}
 
-	retval = wait_for_completion_interruptible_timeout(&buf->completion,
+	timeout = wait_for_completion_interruptible_timeout(&buf->completion,
 			timeout);
-	if (retval == -ERESTARTSYS || !retval) {
+	if (timeout == -ERESTARTSYS || !timeout) {
+		retval = timeout;
 		mutex_lock(&fw_lock);
 		fw_load_abort(fw_priv);
 		mutex_unlock(&fw_lock);
-	} else if (retval > 0) {
+	} else if (timeout > 0) {
 		retval = 0;
 	}
 
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 25425d3f2575..48c0a1d0dd3a 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -388,30 +388,29 @@ static ssize_t show_valid_zones(struct device *dev,
 {
 	struct memory_block *mem = to_memory_block(dev);
 	unsigned long start_pfn, end_pfn;
+	unsigned long valid_start, valid_end;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	struct page *first_page;
 	struct zone *zone;
 
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	end_pfn = start_pfn + nr_pages;
-	first_page = pfn_to_page(start_pfn);
 
 	/* The block contains more than one zone can not be offlined. */
-	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
 		return sprintf(buf, "none\n");
 
-	zone = page_zone(first_page);
+	zone = page_zone(pfn_to_page(valid_start));
 
 	if (zone_idx(zone) == ZONE_MOVABLE - 1) {
 		/*The mem block is the last memoryblock of this zone.*/
-		if (end_pfn == zone_end_pfn(zone))
+		if (valid_end == zone_end_pfn(zone))
 			return sprintf(buf, "%s %s\n",
 					zone->name, (zone + 1)->name);
 	}
 
 	if (zone_idx(zone) == ZONE_MOVABLE) {
 		/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
-		if (start_pfn == zone->zone_start_pfn)
+		if (valid_start == zone->zone_start_pfn)
 			return sprintf(buf, "%s %s\n",
 					zone->name, (zone - 1)->name);
 	}
diff --git a/drivers/base/module.c b/drivers/base/module.c
index db930d3ee312..2a215780eda2 100644
--- a/drivers/base/module.c
+++ b/drivers/base/module.c
@@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv)
 
 static void module_create_drivers_dir(struct module_kobject *mk)
 {
-	if (!mk || mk->drivers_dir)
-		return;
+	static DEFINE_MUTEX(drivers_dir_mutex);
 
-	mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_lock(&drivers_dir_mutex);
+	if (mk && !mk->drivers_dir)
+		mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+	mutex_unlock(&drivers_dir_mutex);
 }
 
 void module_add_driver(struct module *mod, struct device_driver *drv)
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 176b59f5bc47..cb4ad6e98b28 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -96,7 +96,7 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 		int ret;
 
 		ret = of_irq_get(dev->dev.of_node, num);
-		if (ret >= 0 || ret == -EPROBE_DEFER)
+		if (ret > 0 || ret == -EPROBE_DEFER)
 			return ret;
 	}
 
@@ -154,7 +154,7 @@ int platform_get_irq_byname(struct platform_device *dev, const char *name)
 		int ret;
 
 		ret = of_irq_get_byname(dev->dev.of_node, name);
-		if (ret >= 0 || ret == -EPROBE_DEFER)
+		if (ret > 0 || ret == -EPROBE_DEFER)
 			return ret;
 	}
 
@@ -807,7 +807,7 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	char *driver_override, *old = pdev->driver_override, *cp;
+	char *driver_override, *old, *cp;
 
 	if (count > PATH_MAX)
 		return -EINVAL;
@@ -820,12 +820,15 @@ static ssize_t driver_override_store(struct device *dev,
 	if (cp)
 		*cp = '\0';
 
+	device_lock(dev);
+	old = pdev->driver_override;
 	if (strlen(driver_override)) {
 		pdev->driver_override = driver_override;
 	} else {
 		kfree(driver_override);
 		pdev->driver_override = NULL;
 	}
+	device_unlock(dev);
 
 	kfree(old);
 
@@ -836,8 +839,12 @@ static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	ssize_t len;
 
-	return sprintf(buf, "%s\n", pdev->driver_override);
+	device_lock(dev);
+	len = sprintf(buf, "%s\n", pdev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 65f50eccd49b..78b0ece0c867 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1188,7 +1188,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 	}
 
 	dev->power.subsys_data->domain_data = &gpd_data->base;
-	dev->pm_domain = &genpd->domain;
 
 	spin_unlock_irq(&dev->power.lock);
 
@@ -1207,7 +1206,6 @@ static void genpd_free_dev_data(struct device *dev,
 {
 	spin_lock_irq(&dev->power.lock);
 
-	dev->pm_domain = NULL;
 	dev->power.subsys_data->domain_data = NULL;
 
 	spin_unlock_irq(&dev->power.lock);
@@ -1248,6 +1246,8 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (ret)
 		goto out;
 
+	dev->pm_domain = &genpd->domain;
+
 	genpd->device_count++;
 	genpd->max_off_time_changed = true;
 
@@ -1299,6 +1299,8 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	if (genpd->detach_dev)
 		genpd->detach_dev(genpd, dev);
 
+	dev->pm_domain = NULL;
+
 	list_del_init(&pdd->list_node);
 
 	mutex_unlock(&genpd->lock);
@@ -1373,7 +1375,7 @@ EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain);
 int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 			      struct generic_pm_domain *subdomain)
 {
-	struct gpd_link *link;
+	struct gpd_link *l, *link;
 	int ret = -EINVAL;
 
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
@@ -1381,14 +1383,14 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 
 	mutex_lock(&genpd->lock);
 
-	if (!list_empty(&subdomain->slave_links) || subdomain->device_count) {
+	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
 			subdomain->name);
 		ret = -EBUSY;
 		goto out;
 	}
 
-	list_for_each_entry(link, &genpd->master_links, master_node) {
+	list_for_each_entry_safe(link, l, &genpd->master_links, master_node) {
 		if (link->slave != subdomain)
 			continue;
 
@@ -1642,10 +1644,10 @@ EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
  */
 void of_genpd_del_provider(struct device_node *np)
 {
-	struct of_genpd_provider *cp;
+	struct of_genpd_provider *cp, *tmp;
 
 	mutex_lock(&of_genpd_mutex);
-	list_for_each_entry(cp, &of_genpd_providers, link) {
+	list_for_each_entry_safe(cp, tmp, &of_genpd_providers, link) {
 		if (cp->node == np) {
 			list_del(&cp->link);
 			of_node_put(cp->node);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 1710c26ba097..e9b713675c7c 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1022,6 +1022,8 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	TRACE_DEVICE(dev);
 	TRACE_SUSPEND(0);
 
+	dpm_wait_for_children(dev, async);
+
 	if (async_error)
 		goto Complete;
 
@@ -1033,8 +1035,6 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	dpm_wait_for_children(dev, async);
-
 	if (dev->pm_domain) {
 		info = "noirq power domain ";
 		callback = pm_noirq_op(&dev->pm_domain->ops, state);
@@ -1169,6 +1169,8 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
 
 	__pm_runtime_disable(dev, false);
 
+	dpm_wait_for_children(dev, async);
+
 	if (async_error)
 		goto Complete;
 
@@ -1180,8 +1182,6 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	dpm_wait_for_children(dev, async);
-
 	if (dev->pm_domain) {
 		info = "late power domain ";
 		callback = pm_late_early_op(&dev->pm_domain->ops, state);
@@ -1262,14 +1262,15 @@ int dpm_suspend_late(pm_message_t state)
 		error = device_suspend_late(dev);
 
 		mutex_lock(&dpm_list_mtx);
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_late_early_list);
+
 		if (error) {
 			pm_dev_err(dev, state, " late", error);
 			dpm_save_failed_dev(dev_name(dev));
 			put_device(dev);
 			break;
 		}
-		if (!list_empty(&dev->power.entry))
-			list_move(&dev->power.entry, &dpm_late_early_list);
 		put_device(dev);
 
 		if (async_error)
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index b8e76f75073b..f8580900c273 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -809,8 +809,14 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev)
 	}
 
 	opp->u_volt = microvolt[0];
-	opp->u_volt_min = microvolt[1];
-	opp->u_volt_max = microvolt[2];
+
+	if (count == 1) {
+		opp->u_volt_min = opp->u_volt;
+		opp->u_volt_max = opp->u_volt;
+	} else {
+		opp->u_volt_min = microvolt[1];
+		opp->u_volt_max = microvolt[2];
+	}
 
 	if (!of_property_read_u32(opp->np, "opp-microamp", &val))
 		opp->u_amp = val;
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 998fa6b23084..01ac5b1aeaeb 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -20,14 +20,22 @@ static inline void pm_runtime_early_init(struct device *dev)
 extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
+#define WAKE_IRQ_DEDICATED_ALLOCATED	BIT(0)
+#define WAKE_IRQ_DEDICATED_MANAGED	BIT(1)
+#define WAKE_IRQ_DEDICATED_MASK		(WAKE_IRQ_DEDICATED_ALLOCATED | \
+					 WAKE_IRQ_DEDICATED_MANAGED)
+
 struct wake_irq {
 	struct device *dev;
+	unsigned int status;
 	int irq;
-	bool dedicated_irq:1;
 };
 
 extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
 extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_enable_wake_irq_check(struct device *dev,
+					 bool can_change_status);
+extern void dev_pm_disable_wake_irq_check(struct device *dev);
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -102,6 +110,15 @@ static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 {
 }
 
+static inline void dev_pm_enable_wake_irq_check(struct device *dev,
+						bool can_change_status)
+{
+}
+
+static inline void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+}
+
 #endif
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index e1a10a03df8e..3a20dc594338 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -515,7 +515,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
-	dev_pm_enable_wake_irq(dev);
+	dev_pm_enable_wake_irq_check(dev, true);
 	retval = rpm_callback(callback, dev);
 	if (retval)
 		goto fail;
@@ -554,7 +554,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	return retval;
 
  fail:
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	__update_runtime_status(dev, RPM_ACTIVE);
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -737,12 +737,12 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
-		dev_pm_enable_wake_irq(dev);
+		dev_pm_enable_wake_irq_check(dev, false);
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);
@@ -889,13 +889,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
 	if (rpmflags & RPM_GET_PUT) {
 		if (!atomic_dec_and_test(&dev->power.usage_count))
 			return 0;
 	}
 
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
 	spin_lock_irqsave(&dev->power.lock, flags);
 	retval = rpm_idle(dev, rpmflags);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -921,13 +921,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
 	if (rpmflags & RPM_GET_PUT) {
 		if (!atomic_dec_and_test(&dev->power.usage_count))
 			return 0;
 	}
 
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
 	spin_lock_irqsave(&dev->power.lock, flags);
 	retval = rpm_suspend(dev, rpmflags);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -952,7 +952,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
+			dev->power.runtime_status != RPM_ACTIVE);
 
 	if (rpmflags & RPM_GET_PUT)
 		atomic_inc(&dev->power.usage_count);
@@ -1468,11 +1469,16 @@ int pm_runtime_force_resume(struct device *dev)
 		goto out;
 	}
 
-	ret = callback(dev);
+	ret = pm_runtime_set_active(dev);
 	if (ret)
 		goto out;
 
-	pm_runtime_set_active(dev);
+	ret = callback(dev);
+	if (ret) {
+		pm_runtime_set_suspended(dev);
+		goto out;
+	}
+
 	pm_runtime_mark_last_busy(dev);
 out:
 	pm_runtime_enable(dev);
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index a7b46798c81d..39efa7e6c0c0 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -268,6 +268,8 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
 			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
 			value = PM_QOS_LATENCY_ANY;
+		else
+			return -EINVAL;
 	}
 	ret = dev_pm_qos_update_user_latency_tolerance(dev, value);
 	return ret < 0 ? ret : n;
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 0d77cd6fd8d1..404d94c6c8bc 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -110,8 +110,10 @@ void dev_pm_clear_wake_irq(struct device *dev)
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (wirq->dedicated_irq)
+	if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) {
 		free_irq(wirq->irq, wirq);
+		wirq->status &= ~WAKE_IRQ_DEDICATED_MASK;
+	}
 	kfree(wirq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
@@ -179,7 +181,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 
 	wirq->dev = dev;
 	wirq->irq = irq;
-	wirq->dedicated_irq = true;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
 	/*
@@ -195,6 +196,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	if (err)
 		goto err_free_irq;
 
+	wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED;
+
 	return err;
 
 err_free_irq:
@@ -210,9 +213,9 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
  * dev_pm_enable_wake_irq - Enable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_suspend() to enable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_resume() to override the PM runtime core managed wake-up
+ * interrupt handling to enable the wake-up interrupt.
  *
  * Note that for runtime_suspend()) the wake-up interrupts
  * should be unconditionally enabled unlike for suspend()
@@ -222,7 +225,7 @@ void dev_pm_enable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		enable_irq(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
@@ -231,20 +234,73 @@ EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
  * dev_pm_disable_wake_irq - Disable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_resume() to disable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_suspend() to override the PM runtime core managed wake-up
+ * interrupt handling to disable the wake-up interrupt.
  */
 void dev_pm_disable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		disable_irq_nosync(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq);
 
 /**
+ * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt
+ * @dev: Device
+ * @can_change_status: Can change wake-up interrupt status
+ *
+ * Enables wakeirq conditionally. We need to enable wake-up interrupt
+ * lazily on the first rpm_suspend(). This is needed as the consumer device
+ * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would
+ * otherwise try to disable already disabled wakeirq. The wake-up interrupt
+ * starts disabled with IRQ_NOAUTOEN set.
+ *
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ * Caller must hold &dev->power.lock to change wirq->status
+ */
+void dev_pm_enable_wake_irq_check(struct device *dev,
+				  bool can_change_status)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
+		goto enable;
+	} else if (can_change_status) {
+		wirq->status |= WAKE_IRQ_DEDICATED_MANAGED;
+		goto enable;
+	}
+
+	return;
+
+enable:
+	enable_irq(wirq->irq);
+}
+
+/**
+ * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt
+ * @dev: Device
+ *
+ * Disables wake-up interrupt conditionally based on status.
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ */
+void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED)
+		disable_irq_nosync(wirq->irq);
+}
+
+/**
  * dev_pm_arm_wake_irq - Arm device wake-up
  * @wirq: Device wake-up interrupt
  *
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index a1e0b9ab847a..e613633ffe9c 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -60,6 +60,8 @@ static LIST_HEAD(wakeup_sources);
 
 static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
 
+DEFINE_STATIC_SRCU(wakeup_srcu);
+
 static struct wakeup_source deleted_ws = {
 	.name = "deleted",
 	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
@@ -198,7 +200,7 @@ void wakeup_source_remove(struct wakeup_source *ws)
 	spin_lock_irqsave(&events_lock, flags);
 	list_del_rcu(&ws->entry);
 	spin_unlock_irqrestore(&events_lock, flags);
-	synchronize_rcu();
+	synchronize_srcu(&wakeup_srcu);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_remove);
 
@@ -330,13 +332,14 @@ void device_wakeup_detach_irq(struct device *dev)
 void device_wakeup_arm_wake_irqs(void)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->wakeirq)
 			dev_pm_arm_wake_irq(ws->wakeirq);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 
 /**
@@ -347,13 +350,14 @@ void device_wakeup_arm_wake_irqs(void)
 void device_wakeup_disarm_wake_irqs(void)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->wakeirq)
 			dev_pm_disarm_wake_irq(ws->wakeirq);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 
 /**
@@ -807,10 +811,10 @@ EXPORT_SYMBOL_GPL(pm_wakeup_event);
 void pm_print_active_wakeup_sources(void)
 {
 	struct wakeup_source *ws;
-	int active = 0;
+	int srcuidx, active = 0;
 	struct wakeup_source *last_activity_ws = NULL;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
 			pr_info("active wakeup source: %s\n", ws->name);
@@ -826,7 +830,7 @@ void pm_print_active_wakeup_sources(void)
 	if (!active && last_activity_ws)
 		pr_info("last active wakeup source: %s\n",
 			last_activity_ws->name);
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);
 
@@ -953,8 +957,9 @@ void pm_wakep_autosleep_enabled(bool set)
 {
 	struct wakeup_source *ws;
 	ktime_t now = ktime_get();
+	int srcuidx;
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		spin_lock_irq(&ws->lock);
 		if (ws->autosleep_enabled != set) {
@@ -968,7 +973,7 @@ void pm_wakep_autosleep_enabled(bool set)
 		}
 		spin_unlock_irq(&ws->lock);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
 #endif /* CONFIG_PM_AUTOSLEEP */
 
@@ -1029,15 +1034,16 @@ static int print_wakeup_source_stats(struct seq_file *m,
 static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
 {
 	struct wakeup_source *ws;
+	int srcuidx;
 
 	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
 		"expire_count\tactive_since\ttotal_time\tmax_time\t"
 		"last_change\tprevent_suspend_time\n");
 
-	rcu_read_lock();
+	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
 		print_wakeup_source_stats(m, ws);
-	rcu_read_unlock();
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
 
 	print_wakeup_source_stats(m, &deleted_ws);
 
diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c
index 7e58f6560399..4a36e415e938 100644
--- a/drivers/base/regmap/regmap-spmi.c
+++ b/drivers/base/regmap/regmap-spmi.c
@@ -142,7 +142,7 @@ static int regmap_spmi_ext_read(void *context,
 	while (val_size) {
 		len = min_t(size_t, val_size, 8);
 
-		err = spmi_ext_register_readl(context, addr, val, val_size);
+		err = spmi_ext_register_readl(context, addr, val, len);
 		if (err)
 			goto err_out;
 
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 38f156745d53..71df8f2afc6c 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -8,8 +8,6 @@
 #include <linux/bcma/bcma.h>
 #include <linux/delay.h>
 
-#define BCMA_CORE_SIZE		0x1000
-
 #define bcma_err(bus, fmt, ...) \
 	pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__)
 #define bcma_warn(bus, fmt, ...) \
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 59d8d0d14824..327f9e374b44 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -640,8 +640,11 @@ static int bcma_device_probe(struct device *dev)
 					       drv);
 	int err = 0;
 
+	get_device(dev);
 	if (adrv->probe)
 		err = adrv->probe(core);
+	if (err)
+		put_device(dev);
 
 	return err;
 }
@@ -654,6 +657,7 @@ static int bcma_device_remove(struct device *dev)
 
 	if (adrv->remove)
 		adrv->remove(core);
+	put_device(dev);
 
 	return 0;
 }
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index a5880f4ab40e..1914c63ca8b1 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -338,7 +338,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
-		    bio->bi_iter.bi_size & PAGE_MASK)
+		    bio->bi_iter.bi_size & ~PAGE_MASK)
 			goto io_error;
 		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
 		goto out;
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 9462d2752850..8bdc34dbaedf 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -479,8 +479,14 @@ void drbd_bm_cleanup(struct drbd_device *device)
  * this masks out the remaining bits.
  * Returns the number of bits cleared.
  */
+#ifndef BITS_PER_PAGE
 #define BITS_PER_PAGE		(1UL << (PAGE_SHIFT + 3))
 #define BITS_PER_PAGE_MASK	(BITS_PER_PAGE - 1)
+#else
+# if BITS_PER_PAGE != (1UL << (PAGE_SHIFT + 3))
+#  error "ambiguous BITS_PER_PAGE"
+# endif
+#endif
 #define BITS_PER_LONG_MASK	(BITS_PER_LONG - 1)
 static int bm_clear_surplus(struct drbd_bitmap *b)
 {
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 74d97f4bac34..1d58854c4a9f 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1802,7 +1802,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
  * do we need to block DRBD_SIG if sock == &meta.socket ??
  * otherwise wake_asender() might interrupt some send_*Ack !
  */
-		rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
+		rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
 		if (rv == -EAGAIN) {
 			if (we_should_drop_the_connection(connection, sock))
 				break;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 423f4ca7d712..cec36d5c24f5 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -488,6 +488,12 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
 	bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
 	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
 		      bio_segments(bio), blk_rq_bytes(cmd->rq));
+	/*
+	 * This bio may be started from the middle of the 'bvec'
+	 * because of bio splitting, so offset from the bvec must
+	 * be passed to iov iterator
+	 */
+	iter.iov_offset = bio->bi_iter.bi_bvec_done;
 
 	cmd->iocb.ki_pos = pos;
 	cmd->iocb.ki_filp = file;
@@ -1102,9 +1108,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
 		return -EINVAL;
 
+	/* I/O need to be drained during transfer transition */
+	blk_mq_freeze_queue(lo->lo_queue);
+
 	err = loop_release_xfer(lo);
 	if (err)
-		return err;
+		goto exit;
 
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
@@ -1119,12 +1128,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 
 	err = loop_init_xfer(lo, xfer, info);
 	if (err)
-		return err;
+		goto exit;
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit)
-		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
-			return -EFBIG;
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
+			err = -EFBIG;
+			goto exit;
+		}
 
 	loop_config_discard(lo);
 
@@ -1142,13 +1153,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
 		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
 
-	if ((info->lo_flags & LO_FLAGS_PARTSCAN) &&
-	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_flags |= LO_FLAGS_PARTSCAN;
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
-		loop_reread_partitions(lo, lo->lo_device);
-	}
-
 	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
 	lo->lo_init[0] = info->lo_init[0];
 	lo->lo_init[1] = info->lo_init[1];
@@ -1161,7 +1165,17 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
-	return 0;
+ exit:
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
+	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
+	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
+		lo->lo_flags |= LO_FLAGS_PARTSCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		loop_reread_partitions(lo, lo->lo_device);
+	}
+
+	return err;
 }
 
 static int
@@ -1651,7 +1665,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(bd->rq);
 
 	if (lo->lo_state != Lo_bound)
-		return -EIO;
+		return BLK_MQ_RQ_QUEUE_ERROR;
 
 	if (lo->use_dio && !(cmd->rq->cmd_flags & (REQ_FLUSH |
 					REQ_DISCARD)))
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 3457ac8c03e2..55d3d1da72de 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -173,7 +173,13 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
 	struct request *rq;
 
+	if (mtip_check_surprise_removal(dd->pdev))
+		return NULL;
+
 	rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true);
+	if (IS_ERR(rq))
+		return NULL;
+
 	return blk_mq_rq_to_pdu(rq);
 }
 
@@ -233,15 +239,9 @@ static void mtip_async_complete(struct mtip_port *port,
 			"Command tag %d failed due to TFE\n", tag);
 	}
 
-	/* Unmap the DMA scatter list entries */
-	dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, cmd->direction);
-
 	rq = mtip_rq_from_tag(dd, tag);
 
-	if (unlikely(cmd->unaligned))
-		up(&port->cmd_slot_unal);
-
-	blk_mq_end_request(rq, status ? -EIO : 0);
+	blk_mq_complete_request(rq, status);
 }
 
 /*
@@ -581,6 +581,8 @@ static void mtip_completion(struct mtip_port *port,
 		dev_warn(&port->dd->pdev->dev,
 			"Internal command %d completed with TFE\n", tag);
 
+	command->comp_func = NULL;
+	command->comp_data = NULL;
 	complete(waiting);
 }
 
@@ -618,8 +620,6 @@ static void mtip_handle_tfe(struct driver_data *dd)
 
 	port = dd->port;
 
-	set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
-
 	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
@@ -628,7 +628,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 			cmd->comp_func(port, MTIP_TAG_INTERNAL,
 					cmd, PORT_IRQ_TF_ERR);
 		}
-		goto handle_tfe_exit;
+		return;
 	}
 
 	/* clear the tag accumulator */
@@ -701,7 +701,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 			fail_reason = "thermal shutdown";
 		}
 		if (buf[288] == 0xBF) {
-			set_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag);
+			set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag);
 			dev_info(&dd->pdev->dev,
 				"Drive indicates rebuild has failed. Secure erase required.\n");
 			fail_all_ncq_cmds = 1;
@@ -771,11 +771,6 @@ static void mtip_handle_tfe(struct driver_data *dd)
 		}
 	}
 	print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt);
-
-handle_tfe_exit:
-	/* clear eh_active */
-	clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
-	wake_up_interruptible(&port->svc_wait);
 }
 
 /*
@@ -1007,6 +1002,7 @@ static bool mtip_pause_ncq(struct mtip_port *port,
 			(fis->features == 0x27 || fis->features == 0x72 ||
 			 fis->features == 0x62 || fis->features == 0x26))) {
 		clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
+		clear_bit(MTIP_DDF_REBUILD_FAILED_BIT, &port->dd->dd_flag);
 		/* Com reset after secure erase or lowlevel format */
 		mtip_restart_port(port);
 		clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
@@ -1021,12 +1017,14 @@ static bool mtip_pause_ncq(struct mtip_port *port,
  *
  * @port    Pointer to port data structure
  * @timeout Max duration to wait (ms)
+ * @atomic  gfp_t flag to indicate blockable context or not
  *
  * return value
  *	0	Success
  *	-EBUSY  Commands still active
  */
-static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
+static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout,
+								gfp_t atomic)
 {
 	unsigned long to;
 	unsigned int n;
@@ -1037,16 +1035,21 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
 	to = jiffies + msecs_to_jiffies(timeout);
 	do {
 		if (test_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags) &&
-			test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) {
+			test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags) &&
+			atomic == GFP_KERNEL) {
 			msleep(20);
 			continue; /* svc thd is actively issuing commands */
 		}
 
-		msleep(100);
+		if (atomic == GFP_KERNEL)
+			msleep(100);
+		else {
+			cpu_relax();
+			udelay(100);
+		}
+
 		if (mtip_check_surprise_removal(port->dd->pdev))
 			goto err_fault;
-		if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &port->dd->dd_flag))
-			goto err_fault;
 
 		/*
 		 * Ignore s_active bit 0 of array element 0.
@@ -1099,6 +1102,7 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	struct mtip_cmd *int_cmd;
 	struct driver_data *dd = port->dd;
 	int rv = 0;
+	unsigned long start;
 
 	/* Make sure the buffer is 8 byte aligned. This is asic specific. */
 	if (buffer & 0x00000007) {
@@ -1107,6 +1111,10 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	}
 
 	int_cmd = mtip_get_int_command(dd);
+	if (!int_cmd) {
+		dbg_printk(MTIP_DRV_NAME "Unable to allocate tag for PIO cmd\n");
+		return -EFAULT;
+	}
 
 	set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 
@@ -1119,7 +1127,7 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 		if (fis->command != ATA_CMD_STANDBYNOW1) {
 			/* wait for io to complete if non atomic */
 			if (mtip_quiesce_io(port,
-					MTIP_QUIESCE_IO_TIMEOUT_MS) < 0) {
+				MTIP_QUIESCE_IO_TIMEOUT_MS, atomic) < 0) {
 				dev_warn(&dd->pdev->dev,
 					"Failed to quiesce IO\n");
 				mtip_put_int_command(dd, int_cmd);
@@ -1162,6 +1170,8 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	/* Populate the command header */
 	int_cmd->command_header->byte_count = 0;
 
+	start = jiffies;
+
 	/* Issue the command to the hardware */
 	mtip_issue_non_ncq_command(port, MTIP_TAG_INTERNAL);
 
@@ -1170,10 +1180,12 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 		if ((rv = wait_for_completion_interruptible_timeout(
 				&wait,
 				msecs_to_jiffies(timeout))) <= 0) {
+
 			if (rv == -ERESTARTSYS) { /* interrupted */
 				dev_err(&dd->pdev->dev,
-					"Internal command [%02X] was interrupted after %lu ms\n",
-					fis->command, timeout);
+					"Internal command [%02X] was interrupted after %u ms\n",
+					fis->command,
+					jiffies_to_msecs(jiffies - start));
 				rv = -EINTR;
 				goto exec_ic_exit;
 			} else if (rv == 0) /* timeout */
@@ -2897,6 +2909,42 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd)
 	return -EFAULT;
 }
 
+static void mtip_softirq_done_fn(struct request *rq)
+{
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct driver_data *dd = rq->q->queuedata;
+
+	/* Unmap the DMA scatter list entries */
+	dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents,
+							cmd->direction);
+
+	if (unlikely(cmd->unaligned))
+		up(&dd->port->cmd_slot_unal);
+
+	blk_mq_end_request(rq, rq->errors);
+}
+
+static void mtip_abort_cmd(struct request *req, void *data,
+							bool reserved)
+{
+	struct driver_data *dd = data;
+
+	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
+
+	clear_bit(req->tag, dd->port->cmds_to_issue);
+	req->errors = -EIO;
+	mtip_softirq_done_fn(req);
+}
+
+static void mtip_queue_cmd(struct request *req, void *data,
+							bool reserved)
+{
+	struct driver_data *dd = data;
+
+	set_bit(req->tag, dd->port->cmds_to_issue);
+	blk_abort_request(req);
+}
+
 /*
  * service thread to issue queued commands
  *
@@ -2909,7 +2957,7 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd)
 static int mtip_service_thread(void *data)
 {
 	struct driver_data *dd = (struct driver_data *)data;
-	unsigned long slot, slot_start, slot_wrap;
+	unsigned long slot, slot_start, slot_wrap, to;
 	unsigned int num_cmd_slots = dd->slot_groups * 32;
 	struct mtip_port *port = dd->port;
 
@@ -2924,9 +2972,7 @@ static int mtip_service_thread(void *data)
 		 * is in progress nor error handling is active
 		 */
 		wait_event_interruptible(port->svc_wait, (port->flags) &&
-			!(port->flags & MTIP_PF_PAUSE_IO));
-
-		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+			(port->flags & MTIP_PF_SVC_THD_WORK));
 
 		if (kthread_should_stop() ||
 			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
@@ -2936,6 +2982,8 @@ static int mtip_service_thread(void *data)
 				&dd->dd_flag)))
 			goto st_out;
 
+		set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags);
+
 restart_eh:
 		/* Demux bits: start with error handling */
 		if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) {
@@ -2946,6 +2994,32 @@ restart_eh:
 		if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags))
 			goto restart_eh;
 
+		if (test_bit(MTIP_PF_TO_ACTIVE_BIT, &port->flags)) {
+			to = jiffies + msecs_to_jiffies(5000);
+
+			do {
+				mdelay(100);
+			} while (atomic_read(&dd->irq_workers_active) != 0 &&
+				time_before(jiffies, to));
+
+			if (atomic_read(&dd->irq_workers_active) != 0)
+				dev_warn(&dd->pdev->dev,
+					"Completion workers still active!");
+
+			spin_lock(dd->queue->queue_lock);
+			blk_mq_all_tag_busy_iter(*dd->tags.tags,
+							mtip_queue_cmd, dd);
+			spin_unlock(dd->queue->queue_lock);
+
+			set_bit(MTIP_PF_ISSUE_CMDS_BIT, &dd->port->flags);
+
+			if (mtip_device_reset(dd))
+				blk_mq_all_tag_busy_iter(*dd->tags.tags,
+							mtip_abort_cmd, dd);
+
+			clear_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags);
+		}
+
 		if (test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) {
 			slot = 1;
 			/* used to restrict the loop to one iteration */
@@ -2978,10 +3052,8 @@ restart_eh:
 		}
 
 		if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) {
-			if (mtip_ftl_rebuild_poll(dd) < 0)
-				set_bit(MTIP_DDF_REBUILD_FAILED_BIT,
-							&dd->dd_flag);
-			clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
+			if (mtip_ftl_rebuild_poll(dd) == 0)
+				clear_bit(MTIP_PF_REBUILD_BIT, &port->flags);
 		}
 	}
 
@@ -3096,7 +3168,7 @@ static int mtip_hw_get_identify(struct driver_data *dd)
 		if (buf[288] == 0xBF) {
 			dev_info(&dd->pdev->dev,
 				"Drive indicates rebuild has failed.\n");
-			/* TODO */
+			set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag);
 		}
 	}
 
@@ -3270,20 +3342,25 @@ out1:
 	return rv;
 }
 
-static void mtip_standby_drive(struct driver_data *dd)
+static int mtip_standby_drive(struct driver_data *dd)
 {
-	if (dd->sr)
-		return;
+	int rv = 0;
 
+	if (dd->sr || !dd->port)
+		return -ENODEV;
 	/*
 	 * Send standby immediate (E0h) to the drive so that it
 	 * saves its state.
 	 */
 	if (!test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags) &&
-	    !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))
-		if (mtip_standby_immediate(dd->port))
+	    !test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag) &&
+	    !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)) {
+		rv = mtip_standby_immediate(dd->port);
+		if (rv)
 			dev_warn(&dd->pdev->dev,
 				"STANDBY IMMEDIATE failed\n");
+	}
+	return rv;
 }
 
 /*
@@ -3296,10 +3373,6 @@ static void mtip_standby_drive(struct driver_data *dd)
  */
 static int mtip_hw_exit(struct driver_data *dd)
 {
-	/*
-	 * Send standby immediate (E0h) to the drive so that it
-	 * saves its state.
-	 */
 	if (!dd->sr) {
 		/* de-initialize the port. */
 		mtip_deinit_port(dd->port);
@@ -3341,8 +3414,7 @@ static int mtip_hw_shutdown(struct driver_data *dd)
 	 * Send standby immediate (E0h) to the drive so that it
 	 * saves its state.
 	 */
-	if (!dd->sr && dd->port)
-		mtip_standby_immediate(dd->port);
+	mtip_standby_drive(dd);
 
 	return 0;
 }
@@ -3365,7 +3437,7 @@ static int mtip_hw_suspend(struct driver_data *dd)
 	 * Send standby immediate (E0h) to the drive
 	 * so that it saves its state.
 	 */
-	if (mtip_standby_immediate(dd->port) != 0) {
+	if (mtip_standby_drive(dd) != 0) {
 		dev_err(&dd->pdev->dev,
 			"Failed standby-immediate command\n");
 		return -EFAULT;
@@ -3603,6 +3675,28 @@ static int mtip_block_getgeo(struct block_device *dev,
 	return 0;
 }
 
+static int mtip_block_open(struct block_device *dev, fmode_t mode)
+{
+	struct driver_data *dd;
+
+	if (dev && dev->bd_disk) {
+		dd = (struct driver_data *) dev->bd_disk->private_data;
+
+		if (dd) {
+			if (test_bit(MTIP_DDF_REMOVAL_BIT,
+							&dd->dd_flag)) {
+				return -ENODEV;
+			}
+			return 0;
+		}
+	}
+	return -ENODEV;
+}
+
+void mtip_block_release(struct gendisk *disk, fmode_t mode)
+{
+}
+
 /*
  * Block device operation function.
  *
@@ -3610,6 +3704,8 @@ static int mtip_block_getgeo(struct block_device *dev,
  * layer.
  */
 static const struct block_device_operations mtip_block_ops = {
+	.open		= mtip_block_open,
+	.release	= mtip_block_release,
 	.ioctl		= mtip_block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= mtip_block_compat_ioctl,
@@ -3671,10 +3767,9 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 				rq_data_dir(rq))) {
 			return -ENODATA;
 		}
-		if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)))
+		if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag) ||
+			test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)))
 			return -ENODATA;
-		if (test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag))
-			return -ENXIO;
 	}
 
 	if (rq->cmd_flags & REQ_DISCARD) {
@@ -3786,11 +3881,33 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 	return 0;
 }
 
+static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
+								bool reserved)
+{
+	struct driver_data *dd = req->q->queuedata;
+	int ret = BLK_EH_RESET_TIMER;
+
+	if (reserved)
+		goto exit_handler;
+
+	if (test_bit(req->tag, dd->port->cmds_to_issue))
+		goto exit_handler;
+
+	if (test_and_set_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags))
+		goto exit_handler;
+
+	wake_up_interruptible(&dd->port->svc_wait);
+exit_handler:
+	return ret;
+}
+
 static struct blk_mq_ops mtip_mq_ops = {
 	.queue_rq	= mtip_queue_rq,
 	.map_queue	= blk_mq_map_queue,
 	.init_request	= mtip_init_cmd,
 	.exit_request	= mtip_free_cmd,
+	.complete	= mtip_softirq_done_fn,
+	.timeout        = mtip_cmd_timeout,
 };
 
 /*
@@ -3857,7 +3974,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 
 	mtip_hw_debugfs_init(dd);
 
-skip_create_disk:
 	memset(&dd->tags, 0, sizeof(dd->tags));
 	dd->tags.ops = &mtip_mq_ops;
 	dd->tags.nr_hw_queues = 1;
@@ -3867,12 +3983,13 @@ skip_create_disk:
 	dd->tags.numa_node = dd->numa_node;
 	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE;
 	dd->tags.driver_data = dd;
+	dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS;
 
 	rv = blk_mq_alloc_tag_set(&dd->tags);
 	if (rv) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
-		goto block_queue_alloc_init_error;
+		goto block_queue_alloc_tag_error;
 	}
 
 	/* Allocate the request queue. */
@@ -3887,6 +4004,7 @@ skip_create_disk:
 	dd->disk->queue		= dd->queue;
 	dd->queue->queuedata	= dd;
 
+skip_create_disk:
 	/* Initialize the protocol layer. */
 	wait_for_rebuild = mtip_hw_get_identify(dd);
 	if (wait_for_rebuild < 0) {
@@ -3983,8 +4101,9 @@ kthread_run_error:
 read_capacity_error:
 init_hw_cmds_error:
 	blk_cleanup_queue(dd->queue);
-	blk_mq_free_tag_set(&dd->tags);
 block_queue_alloc_init_error:
+	blk_mq_free_tag_set(&dd->tags);
+block_queue_alloc_tag_error:
 	mtip_hw_debugfs_exit(dd);
 disk_index_error:
 	spin_lock(&rssd_index_lock);
@@ -4001,6 +4120,22 @@ protocol_init_error:
 	return rv;
 }
 
+static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
+{
+	struct driver_data *dd = (struct driver_data *)data;
+	struct mtip_cmd *cmd;
+
+	if (likely(!reserv))
+		blk_mq_complete_request(rq, -ENODEV);
+	else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+
+		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
+		if (cmd->comp_func)
+			cmd->comp_func(dd->port, MTIP_TAG_INTERNAL,
+					cmd, -ENODEV);
+	}
+}
+
 /*
  * Block layer deinitialization function.
  *
@@ -4032,12 +4167,23 @@ static int mtip_block_remove(struct driver_data *dd)
 		}
 	}
 
-	if (!dd->sr)
-		mtip_standby_drive(dd);
+	if (!dd->sr) {
+		/*
+		 * Explicitly wait here for IOs to quiesce,
+		 * as mtip_standby_drive usually won't wait for IOs.
+		 */
+		if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS,
+								GFP_KERNEL))
+			mtip_standby_drive(dd);
+	}
 	else
 		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
 						dd->disk->disk_name);
 
+	blk_mq_freeze_queue_start(dd->queue);
+	blk_mq_stop_hw_queues(dd->queue);
+	blk_mq_all_tag_busy_iter(dd->tags.tags[0], mtip_no_dev_cleanup, dd);
+
 	/*
 	 * Delete our gendisk structure. This also removes the device
 	 * from /dev
@@ -4047,7 +4193,8 @@ static int mtip_block_remove(struct driver_data *dd)
 		dd->bdev = NULL;
 	}
 	if (dd->disk) {
-		del_gendisk(dd->disk);
+		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+			del_gendisk(dd->disk);
 		if (dd->disk->queue) {
 			blk_cleanup_queue(dd->queue);
 			blk_mq_free_tag_set(&dd->tags);
@@ -4088,7 +4235,8 @@ static int mtip_block_shutdown(struct driver_data *dd)
 		dev_info(&dd->pdev->dev,
 			"Shutting down %s ...\n", dd->disk->disk_name);
 
-		del_gendisk(dd->disk);
+		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+			del_gendisk(dd->disk);
 		if (dd->disk->queue) {
 			blk_cleanup_queue(dd->queue);
 			blk_mq_free_tag_set(&dd->tags);
@@ -4433,7 +4581,7 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 	struct driver_data *dd = pci_get_drvdata(pdev);
 	unsigned long flags, to;
 
-	set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag);
+	set_bit(MTIP_DDF_REMOVAL_BIT, &dd->dd_flag);
 
 	spin_lock_irqsave(&dev_lock, flags);
 	list_del_init(&dd->online_list);
@@ -4450,12 +4598,17 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 	} while (atomic_read(&dd->irq_workers_active) != 0 &&
 		time_before(jiffies, to));
 
+	if (!dd->sr)
+		fsync_bdev(dd->bdev);
+
 	if (atomic_read(&dd->irq_workers_active) != 0) {
 		dev_warn(&dd->pdev->dev,
 			"Completion workers still active!\n");
 	}
 
-	blk_mq_stop_hw_queues(dd->queue);
+	blk_set_queue_dying(dd->queue);
+	set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag);
+
 	/* Clean up the block layer. */
 	mtip_block_remove(dd);
 
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 3274784008eb..7617888f7944 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -134,16 +134,24 @@ enum {
 	MTIP_PF_EH_ACTIVE_BIT       = 1, /* error handling */
 	MTIP_PF_SE_ACTIVE_BIT       = 2, /* secure erase */
 	MTIP_PF_DM_ACTIVE_BIT       = 3, /* download microcde */
+	MTIP_PF_TO_ACTIVE_BIT       = 9, /* timeout handling */
 	MTIP_PF_PAUSE_IO      =	((1 << MTIP_PF_IC_ACTIVE_BIT) |
 				(1 << MTIP_PF_EH_ACTIVE_BIT) |
 				(1 << MTIP_PF_SE_ACTIVE_BIT) |
-				(1 << MTIP_PF_DM_ACTIVE_BIT)),
+				(1 << MTIP_PF_DM_ACTIVE_BIT) |
+				(1 << MTIP_PF_TO_ACTIVE_BIT)),
 
 	MTIP_PF_SVC_THD_ACTIVE_BIT  = 4,
 	MTIP_PF_ISSUE_CMDS_BIT      = 5,
 	MTIP_PF_REBUILD_BIT         = 6,
 	MTIP_PF_SVC_THD_STOP_BIT    = 8,
 
+	MTIP_PF_SVC_THD_WORK	= ((1 << MTIP_PF_EH_ACTIVE_BIT) |
+				  (1 << MTIP_PF_ISSUE_CMDS_BIT) |
+				  (1 << MTIP_PF_REBUILD_BIT) |
+				  (1 << MTIP_PF_SVC_THD_STOP_BIT) |
+				  (1 << MTIP_PF_TO_ACTIVE_BIT)),
+
 	/* below are bit numbers in 'dd_flag' defined in driver_data */
 	MTIP_DDF_SEC_LOCK_BIT	    = 0,
 	MTIP_DDF_REMOVE_PENDING_BIT = 1,
@@ -153,6 +161,7 @@ enum {
 	MTIP_DDF_RESUME_BIT         = 6,
 	MTIP_DDF_INIT_DONE_BIT      = 7,
 	MTIP_DDF_REBUILD_FAILED_BIT = 8,
+	MTIP_DDF_REMOVAL_BIT	    = 9,
 
 	MTIP_DDF_STOP_IO      = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) |
 				(1 << MTIP_DDF_SEC_LOCK_BIT) |
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 93b3f99b6865..8f1ce6d57a08 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -618,8 +618,8 @@ static void nbd_request_handler(struct request_queue *q)
 			req, req->cmd_type);
 
 		if (unlikely(!nbd->sock)) {
-			dev_err(disk_to_dev(nbd->disk),
-				"Attempted send on closed socket\n");
+			dev_err_ratelimited(disk_to_dev(nbd->disk),
+					    "Attempted send on closed socket\n");
 			req->errors++;
 			nbd_end_request(nbd, req);
 			spin_lock_irq(q->queue_lock);
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 562b5a4ca7b7..78a39f736c64 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -126,7 +126,7 @@
 */
 #include <linux/types.h>
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PD_MAJOR;
 static char *name = PD_NAME;
 static int cluster = 64;
@@ -161,7 +161,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV};
 static DEFINE_MUTEX(pd_mutex);
 static DEFINE_SPINLOCK(pd_lock);
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param(cluster, int, 0);
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 1740d75e8a32..216a94fed5b4 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -117,7 +117,7 @@
 
 */
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PT_MAJOR;
 static char *name = PT_NAME;
 static int disable = 0;
@@ -152,7 +152,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 
 #include <asm/uaccess.h>
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param_array(drive0, int, NULL, 0);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 81ea69fee7ca..fbdddd6f94b8 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1955,7 +1955,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
 
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false,
-					  GFP_ATOMIC);
+					  GFP_NOIO);
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
@@ -2004,7 +2004,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
 	rbd_dev = img_request->rbd_dev;
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops,
-						false, GFP_ATOMIC);
+						false, GFP_NOIO);
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
@@ -2506,7 +2506,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 					bio_chain_clone_range(&bio_list,
 								&bio_offset,
 								clone_size,
-								GFP_ATOMIC);
+								GFP_NOIO);
 			if (!obj_request->bio_list)
 				goto out_unwind;
 		} else if (type == OBJ_REQUEST_PAGES) {
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ca35495a5be..1e5cd39d0cc2 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -641,11 +641,12 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_put_disk;
 
-	q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
+	q = blk_mq_init_queue(&vblk->tag_set);
 	if (IS_ERR(q)) {
 		err = -ENOMEM;
 		goto out_free_tags;
 	}
+	vblk->disk->queue = q;
 
 	q->queuedata = vblk;
 
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 41fb1a917b17..33e23a7a691f 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -595,8 +595,6 @@ int xen_blkif_schedule(void *arg)
 	unsigned long timeout;
 	int ret;
 
-	xen_blkif_get(blkif);
-
 	while (!kthread_should_stop()) {
 		if (try_to_freeze())
 			continue;
@@ -650,7 +648,6 @@ purge_gnt_list:
 		print_stats(blkif);
 
 	blkif->xenblkd = NULL;
-	xen_blkif_put(blkif);
 
 	return 0;
 }
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index f53cff42f8da..923308201375 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -221,7 +221,6 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 	if (blkif->xenblkd) {
 		kthread_stop(blkif->xenblkd);
 		wake_up(&blkif->shutdown_wq);
-		blkif->xenblkd = NULL;
 	}
 
 	/* The above kthread_stop() guarantees that at this point we
@@ -266,9 +265,10 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 
 static void xen_blkif_free(struct xen_blkif *blkif)
 {
-
-	xen_blkif_disconnect(blkif);
+	WARN_ON(xen_blkif_disconnect(blkif));
 	xen_vbd_free(&blkif->vbd);
+	kfree(blkif->be->mode);
+	kfree(blkif->be);
 
 	/* Make sure everything is drained before shutting down */
 	BUG_ON(blkif->persistent_gnt_c != 0);
@@ -445,8 +445,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev)
 		xen_blkif_put(be->blkif);
 	}
 
-	kfree(be->mode);
-	kfree(be);
 	return 0;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 370c2f76016d..62a93b685c54 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -574,13 +574,13 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 
 	if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
 		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
-		clear_page(mem);
+		memset(mem, 0, PAGE_SIZE);
 		return 0;
 	}
 
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE)
-		copy_page(mem, cmem);
+		memcpy(mem, cmem, PAGE_SIZE);
 	else
 		ret = zcomp_decompress(zram->comp, cmem, size, mem);
 	zs_unmap_object(meta->mem_pool, handle);
@@ -738,7 +738,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
 		src = kmap_atomic(page);
-		copy_page(cmem, src);
+		memcpy(cmem, src, PAGE_SIZE);
 		kunmap_atomic(src);
 	} else {
 		memcpy(cmem, src, clen);
@@ -1368,7 +1368,8 @@ static ssize_t hot_remove_store(struct class *class,
 	zram = idr_find(&zram_index_idr, dev_id);
 	if (zram) {
 		ret = zram_remove(zram);
-		idr_remove(&zram_index_idr, dev_id);
+		if (!ret)
+			idr_remove(&zram_index_idr, dev_id);
 	} else {
 		ret = -ENODEV;
 	}
@@ -1377,8 +1378,14 @@ static ssize_t hot_remove_store(struct class *class,
 	return ret ? ret : count;
 }
 
+/*
+ * NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a
+ * sense that reading from this file does alter the state of your system -- it
+ * creates a new un-initialized zram device and returns back this device's
+ * device_id (or an error code if it fails to create a new device).
+ */
 static struct class_attribute zram_control_class_attrs[] = {
-	__ATTR_RO(hot_add),
+	__ATTR(hot_add, 0400, hot_add_show, NULL),
 	__ATTR_WO(hot_remove),
 	__ATTR_NULL,
 };
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index fa893c3ec408..5df8e1234505 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -82,6 +82,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0489, 0xe05f) },
 	{ USB_DEVICE(0x0489, 0xe076) },
 	{ USB_DEVICE(0x0489, 0xe078) },
+	{ USB_DEVICE(0x0489, 0xe095) },
 	{ USB_DEVICE(0x04c5, 0x1330) },
 	{ USB_DEVICE(0x04CA, 0x3004) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
@@ -92,6 +93,8 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x300d) },
 	{ USB_DEVICE(0x04CA, 0x300f) },
 	{ USB_DEVICE(0x04CA, 0x3010) },
+	{ USB_DEVICE(0x04CA, 0x3014) },
+	{ USB_DEVICE(0x04CA, 0x3018) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0930, 0x021c) },
 	{ USB_DEVICE(0x0930, 0x0220) },
@@ -113,10 +116,12 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x13d3, 0x3375) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
+	{ USB_DEVICE(0x13d3, 0x3395) },
 	{ USB_DEVICE(0x13d3, 0x3402) },
 	{ USB_DEVICE(0x13d3, 0x3408) },
 	{ USB_DEVICE(0x13d3, 0x3423) },
 	{ USB_DEVICE(0x13d3, 0x3432) },
+	{ USB_DEVICE(0x13d3, 0x3472) },
 	{ USB_DEVICE(0x13d3, 0x3474) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
@@ -144,6 +149,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -154,6 +160,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
@@ -175,10 +183,12 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 968897108c76..7bb8055bd10c 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -196,6 +196,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -206,6 +207,8 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3018), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
@@ -227,10 +230,12 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
@@ -328,6 +333,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3410), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3416), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x13d3, 0x3459), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3494), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8821AE Bluetooth devices */
 	{ USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK },
@@ -2052,12 +2058,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return -EINVAL;
 	}
 
-	/* At the moment only the hardware variant iBT 3.0 (LnP/SfP) is
-	 * supported by this firmware loading method. This check has been
-	 * put in place to ensure correct forward compatibility options
-	 * when newer hardware variants come along.
+	/* At the moment the iBT 3.0 hardware variants 0x0b (LnP/SfP)
+	 * and 0x0c (WsP) are supported by this firmware loading method.
+	 *
+	 * This check has been put in place to ensure correct forward
+	 * compatibility options when newer hardware variants come along.
 	 */
-	if (ver->hw_variant != 0x0b) {
+	if (ver->hw_variant != 0x0b && ver->hw_variant != 0x0c) {
 		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
 		       hdev->name, ver->hw_variant);
 		kfree_skb(skb);
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index cb852cc750b7..f9b569ef3dd7 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -287,6 +287,9 @@ static int bcm_open(struct hci_uart *hu)
 
 	hu->priv = bcm;
 
+	if (!hu->tty->dev)
+		goto out;
+
 	mutex_lock(&bcm_device_lock);
 	list_for_each(p, &bcm_device_list) {
 		struct bcm_device *dev = list_entry(p, struct bcm_device, list);
@@ -307,7 +310,7 @@ static int bcm_open(struct hci_uart *hu)
 	}
 
 	mutex_unlock(&bcm_device_lock);
-
+out:
 	return 0;
 }
 
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 4a414a5a3165..0c63fce0c1e0 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -307,6 +307,9 @@ static int intel_set_power(struct hci_uart *hu, bool powered)
 	struct list_head *p;
 	int err = -ENODEV;
 
+	if (!hu->tty->dev)
+		return err;
+
 	mutex_lock(&intel_device_list_lock);
 
 	list_for_each(p, &intel_device_list) {
@@ -379,6 +382,9 @@ static void intel_busy_work(struct work_struct *work)
 	struct intel_data *intel = container_of(work, struct intel_data,
 						busy_work);
 
+	if (!intel->hu->tty->dev)
+		return;
+
 	/* Link is busy, delay the suspend */
 	mutex_lock(&intel_device_list_lock);
 	list_for_each(p, &intel_device_list) {
@@ -913,6 +919,8 @@ done:
 	list_for_each(p, &intel_device_list) {
 		struct intel_device *dev = list_entry(p, struct intel_device,
 						      list);
+		if (!hu->tty->dev)
+			break;
 		if (hu->tty->dev->parent == dev->pdev->dev.parent) {
 			if (device_may_wakeup(&dev->pdev->dev))
 				idev = dev;
@@ -1094,6 +1102,9 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 
 	BT_DBG("hu %p skb %p", hu, skb);
 
+	if (!hu->tty->dev)
+		goto out_enqueue;
+
 	/* Be sure our controller is resumed and potential LPM transaction
 	 * completed before enqueuing any packet.
 	 */
@@ -1110,7 +1121,7 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 		}
 	}
 	mutex_unlock(&intel_device_list_lock);
-
+out_enqueue:
 	skb_queue_tail(&intel->txq, skb);
 
 	return 0;
@@ -1234,8 +1245,7 @@ static int intel_probe(struct platform_device *pdev)
 
 	idev->pdev = pdev;
 
-	idev->reset = devm_gpiod_get_optional(&pdev->dev, "reset",
-					      GPIOD_OUT_LOW);
+	idev->reset = devm_gpiod_get(&pdev->dev, "reset", GPIOD_OUT_LOW);
 	if (IS_ERR(idev->reset)) {
 		dev_err(&pdev->dev, "Unable to retrieve gpio\n");
 		return PTR_ERR(idev->reset);
@@ -1247,8 +1257,7 @@ static int intel_probe(struct platform_device *pdev)
 
 		dev_err(&pdev->dev, "No IRQ, falling back to gpio-irq\n");
 
-		host_wake = devm_gpiod_get_optional(&pdev->dev, "host-wake",
-						    GPIOD_IN);
+		host_wake = devm_gpiod_get(&pdev->dev, "host-wake", GPIOD_IN);
 		if (IS_ERR(host_wake)) {
 			dev_err(&pdev->dev, "Unable to retrieve IRQ\n");
 			goto no_irq;
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index ed888e302bc3..597b2d16b775 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -50,6 +50,7 @@ struct vhci_data {
 	wait_queue_head_t read_wait;
 	struct sk_buff_head readq;
 
+	struct mutex open_mutex;
 	struct delayed_work open_timeout;
 };
 
@@ -87,12 +88,15 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	return 0;
 }
 
-static int vhci_create_device(struct vhci_data *data, __u8 opcode)
+static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 {
 	struct hci_dev *hdev;
 	struct sk_buff *skb;
 	__u8 dev_type;
 
+	if (data->hdev)
+		return -EBADFD;
+
 	/* bits 0-1 are dev_type (BR/EDR or AMP) */
 	dev_type = opcode & 0x03;
 
@@ -151,6 +155,17 @@ static int vhci_create_device(struct vhci_data *data, __u8 opcode)
 	return 0;
 }
 
+static int vhci_create_device(struct vhci_data *data, __u8 opcode)
+{
+	int err;
+
+	mutex_lock(&data->open_mutex);
+	err = __vhci_create_device(data, opcode);
+	mutex_unlock(&data->open_mutex);
+
+	return err;
+}
+
 static inline ssize_t vhci_get_user(struct vhci_data *data,
 				    struct iov_iter *from)
 {
@@ -189,11 +204,6 @@ static inline ssize_t vhci_get_user(struct vhci_data *data,
 		break;
 
 	case HCI_VENDOR_PKT:
-		if (data->hdev) {
-			kfree_skb(skb);
-			return -EBADFD;
-		}
-
 		cancel_delayed_work_sync(&data->open_timeout);
 
 		opcode = *((__u8 *) skb->data);
@@ -320,6 +330,7 @@ static int vhci_open(struct inode *inode, struct file *file)
 	skb_queue_head_init(&data->readq);
 	init_waitqueue_head(&data->read_wait);
 
+	mutex_init(&data->open_mutex);
 	INIT_DELAYED_WORK(&data->open_timeout, vhci_open_timeout);
 
 	file->private_data = data;
@@ -333,15 +344,18 @@ static int vhci_open(struct inode *inode, struct file *file)
 static int vhci_release(struct inode *inode, struct file *file)
 {
 	struct vhci_data *data = file->private_data;
-	struct hci_dev *hdev = data->hdev;
+	struct hci_dev *hdev;
 
 	cancel_delayed_work_sync(&data->open_timeout);
 
+	hdev = data->hdev;
+
 	if (hdev) {
 		hci_unregister_dev(hdev);
 		hci_free_dev(hdev);
 	}
 
+	skb_queue_purge(&data->readq);
 	file->private_data = NULL;
 	kfree(data);
 
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index 7082c7268845..0f54cb7ddcbb 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -187,6 +187,7 @@ struct arm_ccn {
 	struct arm_ccn_component *xp;
 
 	struct arm_ccn_dt dt;
+	int mn_id;
 };
 
 
@@ -326,6 +327,7 @@ struct arm_ccn_pmu_event {
 static ssize_t arm_ccn_pmu_event_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 	struct arm_ccn_pmu_event *event = container_of(attr,
 			struct arm_ccn_pmu_event, attr);
 	ssize_t res;
@@ -352,6 +354,9 @@ static ssize_t arm_ccn_pmu_event_show(struct device *dev,
 			res += snprintf(buf + res, PAGE_SIZE - res,
 					",cmp_l=?,cmp_h=?,mask=?");
 		break;
+	case CCN_TYPE_MN:
+		res += snprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id);
+		break;
 	default:
 		res += snprintf(buf + res, PAGE_SIZE - res, ",node=?");
 		break;
@@ -381,9 +386,9 @@ static umode_t arm_ccn_pmu_events_is_visible(struct kobject *kobj,
 }
 
 static struct arm_ccn_pmu_event arm_ccn_pmu_events[] = {
-	CCN_EVENT_MN(eobarrier, "dir=0,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
-	CCN_EVENT_MN(ecbarrier, "dir=0,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
-	CCN_EVENT_MN(dvmop, "dir=0,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
+	CCN_EVENT_MN(eobarrier, "dir=1,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
+	CCN_EVENT_MN(ecbarrier, "dir=1,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
+	CCN_EVENT_MN(dvmop, "dir=1,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
 	CCN_EVENT_HNI(txdatflits, "dir=1,vc=3", CCN_IDX_MASK_ANY),
 	CCN_EVENT_HNI(rxdatflits, "dir=0,vc=3", CCN_IDX_MASK_ANY),
 	CCN_EVENT_HNI(txreqflits, "dir=1,vc=0", CCN_IDX_MASK_ANY),
@@ -757,6 +762,12 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 
 	/* Validate node/xp vs topology */
 	switch (type) {
+	case CCN_TYPE_MN:
+		if (node_xp != ccn->mn_id) {
+			dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp);
+			return -EINVAL;
+		}
+		break;
 	case CCN_TYPE_XP:
 		if (node_xp >= ccn->num_xps) {
 			dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp);
@@ -884,6 +895,10 @@ static void arm_ccn_pmu_xp_dt_config(struct perf_event *event, int enable)
 	struct arm_ccn_component *xp;
 	u32 val, dt_cfg;
 
+	/* Nothing to do for cycle counter */
+	if (hw->idx == CCN_IDX_PMU_CYCLE_COUNTER)
+		return;
+
 	if (CCN_CONFIG_TYPE(event->attr.config) == CCN_TYPE_XP)
 		xp = &ccn->xp[CCN_CONFIG_XP(event->attr.config)];
 	else
@@ -986,7 +1001,7 @@ static void arm_ccn_pmu_xp_watchpoint_config(struct perf_event *event)
 
 	/* Comparison values */
 	writel(cmp_l & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_L(wp));
-	writel((cmp_l >> 32) & 0xefffffff,
+	writel((cmp_l >> 32) & 0x7fffffff,
 			source->base + CCN_XP_DT_CMP_VAL_L(wp) + 4);
 	writel(cmp_h & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_H(wp));
 	writel((cmp_h >> 32) & 0x0fffffff,
@@ -994,7 +1009,7 @@ static void arm_ccn_pmu_xp_watchpoint_config(struct perf_event *event)
 
 	/* Mask */
 	writel(mask_l & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_L(wp));
-	writel((mask_l >> 32) & 0xefffffff,
+	writel((mask_l >> 32) & 0x7fffffff,
 			source->base + CCN_XP_DT_CMP_MASK_L(wp) + 4);
 	writel(mask_h & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_H(wp));
 	writel((mask_h >> 32) & 0x0fffffff,
@@ -1368,6 +1383,8 @@ static int arm_ccn_init_nodes(struct arm_ccn *ccn, int region,
 
 	switch (type) {
 	case CCN_TYPE_MN:
+		ccn->mn_id = id;
+		return 0;
 	case CCN_TYPE_DT:
 		return 0;
 	case CCN_TYPE_XP:
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index e98d15eaa799..1827fc4d15c1 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -150,7 +150,7 @@ static int __init weim_parse_dt(struct platform_device *pdev,
 			return ret;
 	}
 
-	for_each_child_of_node(pdev->dev.of_node, child) {
+	for_each_available_child_of_node(pdev->dev.of_node, child) {
 		if (!child->name)
 			continue;
 
diff --git a/drivers/bus/vexpress-config.c b/drivers/bus/vexpress-config.c
index 6575c0fe6a4e..27ea64fa4f9b 100644
--- a/drivers/bus/vexpress-config.c
+++ b/drivers/bus/vexpress-config.c
@@ -171,6 +171,7 @@ static int vexpress_config_populate(struct device_node *node)
 {
 	struct device_node *bridge;
 	struct device *parent;
+	int ret;
 
 	bridge = of_parse_phandle(node, "arm,vexpress,config-bridge", 0);
 	if (!bridge)
@@ -181,7 +182,11 @@ static int vexpress_config_populate(struct device_node *node)
 	if (WARN_ON(!parent))
 		return -ENODEV;
 
-	return of_platform_populate(node, NULL, NULL, parent);
+	ret = of_platform_populate(node, NULL, NULL, parent);
+
+	put_device(parent);
+
+	return ret;
 }
 
 static int __init vexpress_config_init(void)
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index a043107da2af..3143db57ce44 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -583,10 +583,12 @@ config TELCLOCK
 	  controlling the behavior of this hardware.
 
 config DEVPORT
-	bool
-	depends on !M68K
+	bool "/dev/port character device"
 	depends on ISA || PCI
 	default y
+	help
+	  Say Y here if you want to support the /dev/port device. The /dev/port
+	  device is similar to /dev/mem, but for I/O ports.
 
 source "drivers/s390/char/Kconfig"
 
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 6f497aa1b276..cf25020576fa 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -84,14 +84,14 @@ static size_t rng_buffer_size(void)
 
 static void add_early_randomness(struct hwrng *rng)
 {
-	unsigned char bytes[16];
 	int bytes_read;
+	size_t size = min_t(size_t, 16, rng_buffer_size());
 
 	mutex_lock(&reading_mutex);
-	bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
+	bytes_read = rng_get_data(rng, rng_buffer, size, 1);
 	mutex_unlock(&reading_mutex);
 	if (bytes_read > 0)
-		add_device_randomness(bytes, bytes_read);
+		add_device_randomness(rng_buffer, bytes_read);
 }
 
 static inline void cleanup_rng(struct kref *kref)
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
index 30cf4623184f..7845a38b6604 100644
--- a/drivers/char/hw_random/exynos-rng.c
+++ b/drivers/char/hw_random/exynos-rng.c
@@ -89,6 +89,7 @@ static int exynos_read(struct hwrng *rng, void *buf,
 						struct exynos_rng, rng);
 	u32 *data = buf;
 	int retry = 100;
+	int ret = 4;
 
 	pm_runtime_get_sync(exynos_rng->dev);
 
@@ -97,23 +98,27 @@ static int exynos_read(struct hwrng *rng, void *buf,
 	while (!(exynos_rng_readl(exynos_rng,
 			EXYNOS_PRNG_STATUS_OFFSET) & PRNG_DONE) && --retry)
 		cpu_relax();
-	if (!retry)
-		return -ETIMEDOUT;
+	if (!retry) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
 
 	exynos_rng_writel(exynos_rng, PRNG_DONE, EXYNOS_PRNG_STATUS_OFFSET);
 
 	*data = exynos_rng_readl(exynos_rng, EXYNOS_PRNG_OUT1_OFFSET);
 
+out:
 	pm_runtime_mark_last_busy(exynos_rng->dev);
 	pm_runtime_put_sync_autosuspend(exynos_rng->dev);
 
-	return 4;
+	return ret;
 }
 
 static int exynos_rng_probe(struct platform_device *pdev)
 {
 	struct exynos_rng *exynos_rng;
 	struct resource *res;
+	int ret;
 
 	exynos_rng = devm_kzalloc(&pdev->dev, sizeof(struct exynos_rng),
 					GFP_KERNEL);
@@ -141,7 +146,13 @@ static int exynos_rng_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	return devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
+	ret = devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
+	if (ret) {
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
+
+	return ret;
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 8a1432e8bb80..f5c26a5f6875 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -384,7 +384,12 @@ static int omap_rng_probe(struct platform_device *pdev)
 	}
 
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
+		goto err_ioremap;
+	}
 
 	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
 				get_omap_rng_device_details(priv);
@@ -435,8 +440,15 @@ static int __maybe_unused omap_rng_suspend(struct device *dev)
 static int __maybe_unused omap_rng_resume(struct device *dev)
 {
 	struct omap_rng_dev *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
 
-	pm_runtime_get_sync(dev);
 	priv->pdata->init(priv);
 
 	return 0;
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index e3536da05c88..25372dc381d4 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -3819,6 +3819,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 	while (!list_empty(&intf->waiting_rcv_msgs)) {
 		smi_msg = list_entry(intf->waiting_rcv_msgs.next,
 				     struct ipmi_smi_msg, link);
+		list_del(&smi_msg->link);
 		if (!run_to_completion)
 			spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
 					       flags);
@@ -3828,11 +3829,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf)
 		if (rv > 0) {
 			/*
 			 * To preserve message order, quit if we
-			 * can't handle a message.
+			 * can't handle a message.  Add the message
+			 * back at the head, this is safe because this
+			 * tasklet is the only thing that pulls the
+			 * messages.
 			 */
+			list_add(&smi_msg->link, &intf->waiting_rcv_msgs);
 			break;
 		} else {
-			list_del(&smi_msg->link);
 			if (rv == 0)
 				/* Message handled */
 				ipmi_free_smi_msg(smi_msg);
@@ -3873,6 +3877,9 @@ static void smi_recv_tasklet(unsigned long val)
 	 * because the lower layer is allowed to hold locks while calling
 	 * message delivery.
 	 */
+
+	rcu_read_lock();
+
 	if (!run_to_completion)
 		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
 	if (intf->curr_msg == NULL && !intf->in_shutdown) {
@@ -3895,6 +3902,8 @@ static void smi_recv_tasklet(unsigned long val)
 	if (newmsg)
 		intf->handlers->sender(intf->send_info, newmsg);
 
+	rcu_read_unlock();
+
 	handle_new_recv_msgs(intf);
 }
 
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 90e624662257..f53e8ba2c718 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -758,6 +758,11 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 			       result, len, data[2]);
 		} else if (data[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2
 			   || data[1] != IPMI_GET_MSG_FLAGS_CMD) {
+			/*
+			 * Don't abort here, maybe it was a queued
+			 * response to a previous command.
+			 */
+			ipmi_ssif_unlock_cond(ssif_info, flags);
 			pr_warn(PFX "Invalid response getting flags: %x %x\n",
 				data[0], data[1]);
 		} else {
@@ -888,6 +893,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 		 * for details on the intricacies of this.
 		 */
 		int left;
+		unsigned char *data_to_send;
 
 		ssif_inc_stat(ssif_info, sent_messages_parts);
 
@@ -896,6 +902,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 			left = 32;
 		/* Length byte. */
 		ssif_info->multi_data[ssif_info->multi_pos] = left;
+		data_to_send = ssif_info->multi_data + ssif_info->multi_pos;
 		ssif_info->multi_pos += left;
 		if (left < 32)
 			/*
@@ -909,7 +916,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 		rv = ssif_i2c_send(ssif_info, msg_written_handler,
 				  I2C_SMBUS_WRITE,
 				  SSIF_IPMI_MULTI_PART_REQUEST_MIDDLE,
-				  ssif_info->multi_data + ssif_info->multi_pos,
+				  data_to_send,
 				  I2C_SMBUS_BLOCK_DATA);
 		if (rv < 0) {
 			/* request failed, just return the error. */
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 096f0cef4da1..40d400fe5bb7 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -1162,10 +1162,11 @@ static int wdog_reboot_handler(struct notifier_block *this,
 			ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
 			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 		} else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
-			/* Set a long timer to let the reboot happens, but
-			   reboot if it hangs, but only if the watchdog
+			/* Set a long timer to let the reboot happen or
+			   reset if it hangs, but only if the watchdog
 			   timer was already running. */
-			timeout = 120;
+			if (timeout < 120)
+				timeout = 120;
 			pretimeout = 0;
 			ipmi_watchdog_state = WDOG_TIMEOUT_RESET;
 			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index c4094c4e22c1..34ef474a3923 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -859,7 +859,11 @@ static int __init lp_setup (char *str)
 	} else if (!strcmp(str, "auto")) {
 		parport_nr[0] = LP_PARPORT_AUTO;
 	} else if (!strcmp(str, "none")) {
-		parport_nr[parport_ptr++] = LP_PARPORT_NONE;
+		if (parport_ptr < LP_NO)
+			parport_nr[parport_ptr++] = LP_PARPORT_NONE;
+		else
+			printk(KERN_INFO "lp: too many ports, %s ignored.\n",
+			       str);
 	} else if (!strcmp(str, "reset")) {
 		reset = 1;
 	}
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6b1721f978c2..2898d19fadf5 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -59,6 +59,10 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 #endif
 
 #ifdef CONFIG_STRICT_DEVMEM
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return devmem_is_allowed(pfn);
+}
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	u64 from = ((u64)pfn) << PAGE_SHIFT;
@@ -78,6 +82,10 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	return 1;
 }
 #else
+static inline int page_is_allowed(unsigned long pfn)
+{
+	return 1;
+}
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	return 1;
@@ -125,23 +133,31 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 
 	while (count > 0) {
 		unsigned long remaining;
+		int allowed;
 
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, count))
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
 			return -EPERM;
+		if (allowed == 2) {
+			/* Show zeros for restricted memory. */
+			remaining = clear_user(buf, sz);
+		} else {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr)
+				return -EFAULT;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr)
-			return -EFAULT;
+			remaining = copy_to_user(buf, ptr, sz);
+
+			unxlate_dev_mem_ptr(p, ptr);
+		}
 
-		remaining = copy_to_user(buf, ptr, sz);
-		unxlate_dev_mem_ptr(p, ptr);
 		if (remaining)
 			return -EFAULT;
 
@@ -184,30 +200,36 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 #endif
 
 	while (count > 0) {
+		int allowed;
+
 		sz = size_inside_page(p, count);
 
-		if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+		allowed = page_is_allowed(p >> PAGE_SHIFT);
+		if (!allowed)
 			return -EPERM;
 
-		/*
-		 * On ia64 if a page has been mapped somewhere as uncached, then
-		 * it must also be accessed uncached by the kernel or data
-		 * corruption may occur.
-		 */
-		ptr = xlate_dev_mem_ptr(p);
-		if (!ptr) {
-			if (written)
-				break;
-			return -EFAULT;
-		}
+		/* Skip actual writing when a page is marked as restricted. */
+		if (allowed == 1) {
+			/*
+			 * On ia64 if a page has been mapped somewhere as
+			 * uncached, then it must also be accessed uncached
+			 * by the kernel or data corruption may occur.
+			 */
+			ptr = xlate_dev_mem_ptr(p);
+			if (!ptr) {
+				if (written)
+					break;
+				return -EFAULT;
+			}
 
-		copied = copy_from_user(ptr, buf, sz);
-		unxlate_dev_mem_ptr(p, ptr);
-		if (copied) {
-			written += sz - copied;
-			if (written)
-				break;
-			return -EFAULT;
+			copied = copy_from_user(ptr, buf, sz);
+			unxlate_dev_mem_ptr(p, ptr);
+			if (copied) {
+				written += sz - copied;
+				if (written)
+					break;
+				return -EFAULT;
+			}
 		}
 
 		buf += sz;
@@ -321,6 +343,11 @@ static const struct vm_operations_struct mmap_mem_ops = {
 static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 {
 	size_t size = vma->vm_end - vma->vm_start;
+	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+
+	/* It's illegal to wrap around the end of the physical address space. */
+	if (offset + (phys_addr_t)size - 1 < offset)
+		return -EINVAL;
 
 	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
 		return -EINVAL;
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index fc061f7c2bd1..a7de8ae185a5 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -374,7 +374,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 
 	rc = write_sync_reg(SCR_HOST_TO_READER_START, dev);
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;
@@ -387,7 +387,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	for (i = 0; i < bytes_to_write; i++) {
 		rc = wait_for_bulk_out_ready(dev);
 		if (rc <= 0) {
-			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2Zx\n",
+			DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n",
 			       rc);
 			DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 			if (rc == -ERESTARTSYS)
@@ -403,7 +403,7 @@ static ssize_t cm4040_write(struct file *filp, const char __user *buf,
 	rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev);
 
 	if (rc <= 0) {
-		DEBUGP(5, dev, "write_sync_reg c=%.2Zx\n", rc);
+		DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc);
 		DEBUGP(2, dev, "<- cm4040_write (failed)\n");
 		if (rc == -ERESTARTSYS)
 			return rc;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d0da5d852d41..1822472dffab 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -722,15 +722,18 @@ retry:
 	}
 }
 
-static void credit_entropy_bits_safe(struct entropy_store *r, int nbits)
+static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
 {
 	const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1));
 
+	if (nbits < 0)
+		return -EINVAL;
+
 	/* Cap the value to avoid overflows */
 	nbits = min(nbits,  nbits_max);
-	nbits = max(nbits, -nbits_max);
 
 	credit_entropy_bits(r, nbits);
+	return 0;
 }
 
 /*********************************************************************
@@ -945,6 +948,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	/* award one bit for the contents of the fast pool */
 	credit_entropy_bits(r, credit + 1);
 }
+EXPORT_SYMBOL_GPL(add_interrupt_randomness);
 
 #ifdef CONFIG_BLOCK
 void add_disk_randomness(struct gendisk *disk)
@@ -1457,12 +1461,16 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 static ssize_t
 urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
+	static int maxwarn = 10;
 	int ret;
 
-	if (unlikely(nonblocking_pool.initialized == 0))
-		printk_once(KERN_NOTICE "random: %s urandom read "
-			    "with %d bits of entropy available\n",
-			    current->comm, nonblocking_pool.entropy_total);
+	if (unlikely(nonblocking_pool.initialized == 0) &&
+	    maxwarn > 0) {
+		maxwarn--;
+		printk(KERN_NOTICE "random: %s: uninitialized urandom read "
+		       "(%zd bytes read, %d bits of entropy available)\n",
+		       current->comm, nbytes, nonblocking_pool.entropy_total);
+	}
 
 	nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
 	ret = extract_entropy_user(&nonblocking_pool, buf, nbytes);
@@ -1542,8 +1550,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EPERM;
 		if (get_user(ent_count, p))
 			return -EFAULT;
-		credit_entropy_bits_safe(&input_pool, ent_count);
-		return 0;
+		return credit_entropy_bits_safe(&input_pool, ent_count);
 	case RNDADDENTROPY:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -1557,8 +1564,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 				    size);
 		if (retval < 0)
 			return retval;
-		credit_entropy_bits_safe(&input_pool, ent_count);
-		return 0;
+		return credit_entropy_bits_safe(&input_pool, ent_count);
 	case RNDZAPENTCNT:
 	case RNDCLEARPOOL:
 		/*
@@ -1792,13 +1798,15 @@ int random_int_secret_init(void)
 	return 0;
 }
 
+static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash)
+		__aligned(sizeof(unsigned long));
+
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
  * with the goal of minimal entropy pool depletion. As a result, the random
  * value is not cryptographically secure but for several uses the cost of
  * depleting entropy is too high
  */
-static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
 unsigned int get_random_int(void)
 {
 	__u32 *hash;
@@ -1819,6 +1827,28 @@ unsigned int get_random_int(void)
 EXPORT_SYMBOL(get_random_int);
 
 /*
+ * Same as get_random_int(), but returns unsigned long.
+ */
+unsigned long get_random_long(void)
+{
+	__u32 *hash;
+	unsigned long ret;
+
+	if (arch_get_random_long(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
+	hash[0] += current->pid + jiffies + random_get_entropy();
+	md5_transform(hash, random_int_secret);
+	ret = *(unsigned long *)hash;
+	put_cpu_var(get_random_int_hash);
+
+	return ret;
+}
+EXPORT_SYMBOL(get_random_long);
+
+/*
  * randomize_range() returns a start address such that
  *
  *    [...... <range> .....]
@@ -1846,12 +1876,18 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
 {
 	struct entropy_store *poolp = &input_pool;
 
-	/* Suspend writing if we're above the trickle threshold.
-	 * We'll be woken up again once below random_write_wakeup_thresh,
-	 * or when the calling thread is about to terminate.
-	 */
-	wait_event_interruptible(random_write_wait, kthread_should_stop() ||
+	if (unlikely(nonblocking_pool.initialized == 0))
+		poolp = &nonblocking_pool;
+	else {
+		/* Suspend writing if we're above the trickle
+		 * threshold.  We'll be woken up again once below
+		 * random_write_wakeup_thresh, or when the calling
+		 * thread is about to terminate.
+		 */
+		wait_event_interruptible(random_write_wait,
+					 kthread_should_stop() ||
 			ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
+	}
 	mix_pool_bytes(poolp, buffer, count);
 	credit_entropy_bits(poolp, entropy);
 }
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 45cc39aabeee..a0d9ac6b6cc9 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -29,33 +29,92 @@
 #include "tpm.h"
 #include "tpm_eventlog.h"
 
-static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES);
-static LIST_HEAD(tpm_chip_list);
-static DEFINE_SPINLOCK(driver_lock);
+DEFINE_IDR(dev_nums_idr);
+static DEFINE_MUTEX(idr_lock);
 
 struct class *tpm_class;
 dev_t tpm_devt;
 
-/*
- * tpm_chip_find_get - return tpm_chip for a given chip number
- * @chip_num the device number for the chip
+/**
+ * tpm_try_get_ops() - Get a ref to the tpm_chip
+ * @chip: Chip to ref
+ *
+ * The caller must already have some kind of locking to ensure that chip is
+ * valid. This function will lock the chip so that the ops member can be
+ * accessed safely. The locking prevents tpm_chip_unregister from
+ * completing, so it should not be held for long periods.
+ *
+ * Returns -ERRNO if the chip could not be got.
  */
-struct tpm_chip *tpm_chip_find_get(int chip_num)
+int tpm_try_get_ops(struct tpm_chip *chip)
 {
-	struct tpm_chip *pos, *chip = NULL;
+	int rc = -EIO;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(pos, &tpm_chip_list, list) {
-		if (chip_num != TPM_ANY_NUM && chip_num != pos->dev_num)
-			continue;
+	get_device(&chip->dev);
 
-		if (try_module_get(pos->pdev->driver->owner)) {
-			chip = pos;
-			break;
-		}
+	down_read(&chip->ops_sem);
+	if (!chip->ops)
+		goto out_lock;
+
+	if (!try_module_get(chip->dev.parent->driver->owner))
+		goto out_lock;
+
+	return 0;
+out_lock:
+	up_read(&chip->ops_sem);
+	put_device(&chip->dev);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_try_get_ops);
+
+/**
+ * tpm_put_ops() - Release a ref to the tpm_chip
+ * @chip: Chip to put
+ *
+ * This is the opposite pair to tpm_try_get_ops(). After this returns chip may
+ * be kfree'd.
+ */
+void tpm_put_ops(struct tpm_chip *chip)
+{
+	module_put(chip->dev.parent->driver->owner);
+	up_read(&chip->ops_sem);
+	put_device(&chip->dev);
+}
+EXPORT_SYMBOL_GPL(tpm_put_ops);
+
+/**
+ * tpm_chip_find_get() - return tpm_chip for a given chip number
+ * @chip_num: id to find
+ *
+ * The return'd chip has been tpm_try_get_ops'd and must be released via
+ * tpm_put_ops
+  */
+struct tpm_chip *tpm_chip_find_get(int chip_num)
+{
+	struct tpm_chip *chip, *res = NULL;
+	int chip_prev;
+
+	mutex_lock(&idr_lock);
+
+	if (chip_num == TPM_ANY_NUM) {
+		chip_num = 0;
+		do {
+			chip_prev = chip_num;
+			chip = idr_get_next(&dev_nums_idr, &chip_num);
+			if (chip && !tpm_try_get_ops(chip)) {
+				res = chip;
+				break;
+			}
+		} while (chip_prev != chip_num);
+	} else {
+		chip = idr_find_slowpath(&dev_nums_idr, chip_num);
+		if (chip && !tpm_try_get_ops(chip))
+			res = chip;
 	}
-	rcu_read_unlock();
-	return chip;
+
+	mutex_unlock(&idr_lock);
+
+	return res;
 }
 
 /**
@@ -68,12 +127,48 @@ static void tpm_dev_release(struct device *dev)
 {
 	struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev);
 
-	spin_lock(&driver_lock);
-	clear_bit(chip->dev_num, dev_mask);
-	spin_unlock(&driver_lock);
+	mutex_lock(&idr_lock);
+	idr_remove(&dev_nums_idr, chip->dev_num);
+	mutex_unlock(&idr_lock);
+
 	kfree(chip);
 }
 
+
+/**
+ * tpm_class_shutdown() - prepare the TPM device for loss of power.
+ * @dev: device to which the chip is associated.
+ *
+ * Issues a TPM2_Shutdown command prior to loss of power, as required by the
+ * TPM 2.0 spec.
+ * Then, calls bus- and device- specific shutdown code.
+ *
+ * XXX: This codepath relies on the fact that sysfs is not enabled for
+ * TPM2: sysfs uses an implicit lock on chip->ops, so this could race if TPM2
+ * has sysfs support enabled before TPM sysfs's implicit locking is fixed.
+ */
+static int tpm_class_shutdown(struct device *dev)
+{
+	struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev);
+
+	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
+		down_write(&chip->ops_sem);
+		tpm2_shutdown(chip, TPM2_SU_CLEAR);
+		chip->ops = NULL;
+		up_write(&chip->ops_sem);
+	}
+	/* Allow bus- and device-specific code to run. Note: since chip->ops
+	 * is NULL, more-specific shutdown code will not be able to issue TPM
+	 * commands.
+	 */
+	if (dev->bus && dev->bus->shutdown)
+		dev->bus->shutdown(dev);
+	else if (dev->driver && dev->driver->shutdown)
+		dev->driver->shutdown(dev);
+	return 0;
+}
+
+
 /**
  * tpmm_chip_alloc() - allocate a new struct tpm_chip instance
  * @dev: device to which the chip is associated
@@ -88,37 +183,35 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 				 const struct tpm_class_ops *ops)
 {
 	struct tpm_chip *chip;
+	int rc;
 
 	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
 	if (chip == NULL)
 		return ERR_PTR(-ENOMEM);
 
 	mutex_init(&chip->tpm_mutex);
-	INIT_LIST_HEAD(&chip->list);
+	init_rwsem(&chip->ops_sem);
 
 	chip->ops = ops;
 
-	spin_lock(&driver_lock);
-	chip->dev_num = find_first_zero_bit(dev_mask, TPM_NUM_DEVICES);
-	spin_unlock(&driver_lock);
-
-	if (chip->dev_num >= TPM_NUM_DEVICES) {
+	mutex_lock(&idr_lock);
+	rc = idr_alloc(&dev_nums_idr, NULL, 0, TPM_NUM_DEVICES, GFP_KERNEL);
+	mutex_unlock(&idr_lock);
+	if (rc < 0) {
 		dev_err(dev, "No available tpm device numbers\n");
 		kfree(chip);
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(rc);
 	}
-
-	set_bit(chip->dev_num, dev_mask);
+	chip->dev_num = rc;
 
 	scnprintf(chip->devname, sizeof(chip->devname), "tpm%d", chip->dev_num);
 
-	chip->pdev = dev;
-
 	dev_set_drvdata(dev, chip);
 
 	chip->dev.class = tpm_class;
+	chip->dev.class->shutdown = tpm_class_shutdown;
 	chip->dev.release = tpm_dev_release;
-	chip->dev.parent = chip->pdev;
+	chip->dev.parent = dev;
 #ifdef CONFIG_ACPI
 	chip->dev.groups = chip->groups;
 #endif
@@ -133,14 +226,16 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 	device_initialize(&chip->dev);
 
 	cdev_init(&chip->cdev, &tpm_fops);
-	chip->cdev.owner = chip->pdev->driver->owner;
+	chip->cdev.owner = dev->driver->owner;
 	chip->cdev.kobj.parent = &chip->dev.kobj;
 
+	devm_add_action(dev, (void (*)(void *)) put_device, &chip->dev);
+
 	return chip;
 }
 EXPORT_SYMBOL_GPL(tpmm_chip_alloc);
 
-static int tpm_dev_add_device(struct tpm_chip *chip)
+static int tpm_add_char_device(struct tpm_chip *chip)
 {
 	int rc;
 
@@ -151,7 +246,6 @@ static int tpm_dev_add_device(struct tpm_chip *chip)
 			chip->devname, MAJOR(chip->dev.devt),
 			MINOR(chip->dev.devt), rc);
 
-		device_unregister(&chip->dev);
 		return rc;
 	}
 
@@ -162,16 +256,32 @@ static int tpm_dev_add_device(struct tpm_chip *chip)
 			chip->devname, MAJOR(chip->dev.devt),
 			MINOR(chip->dev.devt), rc);
 
+		cdev_del(&chip->cdev);
 		return rc;
 	}
 
+	/* Make the chip available. */
+	mutex_lock(&idr_lock);
+	idr_replace(&dev_nums_idr, chip, chip->dev_num);
+	mutex_unlock(&idr_lock);
+
 	return rc;
 }
 
-static void tpm_dev_del_device(struct tpm_chip *chip)
+static void tpm_del_char_device(struct tpm_chip *chip)
 {
 	cdev_del(&chip->cdev);
-	device_unregister(&chip->dev);
+	device_del(&chip->dev);
+
+	/* Make the chip unavailable. */
+	mutex_lock(&idr_lock);
+	idr_replace(&dev_nums_idr, NULL, chip->dev_num);
+	mutex_unlock(&idr_lock);
+
+	/* Make the driver uncallable. */
+	down_write(&chip->ops_sem);
+	chip->ops = NULL;
+	up_write(&chip->ops_sem);
 }
 
 static int tpm1_chip_register(struct tpm_chip *chip)
@@ -222,21 +332,15 @@ int tpm_chip_register(struct tpm_chip *chip)
 
 	tpm_add_ppi(chip);
 
-	rc = tpm_dev_add_device(chip);
+	rc = tpm_add_char_device(chip);
 	if (rc)
 		goto out_err;
 
-	/* Make the chip available. */
-	spin_lock(&driver_lock);
-	list_add_tail_rcu(&chip->list, &tpm_chip_list);
-	spin_unlock(&driver_lock);
-
 	chip->flags |= TPM_CHIP_FLAG_REGISTERED;
 
 	if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) {
-		rc = __compat_only_sysfs_link_entry_to_kobj(&chip->pdev->kobj,
-							    &chip->dev.kobj,
-							    "ppi");
+		rc = __compat_only_sysfs_link_entry_to_kobj(
+		    &chip->dev.parent->kobj, &chip->dev.kobj, "ppi");
 		if (rc && rc != -ENOENT) {
 			tpm_chip_unregister(chip);
 			return rc;
@@ -257,6 +361,9 @@ EXPORT_SYMBOL_GPL(tpm_chip_register);
  * Takes the chip first away from the list of available TPM chips and then
  * cleans up all the resources reserved by tpm_chip_register().
  *
+ * Once this function returns the driver call backs in 'op's will not be
+ * running and will no longer start.
+ *
  * NOTE: This function should be only called before deinitializing chip
  * resources.
  */
@@ -265,15 +372,10 @@ void tpm_chip_unregister(struct tpm_chip *chip)
 	if (!(chip->flags & TPM_CHIP_FLAG_REGISTERED))
 		return;
 
-	spin_lock(&driver_lock);
-	list_del_rcu(&chip->list);
-	spin_unlock(&driver_lock);
-	synchronize_rcu();
-
 	if (!(chip->flags & TPM_CHIP_FLAG_TPM2))
-		sysfs_remove_link(&chip->pdev->kobj, "ppi");
+		sysfs_remove_link(&chip->dev.parent->kobj, "ppi");
 
 	tpm1_chip_unregister(chip);
-	tpm_dev_del_device(chip);
+	tpm_del_char_device(chip);
 }
 EXPORT_SYMBOL_GPL(tpm_chip_unregister);
diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c
index de0337ebd658..912ad30be585 100644
--- a/drivers/char/tpm/tpm-dev.c
+++ b/drivers/char/tpm/tpm-dev.c
@@ -61,7 +61,7 @@ static int tpm_open(struct inode *inode, struct file *file)
 	 * by the check of is_open variable, which is protected
 	 * by driver_lock. */
 	if (test_and_set_bit(0, &chip->is_open)) {
-		dev_dbg(chip->pdev, "Another process owns this TPM\n");
+		dev_dbg(&chip->dev, "Another process owns this TPM\n");
 		return -EBUSY;
 	}
 
@@ -79,7 +79,6 @@ static int tpm_open(struct inode *inode, struct file *file)
 	INIT_WORK(&priv->work, timeout_work);
 
 	file->private_data = priv;
-	get_device(chip->pdev);
 	return 0;
 }
 
@@ -137,9 +136,18 @@ static ssize_t tpm_write(struct file *file, const char __user *buf,
 		return -EFAULT;
 	}
 
-	/* atomic tpm command send and result receive */
+	/* atomic tpm command send and result receive. We only hold the ops
+	 * lock during this period so that the tpm can be unregistered even if
+	 * the char dev is held open.
+	 */
+	if (tpm_try_get_ops(priv->chip)) {
+		mutex_unlock(&priv->buffer_mutex);
+		return -EPIPE;
+	}
 	out_size = tpm_transmit(priv->chip, priv->data_buffer,
-				sizeof(priv->data_buffer));
+				sizeof(priv->data_buffer), 0);
+
+	tpm_put_ops(priv->chip);
 	if (out_size < 0) {
 		mutex_unlock(&priv->buffer_mutex);
 		return out_size;
@@ -166,7 +174,6 @@ static int tpm_release(struct inode *inode, struct file *file)
 	file->private_data = NULL;
 	atomic_set(&priv->data_pending, 0);
 	clear_bit(0, &priv->chip->is_open);
-	put_device(priv->chip->pdev);
 	kfree(priv);
 	return 0;
 }
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index c50637db3a8a..aaa5fa95dede 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -328,8 +328,8 @@ EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
 /*
  * Internal kernel interface to transmit TPM commands
  */
-ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
-		     size_t bufsiz)
+ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz,
+		     unsigned int flags)
 {
 	ssize_t rc;
 	u32 count, ordinal;
@@ -343,16 +343,17 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
 	if (count == 0)
 		return -ENODATA;
 	if (count > bufsiz) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"invalid count value %x %zx\n", count, bufsiz);
 		return -E2BIG;
 	}
 
-	mutex_lock(&chip->tpm_mutex);
+	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+		mutex_lock(&chip->tpm_mutex);
 
 	rc = chip->ops->send(chip, (u8 *) buf, count);
 	if (rc < 0) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"tpm_transmit: tpm_send: error %zd\n", rc);
 		goto out;
 	}
@@ -371,7 +372,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
 			goto out_recv;
 
 		if (chip->ops->req_canceled(chip, status)) {
-			dev_err(chip->pdev, "Operation Canceled\n");
+			dev_err(&chip->dev, "Operation Canceled\n");
 			rc = -ECANCELED;
 			goto out;
 		}
@@ -381,30 +382,31 @@ ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
 	} while (time_before(jiffies, stop));
 
 	chip->ops->cancel(chip);
-	dev_err(chip->pdev, "Operation Timed out\n");
+	dev_err(&chip->dev, "Operation Timed out\n");
 	rc = -ETIME;
 	goto out;
 
 out_recv:
 	rc = chip->ops->recv(chip, (u8 *) buf, bufsiz);
 	if (rc < 0)
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"tpm_transmit: tpm_recv: error %zd\n", rc);
 out:
-	mutex_unlock(&chip->tpm_mutex);
+	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+		mutex_unlock(&chip->tpm_mutex);
 	return rc;
 }
 
 #define TPM_DIGEST_SIZE 20
 #define TPM_RET_CODE_IDX 6
 
-ssize_t tpm_transmit_cmd(struct tpm_chip *chip, void *cmd,
-			 int len, const char *desc)
+ssize_t tpm_transmit_cmd(struct tpm_chip *chip, const void *cmd,
+			 int len, unsigned int flags, const char *desc)
 {
-	struct tpm_output_header *header;
+	const struct tpm_output_header *header;
 	int err;
 
-	len = tpm_transmit(chip, (u8 *) cmd, len);
+	len = tpm_transmit(chip, (const u8 *)cmd, len, flags);
 	if (len <  0)
 		return len;
 	else if (len < TPM_HEADER_SIZE)
@@ -414,7 +416,7 @@ ssize_t tpm_transmit_cmd(struct tpm_chip *chip, void *cmd,
 
 	err = be32_to_cpu(header->return_code);
 	if (err != 0 && desc)
-		dev_err(chip->pdev, "A TPM error (%d) occurred %s\n", err,
+		dev_err(&chip->dev, "A TPM error (%d) occurred %s\n", err,
 			desc);
 
 	return err;
@@ -452,7 +454,8 @@ ssize_t tpm_getcap(struct device *dev, __be32 subcap_id, cap_t *cap,
 		tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
 		tpm_cmd.params.getcap_in.subcap = subcap_id;
 	}
-	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, desc);
+	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, 0,
+			      desc);
 	if (!rc)
 		*cap = tpm_cmd.params.getcap_out.cap;
 	return rc;
@@ -468,7 +471,7 @@ void tpm_gen_interrupt(struct tpm_chip *chip)
 	tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
 	tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
 
-	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
+	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, 0,
 			      "attempting to determine the timeouts");
 }
 EXPORT_SYMBOL_GPL(tpm_gen_interrupt);
@@ -489,7 +492,7 @@ static int tpm_startup(struct tpm_chip *chip, __be16 startup_type)
 	start_cmd.header.in = tpm_startup_header;
 
 	start_cmd.params.startup_in.startup_type = startup_type;
-	return tpm_transmit_cmd(chip, &start_cmd, TPM_INTERNAL_RESULT_SIZE,
+	return tpm_transmit_cmd(chip, &start_cmd, TPM_INTERNAL_RESULT_SIZE, 0,
 				"attempting to start the TPM");
 }
 
@@ -505,12 +508,13 @@ int tpm_get_timeouts(struct tpm_chip *chip)
 	tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
 	tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
 	tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
-	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, NULL);
+	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, 0,
+			      NULL);
 
 	if (rc == TPM_ERR_INVALID_POSTINIT) {
 		/* The TPM is not started, we are the first to talk to it.
 		   Execute a startup command. */
-		dev_info(chip->pdev, "Issuing TPM_STARTUP");
+		dev_info(&chip->dev, "Issuing TPM_STARTUP");
 		if (tpm_startup(chip, TPM_ST_CLEAR))
 			return rc;
 
@@ -519,10 +523,10 @@ int tpm_get_timeouts(struct tpm_chip *chip)
 		tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
 		tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
 		rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
-				  NULL);
+				      0, NULL);
 	}
 	if (rc) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"A TPM error (%zd) occurred attempting to determine the timeouts\n",
 			rc);
 		goto duration;
@@ -561,7 +565,7 @@ int tpm_get_timeouts(struct tpm_chip *chip)
 
 	/* Report adjusted timeouts */
 	if (chip->vendor.timeout_adjusted) {
-		dev_info(chip->pdev,
+		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],
@@ -580,7 +584,7 @@ duration:
 	tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
 	tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_DURATION;
 
-	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
+	rc = tpm_transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, 0,
 			      "attempting to determine the durations");
 	if (rc)
 		return rc;
@@ -608,7 +612,7 @@ duration:
 		chip->vendor.duration[TPM_MEDIUM] *= 1000;
 		chip->vendor.duration[TPM_LONG] *= 1000;
 		chip->vendor.duration_adjusted = true;
-		dev_info(chip->pdev, "Adjusting TPM timeout parameters.");
+		dev_info(&chip->dev, "Adjusting TPM timeout parameters.");
 	}
 	return 0;
 }
@@ -636,7 +640,7 @@ static int tpm_continue_selftest(struct tpm_chip *chip)
 	struct tpm_cmd_t cmd;
 
 	cmd.header.in = continue_selftest_header;
-	rc = tpm_transmit_cmd(chip, &cmd, CONTINUE_SELFTEST_RESULT_SIZE,
+	rc = tpm_transmit_cmd(chip, &cmd, CONTINUE_SELFTEST_RESULT_SIZE, 0,
 			      "continue selftest");
 	return rc;
 }
@@ -656,7 +660,7 @@ int tpm_pcr_read_dev(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 
 	cmd.header.in = pcrread_header;
 	cmd.params.pcrread_in.pcr_idx = cpu_to_be32(pcr_idx);
-	rc = tpm_transmit_cmd(chip, &cmd, READ_PCR_RESULT_SIZE,
+	rc = tpm_transmit_cmd(chip, &cmd, READ_PCR_RESULT_SIZE, 0,
 			      "attempting to read a pcr value");
 
 	if (rc == 0)
@@ -683,7 +687,7 @@ int tpm_is_tpm2(u32 chip_num)
 
 	rc = (chip->flags & TPM_CHIP_FLAG_TPM2) != 0;
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 
 	return rc;
 }
@@ -712,7 +716,7 @@ int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf)
 		rc = tpm2_pcr_read(chip, pcr_idx, res_buf);
 	else
 		rc = tpm_pcr_read_dev(chip, pcr_idx, res_buf);
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_pcr_read);
@@ -747,17 +751,17 @@ int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash)
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
 		rc = tpm2_pcr_extend(chip, pcr_idx, hash);
-		tpm_chip_put(chip);
+		tpm_put_ops(chip);
 		return rc;
 	}
 
 	cmd.header.in = pcrextend_header;
 	cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(pcr_idx);
 	memcpy(cmd.params.pcrextend_in.hash, hash, TPM_DIGEST_SIZE);
-	rc = tpm_transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
+	rc = tpm_transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE, 0,
 			      "attempting extend a PCR value");
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_pcr_extend);
@@ -793,12 +797,14 @@ int tpm_do_selftest(struct tpm_chip *chip)
 		/* Attempt to read a PCR value */
 		cmd.header.in = pcrread_header;
 		cmd.params.pcrread_in.pcr_idx = cpu_to_be32(0);
-		rc = tpm_transmit(chip, (u8 *) &cmd, READ_PCR_RESULT_SIZE);
+		rc = tpm_transmit(chip, (u8 *) &cmd, READ_PCR_RESULT_SIZE, 0);
 		/* Some buggy TPMs will not respond to tpm_tis_ready() for
 		 * around 300ms while the self test is ongoing, keep trying
 		 * until the self test duration expires. */
 		if (rc == -ETIME) {
-			dev_info(chip->pdev, HW_ERR "TPM command timed out during continue self test");
+			dev_info(
+			    &chip->dev, HW_ERR
+			    "TPM command timed out during continue self test");
 			msleep(delay_msec);
 			continue;
 		}
@@ -808,7 +814,7 @@ int tpm_do_selftest(struct tpm_chip *chip)
 
 		rc = be32_to_cpu(cmd.header.out.return_code);
 		if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
-			dev_info(chip->pdev,
+			dev_info(&chip->dev,
 				 "TPM is disabled/deactivated (0x%X)\n", rc);
 			/* TPM is disabled and/or deactivated; driver can
 			 * proceed and TPM does handle commands for
@@ -834,9 +840,9 @@ int tpm_send(u32 chip_num, void *cmd, size_t buflen)
 	if (chip == NULL)
 		return -ENODEV;
 
-	rc = tpm_transmit_cmd(chip, cmd, buflen, "attempting tpm_cmd");
+	rc = tpm_transmit_cmd(chip, cmd, buflen, 0, "attempting tpm_cmd");
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_send);
@@ -936,14 +942,15 @@ int tpm_pm_suspend(struct device *dev)
 		cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(tpm_suspend_pcr);
 		memcpy(cmd.params.pcrextend_in.hash, dummy_hash,
 		       TPM_DIGEST_SIZE);
-		rc = tpm_transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
+		rc = tpm_transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE, 0,
 				      "extending dummy pcr before suspend");
 	}
 
 	/* now do the actual savestate */
 	for (try = 0; try < TPM_RETRY; try++) {
 		cmd.header.in = savestate_header;
-		rc = tpm_transmit_cmd(chip, &cmd, SAVESTATE_RESULT_SIZE, NULL);
+		rc = tpm_transmit_cmd(chip, &cmd, SAVESTATE_RESULT_SIZE, 0,
+				      NULL);
 
 		/*
 		 * If the TPM indicates that it is too busy to respond to
@@ -961,10 +968,10 @@ int tpm_pm_suspend(struct device *dev)
 	}
 
 	if (rc)
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"Error (%d) sending savestate before suspend\n", rc);
 	else if (try > 0)
-		dev_warn(chip->pdev, "TPM savestate took %dms\n",
+		dev_warn(&chip->dev, "TPM savestate took %dms\n",
 			 try * TPM_TIMEOUT_RETRY);
 
 	return rc;
@@ -1018,7 +1025,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
 		err = tpm2_get_random(chip, out, max);
-		tpm_chip_put(chip);
+		tpm_put_ops(chip);
 		return err;
 	}
 
@@ -1027,8 +1034,8 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 		tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
 
 		err = tpm_transmit_cmd(chip, &tpm_cmd,
-				   TPM_GETRANDOM_RESULT_SIZE + num_bytes,
-				   "attempting get random");
+				       TPM_GETRANDOM_RESULT_SIZE + num_bytes,
+				       0, "attempting get random");
 		if (err)
 			break;
 
@@ -1040,7 +1047,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 		num_bytes -= recd;
 	} while (retries-- && total < max);
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 	return total ? total : -EIO;
 }
 EXPORT_SYMBOL_GPL(tpm_get_random);
@@ -1066,7 +1073,7 @@ int tpm_seal_trusted(u32 chip_num, struct trusted_key_payload *payload,
 
 	rc = tpm2_seal_trusted(chip, payload, options);
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_seal_trusted);
@@ -1092,7 +1099,8 @@ int tpm_unseal_trusted(u32 chip_num, struct trusted_key_payload *payload,
 
 	rc = tpm2_unseal_trusted(chip, payload, options);
 
-	tpm_chip_put(chip);
+	tpm_put_ops(chip);
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm_unseal_trusted);
@@ -1119,6 +1127,7 @@ static int __init tpm_init(void)
 
 static void __exit tpm_exit(void)
 {
+	idr_destroy(&dev_nums_idr);
 	class_destroy(tpm_class);
 	unregister_chrdev_region(tpm_devt, TPM_NUM_DEVICES);
 }
diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c
index ee66fd4673f3..06ac6e9657d2 100644
--- a/drivers/char/tpm/tpm-sysfs.c
+++ b/drivers/char/tpm/tpm-sysfs.c
@@ -38,8 +38,10 @@ static ssize_t pubek_show(struct device *dev, struct device_attribute *attr,
 
 	struct tpm_chip *chip = dev_get_drvdata(dev);
 
+	memset(&tpm_cmd, 0, sizeof(tpm_cmd));
+
 	tpm_cmd.header.in = tpm_readpubek_header;
-	err = tpm_transmit_cmd(chip, &tpm_cmd, READ_PUBEK_RESULT_SIZE,
+	err = tpm_transmit_cmd(chip, &tpm_cmd, READ_PUBEK_RESULT_SIZE, 0,
 			       "attempting to read the PUBEK");
 	if (err)
 		goto out;
@@ -284,16 +286,28 @@ static const struct attribute_group tpm_dev_group = {
 int tpm_sysfs_add_device(struct tpm_chip *chip)
 {
 	int err;
-	err = sysfs_create_group(&chip->pdev->kobj,
+
+	/* XXX: If you wish to remove this restriction, you must first update
+	 * tpm_sysfs to explicitly lock chip->ops.
+	 */
+	if (chip->flags & TPM_CHIP_FLAG_TPM2)
+		return 0;
+
+	err = sysfs_create_group(&chip->dev.parent->kobj,
 				 &tpm_dev_group);
 
 	if (err)
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"failed to create sysfs attributes, %d\n", err);
 	return err;
 }
 
 void tpm_sysfs_del_device(struct tpm_chip *chip)
 {
-	sysfs_remove_group(&chip->pdev->kobj, &tpm_dev_group);
+	/* The sysfs routines rely on an implicit tpm_try_get_ops, this
+	 * function is called before ops is null'd and the sysfs core
+	 * synchronizes this removal so that no callbacks are running or can
+	 * run again
+	 */
+	sysfs_remove_group(&chip->dev.parent->kobj, &tpm_dev_group);
 }
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index a4257a32964f..772d99b3a8e4 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -34,7 +34,7 @@
 enum tpm_const {
 	TPM_MINOR = 224,	/* officially assigned */
 	TPM_BUFSIZE = 4096,
-	TPM_NUM_DEVICES = 256,
+	TPM_NUM_DEVICES = 65536,
 	TPM_RETRY = 50,		/* 5 seconds */
 };
 
@@ -171,11 +171,16 @@ enum tpm_chip_flags {
 };
 
 struct tpm_chip {
-	struct device *pdev;	/* Device stuff */
 	struct device dev;
 	struct cdev cdev;
 
+	/* A driver callback under ops cannot be run unless ops_sem is held
+	 * (sometimes implicitly, eg for the sysfs code). ops becomes null
+	 * when the driver is unregistered, see tpm_try_get_ops.
+	 */
+	struct rw_semaphore ops_sem;
 	const struct tpm_class_ops *ops;
+
 	unsigned int flags;
 
 	int dev_num;		/* /dev/tpm# */
@@ -195,17 +200,10 @@ struct tpm_chip {
 	acpi_handle acpi_dev_handle;
 	char ppi_version[TPM_PPI_VERSION_LEN + 1];
 #endif /* CONFIG_ACPI */
-
-	struct list_head list;
 };
 
 #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)
 
-static inline void tpm_chip_put(struct tpm_chip *chip)
-{
-	module_put(chip->pdev->driver->owner);
-}
-
 static inline int tpm_read_index(int base, int index)
 {
 	outb(index, base);
@@ -497,12 +495,17 @@ static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value)
 extern struct class *tpm_class;
 extern dev_t tpm_devt;
 extern const struct file_operations tpm_fops;
+extern struct idr dev_nums_idr;
+
+enum tpm_transmit_flags {
+	TPM_TRANSMIT_UNLOCKED	= BIT(0),
+};
 
+ssize_t tpm_transmit(struct tpm_chip *chip, const u8 *buf, size_t bufsiz,
+		     unsigned int flags);
+ssize_t tpm_transmit_cmd(struct tpm_chip *chip, const void *cmd, int len,
+			 unsigned int flags, const char *desc);
 ssize_t	tpm_getcap(struct device *, __be32, cap_t *, const char *);
-ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
-		     size_t bufsiz);
-ssize_t tpm_transmit_cmd(struct tpm_chip *chip, void *cmd, int len,
-			 const char *desc);
 extern int tpm_get_timeouts(struct tpm_chip *);
 extern void tpm_gen_interrupt(struct tpm_chip *);
 extern int tpm_do_selftest(struct tpm_chip *);
@@ -513,6 +516,9 @@ extern int wait_for_tpm_stat(struct tpm_chip *, u8, unsigned long,
 			     wait_queue_head_t *, bool);
 
 struct tpm_chip *tpm_chip_find_get(int chip_num);
+__must_check int tpm_try_get_ops(struct tpm_chip *chip);
+void tpm_put_ops(struct tpm_chip *chip);
+
 extern struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 				       const struct tpm_class_ops *ops);
 extern int tpm_chip_register(struct tpm_chip *chip);
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index c12130485fc1..286bd090a488 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -264,7 +264,7 @@ int tpm2_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 	       sizeof(cmd.params.pcrread_in.pcr_select));
 	cmd.params.pcrread_in.pcr_select[pcr_idx >> 3] = 1 << (pcr_idx & 0x7);
 
-	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd),
+	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0,
 			      "attempting to read a pcr value");
 	if (rc == 0) {
 		buf = cmd.params.pcrread_out.digest;
@@ -312,7 +312,7 @@ int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash)
 	cmd.params.pcrextend_in.hash_alg = cpu_to_be16(TPM2_ALG_SHA1);
 	memcpy(cmd.params.pcrextend_in.digest, hash, TPM_DIGEST_SIZE);
 
-	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd),
+	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0,
 			      "attempting extend a PCR value");
 
 	return rc;
@@ -358,7 +358,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 		cmd.header.in = tpm2_getrandom_header;
 		cmd.params.getrandom_in.size = cpu_to_be16(num_bytes);
 
-		err = tpm_transmit_cmd(chip, &cmd, sizeof(cmd),
+		err = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0,
 				       "attempting get random");
 		if (err)
 			break;
@@ -416,12 +416,12 @@ static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle,
 }
 
 /**
- * tpm2_seal_trusted() - seal a trusted key
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @options: authentication values and other options
+ * tpm2_seal_trusted() - seal the payload of a trusted key
+ * @chip_num: TPM chip to use
  * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
  *
- * Returns < 0 on error and 0 on success.
+ * Return: < 0 on error and 0 on success.
  */
 int tpm2_seal_trusted(struct tpm_chip *chip,
 		      struct trusted_key_payload *payload,
@@ -472,7 +472,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip,
 		goto out;
 	}
 
-	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, "sealing data");
+	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, 0, "sealing data");
 	if (rc)
 		goto out;
 
@@ -494,10 +494,18 @@ out:
 	return rc;
 }
 
-static int tpm2_load(struct tpm_chip *chip,
-		     struct trusted_key_payload *payload,
-		     struct trusted_key_options *options,
-		     u32 *blob_handle)
+/**
+ * tpm2_load_cmd() - execute a TPM2_Load command
+ * @chip_num: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: same as with tpm_transmit_cmd
+ */
+static int tpm2_load_cmd(struct tpm_chip *chip,
+			 struct trusted_key_payload *payload,
+			 struct trusted_key_options *options,
+			 u32 *blob_handle, unsigned int flags)
 {
 	struct tpm_buf buf;
 	unsigned int private_len;
@@ -532,7 +540,7 @@ static int tpm2_load(struct tpm_chip *chip,
 		goto out;
 	}
 
-	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, "loading blob");
+	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, flags, "loading blob");
 	if (!rc)
 		*blob_handle = be32_to_cpup(
 			(__be32 *) &buf.data[TPM_HEADER_SIZE]);
@@ -546,32 +554,50 @@ out:
 	return rc;
 }
 
-static void tpm2_flush_context(struct tpm_chip *chip, u32 handle)
+/**
+ * tpm2_flush_context_cmd() - execute a TPM2_FlushContext command
+ * @chip_num: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: same as with tpm_transmit_cmd
+ */
+static void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle,
+				   unsigned int flags)
 {
 	struct tpm_buf buf;
 	int rc;
 
 	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_FLUSH_CONTEXT);
 	if (rc) {
-		dev_warn(chip->pdev, "0x%08x was not flushed, out of memory\n",
+		dev_warn(&chip->dev, "0x%08x was not flushed, out of memory\n",
 			 handle);
 		return;
 	}
 
 	tpm_buf_append_u32(&buf, handle);
 
-	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, "flushing context");
+	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, flags,
+			      "flushing context");
 	if (rc)
-		dev_warn(chip->pdev, "0x%08x was not flushed, rc=%d\n", handle,
+		dev_warn(&chip->dev, "0x%08x was not flushed, rc=%d\n", handle,
 			 rc);
 
 	tpm_buf_destroy(&buf);
 }
 
-static int tpm2_unseal(struct tpm_chip *chip,
-		       struct trusted_key_payload *payload,
-		       struct trusted_key_options *options,
-		       u32 blob_handle)
+/**
+ * tpm2_unseal_cmd() - execute a TPM2_Unload command
+ * @chip_num: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: same as with tpm_transmit_cmd
+ */
+static int tpm2_unseal_cmd(struct tpm_chip *chip,
+			   struct trusted_key_payload *payload,
+			   struct trusted_key_options *options,
+			   u32 blob_handle, unsigned int flags)
 {
 	struct tpm_buf buf;
 	u16 data_len;
@@ -589,7 +615,7 @@ static int tpm2_unseal(struct tpm_chip *chip,
 			     options->blobauth /* hmac */,
 			     TPM_DIGEST_SIZE);
 
-	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, "unsealing");
+	rc = tpm_transmit_cmd(chip, buf.data, PAGE_SIZE, flags, "unsealing");
 	if (rc > 0)
 		rc = -EPERM;
 
@@ -608,12 +634,12 @@ static int tpm2_unseal(struct tpm_chip *chip,
 }
 
 /**
- * tpm_unseal_trusted() - unseal a trusted key
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @options: authentication values and other options
+ * tpm_unseal_trusted() - unseal the payload of a trusted key
+ * @chip_num: TPM chip to use
  * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
  *
- * Returns < 0 on error and 0 on success.
+ * Return: < 0 on error and 0 on success.
  */
 int tpm2_unseal_trusted(struct tpm_chip *chip,
 			struct trusted_key_payload *payload,
@@ -622,14 +648,17 @@ int tpm2_unseal_trusted(struct tpm_chip *chip,
 	u32 blob_handle;
 	int rc;
 
-	rc = tpm2_load(chip, payload, options, &blob_handle);
+	mutex_lock(&chip->tpm_mutex);
+	rc = tpm2_load_cmd(chip, payload, options, &blob_handle,
+			   TPM_TRANSMIT_UNLOCKED);
 	if (rc)
-		return rc;
-
-	rc = tpm2_unseal(chip, payload, options, blob_handle);
-
-	tpm2_flush_context(chip, blob_handle);
+		goto out;
 
+	rc = tpm2_unseal_cmd(chip, payload, options, blob_handle,
+			     TPM_TRANSMIT_UNLOCKED);
+	tpm2_flush_context_cmd(chip, blob_handle, TPM_TRANSMIT_UNLOCKED);
+out:
+	mutex_unlock(&chip->tpm_mutex);
 	return rc;
 }
 
@@ -655,9 +684,9 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,  u32 *value,
 	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(property_id);
 	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
 
-	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), desc);
+	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0, desc);
 	if (!rc)
-		*value = cmd.params.get_tpm_pt_out.value;
+		*value = be32_to_cpu(cmd.params.get_tpm_pt_out.value);
 
 	return rc;
 }
@@ -689,7 +718,7 @@ int tpm2_startup(struct tpm_chip *chip, u16 startup_type)
 	cmd.header.in = tpm2_startup_header;
 
 	cmd.params.startup_in.startup_type = cpu_to_be16(startup_type);
-	return tpm_transmit_cmd(chip, &cmd, sizeof(cmd),
+	return tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0,
 				"attempting to start the TPM");
 }
 EXPORT_SYMBOL_GPL(tpm2_startup);
@@ -718,13 +747,13 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type)
 	cmd.header.in = tpm2_shutdown_header;
 	cmd.params.startup_in.startup_type = cpu_to_be16(shutdown_type);
 
-	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), "stopping the TPM");
+	rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0, "stopping the TPM");
 
 	/* In places where shutdown command is sent there's no much we can do
 	 * except print the error code on a system failure.
 	 */
 	if (rc < 0)
-		dev_warn(chip->pdev, "transmit returned %d while stopping the TPM",
+		dev_warn(&chip->dev, "transmit returned %d while stopping the TPM",
 			 rc);
 }
 EXPORT_SYMBOL_GPL(tpm2_shutdown);
@@ -784,14 +813,14 @@ static int tpm2_start_selftest(struct tpm_chip *chip, bool full)
 	cmd.header.in = tpm2_selftest_header;
 	cmd.params.selftest_in.full_test = full;
 
-	rc = tpm_transmit_cmd(chip, &cmd, TPM2_SELF_TEST_IN_SIZE,
+	rc = tpm_transmit_cmd(chip, &cmd, TPM2_SELF_TEST_IN_SIZE, 0,
 			      "continue selftest");
 
 	/* At least some prototype chips seem to give RC_TESTING error
 	 * immediately. This is a workaround for that.
 	 */
 	if (rc == TPM2_RC_TESTING) {
-		dev_warn(chip->pdev, "Got RC_TESTING, ignoring\n");
+		dev_warn(&chip->dev, "Got RC_TESTING, ignoring\n");
 		rc = 0;
 	}
 
@@ -836,7 +865,7 @@ int tpm2_do_selftest(struct tpm_chip *chip)
 		cmd.params.pcrread_in.pcr_select[1] = 0x00;
 		cmd.params.pcrread_in.pcr_select[2] = 0x00;
 
-		rc = tpm_transmit_cmd(chip, (u8 *) &cmd, sizeof(cmd), NULL);
+		rc = tpm_transmit_cmd(chip, &cmd, sizeof(cmd), 0, NULL);
 		if (rc < 0)
 			break;
 
@@ -885,7 +914,7 @@ int tpm2_probe(struct tpm_chip *chip)
 	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(0x100);
 	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
 
-	rc = tpm_transmit(chip, (const char *) &cmd, sizeof(cmd));
+	rc = tpm_transmit(chip, (const u8 *)&cmd, sizeof(cmd), 0);
 	if (rc <  0)
 		return rc;
 	else if (rc < TPM_HEADER_SIZE)
diff --git a/drivers/char/tpm/tpm_atmel.c b/drivers/char/tpm/tpm_atmel.c
index dfadad0916a1..a48a878f791d 100644
--- a/drivers/char/tpm/tpm_atmel.c
+++ b/drivers/char/tpm/tpm_atmel.c
@@ -49,7 +49,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	for (i = 0; i < 6; i++) {
 		status = ioread8(chip->vendor.iobase + 1);
 		if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
-			dev_err(chip->pdev, "error reading header\n");
+			dev_err(&chip->dev, "error reading header\n");
 			return -EIO;
 		}
 		*buf++ = ioread8(chip->vendor.iobase);
@@ -60,12 +60,12 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	size = be32_to_cpu(*native_size);
 
 	if (count < size) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"Recv size(%d) less than available space\n", size);
 		for (; i < size; i++) {	/* clear the waiting data anyway */
 			status = ioread8(chip->vendor.iobase + 1);
 			if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
-				dev_err(chip->pdev, "error reading data\n");
+				dev_err(&chip->dev, "error reading data\n");
 				return -EIO;
 			}
 		}
@@ -76,7 +76,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	for (; i < size; i++) {
 		status = ioread8(chip->vendor.iobase + 1);
 		if ((status & ATML_STATUS_DATA_AVAIL) == 0) {
-			dev_err(chip->pdev, "error reading data\n");
+			dev_err(&chip->dev, "error reading data\n");
 			return -EIO;
 		}
 		*buf++ = ioread8(chip->vendor.iobase);
@@ -86,7 +86,7 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	status = ioread8(chip->vendor.iobase + 1);
 
 	if (status & ATML_STATUS_DATA_AVAIL) {
-		dev_err(chip->pdev, "data available is stuck\n");
+		dev_err(&chip->dev, "data available is stuck\n");
 		return -EIO;
 	}
 
@@ -97,9 +97,9 @@ static int tpm_atml_send(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	int i;
 
-	dev_dbg(chip->pdev, "tpm_atml_send:\n");
+	dev_dbg(&chip->dev, "tpm_atml_send:\n");
 	for (i = 0; i < count; i++) {
-		dev_dbg(chip->pdev, "%d 0x%x(%d)\n",  i, buf[i], buf[i]);
+		dev_dbg(&chip->dev, "%d 0x%x(%d)\n",  i, buf[i], buf[i]);
  		iowrite8(buf[i], chip->vendor.iobase);
 	}
 
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 4bb9727c1047..35308dfff754 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -118,8 +118,7 @@ static int crb_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 
 	memcpy_fromio(buf, priv->rsp, 6);
 	expected = be32_to_cpup((__be32 *) &buf[2]);
-
-	if (expected > count)
+	if (expected > count || expected < 6)
 		return -EIO;
 
 	memcpy_fromio(&buf[6], &priv->rsp[6], expected - 6);
@@ -149,6 +148,11 @@ static int crb_send(struct tpm_chip *chip, u8 *buf, size_t len)
 	struct crb_priv *priv = chip->vendor.priv;
 	int rc = 0;
 
+	/* Zero the cancel register so that the next command will not get
+	 * canceled.
+	 */
+	iowrite32(0, &priv->cca->cancel);
+
 	if (len > le32_to_cpu(ioread32(&priv->cca->cmd_size))) {
 		dev_err(&chip->dev,
 			"invalid command count value %x %zx\n",
@@ -182,8 +186,6 @@ static void crb_cancel(struct tpm_chip *chip)
 
 	if ((priv->flags & CRB_FL_ACPI_START) && crb_do_acpi_start(chip))
 		dev_err(&chip->dev, "ACPI Start failed\n");
-
-	iowrite32(0, &priv->cca->cancel);
 }
 
 static bool crb_req_canceled(struct tpm_chip *chip, u8 status)
@@ -310,11 +312,11 @@ static int crb_acpi_remove(struct acpi_device *device)
 	struct device *dev = &device->dev;
 	struct tpm_chip *chip = dev_get_drvdata(dev);
 
-	tpm_chip_unregister(chip);
-
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
 		tpm2_shutdown(chip, TPM2_SU_CLEAR);
 
+	tpm_chip_unregister(chip);
+
 	return 0;
 }
 
diff --git a/drivers/char/tpm/tpm_eventlog.c b/drivers/char/tpm/tpm_eventlog.c
index bd72fb04225e..4e6940acf639 100644
--- a/drivers/char/tpm/tpm_eventlog.c
+++ b/drivers/char/tpm/tpm_eventlog.c
@@ -232,7 +232,7 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v)
 {
 	struct tcpa_event *event = v;
 	struct tcpa_event temp_event;
-	char *tempPtr;
+	char *temp_ptr;
 	int i;
 
 	memcpy(&temp_event, event, sizeof(struct tcpa_event));
@@ -242,10 +242,16 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v)
 	temp_event.event_type = do_endian_conversion(event->event_type);
 	temp_event.event_size = do_endian_conversion(event->event_size);
 
-	tempPtr = (char *)&temp_event;
+	temp_ptr = (char *) &temp_event;
 
-	for (i = 0; i < sizeof(struct tcpa_event) + temp_event.event_size; i++)
-		seq_putc(m, tempPtr[i]);
+	for (i = 0; i < (sizeof(struct tcpa_event) - 1) ; i++)
+		seq_putc(m, temp_ptr[i]);
+
+	temp_ptr = (char *) v;
+
+	for (i = (sizeof(struct tcpa_event) - 1);
+	     i < (sizeof(struct tcpa_event) + temp_event.event_size); i++)
+		seq_putc(m, temp_ptr[i]);
 
 	return 0;
 
diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c
index 8dfb88b9739c..dd8f0eb3170a 100644
--- a/drivers/char/tpm/tpm_i2c_atmel.c
+++ b/drivers/char/tpm/tpm_i2c_atmel.c
@@ -52,7 +52,7 @@ struct priv_data {
 static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len)
 {
 	struct priv_data *priv = chip->vendor.priv;
-	struct i2c_client *client = to_i2c_client(chip->pdev);
+	struct i2c_client *client = to_i2c_client(chip->dev.parent);
 	s32 status;
 
 	priv->len = 0;
@@ -62,7 +62,7 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len)
 
 	status = i2c_master_send(client, buf, len);
 
-	dev_dbg(chip->pdev,
+	dev_dbg(&chip->dev,
 		"%s(buf=%*ph len=%0zx) -> sts=%d\n", __func__,
 		(int)min_t(size_t, 64, len), buf, len, status);
 	return status;
@@ -71,7 +71,7 @@ static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len)
 static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	struct priv_data *priv = chip->vendor.priv;
-	struct i2c_client *client = to_i2c_client(chip->pdev);
+	struct i2c_client *client = to_i2c_client(chip->dev.parent);
 	struct tpm_output_header *hdr =
 		(struct tpm_output_header *)priv->buffer;
 	u32 expected_len;
@@ -88,7 +88,7 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 		return -ENOMEM;
 
 	if (priv->len >= expected_len) {
-		dev_dbg(chip->pdev,
+		dev_dbg(&chip->dev,
 			"%s early(buf=%*ph count=%0zx) -> ret=%d\n", __func__,
 			(int)min_t(size_t, 64, expected_len), buf, count,
 			expected_len);
@@ -97,7 +97,7 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	}
 
 	rc = i2c_master_recv(client, buf, expected_len);
-	dev_dbg(chip->pdev,
+	dev_dbg(&chip->dev,
 		"%s reread(buf=%*ph count=%0zx) -> ret=%d\n", __func__,
 		(int)min_t(size_t, 64, expected_len), buf, count,
 		expected_len);
@@ -106,13 +106,13 @@ static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 
 static void i2c_atmel_cancel(struct tpm_chip *chip)
 {
-	dev_err(chip->pdev, "TPM operation cancellation was requested, but is not supported");
+	dev_err(&chip->dev, "TPM operation cancellation was requested, but is not supported");
 }
 
 static u8 i2c_atmel_read_status(struct tpm_chip *chip)
 {
 	struct priv_data *priv = chip->vendor.priv;
-	struct i2c_client *client = to_i2c_client(chip->pdev);
+	struct i2c_client *client = to_i2c_client(chip->dev.parent);
 	int rc;
 
 	/* The TPM fails the I2C read until it is ready, so we do the entire
@@ -125,7 +125,7 @@ static u8 i2c_atmel_read_status(struct tpm_chip *chip)
 	/* Once the TPM has completed the command the command remains readable
 	 * until another command is issued. */
 	rc = i2c_master_recv(client, priv->buffer, sizeof(priv->buffer));
-	dev_dbg(chip->pdev,
+	dev_dbg(&chip->dev,
 		"%s: sts=%d", __func__, rc);
 	if (rc <= 0)
 		return 0;
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 63d5d22e9e60..f2aa99e34b4b 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -446,7 +446,7 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	/* read first 10 bytes, including tag, paramsize, and result */
 	size = recv_data(chip, buf, TPM_HEADER_SIZE);
 	if (size < TPM_HEADER_SIZE) {
-		dev_err(chip->pdev, "Unable to read header\n");
+		dev_err(&chip->dev, "Unable to read header\n");
 		goto out;
 	}
 
@@ -459,14 +459,14 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	size += recv_data(chip, &buf[TPM_HEADER_SIZE],
 			  expected - TPM_HEADER_SIZE);
 	if (size < expected) {
-		dev_err(chip->pdev, "Unable to read remainder of result\n");
+		dev_err(&chip->dev, "Unable to read remainder of result\n");
 		size = -ETIME;
 		goto out;
 	}
 
 	wait_for_stat(chip, TPM_STS_VALID, chip->vendor.timeout_c, &status);
 	if (status & TPM_STS_DATA_AVAIL) {	/* retry? */
-		dev_err(chip->pdev, "Error left over data\n");
+		dev_err(&chip->dev, "Error left over data\n");
 		size = -EIO;
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index 847f1597fe9b..a1e1474dda30 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -96,13 +96,13 @@ static s32 i2c_nuvoton_write_buf(struct i2c_client *client, u8 offset, u8 size,
 /* read TPM_STS register */
 static u8 i2c_nuvoton_read_status(struct tpm_chip *chip)
 {
-	struct i2c_client *client = to_i2c_client(chip->pdev);
+	struct i2c_client *client = to_i2c_client(chip->dev.parent);
 	s32 status;
 	u8 data;
 
 	status = i2c_nuvoton_read_buf(client, TPM_STS, 1, &data);
 	if (status <= 0) {
-		dev_err(chip->pdev, "%s() error return %d\n", __func__,
+		dev_err(&chip->dev, "%s() error return %d\n", __func__,
 			status);
 		data = TPM_STS_ERR_VAL;
 	}
@@ -127,13 +127,13 @@ static s32 i2c_nuvoton_write_status(struct i2c_client *client, u8 data)
 /* write commandReady to TPM_STS register */
 static void i2c_nuvoton_ready(struct tpm_chip *chip)
 {
-	struct i2c_client *client = to_i2c_client(chip->pdev);
+	struct i2c_client *client = to_i2c_client(chip->dev.parent);
 	s32 status;
 
 	/* this causes the current command to be aborted */
 	status = i2c_nuvoton_write_status(client, TPM_STS_COMMAND_READY);
 	if (status < 0)
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"%s() fail to write TPM_STS.commandReady\n", __func__);
 }
 
@@ -212,7 +212,7 @@ static int i2c_nuvoton_wait_for_stat(struct tpm_chip *chip, u8 mask, u8 value,
 				return 0;
 		} while (time_before(jiffies, stop));
 	}
-	dev_err(chip->pdev, "%s(%02x, %02x) -> timeout\n", __func__, mask,
+	dev_err(&chip->dev, "%s(%02x, %02x) -> timeout\n", __func__, mask,
 		value);
 	return -ETIMEDOUT;
 }
@@ -240,7 +240,7 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client,
 					       &chip->vendor.read_queue) == 0) {
 		burst_count = i2c_nuvoton_get_burstcount(client, chip);
 		if (burst_count < 0) {
-			dev_err(chip->pdev,
+			dev_err(&chip->dev,
 				"%s() fail to read burstCount=%d\n", __func__,
 				burst_count);
 			return -EIO;
@@ -249,12 +249,12 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client,
 		rc = i2c_nuvoton_read_buf(client, TPM_DATA_FIFO_R,
 					  bytes2read, &buf[size]);
 		if (rc < 0) {
-			dev_err(chip->pdev,
+			dev_err(&chip->dev,
 				"%s() fail on i2c_nuvoton_read_buf()=%d\n",
 				__func__, rc);
 			return -EIO;
 		}
-		dev_dbg(chip->pdev, "%s(%d):", __func__, bytes2read);
+		dev_dbg(&chip->dev, "%s(%d):", __func__, bytes2read);
 		size += bytes2read;
 	}
 
@@ -264,7 +264,7 @@ static int i2c_nuvoton_recv_data(struct i2c_client *client,
 /* Read TPM command results */
 static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 {
-	struct device *dev = chip->pdev;
+	struct device *dev = chip->dev.parent;
 	struct i2c_client *client = to_i2c_client(dev);
 	s32 rc;
 	int expected, status, burst_count, retries, size = 0;
@@ -334,7 +334,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 		break;
 	}
 	i2c_nuvoton_ready(chip);
-	dev_dbg(chip->pdev, "%s() -> %d\n", __func__, size);
+	dev_dbg(&chip->dev, "%s() -> %d\n", __func__, size);
 	return size;
 }
 
@@ -347,7 +347,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
  */
 static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len)
 {
-	struct device *dev = chip->pdev;
+	struct device *dev = chip->dev.parent;
 	struct i2c_client *client = to_i2c_client(dev);
 	u32 ordinal;
 	size_t count = 0;
diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c
index 6c488e635fdd..e3cf9f3545c5 100644
--- a/drivers/char/tpm/tpm_infineon.c
+++ b/drivers/char/tpm/tpm_infineon.c
@@ -195,9 +195,9 @@ static int wait(struct tpm_chip *chip, int wait_for_bit)
 	}
 	if (i == TPM_MAX_TRIES) {	/* timeout occurs */
 		if (wait_for_bit == STAT_XFE)
-			dev_err(chip->pdev, "Timeout in wait(STAT_XFE)\n");
+			dev_err(&chip->dev, "Timeout in wait(STAT_XFE)\n");
 		if (wait_for_bit == STAT_RDA)
-			dev_err(chip->pdev, "Timeout in wait(STAT_RDA)\n");
+			dev_err(&chip->dev, "Timeout in wait(STAT_RDA)\n");
 		return -EIO;
 	}
 	return 0;
@@ -220,7 +220,7 @@ static void wait_and_send(struct tpm_chip *chip, u8 sendbyte)
 static void tpm_wtx(struct tpm_chip *chip)
 {
 	number_of_wtx++;
-	dev_info(chip->pdev, "Granting WTX (%02d / %02d)\n",
+	dev_info(&chip->dev, "Granting WTX (%02d / %02d)\n",
 		 number_of_wtx, TPM_MAX_WTX_PACKAGES);
 	wait_and_send(chip, TPM_VL_VER);
 	wait_and_send(chip, TPM_CTRL_WTX);
@@ -231,7 +231,7 @@ static void tpm_wtx(struct tpm_chip *chip)
 
 static void tpm_wtx_abort(struct tpm_chip *chip)
 {
-	dev_info(chip->pdev, "Aborting WTX\n");
+	dev_info(&chip->dev, "Aborting WTX\n");
 	wait_and_send(chip, TPM_VL_VER);
 	wait_and_send(chip, TPM_CTRL_WTX_ABORT);
 	wait_and_send(chip, 0x00);
@@ -257,7 +257,7 @@ recv_begin:
 	}
 
 	if (buf[0] != TPM_VL_VER) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"Wrong transport protocol implementation!\n");
 		return -EIO;
 	}
@@ -272,7 +272,7 @@ recv_begin:
 		}
 
 		if ((size == 0x6D00) && (buf[1] == 0x80)) {
-			dev_err(chip->pdev, "Error handling on vendor layer!\n");
+			dev_err(&chip->dev, "Error handling on vendor layer!\n");
 			return -EIO;
 		}
 
@@ -284,7 +284,7 @@ recv_begin:
 	}
 
 	if (buf[1] == TPM_CTRL_WTX) {
-		dev_info(chip->pdev, "WTX-package received\n");
+		dev_info(&chip->dev, "WTX-package received\n");
 		if (number_of_wtx < TPM_MAX_WTX_PACKAGES) {
 			tpm_wtx(chip);
 			goto recv_begin;
@@ -295,14 +295,14 @@ recv_begin:
 	}
 
 	if (buf[1] == TPM_CTRL_WTX_ABORT_ACK) {
-		dev_info(chip->pdev, "WTX-abort acknowledged\n");
+		dev_info(&chip->dev, "WTX-abort acknowledged\n");
 		return size;
 	}
 
 	if (buf[1] == TPM_CTRL_ERROR) {
-		dev_err(chip->pdev, "ERROR-package received:\n");
+		dev_err(&chip->dev, "ERROR-package received:\n");
 		if (buf[4] == TPM_INF_NAK)
-			dev_err(chip->pdev,
+			dev_err(&chip->dev,
 				"-> Negative acknowledgement"
 				" - retransmit command!\n");
 		return -EIO;
@@ -321,7 +321,7 @@ static int tpm_inf_send(struct tpm_chip *chip, u8 * buf, size_t count)
 
 	ret = empty_fifo(chip, 1);
 	if (ret) {
-		dev_err(chip->pdev, "Timeout while clearing FIFO\n");
+		dev_err(&chip->dev, "Timeout while clearing FIFO\n");
 		return -EIO;
 	}
 
diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c
index 289389ecef84..766370bed60c 100644
--- a/drivers/char/tpm/tpm_nsc.c
+++ b/drivers/char/tpm/tpm_nsc.c
@@ -113,7 +113,7 @@ static int nsc_wait_for_ready(struct tpm_chip *chip)
 	}
 	while (time_before(jiffies, stop));
 
-	dev_info(chip->pdev, "wait for ready failed\n");
+	dev_info(&chip->dev, "wait for ready failed\n");
 	return -EBUSY;
 }
 
@@ -129,12 +129,12 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count)
 		return -EIO;
 
 	if (wait_for_stat(chip, NSC_STATUS_F0, NSC_STATUS_F0, &data) < 0) {
-		dev_err(chip->pdev, "F0 timeout\n");
+		dev_err(&chip->dev, "F0 timeout\n");
 		return -EIO;
 	}
 	if ((data =
 	     inb(chip->vendor.base + NSC_DATA)) != NSC_COMMAND_NORMAL) {
-		dev_err(chip->pdev, "not in normal mode (0x%x)\n",
+		dev_err(&chip->dev, "not in normal mode (0x%x)\n",
 			data);
 		return -EIO;
 	}
@@ -143,7 +143,7 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count)
 	for (p = buffer; p < &buffer[count]; p++) {
 		if (wait_for_stat
 		    (chip, NSC_STATUS_OBF, NSC_STATUS_OBF, &data) < 0) {
-			dev_err(chip->pdev,
+			dev_err(&chip->dev,
 				"OBF timeout (while reading data)\n");
 			return -EIO;
 		}
@@ -154,11 +154,11 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count)
 
 	if ((data & NSC_STATUS_F0) == 0 &&
 	(wait_for_stat(chip, NSC_STATUS_F0, NSC_STATUS_F0, &data) < 0)) {
-		dev_err(chip->pdev, "F0 not set\n");
+		dev_err(&chip->dev, "F0 not set\n");
 		return -EIO;
 	}
 	if ((data = inb(chip->vendor.base + NSC_DATA)) != NSC_COMMAND_EOC) {
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			"expected end of command(0x%x)\n", data);
 		return -EIO;
 	}
@@ -189,19 +189,19 @@ static int tpm_nsc_send(struct tpm_chip *chip, u8 * buf, size_t count)
 		return -EIO;
 
 	if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) {
-		dev_err(chip->pdev, "IBF timeout\n");
+		dev_err(&chip->dev, "IBF timeout\n");
 		return -EIO;
 	}
 
 	outb(NSC_COMMAND_NORMAL, chip->vendor.base + NSC_COMMAND);
 	if (wait_for_stat(chip, NSC_STATUS_IBR, NSC_STATUS_IBR, &data) < 0) {
-		dev_err(chip->pdev, "IBR timeout\n");
+		dev_err(&chip->dev, "IBR timeout\n");
 		return -EIO;
 	}
 
 	for (i = 0; i < count; i++) {
 		if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) {
-			dev_err(chip->pdev,
+			dev_err(&chip->dev,
 				"IBF timeout (while writing data)\n");
 			return -EIO;
 		}
@@ -209,7 +209,7 @@ static int tpm_nsc_send(struct tpm_chip *chip, u8 * buf, size_t count)
 	}
 
 	if (wait_for_stat(chip, NSC_STATUS_IBF, 0, &data) < 0) {
-		dev_err(chip->pdev, "IBF timeout\n");
+		dev_err(&chip->dev, "IBF timeout\n");
 		return -EIO;
 	}
 	outb(NSC_COMMAND_EOC, chip->vendor.base + NSC_COMMAND);
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 65f7eecc45b0..7f13221aeb30 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -293,7 +293,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	/* read first 10 bytes, including tag, paramsize, and result */
 	if ((size =
 	     recv_data(chip, buf, TPM_HEADER_SIZE)) < TPM_HEADER_SIZE) {
-		dev_err(chip->pdev, "Unable to read header\n");
+		dev_err(&chip->dev, "Unable to read header\n");
 		goto out;
 	}
 
@@ -306,7 +306,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	if ((size +=
 	     recv_data(chip, &buf[TPM_HEADER_SIZE],
 		       expected - TPM_HEADER_SIZE)) < expected) {
-		dev_err(chip->pdev, "Unable to read remainder of result\n");
+		dev_err(&chip->dev, "Unable to read remainder of result\n");
 		size = -ETIME;
 		goto out;
 	}
@@ -315,7 +315,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 			  &chip->vendor.int_queue, false);
 	status = tpm_tis_status(chip);
 	if (status & TPM_STS_DATA_AVAIL) {	/* retry? */
-		dev_err(chip->pdev, "Error left over data\n");
+		dev_err(&chip->dev, "Error left over data\n");
 		size = -EIO;
 		goto out;
 	}
@@ -401,7 +401,7 @@ static void disable_interrupts(struct tpm_chip *chip)
 	iowrite32(intmask,
 		  chip->vendor.iobase +
 		  TPM_INT_ENABLE(chip->vendor.locality));
-	free_irq(chip->vendor.irq, chip);
+	devm_free_irq(&chip->dev, chip->vendor.irq, chip);
 	chip->vendor.irq = 0;
 }
 
@@ -463,7 +463,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
 		msleep(1);
 	if (!priv->irq_tested) {
 		disable_interrupts(chip);
-		dev_err(chip->pdev,
+		dev_err(&chip->dev,
 			FW_BUG "TPM interrupt not working, polling instead\n");
 	}
 	priv->irq_tested = true;
@@ -533,7 +533,7 @@ static int probe_itpm(struct tpm_chip *chip)
 
 	rc = tpm_tis_send_data(chip, cmd_getticks, len);
 	if (rc == 0) {
-		dev_info(chip->pdev, "Detected an iTPM.\n");
+		dev_info(&chip->dev, "Detected an iTPM.\n");
 		rc = 1;
 	} else
 		rc = -EFAULT;
@@ -766,7 +766,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info,
 			if (devm_request_irq
 			    (dev, i, tis_int_probe, IRQF_SHARED,
 			     chip->devname, chip) != 0) {
-				dev_info(chip->pdev,
+				dev_info(&chip->dev,
 					 "Unable to request irq: %d for probe\n",
 					 i);
 				continue;
@@ -818,7 +818,7 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info,
 		if (devm_request_irq
 		    (dev, chip->vendor.irq, tis_int_handler, IRQF_SHARED,
 		     chip->devname, chip) != 0) {
-			dev_info(chip->pdev,
+			dev_info(&chip->dev,
 				 "Unable to request irq: %d for use\n",
 				 chip->vendor.irq);
 			chip->vendor.irq = 0;
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 3111f2778079..849f2e29c243 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -305,7 +305,6 @@ static int tpmfront_probe(struct xenbus_device *dev,
 	rv = setup_ring(dev, priv);
 	if (rv) {
 		chip = dev_get_drvdata(&dev->dev);
-		tpm_chip_unregister(chip);
 		ring_free(priv);
 		return rv;
 	}
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index d2406fe25533..be0b09a0fb44 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1130,6 +1130,8 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
+	void *data;
+	int ret;
 
 	if (unlikely(early_put_chars))
 		return early_put_chars(vtermno, buf, count);
@@ -1138,8 +1140,14 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	if (!port)
 		return -EPIPE;
 
-	sg_init_one(sg, buf, count);
-	return __send_to_port(port, sg, 1, count, (void *)buf, false);
+	data = kmemdup(buf, count, GFP_ATOMIC);
+	if (!data)
+		return -ENOMEM;
+
+	sg_init_one(sg, data, count);
+	ret = __send_to_port(port, sg, 1, count, data, false);
+	kfree(data);
+	return ret;
 }
 
 /*
@@ -1533,19 +1541,29 @@ static void remove_port_data(struct port *port)
 	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
+	spin_unlock_irq(&port->inbuf_lock);
 
 	/* Remove buffers we queued up for the Host to send us data in. */
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf, true);
-	spin_unlock_irq(&port->inbuf_lock);
+	do {
+		spin_lock_irq(&port->inbuf_lock);
+		buf = virtqueue_detach_unused_buf(port->in_vq);
+		spin_unlock_irq(&port->inbuf_lock);
+		if (buf)
+			free_buf(buf, true);
+	} while (buf);
 
 	spin_lock_irq(&port->outvq_lock);
 	reclaim_consumed_buffers(port);
+	spin_unlock_irq(&port->outvq_lock);
 
 	/* Free pending buffers from the out-queue. */
-	while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
-		free_buf(buf, true);
-	spin_unlock_irq(&port->outvq_lock);
+	do {
+		spin_lock_irq(&port->outvq_lock);
+		buf = virtqueue_detach_unused_buf(port->out_vq);
+		spin_unlock_irq(&port->outvq_lock);
+		if (buf)
+			free_buf(buf, true);
+	} while (buf);
 }
 
 /*
@@ -1846,7 +1864,7 @@ static void config_work_handler(struct work_struct *work)
 {
 	struct ports_device *portdev;
 
-	portdev = container_of(work, struct ports_device, control_work);
+	portdev = container_of(work, struct ports_device, config_work);
 	if (!use_multiport(portdev)) {
 		struct virtio_device *vdev;
 		struct port *port;
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 820714c72d36..af9e9aff49e5 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -78,7 +78,9 @@ obj-$(CONFIG_ARCH_TEGRA)		+= tegra/
 obj-$(CONFIG_ARCH_OMAP2PLUS)		+= ti/
 obj-$(CONFIG_ARCH_U8500)		+= ux500/
 obj-$(CONFIG_COMMON_CLK_VERSATILE)	+= versatile/
+ifeq ($(CONFIG_COMMON_CLK), y)
 obj-$(CONFIG_X86)			+= x86/
+endif
 obj-$(CONFIG_ARCH_ZX)			+= zte/
 obj-$(CONFIG_ARCH_ZYNQ)			+= zynq/
 obj-$(CONFIG_H8300)		+= h8300/
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
index 61566bcefa53..a165230e7eda 100644
--- a/drivers/clk/at91/clk-h32mx.c
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -116,7 +116,7 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 	h32mxclk->pmc = pmc;
 
 	clk = clk_register(NULL, &h32mxclk->hw);
-	if (!clk) {
+	if (IS_ERR(clk)) {
 		kfree(h32mxclk);
 		return;
 	}
diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index 39bf5820297e..35ab89fe9d7b 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -890,8 +890,14 @@ static void bcm2835_pll_off(struct clk_hw *hw)
 	struct bcm2835_cprman *cprman = pll->cprman;
 	const struct bcm2835_pll_data *data = pll->data;
 
-	cprman_write(cprman, data->cm_ctrl_reg, CM_PLL_ANARST);
-	cprman_write(cprman, data->a2w_ctrl_reg, A2W_PLL_CTRL_PWRDN);
+	spin_lock(&cprman->regs_lock);
+	cprman_write(cprman, data->cm_ctrl_reg,
+		     cprman_read(cprman, data->cm_ctrl_reg) |
+		     CM_PLL_ANARST);
+	cprman_write(cprman, data->a2w_ctrl_reg,
+		     cprman_read(cprman, data->a2w_ctrl_reg) |
+		     A2W_PLL_CTRL_PWRDN);
+	spin_unlock(&cprman->regs_lock);
 }
 
 static int bcm2835_pll_on(struct clk_hw *hw)
@@ -901,6 +907,10 @@ static int bcm2835_pll_on(struct clk_hw *hw)
 	const struct bcm2835_pll_data *data = pll->data;
 	ktime_t timeout;
 
+	cprman_write(cprman, data->a2w_ctrl_reg,
+		     cprman_read(cprman, data->a2w_ctrl_reg) &
+		     ~A2W_PLL_CTRL_PWRDN);
+
 	/* Take the PLL out of reset. */
 	cprman_write(cprman, data->cm_ctrl_reg,
 		     cprman_read(cprman, data->cm_ctrl_reg) & ~CM_PLL_ANARST);
@@ -1068,10 +1078,14 @@ static void bcm2835_pll_divider_off(struct clk_hw *hw)
 	struct bcm2835_cprman *cprman = divider->cprman;
 	const struct bcm2835_pll_divider_data *data = divider->data;
 
+	spin_lock(&cprman->regs_lock);
 	cprman_write(cprman, data->cm_reg,
 		     (cprman_read(cprman, data->cm_reg) &
 		      ~data->load_mask) | data->hold_mask);
-	cprman_write(cprman, data->a2w_reg, A2W_PLL_CHANNEL_DISABLE);
+	cprman_write(cprman, data->a2w_reg,
+		     cprman_read(cprman, data->a2w_reg) |
+		     A2W_PLL_CHANNEL_DISABLE);
+	spin_unlock(&cprman->regs_lock);
 }
 
 static int bcm2835_pll_divider_on(struct clk_hw *hw)
@@ -1080,12 +1094,14 @@ static int bcm2835_pll_divider_on(struct clk_hw *hw)
 	struct bcm2835_cprman *cprman = divider->cprman;
 	const struct bcm2835_pll_divider_data *data = divider->data;
 
+	spin_lock(&cprman->regs_lock);
 	cprman_write(cprman, data->a2w_reg,
 		     cprman_read(cprman, data->a2w_reg) &
 		     ~A2W_PLL_CHANNEL_DISABLE);
 
 	cprman_write(cprman, data->cm_reg,
 		     cprman_read(cprman, data->cm_reg) & ~data->hold_mask);
+	spin_unlock(&cprman->regs_lock);
 
 	return 0;
 }
@@ -1097,13 +1113,15 @@ static int bcm2835_pll_divider_set_rate(struct clk_hw *hw,
 	struct bcm2835_pll_divider *divider = bcm2835_pll_divider_from_hw(hw);
 	struct bcm2835_cprman *cprman = divider->cprman;
 	const struct bcm2835_pll_divider_data *data = divider->data;
-	u32 cm;
-	int ret;
+	u32 cm, div, max_div = 1 << A2W_PLL_DIV_BITS;
 
-	ret = clk_divider_ops.set_rate(hw, rate, parent_rate);
-	if (ret)
-		return ret;
+	div = DIV_ROUND_UP_ULL(parent_rate, rate);
+
+	div = min(div, max_div);
+	if (div == max_div)
+		div = 0;
 
+	cprman_write(cprman, data->a2w_reg, div);
 	cm = cprman_read(cprman, data->cm_reg);
 	cprman_write(cprman, data->cm_reg, cm | data->load_mask);
 	cprman_write(cprman, data->cm_reg, cm & ~data->load_mask);
@@ -1165,8 +1183,9 @@ static u32 bcm2835_clock_choose_div(struct clk_hw *hw,
 		div &= ~unused_frac_mask;
 	}
 
-	/* Clamp to the limits. */
-	div = max(div, unused_frac_mask + 1);
+	/* clamp to min divider of 1 */
+	div = max_t(u32, div, 1 << CM_DIV_FRAC_BITS);
+	/* clamp to the highest possible fractional divider */
 	div = min_t(u32, div, GENMASK(data->int_bits + CM_DIV_FRAC_BITS - 1,
 				      CM_DIV_FRAC_BITS - data->frac_bits));
 
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 3ace102a2a0a..ac9582de64a5 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -354,7 +354,7 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	/* if read only, just return current value */
 	if (divider->flags & CLK_DIVIDER_READ_ONLY) {
-		bestdiv = readl(divider->reg) >> divider->shift;
+		bestdiv = clk_readl(divider->reg) >> divider->shift;
 		bestdiv &= div_mask(divider->width);
 		bestdiv = _get_div(divider->table, bestdiv, divider->flags,
 			divider->width);
@@ -422,6 +422,12 @@ const struct clk_ops clk_divider_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_divider_ops);
 
+const struct clk_ops clk_divider_ro_ops = {
+	.recalc_rate = clk_divider_recalc_rate,
+	.round_rate = clk_divider_round_rate,
+};
+EXPORT_SYMBOL_GPL(clk_divider_ro_ops);
+
 static struct clk *_register_divider(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
@@ -445,7 +451,10 @@ static struct clk *_register_divider(struct device *dev, const char *name,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &clk_divider_ops;
+	if (clk_divider_flags & CLK_DIVIDER_READ_ONLY)
+		init.ops = &clk_divider_ro_ops;
+	else
+		init.ops = &clk_divider_ops;
 	init.flags = flags | CLK_IS_BASIC;
 	init.parent_names = (parent_name ? &parent_name: NULL);
 	init.num_parents = (parent_name ? 1 : 0);
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 7bc1c4527ae4..a5070f9cb0d4 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -700,6 +700,7 @@ static struct clk * __init create_mux_common(struct clockgen *cg,
 					     struct mux_hwclock *hwc,
 					     const struct clk_ops *ops,
 					     unsigned long min_rate,
+					     unsigned long max_rate,
 					     unsigned long pct80_rate,
 					     const char *fmt, int idx)
 {
@@ -728,6 +729,8 @@ static struct clk * __init create_mux_common(struct clockgen *cg,
 			continue;
 		if (rate < min_rate)
 			continue;
+		if (rate > max_rate)
+			continue;
 
 		parent_names[j] = div->name;
 		hwc->parent_to_clksel[j] = i;
@@ -759,14 +762,18 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
 	struct mux_hwclock *hwc;
 	const struct clockgen_pll_div *div;
 	unsigned long plat_rate, min_rate;
-	u64 pct80_rate;
+	u64 max_rate, pct80_rate;
 	u32 clksel;
 
 	hwc = kzalloc(sizeof(*hwc), GFP_KERNEL);
 	if (!hwc)
 		return NULL;
 
-	hwc->reg = cg->regs + 0x20 * idx;
+	if (cg->info.flags & CG_VER3)
+		hwc->reg = cg->regs + 0x70000 + 0x20 * idx;
+	else
+		hwc->reg = cg->regs + 0x20 * idx;
+
 	hwc->info = cg->info.cmux_groups[cg->info.cmux_to_group[idx]];
 
 	/*
@@ -783,8 +790,8 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
 		return NULL;
 	}
 
-	pct80_rate = clk_get_rate(div->clk);
-	pct80_rate *= 8;
+	max_rate = clk_get_rate(div->clk);
+	pct80_rate = max_rate * 8;
 	do_div(pct80_rate, 10);
 
 	plat_rate = clk_get_rate(cg->pll[PLATFORM_PLL].div[PLL_DIV1].clk);
@@ -794,7 +801,7 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
 	else
 		min_rate = plat_rate / 2;
 
-	return create_mux_common(cg, hwc, &cmux_ops, min_rate,
+	return create_mux_common(cg, hwc, &cmux_ops, min_rate, max_rate,
 				 pct80_rate, "cg-cmux%d", idx);
 }
 
@@ -809,7 +816,7 @@ static struct clk * __init create_one_hwaccel(struct clockgen *cg, int idx)
 	hwc->reg = cg->regs + 0x20 * idx + 0x10;
 	hwc->info = cg->info.hwaccel[idx];
 
-	return create_mux_common(cg, hwc, &hwaccel_ops, 0, 0,
+	return create_mux_common(cg, hwc, &hwaccel_ops, 0, ULONG_MAX, 0,
 				 "cg-hwaccel%d", idx);
 }
 
diff --git a/drivers/clk/clk-wm831x.c b/drivers/clk/clk-wm831x.c
index 43f9d15255f4..763aed2de893 100644
--- a/drivers/clk/clk-wm831x.c
+++ b/drivers/clk/clk-wm831x.c
@@ -247,7 +247,7 @@ static int wm831x_clkout_is_prepared(struct clk_hw *hw)
 	if (ret < 0) {
 		dev_err(wm831x->dev, "Unable to read CLOCK_CONTROL_1: %d\n",
 			ret);
-		return true;
+		return false;
 	}
 
 	return (ret & WM831X_CLKOUT_ENA) != 0;
diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c
index 27c0da29eca3..b134a8b15e2c 100644
--- a/drivers/clk/clk-xgene.c
+++ b/drivers/clk/clk-xgene.c
@@ -351,7 +351,8 @@ static int xgene_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		/* Set new divider */
 		data = xgene_clk_read(pclk->param.divider_reg +
 				pclk->param.reg_divider_offset);
-		data &= ~((1 << pclk->param.reg_divider_width) - 1);
+		data &= ~(((1 << pclk->param.reg_divider_width) - 1)
+				<< pclk->param.reg_divider_shift);
 		data |= divider;
 		xgene_clk_write(data, pclk->param.divider_reg +
 					pclk->param.reg_divider_offset);
diff --git a/drivers/clk/imx/clk-imx31.c b/drivers/clk/imx/clk-imx31.c
index 6a964144a5b5..6a49ba2b9671 100644
--- a/drivers/clk/imx/clk-imx31.c
+++ b/drivers/clk/imx/clk-imx31.c
@@ -157,10 +157,8 @@ static void __init _mx31_clocks_init(unsigned long fref)
 	}
 }
 
-int __init mx31_clocks_init(void)
+int __init mx31_clocks_init(unsigned long fref)
 {
-	u32 fref = 26000000; /* default */
-
 	_mx31_clocks_init(fref);
 
 	clk_register_clkdev(clk[gpt_gate], "per", "imx-gpt.0");
diff --git a/drivers/clk/imx/clk-imx35.c b/drivers/clk/imx/clk-imx35.c
index a71d24cb4c06..d302ed3b8225 100644
--- a/drivers/clk/imx/clk-imx35.c
+++ b/drivers/clk/imx/clk-imx35.c
@@ -66,7 +66,7 @@ static const char *std_sel[] = {"ppll", "arm"};
 static const char *ipg_per_sel[] = {"ahb_per_div", "arm_per_div"};
 
 enum mx35_clks {
-	ckih, ckil, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg,
+	ckih, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg,
 	arm_per_div, ahb_per_div, ipg_per, uart_sel, uart_div, esdhc_sel,
 	esdhc1_div, esdhc2_div, esdhc3_div, spdif_sel, spdif_div_pre,
 	spdif_div_post, ssi_sel, ssi1_div_pre, ssi1_div_post, ssi2_div_pre,
@@ -79,7 +79,7 @@ enum mx35_clks {
 	rtc_gate, rtic_gate, scc_gate, sdma_gate, spba_gate, spdif_gate,
 	ssi1_gate, ssi2_gate, uart1_gate, uart2_gate, uart3_gate, usbotg_gate,
 	wdog_gate, max_gate, admux_gate, csi_gate, csi_div, csi_sel, iim_gate,
-	gpu2d_gate, clk_max
+	gpu2d_gate, ckil, clk_max
 };
 
 static struct clk *clk[clk_max];
@@ -115,7 +115,7 @@ static void __init _mx35_clocks_init(void)
 	}
 
 	clk[ckih] = imx_clk_fixed("ckih", 24000000);
-	clk[ckil] = imx_clk_fixed("ckih", 32768);
+	clk[ckil] = imx_clk_fixed("ckil", 32768);
 	clk[mpll] = imx_clk_pllv1(IMX_PLLV1_IMX35, "mpll", "ckih", base + MX35_CCM_MPCTL);
 	clk[ppll] = imx_clk_pllv1(IMX_PLLV1_IMX35, "ppll", "ckih", base + MX35_CCM_PPCTL);
 
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index c1935081d34a..aab64205d866 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -550,6 +550,24 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
 		clk_set_parent(clk[IMX6QDL_CLK_LVDS1_SEL], clk[IMX6QDL_CLK_SATA_REF_100M]);
 
+	/*
+	 * Initialize the GPU clock muxes, so that the maximum specified clock
+	 * rates for the respective SoC are not exceeded.
+	 */
+	if (clk_on_imx6dl()) {
+		clk_set_parent(clk[IMX6QDL_CLK_GPU3D_CORE_SEL],
+			       clk[IMX6QDL_CLK_PLL2_PFD1_594M]);
+		clk_set_parent(clk[IMX6QDL_CLK_GPU2D_CORE_SEL],
+			       clk[IMX6QDL_CLK_PLL2_PFD1_594M]);
+	} else if (clk_on_imx6q()) {
+		clk_set_parent(clk[IMX6QDL_CLK_GPU3D_CORE_SEL],
+			       clk[IMX6QDL_CLK_MMDC_CH0_AXI]);
+		clk_set_parent(clk[IMX6QDL_CLK_GPU3D_SHADER_SEL],
+			       clk[IMX6QDL_CLK_PLL2_PFD1_594M]);
+		clk_set_parent(clk[IMX6QDL_CLK_GPU2D_CORE_SEL],
+			       clk[IMX6QDL_CLK_PLL3_USB_OTG]);
+	}
+
 	imx_register_uart_clocks(uart_clks);
 }
 CLK_OF_DECLARE(imx6q, "fsl,imx6q-ccm", imx6q_clocks_init);
diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c
index c83ae1367abc..d920d410b51d 100644
--- a/drivers/clk/meson/clkc.c
+++ b/drivers/clk/meson/clkc.c
@@ -198,7 +198,7 @@ meson_clk_register_fixed_rate(const struct clk_conf *clk_conf,
 }
 
 void __init meson_clk_register_clks(const struct clk_conf *clk_confs,
-				    size_t nr_confs,
+				    unsigned int nr_confs,
 				    void __iomem *clk_base)
 {
 	unsigned int i;
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
index 251533d87c65..f261b1d292c7 100644
--- a/drivers/clk/mmp/clk-of-mmp2.c
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -313,7 +313,7 @@ static void __init mmp2_clk_init(struct device_node *np)
 	}
 
 	pxa_unit->apmu_base = of_iomap(np, 1);
-	if (!pxa_unit->mpmu_base) {
+	if (!pxa_unit->apmu_base) {
 		pr_err("failed to map apmu registers\n");
 		return;
 	}
diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c
index 64eaf4141c69..427f4bb08665 100644
--- a/drivers/clk/mmp/clk-of-pxa168.c
+++ b/drivers/clk/mmp/clk-of-pxa168.c
@@ -262,7 +262,7 @@ static void __init pxa168_clk_init(struct device_node *np)
 	}
 
 	pxa_unit->apmu_base = of_iomap(np, 1);
-	if (!pxa_unit->mpmu_base) {
+	if (!pxa_unit->apmu_base) {
 		pr_err("failed to map apmu registers\n");
 		return;
 	}
diff --git a/drivers/clk/mmp/clk-of-pxa910.c b/drivers/clk/mmp/clk-of-pxa910.c
index 13d6173326a4..cdf5ba566d3b 100644
--- a/drivers/clk/mmp/clk-of-pxa910.c
+++ b/drivers/clk/mmp/clk-of-pxa910.c
@@ -282,7 +282,7 @@ static void __init pxa910_clk_init(struct device_node *np)
 	}
 
 	pxa_unit->apmu_base = of_iomap(np, 1);
-	if (!pxa_unit->mpmu_base) {
+	if (!pxa_unit->apmu_base) {
 		pr_err("failed to map apmu registers\n");
 		return;
 	}
@@ -294,7 +294,7 @@ static void __init pxa910_clk_init(struct device_node *np)
 	}
 
 	pxa_unit->apbcp_base = of_iomap(np, 3);
-	if (!pxa_unit->mpmu_base) {
+	if (!pxa_unit->apbcp_base) {
 		pr_err("failed to map apbcp registers\n");
 		return;
 	}
diff --git a/drivers/clk/nxp/clk-lpc18xx-ccu.c b/drivers/clk/nxp/clk-lpc18xx-ccu.c
index 13aabbb3acbe..558da89555af 100644
--- a/drivers/clk/nxp/clk-lpc18xx-ccu.c
+++ b/drivers/clk/nxp/clk-lpc18xx-ccu.c
@@ -222,7 +222,7 @@ static void lpc18xx_ccu_register_branch_gate_div(struct lpc18xx_clk_branch *bran
 		div->width = 1;
 
 		div_hw = &div->hw;
-		div_ops = &clk_divider_ops;
+		div_ops = &clk_divider_ro_ops;
 	}
 
 	branch->gate.reg = branch->offset + reg_base;
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index d0a0313d6bef..2e7f03d50f4e 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -2346,6 +2346,7 @@ static struct clk_branch gcc_crypto_ahb_clk = {
 				"pcnoc_bfdcd_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -2381,6 +2382,7 @@ static struct clk_branch gcc_crypto_clk = {
 				"crypto_clk_src",
 			},
 			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
 			.ops = &clk_branch2_ops,
 		},
 	},
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index 66c18bc97857..bdc4b2d07a23 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -2753,7 +2753,7 @@ static struct clk_rcg ce3_src = {
 	},
 	.freq_tbl = clk_tbl_ce3,
 	.clkr = {
-		.enable_reg = 0x2c08,
+		.enable_reg = 0x36c0,
 		.enable_mask = BIT(7),
 		.hw.init = &(struct clk_init_data){
 			.name = "ce3_src",
@@ -2769,7 +2769,7 @@ static struct clk_branch ce3_core_clk = {
 	.halt_reg = 0x2fdc,
 	.halt_bit = 5,
 	.clkr = {
-		.enable_reg = 0x36c4,
+		.enable_reg = 0x36cc,
 		.enable_mask = BIT(4),
 		.hw.init = &(struct clk_init_data){
 			.name = "ce3_core_clk",
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index 2685644826a0..33c20c6b45af 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -153,6 +153,7 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 		return NULL;
 
 	init.name = name;
+	init.flags = 0;
 	init.num_parents = num_parents;
 	init.parent_names = parent_names;
 	init.ops = &rockchip_mmc_clk_ops;
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index abb47608713b..fe728f8dcbe4 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -718,6 +718,7 @@ static const char *const rk3188_critical_clocks[] __initconst = {
 	"hclk_peri",
 	"pclk_cpu",
 	"pclk_peri",
+	"hclk_cpubus"
 };
 
 static void __init rk3188_common_clk_init(struct device_node *np)
diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c
index 7e6b783e6eee..1b148694b633 100644
--- a/drivers/clk/rockchip/clk-rk3368.c
+++ b/drivers/clk/rockchip/clk-rk3368.c
@@ -165,7 +165,7 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkb_data = {
 	.core_reg = RK3368_CLKSEL_CON(0),
 	.div_core_shift = 0,
 	.div_core_mask = 0x1f,
-	.mux_core_shift = 15,
+	.mux_core_shift = 7,
 };
 
 static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = {
@@ -218,29 +218,29 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = {
 	}
 
 static struct rockchip_cpuclk_rate_table rk3368_cpuclkb_rates[] __initdata = {
-	RK3368_CPUCLKB_RATE(1512000000, 2, 6, 6),
-	RK3368_CPUCLKB_RATE(1488000000, 2, 5, 5),
-	RK3368_CPUCLKB_RATE(1416000000, 2, 5, 5),
-	RK3368_CPUCLKB_RATE(1200000000, 2, 4, 4),
-	RK3368_CPUCLKB_RATE(1008000000, 2, 4, 4),
-	RK3368_CPUCLKB_RATE( 816000000, 2, 3, 3),
-	RK3368_CPUCLKB_RATE( 696000000, 2, 3, 3),
-	RK3368_CPUCLKB_RATE( 600000000, 2, 2, 2),
-	RK3368_CPUCLKB_RATE( 408000000, 2, 2, 2),
-	RK3368_CPUCLKB_RATE( 312000000, 2, 2, 2),
+	RK3368_CPUCLKB_RATE(1512000000, 1, 5, 5),
+	RK3368_CPUCLKB_RATE(1488000000, 1, 4, 4),
+	RK3368_CPUCLKB_RATE(1416000000, 1, 4, 4),
+	RK3368_CPUCLKB_RATE(1200000000, 1, 3, 3),
+	RK3368_CPUCLKB_RATE(1008000000, 1, 3, 3),
+	RK3368_CPUCLKB_RATE( 816000000, 1, 2, 2),
+	RK3368_CPUCLKB_RATE( 696000000, 1, 2, 2),
+	RK3368_CPUCLKB_RATE( 600000000, 1, 1, 1),
+	RK3368_CPUCLKB_RATE( 408000000, 1, 1, 1),
+	RK3368_CPUCLKB_RATE( 312000000, 1, 1, 1),
 };
 
 static struct rockchip_cpuclk_rate_table rk3368_cpuclkl_rates[] __initdata = {
-	RK3368_CPUCLKL_RATE(1512000000, 2, 7, 7),
-	RK3368_CPUCLKL_RATE(1488000000, 2, 6, 6),
-	RK3368_CPUCLKL_RATE(1416000000, 2, 6, 6),
-	RK3368_CPUCLKL_RATE(1200000000, 2, 5, 5),
-	RK3368_CPUCLKL_RATE(1008000000, 2, 5, 5),
-	RK3368_CPUCLKL_RATE( 816000000, 2, 4, 4),
-	RK3368_CPUCLKL_RATE( 696000000, 2, 3, 3),
-	RK3368_CPUCLKL_RATE( 600000000, 2, 3, 3),
-	RK3368_CPUCLKL_RATE( 408000000, 2, 2, 2),
-	RK3368_CPUCLKL_RATE( 312000000, 2, 2, 2),
+	RK3368_CPUCLKL_RATE(1512000000, 1, 6, 6),
+	RK3368_CPUCLKL_RATE(1488000000, 1, 5, 5),
+	RK3368_CPUCLKL_RATE(1416000000, 1, 5, 5),
+	RK3368_CPUCLKL_RATE(1200000000, 1, 4, 4),
+	RK3368_CPUCLKL_RATE(1008000000, 1, 4, 4),
+	RK3368_CPUCLKL_RATE( 816000000, 1, 3, 3),
+	RK3368_CPUCLKL_RATE( 696000000, 1, 2, 2),
+	RK3368_CPUCLKL_RATE( 600000000, 1, 2, 2),
+	RK3368_CPUCLKL_RATE( 408000000, 1, 1, 1),
+	RK3368_CPUCLKL_RATE( 312000000, 1, 1, 1),
 };
 
 static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
@@ -384,10 +384,10 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	 * Clock-Architecture Diagram 3
 	 */
 
-	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb_p, 0,
+	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_npll_usb_p, 0,
 			RK3368_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS,
 			RK3368_CLKGATE_CON(4), 6, GFLAGS),
-	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb_p, 0,
+	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_npll_usb_p, 0,
 			RK3368_CLKSEL_CON(15), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3368_CLKGATE_CON(4), 7, GFLAGS),
 
@@ -442,7 +442,7 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0,
 			RK3368_CLKGATE_CON(4), 13, GFLAGS),
 	GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0,
-			RK3368_CLKGATE_CON(5), 12, GFLAGS),
+			RK3368_CLKGATE_CON(4), 12, GFLAGS),
 
 	COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3368_CLKSEL_CON(21), 15, 1, MFLAGS,
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index be6c7fd8315d..9b6c8188efac 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -70,7 +70,7 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 	if (gate_offset >= 0) {
 		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
 		if (!gate)
-			return ERR_PTR(-ENOMEM);
+			goto err_gate;
 
 		gate->flags = gate_flags;
 		gate->reg = base + gate_offset;
@@ -82,7 +82,7 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 	if (div_width > 0) {
 		div = kzalloc(sizeof(*div), GFP_KERNEL);
 		if (!div)
-			return ERR_PTR(-ENOMEM);
+			goto err_div;
 
 		div->flags = div_flags;
 		div->reg = base + muxdiv_offset;
@@ -90,7 +90,9 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 		div->width = div_width;
 		div->lock = lock;
 		div->table = div_table;
-		div_ops = &clk_divider_ops;
+		div_ops = (div_flags & CLK_DIVIDER_READ_ONLY)
+						? &clk_divider_ro_ops
+						: &clk_divider_ops;
 	}
 
 	clk = clk_register_composite(NULL, name, parent_names, num_parents,
@@ -100,6 +102,11 @@ static struct clk *rockchip_clk_register_branch(const char *name,
 				     flags);
 
 	return clk;
+err_div:
+	kfree(gate);
+err_gate:
+	kfree(mux);
+	return ERR_PTR(-ENOMEM);
 }
 
 static struct clk *rockchip_clk_register_frac_branch(const char *name,
diff --git a/drivers/clk/sunxi/clk-simple-gates.c b/drivers/clk/sunxi/clk-simple-gates.c
index 0214c6548afd..97cb4221de25 100644
--- a/drivers/clk/sunxi/clk-simple-gates.c
+++ b/drivers/clk/sunxi/clk-simple-gates.c
@@ -98,6 +98,8 @@ static void __init sunxi_simple_gates_init(struct device_node *node)
 	sunxi_simple_gates_setup(node, NULL, 0);
 }
 
+CLK_OF_DECLARE(sun4i_a10_gates, "allwinner,sun4i-a10-gates-clk",
+	       sunxi_simple_gates_init);
 CLK_OF_DECLARE(sun4i_a10_apb0, "allwinner,sun4i-a10-apb0-gates-clk",
 	       sunxi_simple_gates_init);
 CLK_OF_DECLARE(sun4i_a10_apb1, "allwinner,sun4i-a10-apb1-gates-clk",
diff --git a/drivers/clk/ti/clk-3xxx.c b/drivers/clk/ti/clk-3xxx.c
index 8831e1a05367..11d8aa3ec186 100644
--- a/drivers/clk/ti/clk-3xxx.c
+++ b/drivers/clk/ti/clk-3xxx.c
@@ -22,13 +22,6 @@
 
 #include "clock.h"
 
-/*
- * DPLL5_FREQ_FOR_USBHOST: USBHOST and USBTLL are the only clocks
- * that are sourced by DPLL5, and both of these require this clock
- * to be at 120 MHz for proper operation.
- */
-#define DPLL5_FREQ_FOR_USBHOST		120000000
-
 #define OMAP3430ES2_ST_DSS_IDLE_SHIFT			1
 #define OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT		5
 #define OMAP3430ES2_ST_SSI_IDLE_SHIFT			8
@@ -546,14 +539,21 @@ void __init omap3_clk_lock_dpll5(void)
 	struct clk *dpll5_clk;
 	struct clk *dpll5_m2_clk;
 
+	/*
+	 * Errata sprz319f advisory 2.1 documents a USB host clock drift issue
+	 * that can be worked around using specially crafted dpll5 settings
+	 * with a dpll5_m2 divider set to 8. Set the dpll5 rate to 8x the USB
+	 * host clock rate, its .set_rate handler() will detect that frequency
+	 * and use the errata settings.
+	 */
 	dpll5_clk = clk_get(NULL, "dpll5_ck");
-	clk_set_rate(dpll5_clk, DPLL5_FREQ_FOR_USBHOST);
+	clk_set_rate(dpll5_clk, OMAP3_DPLL5_FREQ_FOR_USBHOST * 8);
 	clk_prepare_enable(dpll5_clk);
 
-	/* Program dpll5_m2_clk divider for no division */
+	/* Program dpll5_m2_clk divider */
 	dpll5_m2_clk = clk_get(NULL, "dpll5_m2_ck");
 	clk_prepare_enable(dpll5_m2_clk);
-	clk_set_rate(dpll5_m2_clk, DPLL5_FREQ_FOR_USBHOST);
+	clk_set_rate(dpll5_m2_clk, OMAP3_DPLL5_FREQ_FOR_USBHOST);
 
 	clk_disable_unprepare(dpll5_m2_clk);
 	clk_disable_unprepare(dpll5_clk);
diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h
index 90f3f472ae1c..13c37f48d9d6 100644
--- a/drivers/clk/ti/clock.h
+++ b/drivers/clk/ti/clock.h
@@ -257,11 +257,20 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
 unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
 				    unsigned long parent_rate);
 
+/*
+ * OMAP3_DPLL5_FREQ_FOR_USBHOST: USBHOST and USBTLL are the only clocks
+ * that are sourced by DPLL5, and both of these require this clock
+ * to be at 120 MHz for proper operation.
+ */
+#define OMAP3_DPLL5_FREQ_FOR_USBHOST	120000000
+
 unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate);
 int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate,
 			 unsigned long parent_rate);
 int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
 				    unsigned long parent_rate, u8 index);
+int omap3_dpll5_set_rate(struct clk_hw *hw, unsigned long rate,
+			 unsigned long parent_rate);
 void omap3_clk_lock_dpll5(void);
 
 unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw,
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index 5519b386edc0..f9a5089ddc79 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -114,6 +114,18 @@ static const struct clk_ops omap3_dpll_ck_ops = {
 	.round_rate	= &omap2_dpll_round_rate,
 };
 
+static const struct clk_ops omap3_dpll5_ck_ops = {
+	.enable		= &omap3_noncore_dpll_enable,
+	.disable	= &omap3_noncore_dpll_disable,
+	.get_parent	= &omap2_init_dpll_parent,
+	.recalc_rate	= &omap3_dpll_recalc,
+	.set_rate	= &omap3_dpll5_set_rate,
+	.set_parent	= &omap3_noncore_dpll_set_parent,
+	.set_rate_and_parent	= &omap3_noncore_dpll_set_rate_and_parent,
+	.determine_rate	= &omap3_noncore_dpll_determine_rate,
+	.round_rate	= &omap2_dpll_round_rate,
+};
+
 static const struct clk_ops omap3_dpll_per_ck_ops = {
 	.enable		= &omap3_noncore_dpll_enable,
 	.disable	= &omap3_noncore_dpll_disable,
@@ -461,7 +473,12 @@ static void __init of_ti_omap3_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd);
+	if ((of_machine_is_compatible("ti,omap3630") ||
+	     of_machine_is_compatible("ti,omap36xx")) &&
+	    !strcmp(node->name, "dpll5_ck"))
+		of_ti_dpll_setup(node, &omap3_dpll5_ck_ops, &dd);
+	else
+		of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_dpll_clock, "ti,omap3-dpll-clock",
 	       of_ti_omap3_dpll_setup);
diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c
index f4dec00fb684..0e9119fae760 100644
--- a/drivers/clk/ti/dpll3xxx.c
+++ b/drivers/clk/ti/dpll3xxx.c
@@ -815,3 +815,70 @@ int omap3_dpll4_set_rate_and_parent(struct clk_hw *hw, unsigned long rate,
 	return omap3_noncore_dpll_set_rate_and_parent(hw, rate, parent_rate,
 						      index);
 }
+
+/* Apply DM3730 errata sprz319 advisory 2.1. */
+static bool omap3_dpll5_apply_errata(struct clk_hw *hw,
+				     unsigned long parent_rate)
+{
+	struct omap3_dpll5_settings {
+		unsigned int rate, m, n;
+	};
+
+	static const struct omap3_dpll5_settings precomputed[] = {
+		/*
+		 * From DM3730 errata advisory 2.1, table 35 and 36.
+		 * The N value is increased by 1 compared to the tables as the
+		 * errata lists register values while last_rounded_field is the
+		 * real divider value.
+		 */
+		{ 12000000,  80,  0 + 1 },
+		{ 13000000, 443,  5 + 1 },
+		{ 19200000,  50,  0 + 1 },
+		{ 26000000, 443, 11 + 1 },
+		{ 38400000,  25,  0 + 1 }
+	};
+
+	const struct omap3_dpll5_settings *d;
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *dd;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(precomputed); ++i) {
+		if (parent_rate == precomputed[i].rate)
+			break;
+	}
+
+	if (i == ARRAY_SIZE(precomputed))
+		return false;
+
+	d = &precomputed[i];
+
+	/* Update the M, N and rounded rate values and program the DPLL. */
+	dd = clk->dpll_data;
+	dd->last_rounded_m = d->m;
+	dd->last_rounded_n = d->n;
+	dd->last_rounded_rate = div_u64((u64)parent_rate * d->m, d->n);
+	omap3_noncore_dpll_program(clk, 0);
+
+	return true;
+}
+
+/**
+ * omap3_dpll5_set_rate - set rate for omap3 dpll5
+ * @hw: clock to change
+ * @rate: target rate for clock
+ * @parent_rate: rate of the parent clock
+ *
+ * Set rate for the DPLL5 clock. Apply the sprz319 advisory 2.1 on OMAP36xx if
+ * the DPLL is used for USB host (detected through the requested rate).
+ */
+int omap3_dpll5_set_rate(struct clk_hw *hw, unsigned long rate,
+			 unsigned long parent_rate)
+{
+	if (rate == OMAP3_DPLL5_FREQ_FOR_USBHOST * 8) {
+		if (omap3_dpll5_apply_errata(hw, parent_rate))
+			return 0;
+	}
+
+	return omap3_noncore_dpll_set_rate(hw, rate, parent_rate);
+}
diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c
index a1cdef6b0f90..897c36c1754a 100644
--- a/drivers/clk/versatile/clk-sp810.c
+++ b/drivers/clk/versatile/clk-sp810.c
@@ -92,6 +92,7 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 	int num = ARRAY_SIZE(parent_names);
 	char name[12];
 	struct clk_init_data init;
+	static int instance;
 	int i;
 	bool deprecated;
 
@@ -118,7 +119,7 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 	deprecated = !of_find_property(node, "assigned-clock-parents", NULL);
 
 	for (i = 0; i < ARRAY_SIZE(sp810->timerclken); i++) {
-		snprintf(name, ARRAY_SIZE(name), "timerclken%d", i);
+		snprintf(name, sizeof(name), "sp810_%d_%d", instance, i);
 
 		sp810->timerclken[i].sp810 = sp810;
 		sp810->timerclken[i].channel = i;
@@ -139,5 +140,6 @@ static void __init clk_sp810_of_setup(struct device_node *node)
 	}
 
 	of_clk_add_provider(node, clk_sp810_timerclken_of_get, sp810);
+	instance++;
 }
 CLK_OF_DECLARE(sp810, "arm,sp810", clk_sp810_of_setup);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index ff44082a0827..47f8aafe3344 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -482,6 +482,7 @@ static void exynos4_local_timer_stop(struct mct_clock_event_device *mevt)
 	if (mct_int_type == MCT_INT_SPI) {
 		if (evt->irq != -1)
 			disable_irq_nosync(evt->irq);
+		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
 	} else {
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
 	}
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 6f3719d73390..e84877a2cacc 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -123,12 +123,16 @@ static struct clock_event_device sun4i_clockevent = {
 	.set_next_event = sun4i_clkevt_next_event,
 };
 
+static void sun4i_timer_clear_interrupt(void)
+{
+	writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG);
+}
 
 static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
 
-	writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+	sun4i_timer_clear_interrupt();
 	evt->event_handler(evt);
 
 	return IRQ_HANDLED;
@@ -193,6 +197,9 @@ static void __init sun4i_timer_init(struct device_node *node)
 	/* Make sure timer is stopped before playing with interrupts */
 	sun4i_clkevt_time_stop(0);
 
+	/* clear timer0 interrupt */
+	sun4i_timer_clear_interrupt();
+
 	sun4i_clockevent.cpumask = cpu_possible_mask;
 	sun4i_clockevent.irq = irq;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 8412ce5f93a7..ebed319657e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -626,9 +626,11 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	unsigned int cur_freq = __cpufreq_get(policy);
-	if (!cur_freq)
-		return sprintf(buf, "<unknown>");
-	return sprintf(buf, "%u\n", cur_freq);
+
+	if (cur_freq)
+		return sprintf(buf, "%u\n", cur_freq);
+
+	return sprintf(buf, "<unknown>\n");
 }
 
 /**
@@ -1184,6 +1186,9 @@ static int cpufreq_online(unsigned int cpu)
 		for_each_cpu(j, policy->related_cpus)
 			per_cpu(cpufreq_cpu_data, j) = policy;
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	} else {
+		policy->min = policy->user_policy.min;
+		policy->max = policy->user_policy.max;
 	}
 
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
@@ -2446,6 +2451,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (!(cpufreq_driver->flags & CPUFREQ_STICKY) &&
 	    list_empty(&cpufreq_policy_list)) {
 		/* if all ->init() calls failed, unregister */
+		ret = -ENODEV;
 		pr_debug("%s: No CPU initialized for driver %s\n", __func__,
 			 driver_data->name);
 		goto err_if_unreg;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 1fa1deb6e91f..c395f9198fd2 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -212,8 +212,8 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 	int ret;
 	ret = sscanf(buf, "%u", &input);
 
-	/* cannot be lower than 11 otherwise freq will not fall */
-	if (ret != 1 || input < 11 || input > 100 ||
+	/* cannot be lower than 1 otherwise freq will not fall */
+	if (ret != 1 || input < 1 || input > 100 ||
 			input >= cs_tuners->up_threshold)
 		return -EINVAL;
 
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 4dbf1db16aca..9cc8abd3d116 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 
 static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 static DEFINE_MUTEX(userspace_mutex);
@@ -31,6 +32,7 @@ static DEFINE_MUTEX(userspace_mutex);
 static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 {
 	int ret = -EINVAL;
+	unsigned int *setspeed = policy->governor_data;
 
 	pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
@@ -38,6 +40,8 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 	if (!per_cpu(cpu_is_managed, policy->cpu))
 		goto err;
 
+	*setspeed = freq;
+
 	ret = __cpufreq_driver_target(policy, freq, CPUFREQ_RELATION_L);
  err:
 	mutex_unlock(&userspace_mutex);
@@ -49,19 +53,45 @@ static ssize_t show_speed(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", policy->cur);
 }
 
+static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed;
+
+	setspeed = kzalloc(sizeof(*setspeed), GFP_KERNEL);
+	if (!setspeed)
+		return -ENOMEM;
+
+	policy->governor_data = setspeed;
+	return 0;
+}
+
 static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
+	unsigned int *setspeed = policy->governor_data;
 	unsigned int cpu = policy->cpu;
 	int rc = 0;
 
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		return cpufreq_userspace_policy_init(policy);
+
+	if (!setspeed)
+		return -EINVAL;
+
 	switch (event) {
+	case CPUFREQ_GOV_POLICY_EXIT:
+		mutex_lock(&userspace_mutex);
+		policy->governor_data = NULL;
+		kfree(setspeed);
+		mutex_unlock(&userspace_mutex);
+		break;
 	case CPUFREQ_GOV_START:
 		BUG_ON(!policy->cur);
 		pr_debug("started managing cpu %u\n", cpu);
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 1;
+		*setspeed = policy->cur;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_STOP:
@@ -69,20 +99,23 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 0;
+		*setspeed = 0;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_LIMITS:
 		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz\n",
-			cpu, policy->min, policy->max,
-			policy->cur);
+		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+			cpu, policy->min, policy->max, policy->cur, *setspeed);
 
-		if (policy->max < policy->cur)
+		if (policy->max < *setspeed)
 			__cpufreq_driver_target(policy, policy->max,
 						CPUFREQ_RELATION_H);
-		else if (policy->min > policy->cur)
+		else if (policy->min > *setspeed)
 			__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_L);
+		else
+			__cpufreq_driver_target(policy, *setspeed,
+						CPUFREQ_RELATION_L);
 		mutex_unlock(&userspace_mutex);
 		break;
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 98fb8821382d..7ff8b15a3422 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -285,14 +285,14 @@ static void intel_pstate_hwp_set(void)
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	u64 value, cap;
 
-	rdmsrl(MSR_HWP_CAPABILITIES, cap);
-	hw_min = HWP_LOWEST_PERF(cap);
-	hw_max = HWP_HIGHEST_PERF(cap);
-	range = hw_max - hw_min;
-
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
+		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+		hw_min = HWP_LOWEST_PERF(cap);
+		hw_max = HWP_HIGHEST_PERF(cap);
+		range = hw_max - hw_min;
+
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 		adj_range = limits->min_perf_pct * range / 100;
 		min = hw_min + adj_range;
@@ -662,11 +662,16 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + tdp_ctrl;
+			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
 			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
 			if (err)
 				goto skip_tar;
 
+			/* For level 1 and 2, bits[23:16] contain the ratio */
+			if (tdp_ctrl)
+				tdp_ratio >>= 16;
+
+			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
 			if (tdp_ratio - 1 == tar) {
 				max_pstate = tar;
 				pr_debug("max_pstate=TAC %x\n", max_pstate);
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index cb501386eb6e..c4b0ef65988c 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -373,8 +373,14 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	if (unlikely(rebooting) && new_index != get_nominal_index())
 		return 0;
 
-	if (!throttled)
+	if (!throttled) {
+		/* we don't want to be preempted while
+		 * checking if the CPU frequency has been throttled
+		 */
+		preempt_disable();
 		powernv_cpufreq_throttle_check(NULL);
+		preempt_enable();
+	}
 
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index d6d425773fa4..5b2db3c6568f 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 	rate = clk_get_rate(s3c_freq->hclk);
 	if (rate < 133 * 1000 * 1000) {
 		pr_err("cpufreq: HCLK not at 133MHz\n");
-		clk_put(s3c_freq->hclk);
 		ret = -EINVAL;
 		goto err_armclk;
 	}
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index 545069d5fdfb..1855b9ee807f 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -50,7 +50,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev,
 		 * call the CPU ops suspend protocol with idle index as a
 		 * parameter.
 		 */
-		arm_cpuidle_suspend(idx);
+		ret = arm_cpuidle_suspend(idx);
 
 		cpu_pm_exit();
 	}
@@ -135,6 +135,7 @@ static int __init arm_idle_init(void)
 		dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 		if (!dev) {
 			pr_err("Failed to allocate cpuidle device\n");
+			ret = -ENOMEM;
 			goto out_fail;
 		}
 		dev->cpu = cpu;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 17a6dc0e2111..d40b2c077746 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -214,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		tick_broadcast_exit();
 	}
 
-	if (!cpuidle_state_is_coupled(drv, entered_state))
+	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
 	diff = ktime_to_us(ktime_sub(time_end, time_start));
@@ -433,6 +433,8 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
 	list_del(&dev->device_list);
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
 	module_put(drv->owner);
+
+	dev->registered = 0;
 }
 
 static void __cpuidle_device_init(struct cpuidle_device *dev)
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index fb16d812c8f5..1dffb13e5c2f 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -1396,9 +1396,9 @@ static int atmel_aes_probe(struct platform_device *pdev)
 	}
 
 	aes_dd->io_base = devm_ioremap_resource(&pdev->dev, aes_res);
-	if (!aes_dd->io_base) {
+	if (IS_ERR(aes_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(aes_dd->io_base);
 		goto res_err;
 	}
 
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 3178f84d2757..7abe908427df 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -963,7 +963,9 @@ static int atmel_sha_finup(struct ahash_request *req)
 	ctx->flags |= SHA_FLAGS_FINUP;
 
 	err1 = atmel_sha_update(req);
-	if (err1 == -EINPROGRESS || err1 == -EBUSY)
+	if (err1 == -EINPROGRESS ||
+	    (err1 == -EBUSY && (ahash_request_flags(req) &
+				CRYPTO_TFM_REQ_MAY_BACKLOG)))
 		return err1;
 
 	/*
@@ -1405,9 +1407,9 @@ static int atmel_sha_probe(struct platform_device *pdev)
 	}
 
 	sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res);
-	if (!sha_dd->io_base) {
+	if (IS_ERR(sha_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(sha_dd->io_base);
 		goto res_err;
 	}
 
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 2c7a628d0375..bf467d7be35c 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -1417,9 +1417,9 @@ static int atmel_tdes_probe(struct platform_device *pdev)
 	}
 
 	tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res);
-	if (!tdes_dd->io_base) {
+	if (IS_ERR(tdes_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(tdes_dd->io_base);
 		goto res_err;
 	}
 
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index ea8189f4b021..f3307fc38e79 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -441,6 +441,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 			       OP_ALG_AAI_CTR_MOD128);
 	const bool is_rfc3686 = alg->caam.rfc3686;
 
+	if (!ctx->authsize)
+		return 0;
+
 	/* NULL encryption / decryption */
 	if (!ctx->enckeylen)
 		return aead_null_set_sh_desc(aead);
@@ -553,7 +556,10 @@ skip_enc:
 
 	/* Read and write assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	if (alg->caam.geniv)
+		append_math_add_imm_u32(desc, VARSEQOUTLEN, REG3, IMM, ivsize);
+	else
+		append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
@@ -562,6 +568,14 @@ skip_enc:
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
 
+	if (alg->caam.geniv) {
+		append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+				LDST_SRCDST_BYTE_CONTEXT |
+				(ctx1_iv_off << LDST_OFFSET_SHIFT));
+		append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_CLASS2INFIFO |
+			    (ctx1_iv_off << MOVE_OFFSET_SHIFT) | ivsize);
+	}
+
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
 		append_load_imm_u32(desc, be32_to_cpu(1), LDST_IMM |
@@ -614,7 +628,7 @@ skip_enc:
 		keys_fit_inline = true;
 
 	/* aead_givencrypt shared descriptor */
-	desc = ctx->sh_desc_givenc;
+	desc = ctx->sh_desc_enc;
 
 	/* Note: Context registers are saved. */
 	init_sh_desc_key_aead(desc, ctx, keys_fit_inline, is_rfc3686);
@@ -645,13 +659,13 @@ copy_iv:
 	append_operation(desc, ctx->class2_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* ivsize + cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
 	/* Read and write assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
+	/* ivsize + cryptlen = seqoutlen - authsize */
+	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
@@ -688,7 +702,9 @@ copy_iv:
 
 	/* Will read cryptlen */
 	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
-	aead_append_src_dst(desc, FIFOLD_TYPE_MSG1OUT2);
+	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_BOTH | KEY_VLF |
+			     FIFOLD_TYPE_MSG1OUT2 | FIFOLD_TYPE_LASTBOTH);
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | KEY_VLF);
 
 	/* Write ICV */
 	append_seq_store(desc, ctx->authsize, LDST_CLASS_2_CCB |
@@ -697,7 +713,7 @@ copy_iv:
 	ctx->sh_desc_enc_dma = dma_map_single(jrdev, desc,
 					      desc_bytes(desc),
 					      DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
+	if (dma_mapping_error(jrdev, ctx->sh_desc_enc_dma)) {
 		dev_err(jrdev, "unable to map shared descriptor\n");
 		return -ENOMEM;
 	}
@@ -2147,7 +2163,7 @@ static void init_authenc_job(struct aead_request *req,
 
 	init_aead_job(req, edesc, all_contig, encrypt);
 
-	if (ivsize && (is_rfc3686 || !(alg->caam.geniv && encrypt)))
+	if (ivsize && ((is_rfc3686 && encrypt) || !alg->caam.geniv))
 		append_load_as_imm(desc, req->iv, ivsize,
 				   LDST_CLASS_1_CCB |
 				   LDST_SRCDST_BYTE_CONTEXT |
@@ -2534,20 +2550,6 @@ static int aead_decrypt(struct aead_request *req)
 	return ret;
 }
 
-static int aead_givdecrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	unsigned int ivsize = crypto_aead_ivsize(aead);
-
-	if (req->cryptlen < ivsize)
-		return -EINVAL;
-
-	req->cryptlen -= ivsize;
-	req->assoclen += ivsize;
-
-	return aead_decrypt(req);
-}
-
 /*
  * allocate and map the ablkcipher extended descriptor for ablkcipher
  */
@@ -3207,7 +3209,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3253,7 +3255,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3299,7 +3301,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3345,7 +3347,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3391,7 +3393,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -3437,7 +3439,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -3483,7 +3485,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3531,7 +3533,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3579,7 +3581,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3627,7 +3629,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3675,7 +3677,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -3723,7 +3725,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -3769,7 +3771,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3815,7 +3817,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3861,7 +3863,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3907,7 +3909,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3953,7 +3955,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -3999,7 +4001,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -4048,7 +4050,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -4099,7 +4101,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -4150,7 +4152,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -4201,7 +4203,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -4252,7 +4254,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -4303,7 +4305,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -4542,6 +4544,15 @@ static int __init caam_algapi_init(void)
 		if (!aes_inst && (alg_sel == OP_ALG_ALGSEL_AES))
 				continue;
 
+		/*
+		 * Check support for AES modes not available
+		 * on LP devices.
+		 */
+		if ((cha_vid & CHA_ID_LS_AES_MASK) == CHA_ID_LS_AES_LP)
+			if ((alg->class1_alg_type & OP_ALG_AAI_MASK) ==
+			     OP_ALG_AAI_XTS)
+				continue;
+
 		t_alg = caam_alg_alloc(alg);
 		if (IS_ERR(t_alg)) {
 			err = PTR_ERR(t_alg);
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 49106ea42887..e06cc5df30be 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -498,7 +498,7 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 	ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result);
 	if (!ret) {
 		/* in progress */
-		wait_for_completion_interruptible(&result.completion);
+		wait_for_completion(&result.completion);
 		ret = result.err;
 #ifdef DEBUG
 		print_hex_dump(KERN_ERR,
@@ -1873,6 +1873,7 @@ caam_hash_alloc(struct caam_hash_template *template,
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
+		t_alg->ahash_alg.setkey = NULL;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 69d4a1326fee..53e61459c69f 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -278,7 +278,8 @@ static int deinstantiate_rng(struct device *ctrldev, int state_handle_mask)
 			/* Try to run it through DECO0 */
 			ret = run_descriptor_deco0(ctrldev, desc, &status);
 
-			if (ret || status) {
+			if (ret ||
+			    (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
 				dev_err(ctrldev,
 					"Failed to deinstantiate RNG4 SH%d\n",
 					sh_idx);
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index f7e0d8d4c3da..8f50a02ff68d 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -248,7 +248,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 struct device *caam_jr_alloc(void)
 {
 	struct caam_drv_private_jr *jrpriv, *min_jrpriv = NULL;
-	struct device *dev = NULL;
+	struct device *dev = ERR_PTR(-ENODEV);
 	int min_tfm_cnt	= INT_MAX;
 	int tfm_cnt;
 
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
index e1eaf4ff9762..3ce1d5cdcbd2 100644
--- a/drivers/crypto/caam/key_gen.c
+++ b/drivers/crypto/caam/key_gen.c
@@ -103,7 +103,7 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 	ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result);
 	if (!ret) {
 		/* in progress */
-		wait_for_completion_interruptible(&result.completion);
+		wait_for_completion(&result.completion);
 		ret = result.err;
 #ifdef DEBUG
 		print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index d89f20c04266..60fc0fa26fd3 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -220,6 +220,42 @@ static int ccp_aes_cmac_digest(struct ahash_request *req)
 	return ccp_aes_cmac_finup(req);
 }
 
+static int ccp_aes_cmac_export(struct ahash_request *req, void *out)
+{
+	struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_aes_cmac_exp_ctx state;
+
+	/* Don't let anything leak to 'out' */
+	memset(&state, 0, sizeof(state));
+
+	state.null_msg = rctx->null_msg;
+	memcpy(state.iv, rctx->iv, sizeof(state.iv));
+	state.buf_count = rctx->buf_count;
+	memcpy(state.buf, rctx->buf, sizeof(state.buf));
+
+	/* 'out' may not be aligned so memcpy from local variable */
+	memcpy(out, &state, sizeof(state));
+
+	return 0;
+}
+
+static int ccp_aes_cmac_import(struct ahash_request *req, const void *in)
+{
+	struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_aes_cmac_exp_ctx state;
+
+	/* 'in' may not be aligned so memcpy to local variable */
+	memcpy(&state, in, sizeof(state));
+
+	memset(rctx, 0, sizeof(*rctx));
+	rctx->null_msg = state.null_msg;
+	memcpy(rctx->iv, state.iv, sizeof(rctx->iv));
+	rctx->buf_count = state.buf_count;
+	memcpy(rctx->buf, state.buf, sizeof(rctx->buf));
+
+	return 0;
+}
+
 static int ccp_aes_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 			       unsigned int key_len)
 {
@@ -352,10 +388,13 @@ int ccp_register_aes_cmac_algs(struct list_head *head)
 	alg->final = ccp_aes_cmac_final;
 	alg->finup = ccp_aes_cmac_finup;
 	alg->digest = ccp_aes_cmac_digest;
+	alg->export = ccp_aes_cmac_export;
+	alg->import = ccp_aes_cmac_import;
 	alg->setkey = ccp_aes_cmac_setkey;
 
 	halg = &alg->halg;
 	halg->digestsize = AES_BLOCK_SIZE;
+	halg->statesize = sizeof(struct ccp_aes_cmac_exp_ctx);
 
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)");
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 52c7395cb8d8..0d0d4529ee36 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -122,6 +122,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
 	unsigned int unit;
+	u32 unit_size;
 	int ret;
 
 	if (!ctx->u.aes.key_len)
@@ -133,11 +134,17 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	if (!req->info)
 		return -EINVAL;
 
-	for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++)
-		if (!(req->nbytes & (unit_size_map[unit].size - 1)))
-			break;
+	unit_size = CCP_XTS_AES_UNIT_SIZE__LAST;
+	if (req->nbytes <= unit_size_map[0].size) {
+		for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) {
+			if (!(req->nbytes & (unit_size_map[unit].size - 1))) {
+				unit_size = unit_size_map[unit].value;
+				break;
+			}
+		}
+	}
 
-	if ((unit_size_map[unit].value == CCP_XTS_AES_UNIT_SIZE__LAST) ||
+	if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) ||
 	    (ctx->u.aes.key_len != AES_KEYSIZE_128)) {
 		/* Use the fallback to process the request for any
 		 * unsupported unit sizes or key sizes
@@ -158,7 +165,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 	rctx->cmd.engine = CCP_ENGINE_XTS_AES_128;
 	rctx->cmd.u.xts.action = (encrypt) ? CCP_AES_ACTION_ENCRYPT
 					   : CCP_AES_ACTION_DECRYPT;
-	rctx->cmd.u.xts.unit_size = unit_size_map[unit].value;
+	rctx->cmd.u.xts.unit_size = unit_size;
 	rctx->cmd.u.xts.key = &ctx->u.aes.key_sg;
 	rctx->cmd.u.xts.key_len = ctx->u.aes.key_len;
 	rctx->cmd.u.xts.iv = &rctx->iv_sg;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index d14b3f28e010..ab9945f2cb7a 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -207,6 +207,46 @@ static int ccp_sha_digest(struct ahash_request *req)
 	return ccp_sha_finup(req);
 }
 
+static int ccp_sha_export(struct ahash_request *req, void *out)
+{
+	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_sha_exp_ctx state;
+
+	/* Don't let anything leak to 'out' */
+	memset(&state, 0, sizeof(state));
+
+	state.type = rctx->type;
+	state.msg_bits = rctx->msg_bits;
+	state.first = rctx->first;
+	memcpy(state.ctx, rctx->ctx, sizeof(state.ctx));
+	state.buf_count = rctx->buf_count;
+	memcpy(state.buf, rctx->buf, sizeof(state.buf));
+
+	/* 'out' may not be aligned so memcpy from local variable */
+	memcpy(out, &state, sizeof(state));
+
+	return 0;
+}
+
+static int ccp_sha_import(struct ahash_request *req, const void *in)
+{
+	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_sha_exp_ctx state;
+
+	/* 'in' may not be aligned so memcpy to local variable */
+	memcpy(&state, in, sizeof(state));
+
+	memset(rctx, 0, sizeof(*rctx));
+	rctx->type = state.type;
+	rctx->msg_bits = state.msg_bits;
+	rctx->first = state.first;
+	memcpy(rctx->ctx, state.ctx, sizeof(rctx->ctx));
+	rctx->buf_count = state.buf_count;
+	memcpy(rctx->buf, state.buf, sizeof(rctx->buf));
+
+	return 0;
+}
+
 static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 			  unsigned int key_len)
 {
@@ -403,9 +443,12 @@ static int ccp_register_sha_alg(struct list_head *head,
 	alg->final = ccp_sha_final;
 	alg->finup = ccp_sha_finup;
 	alg->digest = ccp_sha_digest;
+	alg->export = ccp_sha_export;
+	alg->import = ccp_sha_import;
 
 	halg = &alg->halg;
 	halg->digestsize = def->digest_size;
+	halg->statesize = sizeof(struct ccp_sha_exp_ctx);
 
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index 76a96f0f44c6..a326ec20bfa8 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -129,6 +129,15 @@ struct ccp_aes_cmac_req_ctx {
 	struct ccp_cmd cmd;
 };
 
+struct ccp_aes_cmac_exp_ctx {
+	unsigned int null_msg;
+
+	u8 iv[AES_BLOCK_SIZE];
+
+	unsigned int buf_count;
+	u8 buf[AES_BLOCK_SIZE];
+};
+
 /***** SHA related defines *****/
 #define MAX_SHA_CONTEXT_SIZE	SHA256_DIGEST_SIZE
 #define MAX_SHA_BLOCK_SIZE	SHA256_BLOCK_SIZE
@@ -171,6 +180,19 @@ struct ccp_sha_req_ctx {
 	struct ccp_cmd cmd;
 };
 
+struct ccp_sha_exp_ctx {
+	enum ccp_sha_type type;
+
+	u64 msg_bits;
+
+	unsigned int first;
+
+	u8 ctx[MAX_SHA_CONTEXT_SIZE];
+
+	unsigned int buf_count;
+	u8 buf[MAX_SHA_BLOCK_SIZE];
+};
+
 /***** Common Context Structure *****/
 struct ccp_ctx {
 	int (*complete)(struct crypto_async_request *req, int ret);
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index c0656e7f37b5..80239ae69527 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -420,7 +420,7 @@ static int mv_cesa_probe(struct platform_device *pdev)
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	cesa->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(cesa->regs))
-		return -ENOMEM;
+		return PTR_ERR(cesa->regs);
 
 	ret = mv_cesa_dev_dma_init(cesa);
 	if (ret)
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 9ef51fafdbff..6e105e87b8ff 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -442,6 +442,14 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 			     (unsigned int)ccw,
 			     (unsigned int)be32_to_cpu(crb->ccw));
 
+	/*
+	 * NX842 coprocessor sets 3rd bit in CR register with XER[S0].
+	 * XER[S0] is the integer summary overflow bit which is nothing
+	 * to do NX. Since this bit can be set with other return values,
+	 * mask this bit.
+	 */
+	ret &= ~ICSWX_XERS0;
+
 	switch (ret) {
 	case ICSWX_INITIATED:
 		ret = wait_for_csb(wmem, csb);
@@ -454,10 +462,6 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 		pr_err_ratelimited("ICSWX rejected\n");
 		ret = -EPROTO;
 		break;
-	default:
-		pr_err_ratelimited("Invalid ICSWX return code %x\n", ret);
-		ret = -EPROTO;
-		break;
 	}
 
 	if (!ret)
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 0794f1cc0018..42f0f229f7f7 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -392,7 +392,7 @@ static void nx_of_update_msc(struct device   *dev,
 		     ((bytes_so_far + sizeof(struct msc_triplet)) <= lenp) &&
 		     i < msc->triplets;
 		     i++) {
-			if (msc->fc > NX_MAX_FC || msc->mode > NX_MAX_MODE) {
+			if (msc->fc >= NX_MAX_FC || msc->mode >= NX_MAX_MODE) {
 				dev_err(dev, "unknown function code/mode "
 					"combo: %d/%d (ignored)\n", msc->fc,
 					msc->mode);
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 9e9e196c6d51..45b5adaafa6f 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -2,6 +2,7 @@ $(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \
 			     $(obj)/qat_rsapubkey-asn1.h
 $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \
 			      $(obj)/qat_rsaprivkey-asn1.h
+$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h
 
 clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h
 clean-files += qat_rsaprivkey-asn1.c qat_rsapvivkey-asn1.h
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 3f76bd495bcb..aa1dbeaa9b49 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -227,6 +227,8 @@ void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
 				  uint32_t vf_mask);
 void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev,
 				 uint32_t vf_mask);
+int adf_init_pf_wq(void);
+void adf_exit_pf_wq(void);
 #else
 static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 {
@@ -236,5 +238,14 @@ static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 {
 }
+
+static inline int adf_init_pf_wq(void)
+{
+	return 0;
+}
+
+static inline void adf_exit_pf_wq(void)
+{
+}
 #endif
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index 473d36d91644..e7480f373532 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -469,12 +469,17 @@ static int __init adf_register_ctl_device_driver(void)
 	if (adf_init_aer())
 		goto err_aer;
 
+	if (adf_init_pf_wq())
+		goto err_pf_wq;
+
 	if (qat_crypto_register())
 		goto err_crypto_register;
 
 	return 0;
 
 err_crypto_register:
+	adf_exit_pf_wq();
+err_pf_wq:
 	adf_exit_aer();
 err_aer:
 	adf_chr_drv_destroy();
@@ -487,6 +492,7 @@ static void __exit adf_unregister_ctl_device_driver(void)
 {
 	adf_chr_drv_destroy();
 	adf_exit_aer();
+	adf_exit_pf_wq();
 	qat_crypto_unregister();
 	adf_clean_vf_map(false);
 	mutex_destroy(&adf_ctl_lock);
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
index 1117a8b58280..38a0415e767d 100644
--- a/drivers/crypto/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/qat/qat_common/adf_sriov.c
@@ -119,11 +119,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev)
 	int i;
 	u32 reg;
 
-	/* Workqueue for PF2VF responses */
-	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
-	if (!pf2vf_resp_wq)
-		return -ENOMEM;
-
 	for (i = 0, vf_info = accel_dev->pf.vf_info; i < totalvfs;
 	     i++, vf_info++) {
 		/* This ptr will be populated when VFs will be created */
@@ -216,11 +211,6 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev)
 
 	kfree(accel_dev->pf.vf_info);
 	accel_dev->pf.vf_info = NULL;
-
-	if (pf2vf_resp_wq) {
-		destroy_workqueue(pf2vf_resp_wq);
-		pf2vf_resp_wq = NULL;
-	}
 }
 EXPORT_SYMBOL_GPL(adf_disable_sriov);
 
@@ -304,3 +294,19 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs)
 	return numvfs;
 }
 EXPORT_SYMBOL_GPL(adf_sriov_configure);
+
+int __init adf_init_pf_wq(void)
+{
+	/* Workqueue for PF2VF responses */
+	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
+
+	return !pf2vf_resp_wq ? -ENOMEM : 0;
+}
+
+void adf_exit_pf_wq(void)
+{
+	if (pf2vf_resp_wq) {
+		destroy_workqueue(pf2vf_resp_wq);
+		pf2vf_resp_wq = NULL;
+	}
+}
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 59e4c3af15ed..367b6661ee04 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -1262,8 +1262,8 @@ static struct crypto_alg qat_algs[] = { {
 			.setkey = qat_alg_ablkcipher_xts_setkey,
 			.decrypt = qat_alg_ablkcipher_decrypt,
 			.encrypt = qat_alg_ablkcipher_encrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
+			.min_keysize = 2 * AES_MIN_KEY_SIZE,
+			.max_keysize = 2 * AES_MAX_KEY_SIZE,
 			.ivsize = AES_BLOCK_SIZE,
 		},
 	},
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index a19ee127edca..e72fea737a0d 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -35,6 +35,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq)
 	unsigned int todo;
 	struct sg_mapping_iter mi, mo;
 	unsigned int oi, oo; /* offset for in and out */
+	unsigned long flags;
 
 	if (areq->nbytes == 0)
 		return 0;
@@ -49,7 +50,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq)
 		return -EINVAL;
 	}
 
-	spin_lock_bh(&ss->slock);
+	spin_lock_irqsave(&ss->slock, flags);
 
 	for (i = 0; i < op->keylen; i += 4)
 		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
@@ -117,7 +118,7 @@ release_ss:
 	sg_miter_stop(&mi);
 	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
-	spin_unlock_bh(&ss->slock);
+	spin_unlock_irqrestore(&ss->slock, flags);
 	return err;
 }
 
@@ -149,6 +150,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 	unsigned int ob = 0;	/* offset in buf */
 	unsigned int obo = 0;	/* offset in bufo*/
 	unsigned int obl = 0;	/* length of data in bufo */
+	unsigned long flags;
 
 	if (areq->nbytes == 0)
 		return 0;
@@ -181,7 +183,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 	if (no_chunk == 1)
 		return sun4i_ss_opti_poll(areq);
 
-	spin_lock_bh(&ss->slock);
+	spin_lock_irqsave(&ss->slock, flags);
 
 	for (i = 0; i < op->keylen; i += 4)
 		writel(*(op->key + i / 4), ss->base + SS_KEY0 + i);
@@ -308,7 +310,7 @@ release_ss:
 	sg_miter_stop(&mi);
 	sg_miter_stop(&mo);
 	writel(0, ss->base + SS_CTL);
-	spin_unlock_bh(&ss->slock);
+	spin_unlock_irqrestore(&ss->slock, flags);
 
 	return err;
 }
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index b6f9f42e2985..6a60936b46e0 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr,
 		ptr->eptr = upper_32_bits(dma_addr);
 }
 
+static void copy_talitos_ptr(struct talitos_ptr *dst_ptr,
+			     struct talitos_ptr *src_ptr, bool is_sec1)
+{
+	dst_ptr->ptr = src_ptr->ptr;
+	if (!is_sec1)
+		dst_ptr->eptr = src_ptr->eptr;
+}
+
 static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len,
 			       bool is_sec1)
 {
@@ -796,7 +804,7 @@ static void talitos_unregister_rng(struct device *dev)
  * crypto alg
  */
 #define TALITOS_CRA_PRIORITY		3000
-#define TALITOS_MAX_KEY_SIZE		96
+#define TALITOS_MAX_KEY_SIZE		(AES_MAX_KEY_SIZE + SHA512_BLOCK_SIZE)
 #define TALITOS_MAX_IV_LENGTH		16 /* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 
 struct talitos_ctx {
@@ -827,6 +835,16 @@ struct talitos_ahash_req_ctx {
 	struct scatterlist *psrc;
 };
 
+struct talitos_export_state {
+	u32 hw_context[TALITOS_MDEU_MAX_CONTEXT_SIZE / sizeof(u32)];
+	u8 buf[HASH_MAX_BLOCK_SIZE];
+	unsigned int swinit;
+	unsigned int first;
+	unsigned int last;
+	unsigned int to_hash_later;
+	unsigned int nbuf;
+};
+
 static int aead_setkey(struct crypto_aead *authenc,
 		       const u8 *key, unsigned int keylen)
 {
@@ -1083,21 +1101,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1,
 			      (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
 							   : DMA_TO_DEVICE);
-
 	/* hmac data */
 	desc->ptr[1].len = cpu_to_be16(areq->assoclen);
 	if (sg_count > 1 &&
 	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0,
 					 areq->assoclen,
 					 &edesc->link_tbl[tbl_off])) > 1) {
-		tbl_off += ret;
-
 		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
 			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
 
 		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
+		tbl_off += ret;
 	} else {
 		to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0);
 		desc->ptr[1].j_extent = 0;
@@ -1126,11 +1143,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
 		sg_link_tbl_len += authsize;
 
-	if (sg_count > 1 &&
-	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen,
-					 sg_link_tbl_len,
-					 &edesc->link_tbl[tbl_off])) > 1) {
-		tbl_off += ret;
+	if (sg_count == 1) {
+		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) +
+			       areq->assoclen, 0);
+	} else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count,
+						areq->assoclen, sg_link_tbl_len,
+						&edesc->link_tbl[tbl_off])) >
+		   1) {
 		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
 		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
 					      tbl_off *
@@ -1138,8 +1157,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 					   edesc->dma_len,
 					   DMA_BIDIRECTIONAL);
-	} else
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0);
+		tbl_off += ret;
+	} else {
+		copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0);
+	}
 
 	/* cipher out */
 	desc->ptr[5].len = cpu_to_be16(cryptlen);
@@ -1151,11 +1172,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	edesc->icv_ool = false;
 
-	if (sg_count > 1 &&
-	    (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count,
+	if (sg_count == 1) {
+		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) +
+			       areq->assoclen, 0);
+	} else if ((sg_count =
+			sg_to_link_tbl_offset(areq->dst, sg_count,
 					      areq->assoclen, cryptlen,
-					      &edesc->link_tbl[tbl_off])) >
-	    1) {
+					      &edesc->link_tbl[tbl_off])) > 1) {
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
@@ -1178,8 +1201,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
 
 		edesc->icv_ool = true;
-	} else
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
+	} else {
+		copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0);
+	}
 
 	/* iv out */
 	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
@@ -1364,6 +1388,11 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 {
 	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
 
+	if (keylen > TALITOS_MAX_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
 	memcpy(&ctx->key, key, keylen);
 	ctx->keylen = keylen;
 
@@ -1940,6 +1969,46 @@ static int ahash_digest(struct ahash_request *areq)
 	return ahash_process_req(areq, areq->nbytes);
 }
 
+static int ahash_export(struct ahash_request *areq, void *out)
+{
+	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct talitos_export_state *export = out;
+
+	memcpy(export->hw_context, req_ctx->hw_context,
+	       req_ctx->hw_context_size);
+	memcpy(export->buf, req_ctx->buf, req_ctx->nbuf);
+	export->swinit = req_ctx->swinit;
+	export->first = req_ctx->first;
+	export->last = req_ctx->last;
+	export->to_hash_later = req_ctx->to_hash_later;
+	export->nbuf = req_ctx->nbuf;
+
+	return 0;
+}
+
+static int ahash_import(struct ahash_request *areq, const void *in)
+{
+	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq);
+	const struct talitos_export_state *export = in;
+
+	memset(req_ctx, 0, sizeof(*req_ctx));
+	req_ctx->hw_context_size =
+		(crypto_ahash_digestsize(tfm) <= SHA256_DIGEST_SIZE)
+			? TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256
+			: TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512;
+	memcpy(req_ctx->hw_context, export->hw_context,
+	       req_ctx->hw_context_size);
+	memcpy(req_ctx->buf, export->buf, export->nbuf);
+	req_ctx->swinit = export->swinit;
+	req_ctx->first = export->first;
+	req_ctx->last = export->last;
+	req_ctx->to_hash_later = export->to_hash_later;
+	req_ctx->nbuf = export->nbuf;
+
+	return 0;
+}
+
 struct keyhash_result {
 	struct completion completion;
 	int err;
@@ -2334,6 +2403,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = MD5_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "md5",
 				.cra_driver_name = "md5-talitos",
@@ -2349,6 +2419,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-talitos",
@@ -2364,6 +2435,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA224_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha224",
 				.cra_driver_name = "sha224-talitos",
@@ -2379,6 +2451,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-talitos",
@@ -2394,6 +2467,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA384_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha384",
 				.cra_driver_name = "sha384-talitos",
@@ -2409,6 +2483,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA512_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "sha512",
 				.cra_driver_name = "sha512-talitos",
@@ -2424,6 +2499,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = MD5_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "hmac-md5-talitos",
@@ -2439,6 +2515,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-talitos",
@@ -2454,6 +2531,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA224_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "hmac-sha224-talitos",
@@ -2469,6 +2547,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-talitos",
@@ -2484,6 +2563,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA384_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha384)",
 				.cra_driver_name = "hmac-sha384-talitos",
@@ -2499,6 +2579,7 @@ static struct talitos_alg_template driver_algs[] = {
 	{	.type = CRYPTO_ALG_TYPE_AHASH,
 		.alg.hash = {
 			.halg.digestsize = SHA512_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct talitos_export_state),
 			.halg.base = {
 				.cra_name = "hmac(sha512)",
 				.cra_driver_name = "hmac-sha512-talitos",
@@ -2519,21 +2600,11 @@ struct talitos_crypto_alg {
 	struct talitos_alg_template algt;
 };
 
-static int talitos_cra_init(struct crypto_tfm *tfm)
+static int talitos_init_common(struct talitos_ctx *ctx,
+			       struct talitos_crypto_alg *talitos_alg)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct talitos_crypto_alg *talitos_alg;
-	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct talitos_private *priv;
 
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH)
-		talitos_alg = container_of(__crypto_ahash_alg(alg),
-					   struct talitos_crypto_alg,
-					   algt.alg.hash);
-	else
-		talitos_alg = container_of(alg, struct talitos_crypto_alg,
-					   algt.alg.crypto);
-
 	/* update context with ptr to dev */
 	ctx->dev = talitos_alg->dev;
 
@@ -2551,10 +2622,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
+static int talitos_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct talitos_crypto_alg *talitos_alg;
+	struct talitos_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH)
+		talitos_alg = container_of(__crypto_ahash_alg(alg),
+					   struct talitos_crypto_alg,
+					   algt.alg.hash);
+	else
+		talitos_alg = container_of(alg, struct talitos_crypto_alg,
+					   algt.alg.crypto);
+
+	return talitos_init_common(ctx, talitos_alg);
+}
+
 static int talitos_cra_init_aead(struct crypto_aead *tfm)
 {
-	talitos_cra_init(crypto_aead_tfm(tfm));
-	return 0;
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct talitos_crypto_alg *talitos_alg;
+	struct talitos_ctx *ctx = crypto_aead_ctx(tfm);
+
+	talitos_alg = container_of(alg, struct talitos_crypto_alg,
+				   algt.alg.aead);
+
+	return talitos_init_common(ctx, talitos_alg);
 }
 
 static int talitos_cra_init_ahash(struct crypto_tfm *tfm)
@@ -2677,6 +2771,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		t_alg->algt.alg.hash.finup = ahash_finup;
 		t_alg->algt.alg.hash.digest = ahash_digest;
 		t_alg->algt.alg.hash.setkey = ahash_setkey;
+		t_alg->algt.alg.hash.import = ahash_import;
+		t_alg->algt.alg.hash.export = ahash_export;
 
 		if (!(priv->features & TALITOS_FTR_HMAC_OK) &&
 		    !strncmp(alg->cra_name, "hmac", 4)) {
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 4c243c1ffc7f..790f7cadc1ed 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1440,9 +1440,9 @@ static int ux500_cryp_probe(struct platform_device *pdev)
 
 	device_data->phybase = res->start;
 	device_data->base = devm_ioremap_resource(dev, res);
-	if (!device_data->base) {
+	if (IS_ERR(device_data->base)) {
 		dev_err(dev, "[%s]: ioremap failed!", __func__);
-		ret = -ENOMEM;
+		ret = PTR_ERR(device_data->base);
 		goto out;
 	}
 
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index f47d112041b2..cd4398498495 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -797,7 +797,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 						&device_data->state);
 				memmove(req_ctx->state.buffer,
 					device_data->state.buffer,
-					HASH_BLOCK_SIZE / sizeof(u32));
+					HASH_BLOCK_SIZE);
 				if (ret) {
 					dev_err(device_data->dev,
 						"%s: hash_resume_state() failed!\n",
@@ -848,7 +848,7 @@ static int hash_process_data(struct hash_device_data *device_data,
 
 			memmove(device_data->state.buffer,
 				req_ctx->state.buffer,
-				HASH_BLOCK_SIZE / sizeof(u32));
+				HASH_BLOCK_SIZE);
 			if (ret) {
 				dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
 					__func__);
@@ -1675,9 +1675,9 @@ static int ux500_hash_probe(struct platform_device *pdev)
 
 	device_data->phybase = res->start;
 	device_data->base = devm_ioremap_resource(dev, res);
-	if (!device_data->base) {
+	if (IS_ERR(device_data->base)) {
 		dev_err(dev, "%s: ioremap() failed!\n", __func__);
-		ret = -ENOMEM;
+		ret = PTR_ERR(device_data->base);
 		goto out;
 	}
 	spin_lock_init(&device_data->ctx_lock);
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 0b8fe2ec5315..3f8bb9a40df1 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = {
 	.cra_name = "cbc(aes)",
 	.cra_driver_name = "p8_aes_cbc",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
@@ -191,7 +191,7 @@ struct crypto_alg p8_aes_cbc_alg = {
 	.cra_init = p8_aes_cbc_init,
 	.cra_exit = p8_aes_cbc_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_cbc_setkey,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index ee1306cd8f59..72f138985e18 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = {
 	.cra_name = "ctr(aes)",
 	.cra_driver_name = "p8_aes_ctr",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
@@ -175,7 +175,7 @@ struct crypto_alg p8_aes_ctr_alg = {
 	.cra_init = p8_aes_ctr_init,
 	.cra_exit = p8_aes_ctr_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_ctr_setkey,
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index 2183a2e77641..9cb3a0b715e2 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -26,16 +26,13 @@
 #include <linux/hardirq.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/ghash.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/hash.h>
 #include <crypto/b128ops.h>
 
 #define IN_INTERRUPT in_interrupt()
 
-#define GHASH_BLOCK_SIZE (16)
-#define GHASH_DIGEST_SIZE (16)
-#define GHASH_KEY_LEN (16)
-
 void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
 void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
 void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
@@ -55,16 +52,11 @@ struct p8_ghash_desc_ctx {
 
 static int p8_ghash_init_tfm(struct crypto_tfm *tfm)
 {
-	const char *alg;
+	const char *alg = "ghash-generic";
 	struct crypto_shash *fallback;
 	struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm);
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!(alg = crypto_tfm_alg_name(tfm))) {
-		printk(KERN_ERR "Failed to get algorithm name.\n");
-		return -ENOENT;
-	}
-
 	fallback = crypto_alloc_shash(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback)) {
 		printk(KERN_ERR
@@ -78,10 +70,18 @@ static int p8_ghash_init_tfm(struct crypto_tfm *tfm)
 	crypto_shash_set_flags(fallback,
 			       crypto_shash_get_flags((struct crypto_shash
 						       *) tfm));
-	ctx->fallback = fallback;
 
-	shash_tfm->descsize = sizeof(struct p8_ghash_desc_ctx)
-	    + crypto_shash_descsize(fallback);
+	/* Check if the descsize defined in the algorithm is still enough. */
+	if (shash_tfm->descsize < sizeof(struct p8_ghash_desc_ctx)
+	    + crypto_shash_descsize(fallback)) {
+		printk(KERN_ERR
+		       "Desc size of the fallback implementation (%s) does not match the expected value: %lu vs %u\n",
+		       alg,
+		       shash_tfm->descsize - sizeof(struct p8_ghash_desc_ctx),
+		       crypto_shash_descsize(fallback));
+		return -EINVAL;
+	}
+	ctx->fallback = fallback;
 
 	return 0;
 }
@@ -113,7 +113,7 @@ static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
 {
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
 
-	if (keylen != GHASH_KEY_LEN)
+	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
 
 	preempt_disable();
@@ -215,7 +215,8 @@ struct shash_alg p8_ghash_alg = {
 	.update = p8_ghash_update,
 	.final = p8_ghash_final,
 	.setkey = p8_ghash_setkey,
-	.descsize = sizeof(struct p8_ghash_desc_ctx),
+	.descsize = sizeof(struct p8_ghash_desc_ctx)
+		+ sizeof(struct ghash_desc_ctx),
 	.base = {
 		 .cra_name = "ghash",
 		 .cra_driver_name = "p8_ghash",
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index b9997335f193..b18e67d0e065 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -139,6 +139,26 @@ my $vmr = sub {
     "	vor	$vx,$vy,$vy";
 };
 
+# Some ABIs specify vrsave, special-purpose register #256, as reserved
+# for system use.
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
+my $mtspr = sub {
+    my ($f,$idx,$ra) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	or	$ra,$ra,$ra";
+    } else {
+	"	mtspr	$idx,$ra";
+    }
+};
+my $mfspr = sub {
+    my ($f,$rd,$idx) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	li	$rd,-1";
+    } else {
+	"	mfspr	$rd,$idx";
+    }
+};
+
 # PowerISA 2.06 stuff
 sub vsxmem_op {
     my ($f, $vrt, $ra, $rb, $op) = @_;
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 02f9aa4ebe05..66c073fc8afc 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -242,7 +242,7 @@ struct at_xdmac_lld {
 	u32		mbr_dus;	/* Destination Microblock Stride Register */
 };
 
-
+/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
 struct at_xdmac_desc {
 	struct at_xdmac_lld		lld;
 	enum dma_transfer_direction	direction;
@@ -253,7 +253,7 @@ struct at_xdmac_desc {
 	unsigned int			xfer_size;
 	struct list_head		descs_list;
 	struct list_head		xfer_node;
-};
+} __aligned(sizeof(u64));
 
 static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
 {
@@ -864,8 +864,12 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DIF(0)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
@@ -1042,8 +1046,12 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * access DDR through both ports (at least on SAMA5D4x), so we can use
 	 * the same interface for source and dest, that solves the fact we
 	 * don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_INCREMENTED_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1144,8 +1152,12 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_UBS_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1183,8 +1195,8 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_da=%pad, mbr_ds=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, &desc->lld.mbr_da, &desc->lld.mbr_ds, desc->lld.mbr_ubc,
+		"%s: lld: mbr_da=%pad, mbr_ds=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_da, desc->lld.mbr_ds, desc->lld.mbr_ubc,
 		desc->lld.mbr_cfg);
 
 	return desc;
@@ -1388,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
+	bool			initd;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -1412,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	residue = desc->xfer_size;
 	/*
 	 * Flush FIFO: only relevant when the transfer is source peripheral
-	 * synchronized.
+	 * synchronized. Flush is needed before reading CUBC because data in
+	 * the FIFO are not reported by CUBC. Reporting a residue of the
+	 * transfer length while we have data in FIFO can cause issue.
+	 * Usecase: atmel USART has a timeout which means I have received
+	 * characters but there is no more character received for a while. On
+	 * timeout, it requests the residue. If the data are in the DMA FIFO,
+	 * we will return a residue of the transfer length. It means no data
+	 * received. If an application is waiting for these data, it will hang
+	 * since we won't have another USART timeout without receiving new
+	 * data.
 	 */
 	mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
 	value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
@@ -1423,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
-	 * When processing the residue, we need to read two registers but we
-	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
-	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
-	 * to know how many data are remaining for the current descriptor.
-	 * Since the dma channel is not paused to not loose data, between the
-	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
-	 * descriptor.
-	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
-	 * still using the same descriptor by reading a second time
-	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
-	 * read again AT_XDMAC_CUBC.
+	 * The easiest way to compute the residue should be to pause the DMA
+	 * but doing this can lead to miss some data as some devices don't
+	 * have FIFO.
+	 * We need to read several registers because:
+	 * - DMA is running therefore a descriptor change is possible while
+	 * reading these registers
+	 * - When the block transfer is done, the value of the CUBC register
+	 * is set to its initial value until the fetch of the next descriptor.
+	 * This value will corrupt the residue calculation so we have to skip
+	 * it.
+	 *
+	 * INITD --------                    ------------
+	 *              |____________________|
+	 *       _______________________  _______________
+	 * NDA       @desc2             \/   @desc3
+	 *       _______________________/\_______________
+	 *       __________  ___________  _______________
+	 * CUBC       0    \/ MAX desc1 \/  MAX desc2
+	 *       __________/\___________/\_______________
+	 *
+	 * Since descriptors are aligned on 64 bits, we can assume that
+	 * the update of NDA and CUBC is atomic.
 	 * Memory barriers are used to ensure the read order of the registers.
-	 * A max number of retries is set because unlikely it can never ends if
-	 * we are transferring a lot of data with small buffers.
+	 * A max number of retries is set because unlikely it could never ends.
 	 */
-	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-	rmb();
-	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
 	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
-		rmb();
 		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
-
-		if (likely(cur_nda == check_nda))
-			break;
-
-		cur_nda = check_nda;
+		rmb();
+		initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
 		rmb();
 		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+		rmb();
+		cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+		rmb();
+
+		if ((check_nda == cur_nda) && initd)
+			break;
 	}
 
 	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
@@ -1459,6 +1490,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 
 	/*
+	 * Flush FIFO: only relevant when the transfer is source peripheral
+	 * synchronized. Another flush is needed here because CUBC is updated
+	 * when the controller sends the data write command. It can lead to
+	 * report data that are not written in the memory or the device. The
+	 * FIFO flush ensures that data are really written.
+	 */
+	if ((desc->lld.mbr_cfg & mask) == value) {
+		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+			cpu_relax();
+	}
+
+	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
 	 * microblock.
@@ -2023,7 +2067,7 @@ err_dma_unregister:
 err_clk_disable:
 	clk_disable_unprepare(atxdmac->clk);
 err_free_irq:
-	free_irq(atxdmac->irq, atxdmac->dma.dev);
+	free_irq(atxdmac->irq, atxdmac);
 	return ret;
 }
 
@@ -2039,7 +2083,7 @@ static int at_xdmac_remove(struct platform_device *pdev)
 
 	synchronize_irq(atxdmac->irq);
 
-	free_irq(atxdmac->irq, atxdmac->dma.dev);
+	free_irq(atxdmac->irq, atxdmac);
 
 	for (i = 0; i < atxdmac->dma.chancnt; i++) {
 		struct at_xdmac_chan *atchan = &atxdmac->chan[i];
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 4f099ea29f83..c66133b5e852 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -130,26 +130,14 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
 	u32 cfghi = DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 
 	if (dwc->initialized == true)
 		return;
 
-	if (dws) {
-		/*
-		 * We need controller-specific data to set up slave
-		 * transfers.
-		 */
-		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
-
-		cfghi |= DWC_CFGH_DST_PER(dws->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dws->src_id);
-	} else {
-		cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
-	}
+	cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
 
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
@@ -936,7 +924,7 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 	struct dw_dma_slave *dws = param;
 
-	if (!dws || dws->dma_dev != chan->device->dev)
+	if (dws->dma_dev != chan->device->dev)
 		return false;
 
 	/* We have to copy data since dws can be temporary storage */
@@ -1160,6 +1148,14 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
+	/*
+	 * We need controller-specific data to set up slave transfers.
+	 */
+	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
+		return -EINVAL;
+	}
+
 	/* Enable controller here if needed */
 	if (!dw->in_use)
 		dw_dma_on(dw);
@@ -1221,6 +1217,14 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	spin_lock_irqsave(&dwc->lock, flags);
 	list_splice_init(&dwc->free_list, &list);
 	dwc->descs_allocated = 0;
+
+	/* Clear custom channel configuration */
+	dwc->src_id = 0;
+	dwc->dst_id = 0;
+
+	dwc->src_master = 0;
+	dwc->dst_master = 0;
+
 	dwc->initialized = false;
 
 	/* Disable interrupts */
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 57ff46284f15..c97336a2ba92 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -325,6 +325,8 @@ static int m2p_hw_setup(struct ep93xx_dma_chan *edmac)
 		| M2P_CONTROL_ENABLE;
 	m2p_set_control(edmac, control);
 
+	edmac->buffer = 0;
+
 	return 0;
 }
 
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 823ad728aecf..efc02b98e6ba 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -135,7 +135,7 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc)
 	sr = hsu_chan_readl(hsuc, HSU_CH_SR);
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 
-	return sr;
+	return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY);
 }
 
 irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr)
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index f06579c6d548..26da2865b025 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -41,6 +41,9 @@
 #define HSU_CH_SR_DESCTO(x)	BIT(8 + (x))
 #define HSU_CH_SR_DESCTO_ANY	(BIT(11) | BIT(10) | BIT(9) | BIT(8))
 #define HSU_CH_SR_CHE		BIT(15)
+#define HSU_CH_SR_DESCE(x)	BIT(16 + (x))
+#define HSU_CH_SR_DESCE_ANY	(BIT(19) | BIT(18) | BIT(17) | BIT(16))
+#define HSU_CH_SR_CDESC_ANY	(BIT(31) | BIT(30))
 
 /* Bits in HSU_CH_CR */
 #define HSU_CH_CR_CHA		BIT(0)
diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h
index 690e3b4f8202..b36da3c1073f 100644
--- a/drivers/dma/ioat/hw.h
+++ b/drivers/dma/ioat/hw.h
@@ -64,6 +64,8 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX8	0x6f2e
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX9	0x6f2f
 
+#define PCI_DEVICE_ID_INTEL_IOAT_SKX	0x2021
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 4ef0c5e07912..abb75ebd65ea 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -105,6 +105,8 @@ static struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) },
+
 	/* I/OAT v3.3 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
@@ -250,10 +252,15 @@ static bool is_bdx_ioat(struct pci_dev *pdev)
 	}
 }
 
+static inline bool is_skx_ioat(struct pci_dev *pdev)
+{
+	return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false;
+}
+
 static bool is_xeon_cb32(struct pci_dev *pdev)
 {
 	return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
-		is_hsw_ioat(pdev) || is_bdx_ioat(pdev);
+		is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev);
 }
 
 bool is_bwd_ioat(struct pci_dev *pdev)
@@ -1350,6 +1357,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
 	if (device->version >= IOAT_VER_3_0) {
+		if (is_skx_ioat(pdev))
+			device->version = IOAT_VER_3_2;
 		err = ioat3_dma_probe(device, ioat_dca_enabled);
 
 		if (device->version >= IOAT_VER_3_3)
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 2bf37e68ad0f..284627806b88 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -272,7 +272,7 @@ static void ipu_irq_handler(struct irq_desc *desc)
 	u32 status;
 	int i, line;
 
-	for (i = IPU_IRQ_NR_FN_BANKS; i < IPU_IRQ_NR_BANKS; i++) {
+	for (i = 0; i < IPU_IRQ_NR_BANKS; i++) {
 		struct ipu_irq_bank *bank = irq_bank + i;
 
 		raw_spin_lock(&bank_lock);
@@ -286,22 +286,21 @@ static void ipu_irq_handler(struct irq_desc *desc)
 		raw_spin_unlock(&bank_lock);
 		while ((line = ffs(status))) {
 			struct ipu_irq_map *map;
-			unsigned int irq = NO_IRQ;
+			unsigned int irq;
 
 			line--;
 			status &= ~(1UL << line);
 
 			raw_spin_lock(&bank_lock);
 			map = src2map(32 * i + line);
-			if (map)
-				irq = map->irq;
-			raw_spin_unlock(&bank_lock);
-
 			if (!map) {
+				raw_spin_unlock(&bank_lock);
 				pr_err("IPU: Interrupt on unmapped source %u bank %d\n",
 				       line, i);
 				continue;
 			}
+			irq = map->irq;
+			raw_spin_unlock(&bank_lock);
 			generic_handle_irq(irq);
 		}
 	}
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 17ee758b419f..8250950aab8b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -445,6 +445,9 @@ struct dma_pl330_chan {
 
 	/* for cyclic capability */
 	bool cyclic;
+
+	/* for runtime pm tracking */
+	bool active;
 };
 
 struct pl330_dmac {
@@ -1994,6 +1997,7 @@ static void pl330_tasklet(unsigned long data)
 		_stop(pch->thread);
 		spin_unlock(&pch->thread->dmac->lock);
 		power_down = true;
+		pch->active = false;
 	} else {
 		/* Make sure the PL330 Channel thread is active */
 		spin_lock(&pch->thread->dmac->lock);
@@ -2015,6 +2019,7 @@ static void pl330_tasklet(unsigned long data)
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
 			if (power_down) {
+				pch->active = true;
 				spin_lock(&pch->thread->dmac->lock);
 				_start(pch->thread);
 				spin_unlock(&pch->thread->dmac->lock);
@@ -2129,6 +2134,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
+	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
@@ -2139,6 +2145,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	power_down = pch->active;
+	pch->active = false;
 
 	/* Mark all desc done */
 	list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2156,6 +2164,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	if (power_down)
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
@@ -2302,6 +2312,7 @@ static void pl330_issue_pending(struct dma_chan *chan)
 		 * updated on work_list emptiness status.
 		 */
 		WARN_ON(list_empty(&pch->submitted_list));
+		pch->active = true;
 		pm_runtime_get_sync(pch->dmac->ddma.dev);
 	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index a59061e4221a..55f5d33f6dc7 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -122,6 +122,7 @@ struct pxad_chan {
 struct pxad_device {
 	struct dma_device		slave;
 	int				nr_chans;
+	int				nr_requestors;
 	void __iomem			*base;
 	struct pxad_phy			*phys;
 	spinlock_t			phy_lock;	/* Phy association */
@@ -473,7 +474,7 @@ static void pxad_free_phy(struct pxad_chan *chan)
 		return;
 
 	/* clear the channel mapping in DRCMR */
-	if (chan->drcmr <= DRCMR_CHLNUM) {
+	if (chan->drcmr <= pdev->nr_requestors) {
 		reg = pxad_drcmr(chan->drcmr);
 		writel_relaxed(0, chan->phy->base + reg);
 	}
@@ -509,6 +510,7 @@ static bool is_running_chan_misaligned(struct pxad_chan *chan)
 
 static void phy_enable(struct pxad_phy *phy, bool misaligned)
 {
+	struct pxad_device *pdev;
 	u32 reg, dalgn;
 
 	if (!phy->vchan)
@@ -518,7 +520,8 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned)
 		"%s(); phy=%p(%d) misaligned=%d\n", __func__,
 		phy, phy->idx, misaligned);
 
-	if (phy->vchan->drcmr <= DRCMR_CHLNUM) {
+	pdev = to_pxad_dev(phy->vchan->vc.chan.device);
+	if (phy->vchan->drcmr <= pdev->nr_requestors) {
 		reg = pxad_drcmr(phy->vchan->drcmr);
 		writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
 	}
@@ -914,6 +917,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 {
 	u32 maxburst = 0, dev_addr = 0;
 	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	struct pxad_device *pdev = to_pxad_dev(chan->vc.chan.device);
 
 	*dcmd = 0;
 	if (dir == DMA_DEV_TO_MEM) {
@@ -922,7 +926,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 		dev_addr = chan->cfg.src_addr;
 		*dev_src = dev_addr;
 		*dcmd |= PXA_DCMD_INCTRGADDR;
-		if (chan->drcmr <= DRCMR_CHLNUM)
+		if (chan->drcmr <= pdev->nr_requestors)
 			*dcmd |= PXA_DCMD_FLOWSRC;
 	}
 	if (dir == DMA_MEM_TO_DEV) {
@@ -931,7 +935,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 		dev_addr = chan->cfg.dst_addr;
 		*dev_dst = dev_addr;
 		*dcmd |= PXA_DCMD_INCSRCADDR;
-		if (chan->drcmr <= DRCMR_CHLNUM)
+		if (chan->drcmr <= pdev->nr_requestors)
 			*dcmd |= PXA_DCMD_FLOWTRG;
 	}
 	if (dir == DMA_MEM_TO_MEM)
@@ -1341,13 +1345,15 @@ static struct dma_chan *pxad_dma_xlate(struct of_phandle_args *dma_spec,
 
 static int pxad_init_dmadev(struct platform_device *op,
 			    struct pxad_device *pdev,
-			    unsigned int nr_phy_chans)
+			    unsigned int nr_phy_chans,
+			    unsigned int nr_requestors)
 {
 	int ret;
 	unsigned int i;
 	struct pxad_chan *c;
 
 	pdev->nr_chans = nr_phy_chans;
+	pdev->nr_requestors = nr_requestors;
 	INIT_LIST_HEAD(&pdev->slave.channels);
 	pdev->slave.device_alloc_chan_resources = pxad_alloc_chan_resources;
 	pdev->slave.device_free_chan_resources = pxad_free_chan_resources;
@@ -1382,7 +1388,7 @@ static int pxad_probe(struct platform_device *op)
 	const struct of_device_id *of_id;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
 	struct resource *iores;
-	int ret, dma_channels = 0;
+	int ret, dma_channels = 0, nb_requestors = 0;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
 		DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1399,13 +1405,23 @@ static int pxad_probe(struct platform_device *op)
 		return PTR_ERR(pdev->base);
 
 	of_id = of_match_device(pxad_dt_ids, &op->dev);
-	if (of_id)
+	if (of_id) {
 		of_property_read_u32(op->dev.of_node, "#dma-channels",
 				     &dma_channels);
-	else if (pdata && pdata->dma_channels)
+		ret = of_property_read_u32(op->dev.of_node, "#dma-requests",
+					   &nb_requestors);
+		if (ret) {
+			dev_warn(pdev->slave.dev,
+				 "#dma-requests set to default 32 as missing in OF: %d",
+				 ret);
+			nb_requestors = 32;
+		};
+	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
-	else
+		nb_requestors = pdata->nb_requestors;
+	} else {
 		dma_channels = 32;	/* default 32 channel */
+	}
 
 	dma_cap_set(DMA_SLAVE, pdev->slave.cap_mask);
 	dma_cap_set(DMA_MEMCPY, pdev->slave.cap_mask);
@@ -1422,7 +1438,7 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
 	pdev->slave.dev = &op->dev;
-	ret = pxad_init_dmadev(op, pdev, dma_channels);
+	ret = pxad_init_dmadev(op, pdev, dma_channels, nb_requestors);
 	if (ret) {
 		dev_err(pdev->slave.dev, "unable to register\n");
 		return ret;
@@ -1441,7 +1457,8 @@ static int pxad_probe(struct platform_device *op)
 
 	platform_set_drvdata(op, pdev);
 	pxad_init_debugfs(pdev);
-	dev_info(pdev->slave.dev, "initialized %d channels\n", dma_channels);
+	dev_info(pdev->slave.dev, "initialized %d channels on %d requestors\n",
+		 dma_channels, nb_requestors);
 	return 0;
 }
 
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index f1bcc2a163b3..56410ea75ac5 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -117,7 +117,7 @@ struct usb_dmac {
 #define USB_DMASWR			0x0008
 #define USB_DMASWR_SWR			(1 << 0)
 #define USB_DMAOR			0x0060
-#define USB_DMAOR_AE			(1 << 2)
+#define USB_DMAOR_AE			(1 << 1)
 #define USB_DMAOR_DME			(1 << 0)
 
 #define USB_DMASAR			0x0000
@@ -600,27 +600,30 @@ static irqreturn_t usb_dmac_isr_channel(int irq, void *dev)
 {
 	struct usb_dmac_chan *chan = dev;
 	irqreturn_t ret = IRQ_NONE;
-	u32 mask = USB_DMACHCR_TE;
-	u32 check_bits = USB_DMACHCR_TE | USB_DMACHCR_SP;
+	u32 mask = 0;
 	u32 chcr;
+	bool xfer_end = false;
 
 	spin_lock(&chan->vc.lock);
 
 	chcr = usb_dmac_chan_read(chan, USB_DMACHCR);
-	if (chcr & check_bits)
-		mask |= USB_DMACHCR_DE | check_bits;
+	if (chcr & (USB_DMACHCR_TE | USB_DMACHCR_SP)) {
+		mask |= USB_DMACHCR_DE | USB_DMACHCR_TE | USB_DMACHCR_SP;
+		if (chcr & USB_DMACHCR_DE)
+			xfer_end = true;
+		ret |= IRQ_HANDLED;
+	}
 	if (chcr & USB_DMACHCR_NULL) {
 		/* An interruption of TE will happen after we set FTE */
 		mask |= USB_DMACHCR_NULL;
 		chcr |= USB_DMACHCR_FTE;
 		ret |= IRQ_HANDLED;
 	}
-	usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask);
+	if (mask)
+		usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask);
 
-	if (chcr & check_bits) {
+	if (xfer_end)
 		usb_dmac_isr_transfer_end(chan);
-		ret |= IRQ_HANDLED;
-	}
 
 	spin_unlock(&chan->vc.lock);
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index a415edbe61b1..149ec2bd9bc6 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -146,6 +146,7 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_am335x_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}
 
@@ -310,6 +311,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_dra7_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}
 
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 9eee13ef83a5..d87a47547ba5 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1452,7 +1452,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range,
 	u64 chan_off;
 	u64 dram_base		= get_dram_base(pvt, range);
 	u64 hole_off		= f10_dhar_offset(pvt);
-	u64 dct_sel_base_off	= (pvt->dct_sel_hi & 0xFFFFFC00) << 16;
+	u64 dct_sel_base_off	= (u64)(pvt->dct_sel_hi & 0xFFFFFC00) << 16;
 
 	if (hi_rng) {
 		/*
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 1b2c2187b347..dc68394da682 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -966,7 +966,7 @@ static void edac_inc_ue_error(struct mem_ctl_info *mci,
 	mci->ue_mc += count;
 
 	if (!enable_per_layer_report) {
-		mci->ce_noinfo_count += count;
+		mci->ue_noinfo_count += count;
 		return;
 	}
 
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 58aed67b7eba..3c8f19f5ac81 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -313,7 +313,6 @@ static struct device_type csrow_attr_type = {
  * possible dynamic channel DIMM Label attribute files
  *
  */
-
 DEVICE_CHANNEL(ch0_dimm_label, S_IRUGO | S_IWUSR,
 	channel_dimm_label_show, channel_dimm_label_store, 0);
 DEVICE_CHANNEL(ch1_dimm_label, S_IRUGO | S_IWUSR,
@@ -326,6 +325,10 @@ DEVICE_CHANNEL(ch4_dimm_label, S_IRUGO | S_IWUSR,
 	channel_dimm_label_show, channel_dimm_label_store, 4);
 DEVICE_CHANNEL(ch5_dimm_label, S_IRUGO | S_IWUSR,
 	channel_dimm_label_show, channel_dimm_label_store, 5);
+DEVICE_CHANNEL(ch6_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 6);
+DEVICE_CHANNEL(ch7_dimm_label, S_IRUGO | S_IWUSR,
+	channel_dimm_label_show, channel_dimm_label_store, 7);
 
 /* Total possible dynamic DIMM Label attribute file table */
 static struct attribute *dynamic_csrow_dimm_attr[] = {
@@ -335,6 +338,8 @@ static struct attribute *dynamic_csrow_dimm_attr[] = {
 	&dev_attr_legacy_ch3_dimm_label.attr.attr,
 	&dev_attr_legacy_ch4_dimm_label.attr.attr,
 	&dev_attr_legacy_ch5_dimm_label.attr.attr,
+	&dev_attr_legacy_ch6_dimm_label.attr.attr,
+	&dev_attr_legacy_ch7_dimm_label.attr.attr,
 	NULL
 };
 
@@ -351,6 +356,10 @@ DEVICE_CHANNEL(ch4_ce_count, S_IRUGO,
 		   channel_ce_count_show, NULL, 4);
 DEVICE_CHANNEL(ch5_ce_count, S_IRUGO,
 		   channel_ce_count_show, NULL, 5);
+DEVICE_CHANNEL(ch6_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 6);
+DEVICE_CHANNEL(ch7_ce_count, S_IRUGO,
+		   channel_ce_count_show, NULL, 7);
 
 /* Total possible dynamic ce_count attribute file table */
 static struct attribute *dynamic_csrow_ce_count_attr[] = {
@@ -360,6 +369,8 @@ static struct attribute *dynamic_csrow_ce_count_attr[] = {
 	&dev_attr_legacy_ch3_ce_count.attr.attr,
 	&dev_attr_legacy_ch4_ce_count.attr.attr,
 	&dev_attr_legacy_ch5_ce_count.attr.attr,
+	&dev_attr_legacy_ch6_ce_count.attr.attr,
+	&dev_attr_legacy_ch7_ce_count.attr.attr,
 	NULL
 };
 
@@ -371,9 +382,16 @@ static umode_t csrow_dev_is_visible(struct kobject *kobj,
 
 	if (idx >= csrow->nr_channels)
 		return 0;
+
+	if (idx >= ARRAY_SIZE(dynamic_csrow_ce_count_attr) - 1) {
+		WARN_ONCE(1, "idx: %d\n", idx);
+		return 0;
+	}
+
 	/* Only expose populated DIMMs */
 	if (!csrow->channels[idx]->dimm->nr_pages)
 		return 0;
+
 	return attr->mode;
 }
 
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 01087a38da22..792bdae2b91d 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	i7_dev = get_i7core_dev(mce->socketid);
 	if (!i7_dev)
-		return NOTIFY_BAD;
+		return NOTIFY_DONE;
 
 	mci = i7_dev->mci;
 	pvt = mci->pvt_info;
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 429309c62699..ca64b174f8a3 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -218,8 +218,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = {
 	{ 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc },
 };
 
-#define RIR_RNK_TGT(reg)		GET_BITFIELD(reg, 16, 19)
-#define RIR_OFFSET(reg)		GET_BITFIELD(reg,  2, 14)
+#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \
+	GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19))
+
+#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \
+	GET_BITFIELD(reg,  2, 15) : GET_BITFIELD(reg,  2, 14))
 
 /* Device 16, functions 2-7 */
 
@@ -1117,8 +1120,8 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 		edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
 			 n_tads, gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
-			 (u32)TAD_SOCK(reg),
-			 (u32)TAD_CH(reg),
+			 (u32)(1 << TAD_SOCK(reg)),
+			 (u32)TAD_CH(reg) + 1,
 			 (u32)TAD_TGT0(reg),
 			 (u32)TAD_TGT1(reg),
 			 (u32)TAD_TGT2(reg),
@@ -1175,14 +1178,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 				pci_read_config_dword(pvt->pci_tad[i],
 						      rir_offset[j][k],
 						      &reg);
-				tmp_mb = RIR_OFFSET(reg) << 6;
+				tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6;
 
 				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
 					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
-					 (u32)RIR_RNK_TGT(reg),
+					 (u32)RIR_RNK_TGT(pvt->info.type, reg),
 					 reg);
 			}
 		}
@@ -1396,7 +1399,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	}
 
 	ch_way = TAD_CH(reg) + 1;
-	sck_way = TAD_SOCK(reg) + 1;
+	sck_way = TAD_SOCK(reg);
 
 	if (ch_way == 3)
 		idx = addr >> 6;
@@ -1435,7 +1438,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 		switch(ch_way) {
 		case 2:
 		case 4:
-			sck_xch = 1 << sck_way * (ch_way >> 1);
+			sck_xch = (1 << sck_way) * (ch_way >> 1);
 			break;
 		default:
 			sprintf(msg, "Invalid mirror set. Can't decode addr");
@@ -1453,7 +1456,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 		 n_tads,
 		 addr,
 		 limit,
-		 (u32)TAD_SOCK(reg),
+		 sck_way,
 		 ch_way,
 		 offset,
 		 idx,
@@ -1468,18 +1471,12 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			offset, addr);
 		return -EINVAL;
 	}
-	addr -= offset;
-	/* Store the low bits [0:6] of the addr */
-	ch_addr = addr & 0x7f;
-	/* Remove socket wayness and remove 6 bits */
-	addr >>= 6;
-	addr = div_u64(addr, sck_xch);
-#if 0
-	/* Divide by channel way */
-	addr = addr / ch_way;
-#endif
-	/* Recover the last 6 bits */
-	ch_addr |= addr << 6;
+
+	ch_addr = addr - offset;
+	ch_addr >>= (6 + shiftup);
+	ch_addr /= sck_xch;
+	ch_addr <<= (6 + shiftup);
+	ch_addr |= addr & ((1 << (6 + shiftup)) - 1);
 
 	/*
 	 * Step 3) Decode rank
@@ -1518,7 +1515,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	pci_read_config_dword(pvt->pci_tad[ch_add + base_ch],
 			      rir_offset[n_rir][idx],
 			      &reg);
-	*rank = RIR_RNK_TGT(reg);
+	*rank = RIR_RNK_TGT(pvt->info.type, reg);
 
 	edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
 		 n_rir,
@@ -2260,7 +2257,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	mci = get_mci_for_node_id(mce->socketid);
 	if (!mci)
-		return NOTIFY_BAD;
+		return NOTIFY_DONE;
 	pvt = mci->pvt_info;
 
 	/*
diff --git a/drivers/extcon/extcon-max77843.c b/drivers/extcon/extcon-max77843.c
index 9f9ea334399c..b6cb30d207be 100644
--- a/drivers/extcon/extcon-max77843.c
+++ b/drivers/extcon/extcon-max77843.c
@@ -803,7 +803,7 @@ static int max77843_muic_probe(struct platform_device *pdev)
 	/* Clear IRQ bits before request IRQs */
 	ret = regmap_bulk_read(max77843->regmap_muic,
 			MAX77843_MUIC_REG_INT1, info->status,
-			MAX77843_MUIC_IRQ_NUM);
+			MAX77843_MUIC_STATUS_NUM);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to Clear IRQ bits\n");
 		goto err_muic_irq;
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index f4ea80d602f7..b9d2f76a0cf7 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -73,13 +73,13 @@ struct rfc2734_header {
 
 #define fwnet_get_hdr_lf(h)		(((h)->w0 & 0xc0000000) >> 30)
 #define fwnet_get_hdr_ether_type(h)	(((h)->w0 & 0x0000ffff))
-#define fwnet_get_hdr_dg_size(h)	(((h)->w0 & 0x0fff0000) >> 16)
+#define fwnet_get_hdr_dg_size(h)	((((h)->w0 & 0x0fff0000) >> 16) + 1)
 #define fwnet_get_hdr_fg_off(h)		(((h)->w0 & 0x00000fff))
 #define fwnet_get_hdr_dgl(h)		(((h)->w1 & 0xffff0000) >> 16)
 
-#define fwnet_set_hdr_lf(lf)		((lf)  << 30)
+#define fwnet_set_hdr_lf(lf)		((lf) << 30)
 #define fwnet_set_hdr_ether_type(et)	(et)
-#define fwnet_set_hdr_dg_size(dgs)	((dgs) << 16)
+#define fwnet_set_hdr_dg_size(dgs)	(((dgs) - 1) << 16)
 #define fwnet_set_hdr_fg_off(fgo)	(fgo)
 
 #define fwnet_set_hdr_dgl(dgl)		((dgl) << 16)
@@ -578,6 +578,9 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 	int retval;
 	u16 ether_type;
 
+	if (len <= RFC2374_UNFRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w0 = be32_to_cpu(buf[0]);
 	lf = fwnet_get_hdr_lf(&hdr);
 	if (lf == RFC2374_HDR_UNFRAG) {
@@ -602,7 +605,12 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		return fwnet_finish_incoming_packet(net, skb, source_node_id,
 						    is_broadcast, ether_type);
 	}
+
 	/* A datagram fragment has been received, now the fun begins. */
+
+	if (len <= RFC2374_FRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w1 = ntohl(buf[1]);
 	buf += 2;
 	len -= RFC2374_FRAG_HDR_SIZE;
@@ -614,7 +622,10 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		fg_off = fwnet_get_hdr_fg_off(&hdr);
 	}
 	datagram_label = fwnet_get_hdr_dgl(&hdr);
-	dg_size = fwnet_get_hdr_dg_size(&hdr); /* ??? + 1 */
+	dg_size = fwnet_get_hdr_dg_size(&hdr);
+
+	if (fg_off + len > dg_size)
+		return 0;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
@@ -722,6 +733,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r,
 	fw_send_response(card, r, rcode);
 }
 
+static int gasp_source_id(__be32 *p)
+{
+	return be32_to_cpu(p[0]) >> 16;
+}
+
+static u32 gasp_specifier_id(__be32 *p)
+{
+	return (be32_to_cpu(p[0]) & 0xffff) << 8 |
+	       (be32_to_cpu(p[1]) & 0xff000000) >> 24;
+}
+
+static u32 gasp_version(__be32 *p)
+{
+	return be32_to_cpu(p[1]) & 0xffffff;
+}
+
 static void fwnet_receive_broadcast(struct fw_iso_context *context,
 		u32 cycle, size_t header_length, void *header, void *data)
 {
@@ -731,9 +758,6 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
 	__be32 *buf_ptr;
 	int retval;
 	u32 length;
-	u16 source_node_id;
-	u32 specifier_id;
-	u32 ver;
 	unsigned long offset;
 	unsigned long flags;
 
@@ -750,22 +774,17 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
 
 	spin_unlock_irqrestore(&dev->lock, flags);
 
-	specifier_id =    (be32_to_cpu(buf_ptr[0]) & 0xffff) << 8
-			| (be32_to_cpu(buf_ptr[1]) & 0xff000000) >> 24;
-	ver = be32_to_cpu(buf_ptr[1]) & 0xffffff;
-	source_node_id = be32_to_cpu(buf_ptr[0]) >> 16;
-
-	if (specifier_id == IANA_SPECIFIER_ID &&
-	    (ver == RFC2734_SW_VERSION
+	if (length > IEEE1394_GASP_HDR_SIZE &&
+	    gasp_specifier_id(buf_ptr) == IANA_SPECIFIER_ID &&
+	    (gasp_version(buf_ptr) == RFC2734_SW_VERSION
 #if IS_ENABLED(CONFIG_IPV6)
-	     || ver == RFC3146_SW_VERSION
+	     || gasp_version(buf_ptr) == RFC3146_SW_VERSION
 #endif
-	    )) {
-		buf_ptr += 2;
-		length -= IEEE1394_GASP_HDR_SIZE;
-		fwnet_incoming_packet(dev, buf_ptr, length, source_node_id,
+	    ))
+		fwnet_incoming_packet(dev, buf_ptr + 2,
+				      length - IEEE1394_GASP_HDR_SIZE,
+				      gasp_source_id(buf_ptr),
 				      context->card->generation, true);
-	}
 
 	packet.payload_length = dev->rcv_buffer_size;
 	packet.interrupt = 1;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 027ca212179f..3b52677f459a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -180,6 +180,7 @@ static int generic_ops_register(void)
 {
 	generic_ops.get_variable = efi.get_variable;
 	generic_ops.set_variable = efi.set_variable;
+	generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
 	generic_ops.get_next_variable = efi.get_next_variable;
 	generic_ops.query_variable_store = efi_query_variable_store;
 
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 7f2ea21c730d..6f182fd91a6d 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -202,29 +202,44 @@ static const struct variable_validate variable_validate[] = {
 	{ NULL_GUID, "", NULL },
 };
 
+/*
+ * Check if @var_name matches the pattern given in @match_name.
+ *
+ * @var_name: an array of @len non-NUL characters.
+ * @match_name: a NUL-terminated pattern string, optionally ending in "*". A
+ *              final "*" character matches any trailing characters @var_name,
+ *              including the case when there are none left in @var_name.
+ * @match: on output, the number of non-wildcard characters in @match_name
+ *         that @var_name matches, regardless of the return value.
+ * @return: whether @var_name fully matches @match_name.
+ */
 static bool
 variable_matches(const char *var_name, size_t len, const char *match_name,
 		 int *match)
 {
 	for (*match = 0; ; (*match)++) {
 		char c = match_name[*match];
-		char u = var_name[*match];
 
-		/* Wildcard in the matching name means we've matched */
-		if (c == '*')
+		switch (c) {
+		case '*':
+			/* Wildcard in @match_name means we've matched. */
 			return true;
 
-		/* Case sensitive match */
-		if (!c && *match == len)
-			return true;
+		case '\0':
+			/* @match_name has ended. Has @var_name too? */
+			return (*match == len);
 
-		if (c != u)
+		default:
+			/*
+			 * We've reached a non-wildcard char in @match_name.
+			 * Continue only if there's an identical character in
+			 * @var_name.
+			 */
+			if (*match < len && c == var_name[*match])
+				continue;
 			return false;
-
-		if (!c)
-			return true;
+		}
 	}
-	return true;
 }
 
 bool
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b18bea08ff25..469dc378adeb 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -50,6 +50,7 @@ config GPIO_DEVRES
 config OF_GPIO
 	def_bool y
 	depends on OF
+	depends on HAS_IOMEM
 
 config GPIO_ACPI
 	def_bool y
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 33a1f9779b86..4ea71d505bce 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -551,11 +551,11 @@ static void bcm_kona_gpio_reset(struct bcm_kona_gpio *kona_gpio)
 	/* disable interrupts and clear status */
 	for (i = 0; i < kona_gpio->num_bank; i++) {
 		/* Unlock the entire bank first */
-		bcm_kona_gpio_write_lock_regs(kona_gpio, i, UNLOCK_CODE);
+		bcm_kona_gpio_write_lock_regs(reg_base, i, UNLOCK_CODE);
 		writel(0xffffffff, reg_base + GPIO_INT_MASK(i));
 		writel(0xffffffff, reg_base + GPIO_INT_STATUS(i));
 		/* Now re-lock the bank */
-		bcm_kona_gpio_write_lock_regs(kona_gpio, i, LOCK_CODE);
+		bcm_kona_gpio_write_lock_regs(reg_base, i, LOCK_CODE);
 	}
 }
 
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index 70097472b02c..c50e930d97d3 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -17,7 +17,6 @@
  * Moorestown platform Langwell chip.
  * Medfield platform Penwell chip.
  * Clovertrail platform Cloverview chip.
- * Merrifield platform Tangier chip.
  */
 
 #include <linux/module.h>
@@ -64,10 +63,6 @@ enum GPIO_REG {
 /* intel_mid gpio driver data */
 struct intel_mid_gpio_ddata {
 	u16 ngpio;		/* number of gpio pins */
-	u32 gplr_offset;	/* offset of first GPLR register from base */
-	u32 flis_base;		/* base address of FLIS registers */
-	u32 flis_len;		/* length of FLIS registers */
-	u32 (*get_flis_offset)(int gpio);
 	u32 chip_irq_type;	/* chip interrupt type */
 };
 
@@ -257,15 +252,6 @@ static const struct intel_mid_gpio_ddata gpio_cloverview_core = {
 	.chip_irq_type = INTEL_MID_IRQ_TYPE_EDGE,
 };
 
-static const struct intel_mid_gpio_ddata gpio_tangier = {
-	.ngpio = 192,
-	.gplr_offset = 4,
-	.flis_base = 0xff0c0000,
-	.flis_len = 0x8000,
-	.get_flis_offset = NULL,
-	.chip_irq_type = INTEL_MID_IRQ_TYPE_EDGE,
-};
-
 static const struct pci_device_id intel_gpio_ids[] = {
 	{
 		/* Lincroft */
@@ -292,11 +278,6 @@ static const struct pci_device_id intel_gpio_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x08f7),
 		.driver_data = (kernel_ulong_t)&gpio_cloverview_core,
 	},
-	{
-		/* Tangier */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1199),
-		.driver_data = (kernel_ulong_t)&gpio_tangier,
-	},
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, intel_gpio_ids);
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 48ef368347ab..9e02cb6afb0b 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -329,7 +329,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int irq,
 				irq_hw_number_t hwirq)
 {
 	irq_set_chip_data(irq, h->host_data);
-	irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_level_irq);
+	irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_edge_irq);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 2d4892cc70fb..c844d7eccb6c 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -86,7 +86,7 @@ MODULE_DEVICE_TABLE(acpi, pca953x_acpi_ids);
 #define MAX_BANK 5
 #define BANK_SZ 8
 
-#define NBANK(chip) (chip->gpio_chip.ngpio / BANK_SZ)
+#define NBANK(chip) DIV_ROUND_UP(chip->gpio_chip.ngpio, BANK_SZ)
 
 struct pca953x_chip {
 	unsigned gpio_start;
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 990fa9023e22..3b6bce0518ab 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -155,7 +155,7 @@ static int sa1100_gpio_irqdomain_map(struct irq_domain *d,
 {
 	irq_set_chip_and_handler(irq, &sa1100_gpio_irq_chip,
 				 handle_edge_irq);
-	irq_set_noprobe(irq);
+	irq_set_probe(irq);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c
index 3a5c7011ad3b..8b830996fe02 100644
--- a/drivers/gpio/gpiolib-legacy.c
+++ b/drivers/gpio/gpiolib-legacy.c
@@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (!desc && gpio_is_valid(gpio))
 		return -EPROBE_DEFER;
 
+	err = gpiod_request(desc, label);
+	if (err)
+		return err;
+
 	if (flags & GPIOF_OPEN_DRAIN)
 		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
 
@@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (flags & GPIOF_ACTIVE_LOW)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
-	err = gpiod_request(desc, label);
-	if (err)
-		return err;
-
 	if (flags & GPIOF_DIR_IN)
 		err = gpiod_direction_input(desc);
 	else
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4e4c3083ae56..06d345b087f8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -927,14 +927,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label)
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 done:
-	if (status < 0) {
-		/* Clear flags that might have been set by the caller before
-		 * requesting the GPIO.
-		 */
-		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
-		clear_bit(FLAG_OPEN_DRAIN, &desc->flags);
-		clear_bit(FLAG_OPEN_SOURCE, &desc->flags);
-	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
 	return status;
 }
@@ -2062,28 +2054,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(gpiod_get_optional);
 
-/**
- * gpiod_parse_flags - helper function to parse GPIO lookup flags
- * @desc:	gpio to be setup
- * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
- *		of_get_gpio_hog()
- *
- * Set the GPIO descriptor flags based on the given GPIO lookup flags.
- */
-static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
-{
-	if (lflags & GPIO_ACTIVE_LOW)
-		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
-	if (lflags & GPIO_OPEN_DRAIN)
-		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
-	if (lflags & GPIO_OPEN_SOURCE)
-		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
-}
 
 /**
  * gpiod_configure_flags - helper function to configure a given GPIO
  * @desc:	gpio whose value will be assigned
  * @con_id:	function within the GPIO consumer
+ * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
+ *		of_get_gpio_hog()
  * @dflags:	gpiod_flags - optional GPIO initialization flags
  *
  * Return 0 on success, -ENOENT if no GPIO has been assigned to the
@@ -2091,10 +2068,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
  * occurred while trying to acquire the GPIO.
  */
 static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
-				 enum gpiod_flags dflags)
+		unsigned long lflags, enum gpiod_flags dflags)
 {
 	int status;
 
+	if (lflags & GPIO_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+	if (lflags & GPIO_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+	if (lflags & GPIO_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
 	/* No particular flag request, return here... */
 	if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
 		pr_debug("no flags found for %s\n", con_id);
@@ -2161,13 +2145,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return desc;
 	}
 
-	gpiod_parse_flags(desc, lookupflags);
-
 	status = gpiod_request(desc, con_id);
 	if (status < 0)
 		return ERR_PTR(status);
 
-	status = gpiod_configure_flags(desc, con_id, flags);
+	status = gpiod_configure_flags(desc, con_id, lookupflags, flags);
 	if (status < 0) {
 		dev_dbg(dev, "setup of GPIO %s failed\n", con_id);
 		gpiod_put(desc);
@@ -2223,6 +2205,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 	if (IS_ERR(desc))
 		return desc;
 
+	ret = gpiod_request(desc, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
 	if (active_low)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
@@ -2233,10 +2219,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
 	}
 
-	ret = gpiod_request(desc, NULL);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return desc;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
@@ -2289,8 +2271,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 	chip = gpiod_to_chip(desc);
 	hwnum = gpio_chip_hwgpio(desc);
 
-	gpiod_parse_flags(desc, lflags);
-
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
 		pr_err("requesting hog GPIO %s (chip %s, offset %d) failed\n",
@@ -2298,7 +2278,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 		return PTR_ERR(local_desc);
 	}
 
-	status = gpiod_configure_flags(desc, name, dflags);
+	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
 		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed\n",
 		       name, chip->label, hwnum);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index bb1099c549df..e8e962f7b5cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -532,6 +532,7 @@ struct amdgpu_bo {
 	u64				metadata_flags;
 	void				*metadata;
 	u32				metadata_size;
+	unsigned			prime_shared_count;
 	/* list of all virtual address to which this bo
 	 * is associated to
 	 */
@@ -710,9 +711,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
 int amdgpu_gart_init(struct amdgpu_device *adev);
 void amdgpu_gart_fini(struct amdgpu_device *adev);
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 			int pages);
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, struct page **pagelist,
 		     dma_addr_t *dma_addr, uint32_t flags);
 
@@ -1673,6 +1674,7 @@ struct amdgpu_uvd {
 	struct amdgpu_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
+	unsigned		fw_version;
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
 	struct delayed_work	idle_work;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 9416e0f5c1db..f4cae5357e40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -331,6 +331,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 			    (le16_to_cpu(path->usConnObjectId) &
 			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
+			/* Skip TV/CV support */
+			if ((le16_to_cpu(path->usDeviceTag) ==
+			     ATOM_DEVICE_TV1_SUPPORT) ||
+			    (le16_to_cpu(path->usDeviceTag) ==
+			     ATOM_DEVICE_CV_SUPPORT))
+				continue;
+
+			if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) {
+				DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n",
+					  con_obj_id, le16_to_cpu(path->usDeviceTag));
+				continue;
+			}
+
 			connector_type =
 				object_connector_convert[con_obj_id];
 			connector_object_id = con_obj_id;
@@ -566,28 +579,19 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)
 		    le16_to_cpu(firmware_info->info.usReferenceClock);
 		ppll->reference_div = 0;
 
-		if (crev < 2)
-			ppll->pll_out_min =
-				le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output);
-		else
-			ppll->pll_out_min =
-				le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output);
+		ppll->pll_out_min =
+			le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output);
 		ppll->pll_out_max =
 		    le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output);
 
-		if (crev >= 4) {
-			ppll->lcd_pll_out_min =
-				le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
-			if (ppll->lcd_pll_out_min == 0)
-				ppll->lcd_pll_out_min = ppll->pll_out_min;
-			ppll->lcd_pll_out_max =
-				le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100;
-			if (ppll->lcd_pll_out_max == 0)
-				ppll->lcd_pll_out_max = ppll->pll_out_max;
-		} else {
+		ppll->lcd_pll_out_min =
+			le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
+		if (ppll->lcd_pll_out_min == 0)
 			ppll->lcd_pll_out_min = ppll->pll_out_min;
+		ppll->lcd_pll_out_max =
+			le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100;
+		if (ppll->lcd_pll_out_max == 0)
 			ppll->lcd_pll_out_max = ppll->pll_out_max;
-		}
 
 		if (ppll->pll_out_min == 0)
 			ppll->pll_out_min = 64800;
@@ -677,6 +681,10 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)
 			DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n",
 				 adev->clock.default_dispclk / 100);
 			adev->clock.default_dispclk = 60000;
+		} else if (adev->clock.default_dispclk <= 60000) {
+			DRM_INFO("Changing default dispclk from %dMhz to 625Mhz\n",
+				 adev->clock.default_dispclk / 100);
+			adev->clock.default_dispclk = 62500;
 		}
 		adev->clock.dp_extclk =
 			le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 5a8fbadbd27b..29adbbe225c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 
 #include "amdgpu_acpi.h"
 
@@ -256,6 +257,10 @@ static int amdgpu_atpx_set_discrete_state(struct amdgpu_atpx *atpx, u8 state)
 		if (!info)
 			return -EIO;
 		kfree(info);
+
+		/* 200ms delay is required after off */
+		if (state == 0)
+			msleep(200);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index f82a2dd83874..3c7a7235988d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -117,7 +117,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 			entry->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 		}
 		entry->tv.bo = &entry->robj->tbo;
-		entry->tv.shared = true;
+		entry->tv.shared = !entry->robj->prime_shared_count;
 
 		if (entry->prefered_domains == AMDGPU_GEM_DOMAIN_GDS)
 			gds_obj = entry->robj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 119cdc2c43e7..930083336968 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -194,12 +194,12 @@ int amdgpu_connector_get_monitor_bpc(struct drm_connector *connector)
 				bpc = 8;
 				DRM_DEBUG("%s: HDMI deep color 10 bpc exceeds max tmds clock. Using %d bpc.\n",
 					  connector->name, bpc);
-			} else if (bpc > 8) {
-				/* max_tmds_clock missing, but hdmi spec mandates it for deep color. */
-				DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n",
-					  connector->name);
-				bpc = 8;
 			}
+		} else if (bpc > 8) {
+			/* max_tmds_clock missing, but hdmi spec mandates it for deep color. */
+			DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n",
+				  connector->name);
+			bpc = 8;
 		}
 	}
 
@@ -1690,7 +1690,6 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 						   DRM_MODE_SCALE_NONE);
 			/* no HPD on analog connectors */
 			amdgpu_connector->hpd.hpd = AMDGPU_HPD_NONE;
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			break;
@@ -1893,8 +1892,10 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 	}
 
 	if (amdgpu_connector->hpd.hpd == AMDGPU_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 25a3e2485cc2..2bc17a907ecf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -124,6 +124,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 		}
 		break;
 	}
+
+	if (!(*out_ring && (*out_ring)->adev)) {
+		DRM_ERROR("Ring %d is not initialized on IP %d\n",
+			  ring, ip_type);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c961fe093e12..16302f7d59f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1793,7 +1793,23 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	drm_kms_helper_poll_enable(dev);
+
+	/*
+	 * Most of the connector probing functions try to acquire runtime pm
+	 * refs to ensure that the GPU is powered on when connector polling is
+	 * performed. Since we're calling this from a runtime PM callback,
+	 * trying to acquire rpm refs will cause us to deadlock.
+	 *
+	 * Since we're guaranteed to be holding the rpm lock, it's safe to
+	 * temporarily disable the rpm helpers so this doesn't deadlock us.
+	 */
+#ifdef CONFIG_PM
+	dev->dev->power.disable_depth++;
+#endif
 	drm_helper_hpd_irq_event(dev);
+#ifdef CONFIG_PM
+	dev->dev->power.disable_depth--;
+#endif
 
 	if (fbcon) {
 		amdgpu_fbdev_set_suspend(adev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 7b7f4aba60c0..14f57d9915e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -113,24 +113,26 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
 	printk("\n");
 }
 
+
 u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_crtc *crtc;
 	struct amdgpu_crtc *amdgpu_crtc;
-	u32 line_time_us, vblank_lines;
+	u32 vblank_in_pixels;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
 	if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			amdgpu_crtc = to_amdgpu_crtc(crtc);
 			if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) {
-				line_time_us = (amdgpu_crtc->hw_mode.crtc_htotal * 1000) /
-					amdgpu_crtc->hw_mode.clock;
-				vblank_lines = amdgpu_crtc->hw_mode.crtc_vblank_end -
+				vblank_in_pixels =
+					amdgpu_crtc->hw_mode.crtc_htotal *
+					(amdgpu_crtc->hw_mode.crtc_vblank_end -
 					amdgpu_crtc->hw_mode.crtc_vdisplay +
-					(amdgpu_crtc->v_border * 2);
-				vblank_time_us = vblank_lines * line_time_us;
+					(amdgpu_crtc->v_border * 2));
+
+				vblank_time_us = vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock;
 				break;
 			}
 		}
@@ -150,7 +152,7 @@ u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev)
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			amdgpu_crtc = to_amdgpu_crtc(crtc);
 			if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) {
-				vrefresh = amdgpu_crtc->hw_mode.vrefresh;
+				vrefresh = drm_mode_vrefresh(&amdgpu_crtc->hw_mode);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 7312d729d300..22a613a95bf0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev)
  * Unbinds the requested pages from the gart page table and
  * replaces them with the dummy page (all asics).
  */
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 			int pages)
 {
 	unsigned t;
@@ -269,7 +269,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
  * (all asics).
  * Returns 0 for success, -EINVAL for failure.
  */
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, struct page **pagelist, dma_addr_t *dma_addr,
 		     uint32_t flags)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 9e25edafa721..c77a1ebfc632 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -288,7 +288,7 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 {
 	unsigned i;
-	int r;
+	int r, ret = 0;
 
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -309,10 +309,11 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 			} else {
 				/* still not good, but we can live with it */
 				DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
+				ret = r;
 			}
 		}
 	}
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 7c42ff670080..a0924330d125 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/irq.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/amdgpu_drm.h>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index e23843f4d877..a5c824078472 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -227,7 +227,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			type = AMD_IP_BLOCK_TYPE_UVD;
 			ring_mask = adev->uvd.ring.ready ? 1 : 0;
 			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 8;
+			ib_size_alignment = 16;
 			break;
 		case AMDGPU_HW_IP_VCE:
 			type = AMD_IP_BLOCK_TYPE_VCE;
@@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			fw_info.feature = adev->vce.fb_version;
 			break;
 		case AMDGPU_INFO_FW_UVD:
-			fw_info.ver = 0;
+			fw_info.ver = adev->uvd.fw_version;
 			fw_info.feature = 0;
 			break;
 		case AMDGPU_INFO_FW_GMC:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 064ebb347074..89df7871653d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -52,7 +52,7 @@ struct amdgpu_hpd;
 
 #define AMDGPU_MAX_HPD_PINS 6
 #define AMDGPU_MAX_CRTCS 6
-#define AMDGPU_MAX_AFMT_BLOCKS 7
+#define AMDGPU_MAX_AFMT_BLOCKS 9
 
 enum amdgpu_rmx_type {
 	RMX_OFF,
@@ -308,8 +308,8 @@ struct amdgpu_mode_info {
 	struct atom_context *atom_context;
 	struct card_info *atom_card_info;
 	bool mode_config_initialized;
-	struct amdgpu_crtc *crtcs[6];
-	struct amdgpu_afmt *afmt[7];
+	struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS];
+	struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS];
 	/* DVI-I properties */
 	struct drm_property *coherent_mode_property;
 	/* DAC enable load detect */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index b8fbbd7699e4..73628c7599e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -540,6 +540,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 	if (!metadata_size) {
 		if (bo->metadata_size) {
 			kfree(bo->metadata);
+			bo->metadata = NULL;
 			bo->metadata_size = 0;
 		}
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 59f735a933a9..e6a7d30c3747 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -77,20 +77,36 @@ struct drm_gem_object *amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	list_add_tail(&bo->list, &adev->gem.objects);
 	mutex_unlock(&adev->gem.mutex);
 
+	bo->prime_shared_count = 1;
 	return &bo->gem_base;
 }
 
 int amdgpu_gem_prime_pin(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	int ret = 0;
+	long ret = 0;
 
 	ret = amdgpu_bo_reserve(bo, false);
 	if (unlikely(ret != 0))
 		return ret;
 
+	/*
+	 * Wait for all shared fences to complete before we switch to future
+	 * use of exclusive fence on this prime shared bo.
+	 */
+	ret = reservation_object_wait_timeout_rcu(bo->tbo.resv, true, false,
+						  MAX_SCHEDULE_TIMEOUT);
+	if (unlikely(ret < 0)) {
+		DRM_DEBUG_PRIME("Fence wait failed: %li\n", ret);
+		amdgpu_bo_unreserve(bo);
+		return ret;
+	}
+
 	/* pin buffer into GTT */
 	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	if (likely(ret == 0))
+		bo->prime_shared_count++;
+
 	amdgpu_bo_unreserve(bo);
 	return ret;
 }
@@ -105,6 +121,8 @@ void amdgpu_gem_prime_unpin(struct drm_gem_object *obj)
 		return;
 
 	amdgpu_bo_unpin(bo);
+	if (bo->prime_shared_count)
+		bo->prime_shared_count--;
 	amdgpu_bo_unreserve(bo);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 1cbb16e15307..e40a6d8b0b92 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -233,8 +233,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 	adev = amdgpu_get_adev(bo->bdev);
 	ring = adev->mman.buffer_funcs_ring;
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;
 
 	switch (old_mem->mem_type) {
 	case TTM_PL_VRAM:
@@ -1126,6 +1126,9 @@ static ssize_t amdgpu_ttm_vram_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (*pos >= adev->mc.mc_vram_size)
+		return -ENXIO;
+
 	while (size) {
 		unsigned long flags;
 		uint32_t value;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 53f987aeeacf..3b35ad83867c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -156,6 +156,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
 		version_major, version_minor, family_id);
 
+	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
+				(family_id << 8));
+
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		 +  AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE;
 	r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true,
@@ -273,6 +276,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 	memcpy(adev->uvd.cpu_addr, (adev->uvd.fw->data) + offset,
 		(adev->uvd.fw->size) - offset);
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
+
 	size = amdgpu_bo_size(adev->uvd.vcpu_bo);
 	size -= le32_to_cpu(hdr->ucode_size_bytes);
 	ptr = adev->uvd.cpu_addr;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index a745eeeb5d82..bb0da76051a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -220,6 +220,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_VCE_HANDLES)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
 	/* TODO: suspending running encoding sessions isn't supported */
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
index 49aa35016653..247b088990dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_crtc.c
@@ -164,7 +164,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state)
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating);
-	ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args;
+	ENABLE_DISP_POWER_GATING_PS_ALLOCATION args;
 
 	memset(&args, 0, sizeof(args));
 
@@ -177,7 +177,7 @@ void amdgpu_atombios_crtc_powergate(struct drm_crtc *crtc, int state)
 void amdgpu_atombios_crtc_powergate_init(struct amdgpu_device *adev)
 {
 	int index = GetIndexIntoMasterTable(COMMAND, EnableDispPowerGating);
-	ENABLE_DISP_POWER_GATING_PARAMETERS_V2_1 args;
+	ENABLE_DISP_POWER_GATING_PS_ALLOCATION args;
 
 	memset(&args, 0, sizeof(args));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 92b6acadfc52..7f85c2c1d681 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -243,7 +243,7 @@ static void amdgpu_atombios_dp_get_adjust_train(const u8 link_status[DP_LINK_STA
 
 /* convert bits per color to bits per pixel */
 /* get bpc from the EDID */
-static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
+static unsigned amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
 {
 	if (bpc == 0)
 		return 24;
@@ -251,64 +251,44 @@ static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
 		return bpc * 3;
 }
 
-/* get the max pix clock supported by the link rate and lane num */
-static int amdgpu_atombios_dp_get_max_dp_pix_clock(int link_rate,
-					    int lane_num,
-					    int bpp)
-{
-	return (link_rate * lane_num * 8) / bpp;
-}
-
 /***** amdgpu specific DP functions *****/
 
-/* 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.
- */
-static int amdgpu_atombios_dp_get_dp_lane_number(struct drm_connector *connector,
+static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector,
 						 const u8 dpcd[DP_DPCD_SIZE],
-						 int pix_clock)
+						 unsigned pix_clock,
+						 unsigned *dp_lanes, unsigned *dp_rate)
 {
-	int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
-	int max_lane_num = drm_dp_max_lane_count(dpcd);
-	int lane_num;
-	int max_dp_pix_clock;
-
-	for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) {
-		max_dp_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp);
-		if (pix_clock <= max_dp_pix_clock)
-			break;
-	}
-
-	return lane_num;
-}
-
-static int amdgpu_atombios_dp_get_dp_link_clock(struct drm_connector *connector,
-						const u8 dpcd[DP_DPCD_SIZE],
-						int pix_clock)
-{
-	int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
-	int lane_num, max_pix_clock;
+	unsigned bpp =
+		amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
+	static const unsigned link_rates[3] = { 162000, 270000, 540000 };
+	unsigned max_link_rate = drm_dp_max_link_rate(dpcd);
+	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
+	unsigned lane_num, i, max_pix_clock;
 
 	if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		return 270000;
-
-	lane_num = amdgpu_atombios_dp_get_dp_lane_number(connector, dpcd, pix_clock);
-	max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(162000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 162000;
-	max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(270000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 270000;
-	if (amdgpu_connector_is_dp12_capable(connector)) {
-		max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(540000, lane_num, bpp);
-		if (pix_clock <= max_pix_clock)
-			return 540000;
+	    ENCODER_OBJECT_ID_NUTMEG) {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			max_pix_clock = (lane_num * 270000 * 8) / bpp;
+			if (max_pix_clock >= pix_clock) {
+				*dp_lanes = lane_num;
+				*dp_rate = 270000;
+				return 0;
+			}
+		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+			for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+				max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+				if (max_pix_clock >= pix_clock) {
+					*dp_lanes = lane_num;
+					*dp_rate = link_rates[i];
+					return 0;
+				}
+			}
+		}
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return -EINVAL;
 }
 
 static u8 amdgpu_atombios_dp_encoder_service(struct amdgpu_device *adev,
@@ -422,6 +402,7 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *dig_connector;
+	int ret;
 
 	if (!amdgpu_connector->con_priv)
 		return;
@@ -429,10 +410,14 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 
 	if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 	    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-		dig_connector->dp_clock =
-			amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
-		dig_connector->dp_lane_count =
-			amdgpu_atombios_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock);
+		ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd,
+							    mode->clock,
+							    &dig_connector->dp_lane_count,
+							    &dig_connector->dp_clock);
+		if (ret) {
+			dig_connector->dp_clock = 0;
+			dig_connector->dp_lane_count = 0;
+		}
 	}
 }
 
@@ -441,14 +426,17 @@ int amdgpu_atombios_dp_mode_valid_helper(struct drm_connector *connector,
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *dig_connector;
-	int dp_clock;
+	unsigned dp_lanes, dp_clock;
+	int ret;
 
 	if (!amdgpu_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = amdgpu_connector->con_priv;
 
-	dp_clock =
-		amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
+	ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd,
+						    mode->clock, &dp_lanes, &dp_clock);
+	if (ret)
+		return MODE_CLOCK_HIGH;
 
 	if ((dp_clock == 540000) &&
 	    (!amdgpu_connector_is_dp12_capable(connector)))
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index 1e0bba29e167..542517d4e584 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -98,6 +98,7 @@ amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encode
 		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
 			if (dig->backlight_level == 0)
 				amdgpu_atombios_encoder_setup_dig_transmitter(encoder,
 								       ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
@@ -298,6 +299,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder,
 	    && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2)))
 		adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2;
 
+	/* vertical FP must be at least 1 */
+	if (mode->crtc_vsync_start == mode->crtc_vdisplay)
+		adjusted_mode->crtc_vsync_start++;
+
 	/* get the native mode for scaling */
 	if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT))
 		amdgpu_panel_mode_fixup(encoder, adjusted_mode);
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 57a2e347f04d..0f0094b58d1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -893,6 +893,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev)
 	u32 vblank_time = amdgpu_dpm_get_vblank_time(adev);
 	u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+	 * blanking period would allow it
+	 */
+	if (amdgpu_dpm_get_vrefresh(adev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 5f712ceddf08..c568293cb6c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -52,6 +52,7 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
+static int cik_sdma_soft_reset(void *handle);
 
 MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
 MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
@@ -1030,6 +1031,8 @@ static int cik_sdma_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cik_sdma_soft_reset(handle);
+
 	return cik_sdma_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 8035d4d6a4f5..653917a3bcc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -1955,10 +1955,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 		}
 	} else { /*pi->caps_vce_pg*/
 		cz_update_vce_dpm(adev);
-		cz_enable_vce_dpm(adev, true);
+		cz_enable_vce_dpm(adev, !gate);
 	}
-
-	return;
 }
 
 const struct amd_ip_funcs cz_dpm_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 4dcc8fba5792..3a25da4a6e60 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -419,16 +419,6 @@ static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
-		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
-		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
-			/* don't try to enable hpd on eDP or LVDS avoid breaking the
-			 * aux dp channel on imac and help (but not completely fix)
-			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
-			 * also avoid interrupt storms during dpms.
-			 */
-			continue;
-		}
-
 		switch (amdgpu_connector->hpd.hpd) {
 		case AMDGPU_HPD_1:
 			idx = 0;
@@ -452,6 +442,19 @@ static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
 			continue;
 		}
 
+		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
+		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
+			/* don't try to enable hpd on eDP or LVDS avoid breaking the
+			 * aux dp channel on imac and help (but not completely fix)
+			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
+			 * also avoid interrupt storms during dpms.
+			 */
+			tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[idx]);
+			tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_EN, 0);
+			WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[idx], tmp);
+			continue;
+		}
+
 		tmp = RREG32(mmDC_HPD_CONTROL + hpd_offsets[idx]);
 		tmp = REG_SET_FIELD(tmp, DC_HPD_CONTROL, DC_HPD_EN, 1);
 		WREG32(mmDC_HPD_CONTROL + hpd_offsets[idx], tmp);
@@ -1123,23 +1126,10 @@ static u32 dce_v10_0_latency_watermark(struct dce10_wm_params *wm)
 	a.full = dfixed_const(available_bandwidth);
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
+	tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512);
+	tmp = min(dfixed_trunc(a), tmp);
 
-	b.full = dfixed_const(mc_latency + 512);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(b, c);
-
-	c.full = dfixed_const(dmif_size);
-	b.full = dfixed_div(c, b);
-
-	tmp = min(dfixed_trunc(a), dfixed_trunc(b));
-
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(tmp, dfixed_trunc(b));
+	lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);
@@ -1247,14 +1237,14 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 {
 	struct drm_display_mode *mode = &amdgpu_crtc->base.mode;
 	struct dce10_wm_params wm_low, wm_high;
-	u32 pixel_period;
+	u32 active_time;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
 	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
-		pixel_period = 1000000 / (u32)mode->clock;
-		line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535);
+		active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock;
+		line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535);
 
 		/* watermark for high clocks */
 		if (adev->pm.dpm_enabled) {
@@ -1269,7 +1259,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_high.disp_clk = mode->clock;
 		wm_high.src_width = mode->crtc_hdisplay;
-		wm_high.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_high.active_time = active_time;
 		wm_high.blank_time = line_time - wm_high.active_time;
 		wm_high.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -1308,7 +1298,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_low.disp_clk = mode->clock;
 		wm_low.src_width = mode->crtc_hdisplay;
-		wm_low.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_low.active_time = active_time;
 		wm_low.blank_time = line_time - wm_low.active_time;
 		wm_low.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 8f1e51128b33..d6d3cda77762 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -409,16 +409,6 @@ static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
-		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
-		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
-			/* don't try to enable hpd on eDP or LVDS avoid breaking the
-			 * aux dp channel on imac and help (but not completely fix)
-			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
-			 * also avoid interrupt storms during dpms.
-			 */
-			continue;
-		}
-
 		switch (amdgpu_connector->hpd.hpd) {
 		case AMDGPU_HPD_1:
 			idx = 0;
@@ -442,6 +432,19 @@ static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
 			continue;
 		}
 
+		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
+		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
+			/* don't try to enable hpd on eDP or LVDS avoid breaking the
+			 * aux dp channel on imac and help (but not completely fix)
+			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
+			 * also avoid interrupt storms during dpms.
+			 */
+			tmp = RREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[idx]);
+			tmp = REG_SET_FIELD(tmp, DC_HPD_INT_CONTROL, DC_HPD_INT_EN, 0);
+			WREG32(mmDC_HPD_INT_CONTROL + hpd_offsets[idx], tmp);
+			continue;
+		}
+
 		tmp = RREG32(mmDC_HPD_CONTROL + hpd_offsets[idx]);
 		tmp = REG_SET_FIELD(tmp, DC_HPD_CONTROL, DC_HPD_EN, 1);
 		WREG32(mmDC_HPD_CONTROL + hpd_offsets[idx], tmp);
@@ -1111,23 +1114,10 @@ static u32 dce_v11_0_latency_watermark(struct dce10_wm_params *wm)
 	a.full = dfixed_const(available_bandwidth);
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
+	tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512);
+	tmp = min(dfixed_trunc(a), tmp);
 
-	b.full = dfixed_const(mc_latency + 512);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(b, c);
-
-	c.full = dfixed_const(dmif_size);
-	b.full = dfixed_div(c, b);
-
-	tmp = min(dfixed_trunc(a), dfixed_trunc(b));
-
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(tmp, dfixed_trunc(b));
+	lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);
@@ -1235,14 +1225,14 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 {
 	struct drm_display_mode *mode = &amdgpu_crtc->base.mode;
 	struct dce10_wm_params wm_low, wm_high;
-	u32 pixel_period;
+	u32 active_time;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
 	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
-		pixel_period = 1000000 / (u32)mode->clock;
-		line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535);
+		active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock;
+		line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535);
 
 		/* watermark for high clocks */
 		if (adev->pm.dpm_enabled) {
@@ -1257,7 +1247,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_high.disp_clk = mode->clock;
 		wm_high.src_width = mode->crtc_hdisplay;
-		wm_high.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_high.active_time = active_time;
 		wm_high.blank_time = line_time - wm_high.active_time;
 		wm_high.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -1296,7 +1286,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_low.disp_clk = mode->clock;
 		wm_low.src_width = mode->crtc_hdisplay;
-		wm_low.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_low.active_time = active_time;
 		wm_low.blank_time = line_time - wm_low.active_time;
 		wm_low.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -3030,6 +3020,7 @@ static int dce_v11_0_sw_fini(void *handle)
 
 	dce_v11_0_afmt_fini(adev);
 
+	drm_mode_config_cleanup(adev->ddev);
 	adev->mode_info.mode_config_initialized = false;
 
 	return 0;
@@ -3700,9 +3691,15 @@ static void dce_v11_0_encoder_add(struct amdgpu_device *adev,
 	default:
 		encoder->possible_crtcs = 0x3;
 		break;
+	case 3:
+		encoder->possible_crtcs = 0x7;
+		break;
 	case 4:
 		encoder->possible_crtcs = 0xf;
 		break;
+	case 5:
+		encoder->possible_crtcs = 0x1f;
+		break;
 	case 6:
 		encoder->possible_crtcs = 0x3f;
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 42d954dc436d..d6e51d4b04f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -392,15 +392,6 @@ static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
-		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
-		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
-			/* don't try to enable hpd on eDP or LVDS avoid breaking the
-			 * aux dp channel on imac and help (but not completely fix)
-			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
-			 * also avoid interrupt storms during dpms.
-			 */
-			continue;
-		}
 		switch (amdgpu_connector->hpd.hpd) {
 		case AMDGPU_HPD_1:
 			WREG32(mmDC_HPD1_CONTROL, tmp);
@@ -423,6 +414,45 @@ static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
 		default:
 			break;
 		}
+
+		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP ||
+		    connector->connector_type == DRM_MODE_CONNECTOR_LVDS) {
+			/* don't try to enable hpd on eDP or LVDS avoid breaking the
+			 * aux dp channel on imac and help (but not completely fix)
+			 * https://bugzilla.redhat.com/show_bug.cgi?id=726143
+			 * also avoid interrupt storms during dpms.
+			 */
+			u32 dc_hpd_int_cntl_reg, dc_hpd_int_cntl;
+
+			switch (amdgpu_connector->hpd.hpd) {
+			case AMDGPU_HPD_1:
+				dc_hpd_int_cntl_reg = mmDC_HPD1_INT_CONTROL;
+				break;
+			case AMDGPU_HPD_2:
+				dc_hpd_int_cntl_reg = mmDC_HPD2_INT_CONTROL;
+				break;
+			case AMDGPU_HPD_3:
+				dc_hpd_int_cntl_reg = mmDC_HPD3_INT_CONTROL;
+				break;
+			case AMDGPU_HPD_4:
+				dc_hpd_int_cntl_reg = mmDC_HPD4_INT_CONTROL;
+				break;
+			case AMDGPU_HPD_5:
+				dc_hpd_int_cntl_reg = mmDC_HPD5_INT_CONTROL;
+				break;
+			case AMDGPU_HPD_6:
+				dc_hpd_int_cntl_reg = mmDC_HPD6_INT_CONTROL;
+				break;
+			default:
+				continue;
+			}
+
+			dc_hpd_int_cntl = RREG32(dc_hpd_int_cntl_reg);
+			dc_hpd_int_cntl &= ~DC_HPD1_INT_CONTROL__DC_HPD1_INT_EN_MASK;
+			WREG32(dc_hpd_int_cntl_reg, dc_hpd_int_cntl);
+			continue;
+		}
+
 		dce_v8_0_hpd_set_polarity(adev, amdgpu_connector->hpd.hpd);
 		amdgpu_irq_get(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
@@ -1066,23 +1096,10 @@ static u32 dce_v8_0_latency_watermark(struct dce8_wm_params *wm)
 	a.full = dfixed_const(available_bandwidth);
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
+	tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512);
+	tmp = min(dfixed_trunc(a), tmp);
 
-	b.full = dfixed_const(mc_latency + 512);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(b, c);
-
-	c.full = dfixed_const(dmif_size);
-	b.full = dfixed_div(c, b);
-
-	tmp = min(dfixed_trunc(a), dfixed_trunc(b));
-
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(tmp, dfixed_trunc(b));
+	lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);
@@ -1190,14 +1207,14 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 {
 	struct drm_display_mode *mode = &amdgpu_crtc->base.mode;
 	struct dce8_wm_params wm_low, wm_high;
-	u32 pixel_period;
+	u32 active_time;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
 	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
-		pixel_period = 1000000 / (u32)mode->clock;
-		line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535);
+		active_time = 1000000UL * (u32)mode->crtc_hdisplay / (u32)mode->clock;
+		line_time = min((u32) (1000000UL * (u32)mode->crtc_htotal / (u32)mode->clock), (u32)65535);
 
 		/* watermark for high clocks */
 		if (adev->pm.dpm_enabled) {
@@ -1212,7 +1229,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_high.disp_clk = mode->clock;
 		wm_high.src_width = mode->crtc_hdisplay;
-		wm_high.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_high.active_time = active_time;
 		wm_high.blank_time = line_time - wm_high.active_time;
 		wm_high.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
@@ -1251,7 +1268,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 
 		wm_low.disp_clk = mode->clock;
 		wm_low.src_width = mode->crtc_hdisplay;
-		wm_low.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_low.active_time = active_time;
 		wm_low.blank_time = line_time - wm_low.active_time;
 		wm_low.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index aa491540ba85..b57fffc2d4af 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3628,7 +3628,7 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned vm_id, uint64_t pd_addr)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
-	uint32_t seq = ring->fence_drv.sync_seq;
+	uint32_t seq = ring->fence_drv.sync_seq[ring->idx];
 	uint64_t addr = ring->fence_drv.gpu_addr;
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
@@ -5463,7 +5463,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev,
 	case 2:
 		for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 			ring = &adev->gfx.compute_ring[i];
-			if ((ring->me == me_id) & (ring->pipe == pipe_id))
+			if ((ring->me == me_id) && (ring->pipe == pipe_id))
 				amdgpu_fence_process(ring);
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 272110cc18c2..df17fababbd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -167,6 +167,7 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev)
 		break;
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
+	case CHIP_MULLINS:
 		return 0;
 	default: BUG();
 	}
@@ -898,14 +899,6 @@ static int gmc_v7_0_early_init(void *handle)
 	gmc_v7_0_set_gart_funcs(adev);
 	gmc_v7_0_set_irq_funcs(adev);
 
-	if (adev->flags & AMD_IS_APU) {
-		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
-	} else {
-		u32 tmp = RREG32(mmMC_SEQ_MISC0);
-		tmp &= MC_SEQ_MISC0__MT__MASK;
-		adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp);
-	}
-
 	return 0;
 }
 
@@ -926,6 +919,14 @@ static int gmc_v7_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	if (adev->flags & AMD_IS_APU) {
+		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
+	} else {
+		u32 tmp = RREG32(mmMC_SEQ_MISC0);
+		tmp &= MC_SEQ_MISC0__MT__MASK;
+		adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp);
+	}
+
 	r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ba4ad00ba8b4..08423089fb84 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -852,14 +852,6 @@ static int gmc_v8_0_early_init(void *handle)
 	gmc_v8_0_set_gart_funcs(adev);
 	gmc_v8_0_set_irq_funcs(adev);
 
-	if (adev->flags & AMD_IS_APU) {
-		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
-	} else {
-		u32 tmp = RREG32(mmMC_SEQ_MISC0);
-		tmp &= MC_SEQ_MISC0__MT__MASK;
-		adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp);
-	}
-
 	return 0;
 }
 
@@ -870,6 +862,8 @@ static int gmc_v8_0_late_init(void *handle)
 	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
 }
 
+#define mmMC_SEQ_MISC0_FIJI 0xA71
+
 static int gmc_v8_0_sw_init(void *handle)
 {
 	int r;
@@ -880,6 +874,19 @@ static int gmc_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	if (adev->flags & AMD_IS_APU) {
+		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
+	} else {
+		u32 tmp;
+
+		if (adev->asic_type == CHIP_FIJI)
+			tmp = RREG32(mmMC_SEQ_MISC0_FIJI);
+		else
+			tmp = RREG32(mmMC_SEQ_MISC0);
+		tmp &= MC_SEQ_MISC0__MT__MASK;
+		adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp);
+	}
+
 	r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 7e9154c7f1db..d1c9525d81eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2258,7 +2258,7 @@ static void kv_apply_state_adjust_rules(struct amdgpu_device *adev,
 	if (pi->caps_stable_p_state) {
 		stable_p_state_sclk = (max_limits->sclk * 75) / 100;
 
-		for (i = table->count - 1; i >= 0; i++) {
+		for (i = table->count - 1; i >= 0; i--) {
 			if (stable_p_state_sclk >= table->entries[i].clk) {
 				stable_p_state_sclk = table->entries[i].clk;
 				break;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 2cf50180cc51..b1c7a9b3631b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -32,8 +32,8 @@
 #include "oss/oss_2_4_d.h"
 #include "oss/oss_2_4_sh_mask.h"
 
-#include "gmc/gmc_8_1_d.h"
-#include "gmc/gmc_8_1_sh_mask.h"
+#include "gmc/gmc_7_1_d.h"
+#include "gmc/gmc_7_1_sh_mask.h"
 
 #include "gca/gfx_8_0_d.h"
 #include "gca/gfx_8_0_enum.h"
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index c34c393e9aea..d5e19b5fbbfb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -513,7 +513,7 @@ static int dbgdev_wave_control_set_registers(
 				union SQ_CMD_BITS *in_reg_sq_cmd,
 				union GRBM_GFX_INDEX_BITS *in_reg_gfx_index)
 {
-	int status;
+	int status = 0;
 	union SQ_CMD_BITS reg_sq_cmd;
 	union GRBM_GFX_INDEX_BITS reg_gfx_index;
 	struct HsaDbgWaveMsgAMDGen2 *pMsg;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 9be007081b72..eb1da83c9902 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 	pqm_uninit(&p->pqm);
 
 	/* Iterate over all process device data structure and check
-	 * if we should reset all wavefronts */
-	list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+	 * if we should delete debug managers and reset all wavefronts
+	 */
+	list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+		if ((pdd->dev->dbgmgr) &&
+				(pdd->dev->dbgmgr->pasid == p->pasid))
+			kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
+
 		if (pdd->reset_wavefronts) {
 			pr_warn("amdkfd: Resetting all wave fronts\n");
 			dbgdev_wave_reset_wavefronts(pdd->dev, p);
 			pdd->reset_wavefronts = false;
 		}
+	}
 
 	mutex_unlock(&p->mutex);
 
@@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid)
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 
+	/*
+	 * Look for the process that matches the pasid. If there is no such
+	 * process, we either released it in amdkfd's own notifier, or there
+	 * is a bug. Unfortunately, there is no way to tell...
+	 */
 	hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes)
-		if (p->pasid == pasid)
-			break;
+		if (p->pasid == pasid) {
 
-	srcu_read_unlock(&kfd_processes_srcu, idx);
+			srcu_read_unlock(&kfd_processes_srcu, idx);
 
-	BUG_ON(p->pasid != pasid);
+			pr_debug("Unbinding process %d from IOMMU\n", pasid);
 
-	mutex_lock(&p->mutex);
+			mutex_lock(&p->mutex);
 
-	if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
-		kfd_dbgmgr_destroy(dev->dbgmgr);
+			if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
+				kfd_dbgmgr_destroy(dev->dbgmgr);
 
-	pqm_uninit(&p->pqm);
+			pqm_uninit(&p->pqm);
 
-	pdd = kfd_get_process_device_data(dev, p);
+			pdd = kfd_get_process_device_data(dev, p);
 
-	if (!pdd) {
-		mutex_unlock(&p->mutex);
-		return;
-	}
+			if (!pdd) {
+				mutex_unlock(&p->mutex);
+				return;
+			}
 
-	if (pdd->reset_wavefronts) {
-		dbgdev_wave_reset_wavefronts(pdd->dev, p);
-		pdd->reset_wavefronts = false;
-	}
+			if (pdd->reset_wavefronts) {
+				dbgdev_wave_reset_wavefronts(pdd->dev, p);
+				pdd->reset_wavefronts = false;
+			}
 
-	/*
-	 * Just mark pdd as unbound, because we still need it to call
-	 * amd_iommu_unbind_pasid() in when the process exits.
-	 * We don't call amd_iommu_unbind_pasid() here
-	 * because the IOMMU called us.
-	 */
-	pdd->bound = false;
+			/*
+			 * Just mark pdd as unbound, because we still need it
+			 * to call amd_iommu_unbind_pasid() in when the
+			 * process exits.
+			 * We don't call amd_iommu_unbind_pasid() here
+			 * because the IOMMU called us.
+			 */
+			pdd->bound = false;
 
-	mutex_unlock(&p->mutex);
+			mutex_unlock(&p->mutex);
+
+			return;
+		}
+
+	srcu_read_unlock(&kfd_processes_srcu, idx);
 }
 
 struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p)
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 05f6522c0457..b5c64edeb668 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -113,6 +113,11 @@ struct ast_private {
 	struct ttm_bo_kmap_obj cache_kmap;
 	int next_cursor;
 	bool support_wide_screen;
+	enum {
+		ast_use_p2a,
+		ast_use_dt,
+		ast_use_defaults
+	} config_mode;
 
 	enum ast_tx_chip tx_chip_type;
 	u8 dp501_maxclk;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index e0b4586a26fd..498a94069e6b 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -62,13 +62,84 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast,
 	return ret;
 }
 
+static void ast_detect_config_mode(struct drm_device *dev, u32 *scu_rev)
+{
+	struct device_node *np = dev->pdev->dev.of_node;
+	struct ast_private *ast = dev->dev_private;
+	uint32_t data, jregd0, jregd1;
+
+	/* Defaults */
+	ast->config_mode = ast_use_defaults;
+	*scu_rev = 0xffffffff;
+
+	/* Check if we have device-tree properties */
+	if (np && !of_property_read_u32(np, "aspeed,scu-revision-id",
+					scu_rev)) {
+		/* We do, disable P2A access */
+		ast->config_mode = ast_use_dt;
+		DRM_INFO("Using device-tree for configuration\n");
+		return;
+	}
+
+	/* Not all families have a P2A bridge */
+	if (dev->pdev->device != PCI_CHIP_AST2000)
+		return;
+
+	/*
+	 * The BMC will set SCU 0x40 D[12] to 1 if the P2 bridge
+	 * is disabled. We force using P2A if VGA only mode bit
+	 * is set D[7]
+	 */
+	jregd0 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff);
+	jregd1 = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
+	if (!(jregd0 & 0x80) || !(jregd1 & 0x10)) {
+		/* Double check it's actually working */
+		data = ast_read32(ast, 0xf004);
+		if (data != 0xFFFFFFFF) {
+			/* P2A works, grab silicon revision */
+			ast->config_mode = ast_use_p2a;
+
+			DRM_INFO("Using P2A bridge for configuration\n");
+
+			/* Read SCU7c (silicon revision register) */
+			ast_write32(ast, 0xf004, 0x1e6e0000);
+			ast_write32(ast, 0xf000, 0x1);
+			*scu_rev = ast_read32(ast, 0x1207c);
+			return;
+		}
+	}
+
+	/* We have a P2A bridge but it's disabled */
+	DRM_INFO("P2A bridge disabled, using default configuration\n");
+}
 
 static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 {
 	struct ast_private *ast = dev->dev_private;
-	uint32_t data, jreg;
+	uint32_t jreg, scu_rev;
+
+	/*
+	 * If VGA isn't enabled, we need to enable now or subsequent
+	 * access to the scratch registers will fail. We also inform
+	 * our caller that it needs to POST the chip
+	 * (Assumption: VGA not enabled -> need to POST)
+	 */
+	if (!ast_is_vga_enabled(dev)) {
+		ast_enable_vga(dev);
+		DRM_INFO("VGA not enabled on entry, requesting chip POST\n");
+		*need_post = true;
+	} else
+		*need_post = false;
+
+
+	/* Enable extended register access */
+	ast_enable_mmio(dev);
 	ast_open_key(ast);
 
+	/* Find out whether P2A works or whether to use device-tree */
+	ast_detect_config_mode(dev, &scu_rev);
+
+	/* Identify chipset */
 	if (dev->pdev->device == PCI_CHIP_AST1180) {
 		ast->chip = AST1100;
 		DRM_INFO("AST 1180 detected\n");
@@ -80,12 +151,7 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 			ast->chip = AST2300;
 			DRM_INFO("AST 2300 detected\n");
 		} else if (dev->pdev->revision >= 0x10) {
-			uint32_t data;
-			ast_write32(ast, 0xf004, 0x1e6e0000);
-			ast_write32(ast, 0xf000, 0x1);
-
-			data = ast_read32(ast, 0x1207c);
-			switch (data & 0x0300) {
+			switch (scu_rev & 0x0300) {
 			case 0x0200:
 				ast->chip = AST1100;
 				DRM_INFO("AST 1100 detected\n");
@@ -110,20 +176,6 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 		}
 	}
 
-	/*
-	 * If VGA isn't enabled, we need to enable now or subsequent
-	 * access to the scratch registers will fail. We also inform
-	 * our caller that it needs to POST the chip
-	 * (Assumption: VGA not enabled -> need to POST)
-	 */
-	if (!ast_is_vga_enabled(dev)) {
-		ast_enable_vga(dev);
-		ast_enable_mmio(dev);
-		DRM_INFO("VGA not enabled on entry, requesting chip POST\n");
-		*need_post = true;
-	} else
-		*need_post = false;
-
 	/* Check if we support wide screen */
 	switch (ast->chip) {
 	case AST1180:
@@ -140,14 +192,11 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 			ast->support_wide_screen = true;
 		else {
 			ast->support_wide_screen = false;
-			/* Read SCU7c (silicon revision register) */
-			ast_write32(ast, 0xf004, 0x1e6e0000);
-			ast_write32(ast, 0xf000, 0x1);
-			data = ast_read32(ast, 0x1207c);
-			data &= 0x300;
-			if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
+			if (ast->chip == AST2300 &&
+			    (scu_rev & 0x300) == 0x0) /* ast1300 */
 				ast->support_wide_screen = true;
-			if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
+			if (ast->chip == AST2400 &&
+			    (scu_rev & 0x300) == 0x100) /* ast1400 */
 				ast->support_wide_screen = true;
 		}
 		break;
@@ -212,28 +261,49 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 
 static int ast_get_dram_info(struct drm_device *dev)
 {
+	struct device_node *np = dev->pdev->dev.of_node;
 	struct ast_private *ast = dev->dev_private;
-	uint32_t data, data2;
-	uint32_t denum, num, div, ref_pll;
-
-	ast_write32(ast, 0xf004, 0x1e6e0000);
-	ast_write32(ast, 0xf000, 0x1);
-
-
-	ast_write32(ast, 0x10000, 0xfc600309);
+	uint32_t mcr_cfg, mcr_scu_mpll, mcr_scu_strap;
+	uint32_t denum, num, div, ref_pll, dsel;
 
-	do {
-		;
-	} while (ast_read32(ast, 0x10000) != 0x01);
-	data = ast_read32(ast, 0x10004);
+	switch (ast->config_mode) {
+	case ast_use_dt:
+		/*
+		 * If some properties are missing, use reasonable
+		 * defaults for AST2400
+		 */
+		if (of_property_read_u32(np, "aspeed,mcr-configuration",
+					 &mcr_cfg))
+			mcr_cfg = 0x00000577;
+		if (of_property_read_u32(np, "aspeed,mcr-scu-mpll",
+					 &mcr_scu_mpll))
+			mcr_scu_mpll = 0x000050C0;
+		if (of_property_read_u32(np, "aspeed,mcr-scu-strap",
+					 &mcr_scu_strap))
+			mcr_scu_strap = 0;
+		break;
+	case ast_use_p2a:
+		ast_write32(ast, 0xf004, 0x1e6e0000);
+		ast_write32(ast, 0xf000, 0x1);
+		mcr_cfg = ast_read32(ast, 0x10004);
+		mcr_scu_mpll = ast_read32(ast, 0x10120);
+		mcr_scu_strap = ast_read32(ast, 0x10170);
+		break;
+	case ast_use_defaults:
+	default:
+		ast->dram_bus_width = 16;
+		ast->dram_type = AST_DRAM_1Gx16;
+		ast->mclk = 396;
+		return 0;
+	}
 
-	if (data & 0x40)
+	if (mcr_cfg & 0x40)
 		ast->dram_bus_width = 16;
 	else
 		ast->dram_bus_width = 32;
 
 	if (ast->chip == AST2300 || ast->chip == AST2400) {
-		switch (data & 0x03) {
+		switch (mcr_cfg & 0x03) {
 		case 0:
 			ast->dram_type = AST_DRAM_512Mx16;
 			break;
@@ -249,13 +319,13 @@ static int ast_get_dram_info(struct drm_device *dev)
 			break;
 		}
 	} else {
-		switch (data & 0x0c) {
+		switch (mcr_cfg & 0x0c) {
 		case 0:
 		case 4:
 			ast->dram_type = AST_DRAM_512Mx16;
 			break;
 		case 8:
-			if (data & 0x40)
+			if (mcr_cfg & 0x40)
 				ast->dram_type = AST_DRAM_1Gx16;
 			else
 				ast->dram_type = AST_DRAM_512Mx32;
@@ -266,17 +336,15 @@ static int ast_get_dram_info(struct drm_device *dev)
 		}
 	}
 
-	data = ast_read32(ast, 0x10120);
-	data2 = ast_read32(ast, 0x10170);
-	if (data2 & 0x2000)
+	if (mcr_scu_strap & 0x2000)
 		ref_pll = 14318;
 	else
 		ref_pll = 12000;
 
-	denum = data & 0x1f;
-	num = (data & 0x3fe0) >> 5;
-	data = (data & 0xc000) >> 14;
-	switch (data) {
+	denum = mcr_scu_mpll & 0x1f;
+	num = (mcr_scu_mpll & 0x3fe0) >> 5;
+	dsel = (mcr_scu_mpll & 0xc000) >> 14;
+	switch (dsel) {
 	case 3:
 		div = 0x4;
 		break;
@@ -429,7 +497,9 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 	ast_detect_chip(dev, &need_post);
 
 	if (ast->chip != AST1180) {
-		ast_get_dram_info(dev);
+		ret = ast_get_dram_info(dev);
+		if (ret)
+			goto out_free;
 		ast->vram_size = ast_get_vram_info(dev);
 		DRM_INFO("dram %d %d %d %08x\n", ast->mclk, ast->dram_type, ast->dram_bus_width, ast->vram_size);
 	}
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 810c51d92b99..c7c58becb25d 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -58,13 +58,9 @@ bool ast_is_vga_enabled(struct drm_device *dev)
 		/* TODO 1180 */
 	} else {
 		ch = ast_io_read8(ast, AST_IO_VGA_ENABLE_PORT);
-		if (ch) {
-			ast_open_key(ast);
-			ch = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff);
-			return ch & 0x04;
-		}
+		return !!(ch & 0x01);
 	}
-	return 0;
+	return false;
 }
 
 static const u8 extreginfo[] = { 0x0f, 0x04, 0x1c, 0xff };
@@ -375,16 +371,21 @@ void ast_post_gpu(struct drm_device *dev)
 	pci_write_config_dword(ast->dev->pdev, 0x04, reg);
 
 	ast_enable_vga(dev);
-	ast_enable_mmio(dev);
 	ast_open_key(ast);
+	ast_enable_mmio(dev);
 	ast_set_def_ext_reg(dev);
 
-	if (ast->chip == AST2300 || ast->chip == AST2400)
-		ast_init_dram_2300(dev);
-	else
-		ast_init_dram_reg(dev);
+	if (ast->config_mode == ast_use_p2a) {
+		if (ast->chip == AST2300 || ast->chip == AST2400)
+			ast_init_dram_2300(dev);
+		else
+			ast_init_dram_reg(dev);
 
-	ast_init_3rdtx(dev);
+		ast_init_3rdtx(dev);
+	} else {
+		if (ast->tx_chip_type != AST_TX_NONE)
+			ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80);	/* Enable DVO */
+	}
 }
 
 /* AST 2300 DRAM settings */
@@ -1630,12 +1631,44 @@ static void ast_init_dram_2300(struct drm_device *dev)
 		temp |= 0x73;
 		ast_write32(ast, 0x12008, temp);
 
+		param.dram_freq = 396;
 		param.dram_type = AST_DDR3;
+		temp = ast_mindwm(ast, 0x1e6e2070);
 		if (temp & 0x01000000)
 			param.dram_type = AST_DDR2;
-		param.dram_chipid = ast->dram_type;
-		param.dram_freq = ast->mclk;
-		param.vram_size = ast->vram_size;
+                switch (temp & 0x18000000) {
+		case 0:
+			param.dram_chipid = AST_DRAM_512Mx16;
+			break;
+		default:
+		case 0x08000000:
+			param.dram_chipid = AST_DRAM_1Gx16;
+			break;
+		case 0x10000000:
+			param.dram_chipid = AST_DRAM_2Gx16;
+			break;
+		case 0x18000000:
+			param.dram_chipid = AST_DRAM_4Gx16;
+			break;
+		}
+                switch (temp & 0x0c) {
+                default:
+		case 0x00:
+			param.vram_size = AST_VIDMEM_SIZE_8M;
+			break;
+
+		case 0x04:
+			param.vram_size = AST_VIDMEM_SIZE_16M;
+			break;
+
+		case 0x08:
+			param.vram_size = AST_VIDMEM_SIZE_32M;
+			break;
+
+		case 0x0c:
+			param.vram_size = AST_VIDMEM_SIZE_64M;
+			break;
+		}
 
 		if (param.dram_type == AST_DDR3) {
 			get_ddr3_info(ast, &param);
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index d0299aed517e..e231176cb66b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -316,25 +316,27 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane,
 			u32 *coeff_tab = heo_upscaling_ycoef;
 			u32 max_memsize;
 
-			if (state->crtc_w < state->src_w)
+			if (state->crtc_h < state->src_h)
 				coeff_tab = heo_downscaling_ycoef;
 			for (i = 0; i < ARRAY_SIZE(heo_upscaling_ycoef); i++)
 				atmel_hlcdc_layer_update_cfg(&plane->layer,
 							     33 + i,
 							     0xffffffff,
 							     coeff_tab[i]);
-			factor = ((8 * 256 * state->src_w) - (256 * 4)) /
-				 state->crtc_w;
+			factor = ((8 * 256 * state->src_h) - (256 * 4)) /
+				 state->crtc_h;
 			factor++;
-			max_memsize = ((factor * state->crtc_w) + (256 * 4)) /
+			max_memsize = ((factor * state->crtc_h) + (256 * 4)) /
 				      2048;
-			if (max_memsize > state->src_w)
+			if (max_memsize > state->src_h)
 				factor--;
 			factor_reg |= (factor << 16) | 0x80000000;
 		}
 
 		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff,
 					     factor_reg);
+	} else {
+		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index aeee083c7f95..50d74e5ce41b 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -150,7 +150,7 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 	for (i = 0; i < state->num_connector; i++) {
 		struct drm_connector *connector = state->connectors[i];
 
-		if (!connector)
+		if (!connector || !connector->funcs)
 			continue;
 
 		/*
@@ -367,6 +367,8 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 		drm_property_unreference_blob(state->mode_blob);
 	state->mode_blob = NULL;
 
+	memset(&state->mode, 0, sizeof(state->mode));
+
 	if (blob) {
 		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
 		    drm_mode_convert_umode(&state->mode,
@@ -379,7 +381,6 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
 				 state->mode.name, state);
 	} else {
-		memset(&state->mode, 0, sizeof(state->mode));
 		state->enable = false;
 		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
 				 state);
@@ -1246,6 +1247,9 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 	if (config->funcs->atomic_check)
 		ret = config->funcs->atomic_check(state->dev, state);
 
+	if (ret)
+		return ret;
+
 	if (!state->allow_modeset) {
 		for_each_crtc_in_state(state, crtc, crtc_state, i) {
 			if (drm_atomic_crtc_needs_modeset(crtc_state)) {
@@ -1256,7 +1260,7 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 		}
 	}
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(drm_atomic_check_only);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index e5aec45bf985..ea443fafb934 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -108,7 +108,6 @@ steal_encoder(struct drm_atomic_state *state,
 	struct drm_crtc_state *crtc_state;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
-	int ret;
 
 	/*
 	 * We can only steal an encoder coming from a connector, which means we
@@ -139,9 +138,6 @@ steal_encoder(struct drm_atomic_state *state,
 		if (IS_ERR(connector_state))
 			return PTR_ERR(connector_state);
 
-		ret = drm_atomic_set_crtc_for_connector(connector_state, NULL);
-		if (ret)
-			return ret;
 		connector_state->best_encoder = NULL;
 	}
 
@@ -269,7 +265,7 @@ mode_fixup(struct drm_atomic_state *state)
 	struct drm_connector *connector;
 	struct drm_connector_state *conn_state;
 	int i;
-	bool ret;
+	int ret;
 
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		if (!crtc_state->mode_changed &&
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 6743ff7dccfa..7f4a6c550319 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -136,6 +136,7 @@ drm_clflush_virt_range(void *addr, unsigned long length)
 		mb();
 		for (; addr < end; addr += size)
 			clflushopt(addr);
+		clflushopt(end - 1); /* force serialisation */
 		mb();
 		return;
 	}
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 24c5434abd1c..5e4bb4837bae 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2682,8 +2682,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 			goto out;
 		}
 
-		drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
-
 		/*
 		 * Check whether the primary plane supports the fb pixel format.
 		 * Drivers not implementing the universal planes API use a
@@ -3316,6 +3314,24 @@ int drm_mode_addfb2(struct drm_device *dev,
 	return 0;
 }
 
+struct drm_mode_rmfb_work {
+	struct work_struct work;
+	struct list_head fbs;
+};
+
+static void drm_mode_rmfb_work_fn(struct work_struct *w)
+{
+	struct drm_mode_rmfb_work *arg = container_of(w, typeof(*arg), work);
+
+	while (!list_empty(&arg->fbs)) {
+		struct drm_framebuffer *fb =
+			list_first_entry(&arg->fbs, typeof(*fb), filp_head);
+
+		list_del_init(&fb->filp_head);
+		drm_framebuffer_remove(fb);
+	}
+}
+
 /**
  * drm_mode_rmfb - remove an FB from the configuration
  * @dev: drm device for the ioctl
@@ -3356,7 +3372,25 @@ int drm_mode_rmfb(struct drm_device *dev,
 	mutex_unlock(&dev->mode_config.fb_lock);
 	mutex_unlock(&file_priv->fbs_lock);
 
-	drm_framebuffer_unreference(fb);
+	/*
+	 * we now own the reference that was stored in the fbs list
+	 *
+	 * drm_framebuffer_remove may fail with -EINTR on pending signals,
+	 * so run this in a separate stack as there's no way to correctly
+	 * handle this after the fb is already removed from the lookup table.
+	 */
+	if (atomic_read(&fb->refcount.refcount) > 1) {
+		struct drm_mode_rmfb_work arg;
+
+		INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn);
+		INIT_LIST_HEAD(&arg.fbs);
+		list_add_tail(&fb->filp_head, &arg.fbs);
+
+		schedule_work(&arg.work);
+		flush_work(&arg.work);
+		destroy_work_on_stack(&arg.work);
+	} else
+		drm_framebuffer_unreference(fb);
 
 	return 0;
 
@@ -3509,7 +3543,6 @@ out_err1:
 	return ret;
 }
 
-
 /**
  * drm_fb_release - remove and free the FBs on this file
  * @priv: drm file for the ioctl
@@ -3524,6 +3557,9 @@ out_err1:
 void drm_fb_release(struct drm_file *priv)
 {
 	struct drm_framebuffer *fb, *tfb;
+	struct drm_mode_rmfb_work arg;
+
+	INIT_LIST_HEAD(&arg.fbs);
 
 	/*
 	 * When the file gets released that means no one else can access the fb
@@ -3536,10 +3572,22 @@ void drm_fb_release(struct drm_file *priv)
 	 * at it any more.
 	 */
 	list_for_each_entry_safe(fb, tfb, &priv->fbs, filp_head) {
-		list_del_init(&fb->filp_head);
+		if (atomic_read(&fb->refcount.refcount) > 1) {
+			list_move_tail(&fb->filp_head, &arg.fbs);
+		} else {
+			list_del_init(&fb->filp_head);
 
-		/* This drops the fpriv->fbs reference. */
-		drm_framebuffer_unreference(fb);
+			/* This drops the fpriv->fbs reference. */
+			drm_framebuffer_unreference(fb);
+		}
+	}
+
+	if (!list_empty(&arg.fbs)) {
+		INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn);
+
+		schedule_work(&arg.work);
+		flush_work(&arg.work);
+		destroy_work_on_stack(&arg.work);
 	}
 }
 
@@ -5183,6 +5231,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
 	    page_flip->reserved != 0)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 9535c5b60387..7e5a97204051 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -178,7 +178,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 {
 	struct drm_dp_aux_msg msg;
 	unsigned int retry;
-	int err;
+	int err = 0;
 
 	memset(&msg, 0, sizeof(msg));
 	msg.address = offset;
@@ -186,6 +186,8 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 	msg.buffer = buffer;
 	msg.size = size;
 
+	mutex_lock(&aux->hw_mutex);
+
 	/*
 	 * The specification doesn't give any recommendation on how often to
 	 * retry native transactions. We used to retry 7 times like for
@@ -194,25 +196,24 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 	 */
 	for (retry = 0; retry < 32; retry++) {
 
-		mutex_lock(&aux->hw_mutex);
 		err = aux->transfer(aux, &msg);
-		mutex_unlock(&aux->hw_mutex);
 		if (err < 0) {
 			if (err == -EBUSY)
 				continue;
 
-			return err;
+			goto unlock;
 		}
 
 
 		switch (msg.reply & DP_AUX_NATIVE_REPLY_MASK) {
 		case DP_AUX_NATIVE_REPLY_ACK:
 			if (err < size)
-				return -EPROTO;
-			return err;
+				err = -EPROTO;
+			goto unlock;
 
 		case DP_AUX_NATIVE_REPLY_NACK:
-			return -EIO;
+			err = -EIO;
+			goto unlock;
 
 		case DP_AUX_NATIVE_REPLY_DEFER:
 			usleep_range(AUX_RETRY_INTERVAL, AUX_RETRY_INTERVAL + 100);
@@ -221,7 +222,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 	}
 
 	DRM_DEBUG_KMS("too many retries, giving up\n");
-	return -EIO;
+	err = -EIO;
+
+unlock:
+	mutex_unlock(&aux->hw_mutex);
+	return err;
 }
 
 /**
@@ -543,9 +548,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 	int max_retries = max(7, drm_dp_i2c_retry_count(msg, dp_aux_i2c_speed_khz));
 
 	for (retry = 0, defer_i2c = 0; retry < (max_retries + defer_i2c); retry++) {
-		mutex_lock(&aux->hw_mutex);
 		ret = aux->transfer(aux, msg);
-		mutex_unlock(&aux->hw_mutex);
 		if (ret < 0) {
 			if (ret == -EBUSY)
 				continue;
@@ -684,6 +687,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs,
 
 	memset(&msg, 0, sizeof(msg));
 
+	mutex_lock(&aux->hw_mutex);
+
 	for (i = 0; i < num; i++) {
 		msg.address = msgs[i].addr;
 		drm_dp_i2c_msg_set_request(&msg, &msgs[i]);
@@ -738,6 +743,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs,
 	msg.size = 0;
 	(void)drm_dp_i2c_do_msg(aux, &msg);
 
+	mutex_unlock(&aux->hw_mutex);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 39d7e2e15c11..58bf94b69186 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -330,6 +330,13 @@ static bool drm_dp_sideband_msg_build(struct drm_dp_sideband_msg_rx *msg,
 			return false;
 		}
 
+		/*
+		 * ignore out-of-order messages or messages that are part of a
+		 * failed transaction
+		 */
+		if (!recv_hdr.somt && !msg->have_somt)
+			return false;
+
 		/* get length contained in this portion */
 		msg->curchunk_len = recv_hdr.msg_len;
 		msg->curchunk_hdrlen = hdrlen;
@@ -909,6 +916,7 @@ static void drm_dp_destroy_port(struct kref *kref)
 		/* no need to clean up vcpi
 		 * as if we have no connector we never setup a vcpi */
 		drm_dp_port_teardown_pdt(port, port->pdt);
+		port->pdt = DP_PEER_DEVICE_NONE;
 	}
 	kfree(port);
 }
@@ -1154,7 +1162,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 			drm_dp_put_port(port);
 			goto out;
 		}
-		if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+		if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
+		     port->pdt == DP_PEER_DEVICE_SST_SINK) &&
+		    port->port_num >= DP_MST_LOGICAL_PORT_0) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
 			drm_mode_connector_set_tile_property(port->connector);
 		}
@@ -1665,13 +1675,19 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	struct drm_dp_mst_branch *mstb;
 	int len, ret, port_num;
 
+	port = drm_dp_get_validated_port_ref(mgr, port);
+	if (!port)
+		return -EINVAL;
+
 	port_num = port->port_num;
 	mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent);
 	if (!mstb) {
 		mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num);
 
-		if (!mstb)
+		if (!mstb) {
+			drm_dp_put_port(port);
 			return -EINVAL;
+		}
 	}
 
 	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
@@ -1697,6 +1713,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr,
 	kfree(txmsg);
 fail_put:
 	drm_dp_put_mst_branch_device(mstb);
+	drm_dp_put_port(port);
 	return ret;
 }
 
@@ -1779,6 +1796,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 		req_payload.start_slot = cur_slots;
 		if (mgr->proposed_vcpis[i]) {
 			port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi);
+			port = drm_dp_get_validated_port_ref(mgr, port);
+			if (!port) {
+				mutex_unlock(&mgr->payload_lock);
+				return -EINVAL;
+			}
 			req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots;
 		} else {
 			port = NULL;
@@ -1797,13 +1819,16 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 				mgr->payloads[i].num_slots = req_payload.num_slots;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
-				drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
+				drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]);
 				req_payload.payload_state = mgr->payloads[i].payload_state;
 				mgr->payloads[i].start_slot = 0;
 			}
 			mgr->payloads[i].payload_state = req_payload.payload_state;
 		}
 		cur_slots += req_payload.num_slots;
+
+		if (port)
+			drm_dp_put_port(port);
 	}
 
 	for (i = 0; i < mgr->max_payloads; i++) {
@@ -2109,6 +2134,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 
 	if (mgr->mst_primary) {
 		int sret;
+		u8 guid[16];
+
 		sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE);
 		if (sret != DP_RECEIVER_CAP_SIZE) {
 			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
@@ -2123,6 +2150,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
 			ret = -1;
 			goto out_unlock;
 		}
+
+		/* Some hubs forget their guids after they resume */
+		sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+		if (sret != 16) {
+			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
+			ret = -1;
+			goto out_unlock;
+		}
+		drm_dp_check_mstb_guid(mgr->mst_primary, guid);
+
 		ret = 0;
 	} else
 		ret = -1;
@@ -2133,7 +2170,7 @@ out_unlock:
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_resume);
 
-static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up)
+static bool drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up)
 {
 	int len;
 	u8 replyblock[32];
@@ -2148,12 +2185,12 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up)
 			       replyblock, len);
 	if (ret != len) {
 		DRM_DEBUG_KMS("failed to read DPCD down rep %d %d\n", len, ret);
-		return;
+		return false;
 	}
 	ret = drm_dp_sideband_msg_build(msg, replyblock, len, true);
 	if (!ret) {
 		DRM_DEBUG_KMS("sideband msg build failed %d\n", replyblock[0]);
-		return;
+		return false;
 	}
 	replylen = msg->curchunk_len + msg->curchunk_hdrlen;
 
@@ -2165,21 +2202,32 @@ static void drm_dp_get_one_sb_msg(struct drm_dp_mst_topology_mgr *mgr, bool up)
 		ret = drm_dp_dpcd_read(mgr->aux, basereg + curreply,
 				    replyblock, len);
 		if (ret != len) {
-			DRM_DEBUG_KMS("failed to read a chunk\n");
+			DRM_DEBUG_KMS("failed to read a chunk (len %d, ret %d)\n",
+				      len, ret);
+			return false;
 		}
+
 		ret = drm_dp_sideband_msg_build(msg, replyblock, len, false);
-		if (ret == false)
+		if (!ret) {
 			DRM_DEBUG_KMS("failed to build sideband msg\n");
+			return false;
+		}
+
 		curreply += len;
 		replylen -= len;
 	}
+	return true;
 }
 
 static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr)
 {
 	int ret = 0;
 
-	drm_dp_get_one_sb_msg(mgr, false);
+	if (!drm_dp_get_one_sb_msg(mgr, false)) {
+		memset(&mgr->down_rep_recv, 0,
+		       sizeof(struct drm_dp_sideband_msg_rx));
+		return 0;
+	}
 
 	if (mgr->down_rep_recv.have_eomt) {
 		struct drm_dp_sideband_msg_tx *txmsg;
@@ -2235,7 +2283,12 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr)
 static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 {
 	int ret = 0;
-	drm_dp_get_one_sb_msg(mgr, true);
+
+	if (!drm_dp_get_one_sb_msg(mgr, true)) {
+		memset(&mgr->up_req_recv, 0,
+		       sizeof(struct drm_dp_sideband_msg_rx));
+		return 0;
+	}
 
 	if (mgr->up_req_recv.have_eomt) {
 		struct drm_dp_sideband_msg_req_body msg;
@@ -2287,7 +2340,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 			DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn);
 		}
 
-		drm_dp_put_mst_branch_device(mstb);
+		if (mstb)
+			drm_dp_put_mst_branch_device(mstb);
+
 		memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx));
 	}
 	return ret;
@@ -2845,13 +2900,12 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 		mgr->cbs->destroy_connector(mgr, port->connector);
 
 		drm_dp_port_teardown_pdt(port, port->pdt);
+		port->pdt = DP_PEER_DEVICE_NONE;
 
 		if (!port->input && port->vcpi.vcpi > 0) {
-			if (mgr->mst_state) {
-				drm_dp_mst_reset_vcpi_slots(mgr, port);
-				drm_dp_update_payload_part1(mgr);
-				drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
-			}
+			drm_dp_mst_reset_vcpi_slots(mgr, port);
+			drm_dp_update_payload_part1(mgr);
+			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
 		}
 
 		kref_put(&port->kref, drm_dp_free_mst_port);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index d5d2c03fd136..c0106fd9fae9 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -73,6 +73,10 @@
 #define EDID_QUIRK_FORCE_8BPC			(1 << 8)
 /* Force 12bpc */
 #define EDID_QUIRK_FORCE_12BPC			(1 << 9)
+/* Force 6bpc */
+#define EDID_QUIRK_FORCE_6BPC			(1 << 10)
+/* Force 10bpc */
+#define EDID_QUIRK_FORCE_10BPC			(1 << 11)
 
 struct detailed_mode_closure {
 	struct drm_connector *connector;
@@ -99,6 +103,9 @@ static struct edid_quirk {
 	/* Unknown Acer */
 	{ "ACR", 2423, EDID_QUIRK_FIRST_DETAILED_PREFERRED },
 
+	/* AEO model 0 reports 8 bpc, but is a 6 bpc panel */
+	{ "AEO", 0, EDID_QUIRK_FORCE_6BPC },
+
 	/* Belinea 10 15 55 */
 	{ "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 },
 	{ "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 },
@@ -112,6 +119,9 @@ static struct edid_quirk {
 	{ "FCM", 13600, EDID_QUIRK_PREFER_LARGE_75 |
 	  EDID_QUIRK_DETAILED_IN_CM },
 
+	/* LGD panel of HP zBook 17 G2, eDP 10 bpc, but reports unknown bpc */
+	{ "LGD", 764, EDID_QUIRK_FORCE_10BPC },
+
 	/* LG Philips LCD LP154W01-A5 */
 	{ "LPL", 0, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE },
 	{ "LPL", 0x2a00, EDID_QUIRK_DETAILED_USE_MAXIMUM_SIZE },
@@ -139,6 +149,9 @@ static struct edid_quirk {
 
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
+
+	/* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
+	{ "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
 };
 
 /*
@@ -3820,9 +3833,15 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 
 	drm_add_display_info(edid, &connector->display_info, connector);
 
+	if (quirks & EDID_QUIRK_FORCE_6BPC)
+		connector->display_info.bpc = 6;
+
 	if (quirks & EDID_QUIRK_FORCE_8BPC)
 		connector->display_info.bpc = 8;
 
+	if (quirks & EDID_QUIRK_FORCE_10BPC)
+		connector->display_info.bpc = 10;
+
 	if (quirks & EDID_QUIRK_FORCE_12BPC)
 		connector->display_info.bpc = 12;
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 69cbab5e5c81..5ad036741b99 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1899,7 +1899,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			  int n, int width, int height)
 {
 	int c, o;
-	struct drm_device *dev = fb_helper->dev;
 	struct drm_connector *connector;
 	const struct drm_connector_helper_funcs *connector_funcs;
 	struct drm_encoder *encoder;
@@ -1918,7 +1917,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	if (modes[n] == NULL)
 		return best_score;
 
-	crtcs = kzalloc(dev->mode_config.num_connector *
+	crtcs = kzalloc(fb_helper->connector_count *
 			sizeof(struct drm_fb_helper_crtc *), GFP_KERNEL);
 	if (!crtcs)
 		return best_score;
@@ -1964,7 +1963,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 		if (score > best_score) {
 			best_score = score;
 			memcpy(best_crtcs, crtcs,
-			       dev->mode_config.num_connector *
+			       fb_helper->connector_count *
 			       sizeof(struct drm_fb_helper_crtc *));
 		}
 	}
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index c7de454e8e88..9147113139be 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -338,27 +338,32 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	spin_unlock(&file_priv->table_lock);
 	idr_preload_end();
 	mutex_unlock(&dev->object_name_lock);
-	if (ret < 0) {
-		drm_gem_object_handle_unreference_unlocked(obj);
-		return ret;
-	}
+	if (ret < 0)
+		goto err_unref;
+
 	*handlep = ret;
 
 	ret = drm_vma_node_allow(&obj->vma_node, file_priv->filp);
-	if (ret) {
-		drm_gem_handle_delete(file_priv, *handlep);
-		return ret;
-	}
+	if (ret)
+		goto err_remove;
 
 	if (dev->driver->gem_open_object) {
 		ret = dev->driver->gem_open_object(obj, file_priv);
-		if (ret) {
-			drm_gem_handle_delete(file_priv, *handlep);
-			return ret;
-		}
+		if (ret)
+			goto err_revoke;
 	}
 
 	return 0;
+
+err_revoke:
+	drm_vma_node_revoke(&obj->vma_node, file_priv->filp);
+err_remove:
+	spin_lock(&file_priv->table_lock);
+	idr_remove(&file_priv->object_idr, *handlep);
+	spin_unlock(&file_priv->table_lock);
+err_unref:
+	drm_gem_object_handle_unreference_unlocked(obj);
+	return ret;
 }
 
 /**
@@ -710,13 +715,13 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_gem_object *obj = ptr;
 	struct drm_device *dev = obj->dev;
 
+	if (dev->driver->gem_close_object)
+		dev->driver->gem_close_object(obj, file_priv);
+
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_gem_remove_prime_handles(obj, file_priv);
 	drm_vma_node_revoke(&obj->vma_node, file_priv->filp);
 
-	if (dev->driver->gem_close_object)
-		dev->driver->gem_close_object(obj, file_priv);
-
 	drm_gem_object_handle_unreference_unlocked(obj);
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index 57676f8d7ecf..a6289752be16 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -1015,6 +1015,7 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
 typedef struct drm_mode_fb_cmd232 {
 	u32 fb_id;
 	u32 width;
@@ -1071,6 +1072,7 @@ static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd,
 
 	return 0;
 }
+#endif
 
 static drm_ioctl_compat_t *drm_compat_ioctls[] = {
 	[DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version,
@@ -1104,7 +1106,9 @@ static drm_ioctl_compat_t *drm_compat_ioctls[] = {
 	[DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw,
 #endif
 	[DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank,
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
 	[DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2,
+#endif
 };
 
 /**
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index cd74a0953f42..71a10f08522e 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1401,6 +1401,13 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev,
 		return NULL;
 
 	mode->type |= DRM_MODE_TYPE_USERDEF;
+	/* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */
+	if (cmd->xres == 1366 && mode->hdisplay == 1368) {
+		mode->hdisplay = 1366;
+		mode->hsync_start--;
+		mode->hsync_end--;
+		drm_mode_set_name(mode);
+	}
 	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 	return mode;
 }
@@ -1487,6 +1494,8 @@ int drm_mode_convert_umode(struct drm_display_mode *out,
 	if (out->status != MODE_OK)
 		goto out;
 
+	drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V);
+
 	ret = 0;
 
 out:
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 9f935f55d74c..968b31f39884 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -339,14 +339,17 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
  * using the PRIME helpers.
  */
 struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
-				     struct drm_gem_object *obj, int flags)
+				     struct drm_gem_object *obj,
+				     int flags)
 {
-	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-
-	exp_info.ops = &drm_gem_prime_dmabuf_ops;
-	exp_info.size = obj->size;
-	exp_info.flags = flags;
-	exp_info.priv = obj;
+	struct dma_buf_export_info exp_info = {
+		.exp_name = KBUILD_MODNAME, /* white lie for debug */
+		.owner = dev->driver->fops->owner,
+		.ops = &drm_gem_prime_dmabuf_ops,
+		.size = obj->size,
+		.flags = flags,
+		.priv = obj,
+	};
 
 	if (dev->driver->gem_prime_res_obj)
 		exp_info.resv = dev->driver->gem_prime_res_obj(obj);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 7f55ba6771c6..011211e4167d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -101,7 +101,7 @@ int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 
 err:
-	list_for_each_entry_reverse(subdrv, &subdrv->list, list) {
+	list_for_each_entry_continue_reverse(subdrv, &exynos_drm_subdrv_list, list) {
 		if (subdrv->close)
 			subdrv->close(dev, subdrv->dev, file);
 	}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 17cea400ae32..d3de377dc857 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -220,7 +220,7 @@ i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter)
  * FIXME: This is the old dp aux helper, gma500 is the last driver that needs to
  * be ported over to the new helper code in drm_dp_helper.c like i915 or radeon.
  */
-static int __deprecated
+static int
 i2c_dp_aux_add_bus(struct i2c_adapter *adapter)
 {
 	int error;
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
index 6b43ae3ffd73..1616af209bfc 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
@@ -72,7 +72,7 @@ static const char *const dsi_errors[] = {
 	"RX Prot Violation",
 	"HS Generic Write FIFO Full",
 	"LP Generic Write FIFO Full",
-	"Generic Read Data Avail"
+	"Generic Read Data Avail",
 	"Special Packet Sent",
 	"Tearing Effect",
 };
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 92e7e5795398..db98ab5cde3d 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -484,6 +484,9 @@ static const struct file_operations psb_gem_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = psb_unlocked_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
index ce0645d0c1e5..61e3a097a478 100644
--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
@@ -783,20 +783,23 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (scan->type & DRM_MODE_TYPE_PREFERRED) {
 			mode_dev->panel_fixed_mode =
 			    drm_mode_duplicate(dev, scan);
+			DRM_DEBUG_KMS("Using mode from DDC\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}
 
 	/* Failed to get EDID, what about VBT? do we need this? */
-	if (mode_dev->vbt_mode)
+	if (dev_priv->lfp_lvds_vbt_mode) {
 		mode_dev->panel_fixed_mode =
-		    drm_mode_duplicate(dev, mode_dev->vbt_mode);
+			drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode);
 
-	if (!mode_dev->panel_fixed_mode)
-		if (dev_priv->lfp_lvds_vbt_mode)
-			mode_dev->panel_fixed_mode =
-				drm_mode_duplicate(dev,
-					dev_priv->lfp_lvds_vbt_mode);
+		if (mode_dev->panel_fixed_mode) {
+			mode_dev->panel_fixed_mode->type |=
+				DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using mode from VBT\n");
+			goto out;
+		}
+	}
 
 	/*
 	 * If we didn't get EDID, try checking if the panel is already turned
@@ -813,6 +816,7 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		if (mode_dev->panel_fixed_mode) {
 			mode_dev->panel_fixed_mode->type |=
 			    DRM_MODE_TYPE_PREFERRED;
+			DRM_DEBUG_KMS("Using pre-programmed mode\n");
 			goto out;	/* FIXME: check for quirks */
 		}
 	}
diff --git a/drivers/gpu/drm/i2c/adv7511.c b/drivers/gpu/drm/i2c/adv7511.c
index 00416f23b5cb..dba5c0ea0827 100644
--- a/drivers/gpu/drm/i2c/adv7511.c
+++ b/drivers/gpu/drm/i2c/adv7511.c
@@ -36,7 +36,10 @@ struct adv7511 {
 	bool edid_read;
 
 	wait_queue_head_t wq;
+	struct work_struct hpd_work;
+
 	struct drm_encoder *encoder;
+	struct drm_connector connector;
 
 	bool embedded_sync;
 	enum adv7511_sync_polarity vsync_polarity;
@@ -48,6 +51,10 @@ struct adv7511 {
 	struct gpio_desc *gpio_pd;
 };
 
+static const int edid_i2c_addr = 0x7e;
+static const int packet_i2c_addr = 0x70;
+static const int cec_i2c_addr = 0x78;
+
 static struct adv7511 *encoder_to_adv7511(struct drm_encoder *encoder)
 {
 	return to_encoder_slave(encoder)->slave_priv;
@@ -362,12 +369,19 @@ static void adv7511_power_on(struct adv7511 *adv7511)
 {
 	adv7511->current_edid_segment = -1;
 
-	regmap_write(adv7511->regmap, ADV7511_REG_INT(0),
-		     ADV7511_INT0_EDID_READY);
-	regmap_write(adv7511->regmap, ADV7511_REG_INT(1),
-		     ADV7511_INT1_DDC_ERROR);
 	regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER,
 			   ADV7511_POWER_POWER_DOWN, 0);
+	if (adv7511->i2c_main->irq) {
+		/*
+		 * Documentation says the INT_ENABLE registers are reset in
+		 * POWER_DOWN mode. My 7511w preserved the bits, however.
+		 * Still, let's be safe and stick to the documentation.
+		 */
+		regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(0),
+			     ADV7511_INT0_EDID_READY);
+		regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(1),
+			     ADV7511_INT1_DDC_ERROR);
+	}
 
 	/*
 	 * Per spec it is allowed to pulse the HDP signal to indicate that the
@@ -422,7 +436,27 @@ static bool adv7511_hpd(struct adv7511 *adv7511)
 	return false;
 }
 
-static int adv7511_irq_process(struct adv7511 *adv7511)
+static void adv7511_hpd_work(struct work_struct *work)
+{
+	struct adv7511 *adv7511 = container_of(work, struct adv7511, hpd_work);
+	enum drm_connector_status status;
+	unsigned int val;
+	int ret;
+	ret = regmap_read(adv7511->regmap, ADV7511_REG_STATUS, &val);
+	if (ret < 0)
+		status = connector_status_disconnected;
+	else if (val & ADV7511_STATUS_HPD)
+		status = connector_status_connected;
+	else
+		status = connector_status_disconnected;
+
+	if (adv7511->connector.status != status) {
+		adv7511->connector.status = status;
+		drm_kms_helper_hotplug_event(adv7511->connector.dev);
+	}
+}
+
+static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd)
 {
 	unsigned int irq0, irq1;
 	int ret;
@@ -438,8 +472,8 @@ static int adv7511_irq_process(struct adv7511 *adv7511)
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0);
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1);
 
-	if (irq0 & ADV7511_INT0_HDP && adv7511->encoder)
-		drm_helper_hpd_irq_event(adv7511->encoder->dev);
+	if (process_hpd && irq0 & ADV7511_INT0_HDP && adv7511->encoder)
+		schedule_work(&adv7511->hpd_work);
 
 	if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) {
 		adv7511->edid_read = true;
@@ -456,7 +490,7 @@ static irqreturn_t adv7511_irq_handler(int irq, void *devid)
 	struct adv7511 *adv7511 = devid;
 	int ret;
 
-	ret = adv7511_irq_process(adv7511);
+	ret = adv7511_irq_process(adv7511, true);
 	return ret < 0 ? IRQ_NONE : IRQ_HANDLED;
 }
 
@@ -473,7 +507,7 @@ static int adv7511_wait_for_edid(struct adv7511 *adv7511, int timeout)
 				adv7511->edid_read, msecs_to_jiffies(timeout));
 	} else {
 		for (; timeout > 0; timeout -= 25) {
-			ret = adv7511_irq_process(adv7511);
+			ret = adv7511_irq_process(adv7511, false);
 			if (ret < 0)
 				break;
 
@@ -567,13 +601,18 @@ static int adv7511_get_modes(struct drm_encoder *encoder,
 
 	/* Reading the EDID only works if the device is powered */
 	if (!adv7511->powered) {
-		regmap_write(adv7511->regmap, ADV7511_REG_INT(0),
-			     ADV7511_INT0_EDID_READY);
-		regmap_write(adv7511->regmap, ADV7511_REG_INT(1),
-			     ADV7511_INT1_DDC_ERROR);
 		regmap_update_bits(adv7511->regmap, ADV7511_REG_POWER,
 				   ADV7511_POWER_POWER_DOWN, 0);
+		if (adv7511->i2c_main->irq) {
+			regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(0),
+				     ADV7511_INT0_EDID_READY);
+			regmap_write(adv7511->regmap, ADV7511_REG_INT_ENABLE(1),
+				     ADV7511_INT1_DDC_ERROR);
+		}
 		adv7511->current_edid_segment = -1;
+		/* Reset the EDID_I2C_ADDR register as it might be cleared */
+		regmap_write(adv7511->regmap, ADV7511_REG_EDID_I2C_ADDR,
+				edid_i2c_addr);
 	}
 
 	edid = drm_do_get_edid(connector, adv7511_get_edid_block, adv7511);
@@ -849,10 +888,6 @@ static int adv7511_parse_dt(struct device_node *np,
 	return 0;
 }
 
-static const int edid_i2c_addr = 0x7e;
-static const int packet_i2c_addr = 0x70;
-static const int cec_i2c_addr = 0x78;
-
 static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 {
 	struct adv7511_link_config link_config;
@@ -913,6 +948,8 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	if (!adv7511->i2c_edid)
 		return -ENOMEM;
 
+	INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work);
+
 	if (i2c->irq) {
 		init_waitqueue_head(&adv7511->wq);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d3ce4da6a6ad..5044f2257e89 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1159,7 +1159,7 @@ struct intel_gen6_power_mgmt {
 	struct intel_rps_client semaphores, mmioflips;
 
 	/* manual wa residency calculations */
-	struct intel_rps_ei up_ei, down_ei;
+	struct intel_rps_ei ei;
 
 	/*
 	 * Protects RPS/RC6 register access and PCU communication.
@@ -2150,21 +2150,19 @@ struct drm_i915_gem_object {
 	/** Record of address bit 17 of each page at last unbind. */
 	unsigned long *bit_17;
 
-	union {
-		/** for phy allocated objects */
-		struct drm_dma_handle *phys_handle;
-
-		struct i915_gem_userptr {
-			uintptr_t ptr;
-			unsigned read_only :1;
-			unsigned workers :4;
+	struct i915_gem_userptr {
+		uintptr_t ptr;
+		unsigned read_only :1;
+		unsigned workers :4;
 #define I915_GEM_USERPTR_MAX_WORKERS 15
 
-			struct i915_mm_struct *mm;
-			struct i915_mmu_object *mmu_object;
-			struct work_struct *work;
-		} userptr;
-	};
+		struct i915_mm_struct *mm;
+		struct i915_mmu_object *mmu_object;
+		struct work_struct *work;
+	} userptr;
+
+	/** for phys allocated objects */
+	struct drm_dma_handle *phys_handle;
 };
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
@@ -3313,6 +3311,9 @@ static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
 }
 extern void intel_i2c_reset(struct drm_device *dev);
 
+/* intel_bios.c */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port);
+
 /* intel_opregion.c */
 #ifdef CONFIG_ACPI
 extern int intel_opregion_setup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 86c7500454b4..b37fe0df743e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2747,6 +2747,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev)
 		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
 
 		ppgtt->base.cleanup(&ppgtt->base);
+		kfree(ppgtt);
 	}
 
 	if (drm_mm_initialized(&vm->mm)) {
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index f7df54a8ee2b..c0a96f1ee18e 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -39,7 +39,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 87e919a06b27..5d2323a40c25 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -108,17 +108,28 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 		pci_read_config_dword(dev->pdev, 0x5c, &base);
 		base &= ~((1<<20) - 1);
 	} else if (IS_I865G(dev)) {
+		u32 tseg_size = 0;
 		u16 toud = 0;
+		u8 tmp;
+
+		pci_bus_read_config_byte(dev->pdev->bus, PCI_DEVFN(0, 0),
+					 I845_ESMRAMC, &tmp);
+
+		if (tmp & TSEG_ENABLE) {
+			switch (tmp & I845_TSEG_SIZE_MASK) {
+			case I845_TSEG_SIZE_512K:
+				tseg_size = KB(512);
+				break;
+			case I845_TSEG_SIZE_1M:
+				tseg_size = MB(1);
+				break;
+			}
+		}
 
-		/*
-		 * FIXME is the graphics stolen memory region
-		 * always at TOUD? Ie. is it always the last
-		 * one to be allocated by the BIOS?
-		 */
 		pci_bus_read_config_word(dev->pdev->bus, PCI_DEVFN(0, 0),
 					 I865_TOUD, &toud);
 
-		base = toud << 16;
+		base = (toud << 16) + tseg_size;
 	} else if (IS_I85X(dev)) {
 		u32 tseg_size = 0;
 		u32 tom;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0f42a2782afc..b7b0a38acd67 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -994,68 +994,51 @@ static void vlv_c0_read(struct drm_i915_private *dev_priv,
 	ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
 }
 
-static bool vlv_c0_above(struct drm_i915_private *dev_priv,
-			 const struct intel_rps_ei *old,
-			 const struct intel_rps_ei *now,
-			 int threshold)
-{
-	u64 time, c0;
-	unsigned int mul = 100;
-
-	if (old->cz_clock == 0)
-		return false;
-
-	if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
-		mul <<= 8;
-
-	time = now->cz_clock - old->cz_clock;
-	time *= threshold * dev_priv->czclk_freq;
-
-	/* Workload can be split between render + media, e.g. SwapBuffers
-	 * being blitted in X after being rendered in mesa. To account for
-	 * this we need to combine both engines into our activity counter.
-	 */
-	c0 = now->render_c0 - old->render_c0;
-	c0 += now->media_c0 - old->media_c0;
-	c0 *= mul * VLV_CZ_CLOCK_TO_MILLI_SEC;
-
-	return c0 >= time;
-}
-
 void gen6_rps_reset_ei(struct drm_i915_private *dev_priv)
 {
-	vlv_c0_read(dev_priv, &dev_priv->rps.down_ei);
-	dev_priv->rps.up_ei = dev_priv->rps.down_ei;
+	memset(&dev_priv->rps.ei, 0, sizeof(dev_priv->rps.ei));
 }
 
 static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 {
+	const struct intel_rps_ei *prev = &dev_priv->rps.ei;
 	struct intel_rps_ei now;
 	u32 events = 0;
 
-	if ((pm_iir & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) == 0)
+	if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
 		return 0;
 
 	vlv_c0_read(dev_priv, &now);
 	if (now.cz_clock == 0)
 		return 0;
 
-	if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
-		if (!vlv_c0_above(dev_priv,
-				  &dev_priv->rps.down_ei, &now,
-				  dev_priv->rps.down_threshold))
-			events |= GEN6_PM_RP_DOWN_THRESHOLD;
-		dev_priv->rps.down_ei = now;
-	}
+	if (prev->cz_clock) {
+		u64 time, c0;
+		unsigned int mul;
 
-	if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
-		if (vlv_c0_above(dev_priv,
-				 &dev_priv->rps.up_ei, &now,
-				 dev_priv->rps.up_threshold))
-			events |= GEN6_PM_RP_UP_THRESHOLD;
-		dev_priv->rps.up_ei = now;
+		mul = VLV_CZ_CLOCK_TO_MILLI_SEC * 100; /* scale to threshold% */
+		if (I915_READ(VLV_COUNTER_CONTROL) & VLV_COUNT_RANGE_HIGH)
+			mul <<= 8;
+
+		time = now.cz_clock - prev->cz_clock;
+		time *= dev_priv->czclk_freq;
+
+		/* Workload can be split between render + media,
+		 * e.g. SwapBuffers being blitted in X after being rendered in
+		 * mesa. To account for this we need to combine both engines
+		 * into our activity counter.
+		 */
+		c0 = now.render_c0 - prev->render_c0;
+		c0 += now.media_c0 - prev->media_c0;
+		c0 *= mul;
+
+		if (c0 > time * dev_priv->rps.up_threshold)
+			events = GEN6_PM_RP_UP_THRESHOLD;
+		else if (c0 < time * dev_priv->rps.down_threshold)
+			events = GEN6_PM_RP_DOWN_THRESHOLD;
 	}
 
+	dev_priv->rps.ei = now;
 	return events;
 }
 
@@ -4390,7 +4373,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	/* Let's track the enabled rps events */
 	if (IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		/* WaGsvRC0ResidencyMethod:vlv */
-		dev_priv->pm_rps_events = GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED;
+		dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
 	else
 		dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index bc7b8faba84d..cace154bbdc0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2838,7 +2838,14 @@ enum skl_disp_power_wells {
 #define GEN6_RP_STATE_CAP	(MCHBAR_MIRROR_BASE_SNB + 0x5998)
 #define BXT_RP_STATE_CAP        0x138170
 
-#define INTERVAL_1_28_US(us)	(((us) * 100) >> 7)
+/*
+ * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
+ * 8300) freezing up around GPU hangs. Looks as if even
+ * scheduling/timer interrupts start misbehaving if the RPS
+ * EI/thresholds are "bad", leading to a very sluggish or even
+ * frozen machine.
+ */
+#define INTERVAL_1_28_US(us)	roundup(((us) * 100) >> 7, 25)
 #define INTERVAL_1_33_US(us)	(((us) * 3)   >> 2)
 #define INTERVAL_0_833_US(us)	(((us) * 6) / 5)
 #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \
@@ -3233,19 +3240,20 @@ enum skl_disp_power_wells {
 
 #define PORT_HOTPLUG_STAT	(dev_priv->info.display_mmio_offset + 0x61114)
 /*
- * HDMI/DP bits are gen4+
+ * HDMI/DP bits are g4x+
  *
  * 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)
+/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */
+#define   PORTD_HOTPLUG_LIVE_STATUS_GM45	(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_GM45	(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_GM45	(1 << 27)
+/* G4X/VLV/CHV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
 #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   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTD_HOTPLUG_INT_LONG_PULSE		(2 << 21)
 #define   PORTD_HOTPLUG_INT_SHORT_PULSE		(1 << 21)
@@ -7350,6 +7358,8 @@ enum skl_disp_power_wells {
 #define  TRANS_CLK_SEL_DISABLED		(0x0<<29)
 #define  TRANS_CLK_SEL_PORT(x)		(((x)+1)<<29)
 
+#define CDCLK_FREQ			0x46200
+
 #define TRANSA_MSA_MISC			0x60410
 #define TRANSB_MSA_MISC			0x61410
 #define TRANSC_MSA_MISC			0x62410
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index ce82f9c7df24..d14bdc537587 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1351,3 +1351,42 @@ intel_parse_bios(struct drm_device *dev)
 
 	return 0;
 }
+
+/**
+ * intel_bios_is_port_present - is the specified digital port present
+ * @dev_priv:	i915 device instance
+ * @port:	port to check
+ *
+ * Return true if the device in %port is present.
+ */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
+{
+	static const struct {
+		u16 dp, hdmi;
+	} port_mapping[] = {
+		[PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, },
+		[PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
+		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
+		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+	};
+	int i;
+
+	/* FIXME maybe deal with port A as well? */
+	if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
+		return false;
+
+	if (!dev_priv->vbt.child_dev_num)
+		return false;
+
+	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
+		const union child_device_config *p_child =
+			&dev_priv->vbt.child_dev[i];
+		if ((p_child->common.dvo_port == port_mapping[port].dp ||
+		     p_child->common.dvo_port == port_mapping[port].hdmi) &&
+		    (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING |
+						    DEVICE_TYPE_DISPLAYPORT_OUTPUT)))
+			return true;
+	}
+
+	return false;
+}
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 6a2c76e367a5..63fea6a2869c 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -248,8 +248,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	/* LPT FDI RX only supports 8bpc. */
-	if (HAS_PCH_LPT(dev))
+	if (HAS_PCH_LPT(dev)) {
+		if (pipe_config->bw_constrained && pipe_config->pipe_bpp < 24) {
+			DRM_DEBUG_KMS("LPT only supports 24bpp\n");
+			return false;
+		}
+
 		pipe_config->pipe_bpp = 24;
+	}
 
 	/* FDI must always be 2.7 GHz */
 	if (HAS_DDI(dev)) {
@@ -439,6 +445,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = crt->base.base.dev->dev_private;
 	struct edid *edid;
 	struct i2c_adapter *i2c;
+	bool ret = false;
 
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
@@ -455,17 +462,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 */
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
-			return true;
+			ret = true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
-
-		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 	} else {
 		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n");
 	}
 
 	kfree(edid);
 
-	return false;
+	return ret;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 9e530a739354..fc28c512ece3 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -180,7 +180,8 @@ struct stepping_info {
 static const struct stepping_info skl_stepping_info[] = {
 		{'A', '0'}, {'B', '0'}, {'C', '0'},
 		{'D', '0'}, {'E', '0'}, {'F', '0'},
-		{'G', '0'}, {'H', '0'}, {'I', '0'}
+		{'G', '0'}, {'H', '0'}, {'I', '0'},
+		{'J', '0'}, {'K', '0'}
 };
 
 static struct stepping_info bxt_stepping_info[] = {
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 7e6158b889da..3c6b07683bd9 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -464,9 +464,17 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
 	} else if (IS_BROADWELL(dev)) {
 		ddi_translations_fdi = bdw_ddi_translations_fdi;
 		ddi_translations_dp = bdw_ddi_translations_dp;
-		ddi_translations_edp = bdw_ddi_translations_edp;
+
+		if (dev_priv->edp_low_vswing) {
+			ddi_translations_edp = bdw_ddi_translations_edp;
+			n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp);
+		} else {
+			ddi_translations_edp = bdw_ddi_translations_dp;
+			n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
+		}
+
 		ddi_translations_hdmi = bdw_ddi_translations_hdmi;
-		n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp);
+
 		n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
 		n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
 		hdmi_default_entry = 7;
@@ -3188,12 +3196,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	intel_ddi_clock_get(encoder, pipe_config);
 }
 
-static void intel_ddi_destroy(struct drm_encoder *encoder)
-{
-	/* HDMI has nothing special to destroy, so we can go with this. */
-	intel_dp_encoder_destroy(encoder);
-}
-
 static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
@@ -3212,7 +3214,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 }
 
 static const struct drm_encoder_funcs intel_ddi_funcs = {
-	.destroy = intel_ddi_destroy,
+	.reset = intel_dp_encoder_reset,
+	.destroy = intel_dp_encoder_destroy,
 };
 
 static struct intel_connector *
@@ -3284,6 +3287,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	intel_encoder->post_disable = intel_ddi_post_disable;
 	intel_encoder->get_hw_state = intel_ddi_get_hw_state;
 	intel_encoder->get_config = intel_ddi_get_config;
+	intel_encoder->suspend = intel_dp_encoder_suspend;
 
 	intel_dig_port->port = port;
 	intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f859a5b87ed4..4f5d07bb3511 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2950,13 +2950,13 @@ u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier,
 	}
 }
 
-unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
-				     struct drm_i915_gem_object *obj,
-				     unsigned int plane)
+u32 intel_plane_obj_offset(struct intel_plane *intel_plane,
+			   struct drm_i915_gem_object *obj,
+			   unsigned int plane)
 {
 	const struct i915_ggtt_view *view = &i915_ggtt_view_normal;
 	struct i915_vma *vma;
-	unsigned char *offset;
+	u64 offset;
 
 	if (intel_rotation_90_or_270(intel_plane->base.state->rotation))
 		view = &i915_ggtt_view_rotated;
@@ -2966,14 +2966,16 @@ unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
 		view->type))
 		return -1;
 
-	offset = (unsigned char *)vma->node.start;
+	offset = vma->node.start;
 
 	if (plane == 1) {
 		offset += vma->ggtt_view.rotation_info.uv_start_page *
 			  PAGE_SIZE;
 	}
 
-	return (unsigned long)offset;
+	WARN_ON(upper_32_bits(offset));
+
+	return lower_32_bits(offset);
 }
 
 static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
@@ -3099,7 +3101,7 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc,
 	u32 tile_height, plane_offset, plane_size;
 	unsigned int rotation;
 	int x_offset, y_offset;
-	unsigned long surf_addr;
+	u32 surf_addr;
 	struct intel_crtc_state *crtc_state = intel_crtc->config;
 	struct intel_plane_state *plane_state;
 	int src_x = 0, src_y = 0, src_w = 0, src_h = 0;
@@ -3946,10 +3948,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->work);
-
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
+
+	queue_work(dev_priv->wq, &work->work);
 }
 
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
@@ -4447,7 +4449,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state)
 		      intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX);
 
 	return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
-		&state->scaler_state.scaler_id, DRM_ROTATE_0,
+		&state->scaler_state.scaler_id, BIT(DRM_ROTATE_0),
 		state->pipe_src_w, state->pipe_src_h,
 		adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay);
 }
@@ -8228,12 +8230,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_encoder *encoder;
+	int i;
 	u32 val, final;
 	bool has_lvds = false;
 	bool has_cpu_edp = false;
 	bool has_panel = false;
 	bool has_ck505 = false;
 	bool can_ssc = false;
+	bool using_ssc_source = false;
 
 	/* We need to take the global config into account */
 	for_each_intel_encoder(dev, encoder) {
@@ -8260,8 +8264,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		can_ssc = true;
 	}
 
-	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n",
-		      has_panel, has_lvds, has_ck505);
+	/* Check if any DPLLs are using the SSC source */
+	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+		u32 temp = I915_READ(PCH_DPLL(i));
+
+		if (!(temp & DPLL_VCO_ENABLE))
+			continue;
+
+		if ((temp & PLL_REF_INPUT_MASK) ==
+		    PLLB_REF_INPUT_SPREADSPECTRUMIN) {
+			using_ssc_source = true;
+			break;
+		}
+	}
+
+	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n",
+		      has_panel, has_lvds, has_ck505, using_ssc_source);
 
 	/* Ironlake: try to setup display ref clock before DPLL
 	 * enabling. This is only under driver's control after
@@ -8298,9 +8316,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 				final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
 		} else
 			final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
-	} else {
-		final |= DREF_SSC_SOURCE_DISABLE;
-		final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
+	} else if (using_ssc_source) {
+		final |= DREF_SSC_SOURCE_ENABLE;
+		final |= DREF_SSC1_ENABLE;
 	}
 
 	if (final == val)
@@ -8346,7 +8364,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 	} else {
-		DRM_DEBUG_KMS("Disabling SSC entirely\n");
+		DRM_DEBUG_KMS("Disabling CPU source output\n");
 
 		val &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
 
@@ -8357,16 +8375,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 
-		/* Turn off the SSC source */
-		val &= ~DREF_SSC_SOURCE_MASK;
-		val |= DREF_SSC_SOURCE_DISABLE;
+		if (!using_ssc_source) {
+			DRM_DEBUG_KMS("Disabling SSC source\n");
 
-		/* Turn off SSC1 */
-		val &= ~DREF_SSC1_ENABLE;
+			/* Turn off the SSC source */
+			val &= ~DREF_SSC_SOURCE_MASK;
+			val |= DREF_SSC_SOURCE_DISABLE;
 
-		I915_WRITE(PCH_DREF_CONTROL, val);
-		POSTING_READ(PCH_DREF_CONTROL);
-		udelay(200);
+			/* Turn off SSC1 */
+			val &= ~DREF_SSC1_ENABLE;
+
+			I915_WRITE(PCH_DREF_CONTROL, val);
+			POSTING_READ(PCH_DREF_CONTROL);
+			udelay(200);
+		}
 	}
 
 	BUG_ON(val != final);
@@ -9669,6 +9691,8 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
 	sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
+	I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1);
+
 	intel_update_cdclk(dev);
 
 	WARN(cdclk != dev_priv->cdclk_freq,
@@ -11930,21 +11954,11 @@ connected_sink_compute_bpp(struct intel_connector *connector,
 		pipe_config->pipe_bpp = connector->base.display_info.bpc*3;
 	}
 
-	/* Clamp bpp to default limit on screens without EDID 1.4 */
-	if (connector->base.display_info.bpc == 0) {
-		int type = connector->base.connector_type;
-		int clamp_bpp = 24;
-
-		/* Fall back to 18 bpp when DP sink capability is unknown. */
-		if (type == DRM_MODE_CONNECTOR_DisplayPort ||
-		    type == DRM_MODE_CONNECTOR_eDP)
-			clamp_bpp = 18;
-
-		if (bpp > clamp_bpp) {
-			DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n",
-				      bpp, clamp_bpp);
-			pipe_config->pipe_bpp = clamp_bpp;
-		}
+	/* Clamp bpp to 8 on screens without EDID 1.4 */
+	if (connector->base.display_info.bpc == 0 && bpp > 24) {
+		DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n",
+			      bpp);
+		pipe_config->pipe_bpp = 24;
 	}
 }
 
@@ -14148,6 +14162,8 @@ static void intel_setup_outputs(struct drm_device *dev)
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev)) {
+		bool has_edp, has_port;
+
 		/*
 		 * The DP_DETECTED bit is the latched state of the DDC
 		 * SDA pin at boot. However since eDP doesn't require DDC
@@ -14156,27 +14172,37 @@ static void intel_setup_outputs(struct drm_device *dev)
 		 * Thus we can't rely on the DP_DETECTED bit alone to detect
 		 * eDP ports. Consult the VBT as well as DP_DETECTED to
 		 * detect eDP ports.
+		 *
+		 * Sadly the straps seem to be missing sometimes even for HDMI
+		 * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap
+		 * and VBT for the presence of the port. Additionally we can't
+		 * trust the port type the VBT declares as we've seen at least
+		 * HDMI ports that the VBT claim are DP or eDP.
 		 */
-		if (I915_READ(VLV_HDMIB) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_B))
+		has_edp = intel_dp_is_edp(dev, PORT_B);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_B);
+		if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B);
+		if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIB, PORT_B);
-		if (I915_READ(VLV_DP_B) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_B))
-			intel_dp_init(dev, VLV_DP_B, PORT_B);
 
-		if (I915_READ(VLV_HDMIC) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_C))
+		has_edp = intel_dp_is_edp(dev, PORT_C);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_C);
+		if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C);
+		if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIC, PORT_C);
-		if (I915_READ(VLV_DP_C) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_C))
-			intel_dp_init(dev, VLV_DP_C, PORT_C);
 
 		if (IS_CHERRYVIEW(dev)) {
-			/* eDP not supported on port D, so don't check VBT */
-			if (I915_READ(CHV_HDMID) & SDVO_DETECTED)
-				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
-			if (I915_READ(CHV_DP_D) & DP_DETECTED)
+			/*
+			 * eDP not supported on port D,
+			 * so no need to worry about it
+			 */
+			has_port = intel_bios_is_port_present(dev_priv, PORT_D);
+			if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port)
 				intel_dp_init(dev, CHV_DP_D, PORT_D);
+			if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port)
+				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
 		}
 
 		intel_dsi_init(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 78b8ec84d576..0f8367da0663 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3628,8 +3628,7 @@ static bool
 intel_dp_reset_link_train(struct intel_dp *intel_dp, uint32_t *DP,
 			uint8_t dp_train_pat)
 {
-	if (!intel_dp->train_set_valid)
-		memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
+	memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
 	intel_dp_set_signal_levels(intel_dp, DP);
 	return intel_dp_set_link_train(intel_dp, DP, dp_train_pat);
 }
@@ -3746,22 +3745,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 			break;
 		}
 
-		/*
-		 * if we used previously trained voltage and pre-emphasis values
-		 * and we don't get clock recovery, reset link training values
-		 */
-		if (intel_dp->train_set_valid) {
-			DRM_DEBUG_KMS("clock recovery not ok, reset");
-			/* clear the flag as we are not reusing train set */
-			intel_dp->train_set_valid = false;
-			if (!intel_dp_reset_link_train(intel_dp, &DP,
-						       DP_TRAINING_PATTERN_1 |
-						       DP_LINK_SCRAMBLING_DISABLE)) {
-				DRM_ERROR("failed to enable link training\n");
-				return;
-			}
-			continue;
-		}
 
 		/* Check to see if we've tried the max voltage */
 		for (i = 0; i < intel_dp->lane_count; i++)
@@ -3854,7 +3837,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 		/* Make sure clock is still ok */
 		if (!drm_dp_clock_recovery_ok(link_status,
 					      intel_dp->lane_count)) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp, &DP,
 						training_pattern |
@@ -3871,7 +3853,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 
 		/* Try 5 times, then try clock recovery if that fails */
 		if (tries > 5) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp, &DP,
 						training_pattern |
@@ -3893,10 +3874,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 
 	intel_dp->DP = DP;
 
-	if (channel_eq) {
-		intel_dp->train_set_valid = true;
+	if (channel_eq)
 		DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
-	}
 }
 
 void intel_dp_stop_link_train(struct intel_dp *intel_dp)
@@ -4613,20 +4592,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv,
+					struct intel_digital_port *port)
 {
 	u32 bit;
 
 	switch (port->port) {
 	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTB_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTC_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTD_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	default:
 		MISSING_CASE(port->port);
@@ -4669,7 +4648,7 @@ static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv,
  *
  * Return %true if @port is connected, %false otherwise.
  */
-bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
+static bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 					 struct intel_digital_port *port)
 {
 	if (HAS_PCH_IBX(dev_priv))
@@ -4678,8 +4657,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 		return cpt_digital_port_connected(dev_priv, port);
 	else if (IS_BROXTON(dev_priv))
 		return bxt_digital_port_connected(dev_priv, port);
-	else if (IS_VALLEYVIEW(dev_priv))
-		return vlv_digital_port_connected(dev_priv, port);
+	else if (IS_GM45(dev_priv))
+		return gm45_digital_port_connected(dev_priv, port);
 	else
 		return g4x_digital_port_connected(dev_priv, port);
 }
@@ -5035,7 +5014,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	kfree(intel_dig_port);
 }
 
-static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
+void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
 
@@ -5077,15 +5056,17 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 	edp_panel_vdd_schedule_off(intel_dp);
 }
 
-static void intel_dp_encoder_reset(struct drm_encoder *encoder)
+void intel_dp_encoder_reset(struct drm_encoder *encoder)
 {
-	struct intel_dp *intel_dp;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+	if (!HAS_DDI(dev_priv))
+		intel_dp->DP = I915_READ(intel_dp->output_reg);
 
 	if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP)
 		return;
 
-	intel_dp = enc_to_intel_dp(encoder);
-
 	pps_lock(intel_dp);
 
 	/*
@@ -5157,9 +5138,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	intel_display_power_get(dev_priv, power_domain);
 
 	if (long_hpd) {
-		/* indicate that we need to restart link training */
-		intel_dp->train_set_valid = false;
-
 		if (!intel_digital_port_connected(dev_priv, intel_dig_port))
 			goto mst_fail;
 
@@ -6135,8 +6113,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	return true;
 }
 
-void
-intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
+bool intel_dp_init(struct drm_device *dev,
+		   int output_reg,
+		   enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_digital_port *intel_dig_port;
@@ -6146,7 +6125,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 
 	intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL);
 	if (!intel_dig_port)
-		return;
+		return false;
 
 	intel_connector = intel_connector_alloc();
 	if (!intel_connector)
@@ -6201,15 +6180,14 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	if (!intel_dp_init_connector(intel_dig_port, intel_connector))
 		goto err_init_connector;
 
-	return;
+	return true;
 
 err_init_connector:
 	drm_encoder_cleanup(encoder);
 	kfree(intel_connector);
 err_connector_alloc:
 	kfree(intel_dig_port);
-
-	return;
+	return false;
 }
 
 void intel_dp_mst_suspend(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 0639275fc471..06bd9257acdc 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -477,6 +477,8 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_device *dev = connector->dev;
 
+	intel_connector->unregister(intel_connector);
+
 	/* need to nuke the connector */
 	drm_modeset_lock_all(dev);
 	if (connector->state->crtc) {
@@ -490,11 +492,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 
 		WARN(ret, "Disabling mst crtc failed with %i\n", ret);
 	}
-	drm_modeset_unlock_all(dev);
 
-	intel_connector->unregister(intel_connector);
-
-	drm_modeset_lock_all(dev);
 	intel_connector_remove_from_fbdev(intel_connector);
 	drm_connector_cleanup(connector);
 	drm_modeset_unlock_all(dev);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0d00f07b7163..722aa159cd28 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -783,7 +783,6 @@ struct intel_dp {
 				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider);
-	bool train_set_valid;
 
 	/* Displayport compliance testing */
 	unsigned long compliance_test_type;
@@ -1178,9 +1177,9 @@ void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
 
-unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
-				     struct drm_i915_gem_object *obj,
-				     unsigned int plane);
+u32 intel_plane_obj_offset(struct intel_plane *intel_plane,
+			   struct drm_i915_gem_object *obj,
+			   unsigned int plane);
 
 u32 skl_plane_ctl_format(uint32_t pixel_format);
 u32 skl_plane_ctl_tiling(uint64_t fb_modifier);
@@ -1196,7 +1195,7 @@ void intel_csr_ucode_fini(struct drm_device *dev);
 void assert_csr_loaded(struct drm_i915_private *dev_priv);
 
 /* intel_dp.c */
-void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
+bool intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 			     struct intel_connector *intel_connector);
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
@@ -1204,6 +1203,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp,
 void intel_dp_start_link_train(struct intel_dp *intel_dp);
 void intel_dp_stop_link_train(struct intel_dp *intel_dp);
 void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
+void intel_dp_encoder_reset(struct drm_encoder *encoder);
+void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
 int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc);
 bool intel_dp_compute_config(struct intel_encoder *encoder,
@@ -1230,8 +1231,6 @@ void intel_edp_drrs_disable(struct intel_dp *intel_dp);
 void intel_edp_drrs_invalidate(struct drm_device *dev,
 		unsigned frontbuffer_bits);
 void intel_edp_drrs_flush(struct drm_device *dev, unsigned frontbuffer_bits);
-bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
-					 struct intel_digital_port *port);
 void hsw_dp_set_ddi_pll_sel(struct intel_crtc_state *pipe_config);
 
 /* intel_dp_mst.c */
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 4fd5fdfef6bd..c0c094d5b822 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -362,12 +362,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	uint64_t conn_configured = 0, mask;
 	int pass = 0;
 
-	save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool),
+	save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool),
 			       GFP_KERNEL);
 	if (!save_enabled)
 		return false;
 
-	memcpy(save_enabled, enabled, dev->mode_config.num_connector);
+	memcpy(save_enabled, enabled, fb_helper->connector_count);
 	mask = (1 << fb_helper->connector_count) - 1;
 retry:
 	for (i = 0; i < fb_helper->connector_count; i++) {
@@ -501,7 +501,7 @@ retry:
 	if (fallback) {
 bail:
 		DRM_DEBUG_KMS("Not using firmware configuration\n");
-		memcpy(enabled, save_enabled, dev->mode_config.num_connector);
+		memcpy(enabled, save_enabled, fb_helper->connector_count);
 		kfree(save_enabled);
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index e6c035b0fc1c..1ea8532f5ab2 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1331,19 +1331,18 @@ intel_hdmi_unset_edid(struct drm_connector *connector)
 }
 
 static bool
-intel_hdmi_set_edid(struct drm_connector *connector, bool force)
+intel_hdmi_set_edid(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
-	struct edid *edid = NULL;
+	struct edid *edid;
 	bool connected = false;
 
 	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
-	if (force)
-		edid = drm_get_edid(connector,
-				    intel_gmbus_get_adapter(dev_priv,
-				    intel_hdmi->ddc_bus));
+	edid = drm_get_edid(connector,
+			    intel_gmbus_get_adapter(dev_priv,
+			    intel_hdmi->ddc_bus));
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
 
@@ -1371,29 +1370,16 @@ static enum drm_connector_status
 intel_hdmi_detect(struct drm_connector *connector, bool force)
 {
 	enum drm_connector_status status;
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	bool live_status = false;
-	unsigned int try;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 
 	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
-	for (try = 0; !live_status && try < 9; try++) {
-		if (try)
-			msleep(10);
-		live_status = intel_digital_port_connected(dev_priv,
-				hdmi_to_dig_port(intel_hdmi));
-	}
-
-	if (!live_status)
-		DRM_DEBUG_KMS("Live status not up!");
-
 	intel_hdmi_unset_edid(connector);
 
-	if (intel_hdmi_set_edid(connector, live_status)) {
+	if (intel_hdmi_set_edid(connector)) {
 		struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 
 		hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
@@ -1419,7 +1405,7 @@ intel_hdmi_force(struct drm_connector *connector)
 	if (connector->status != connector_status_connected)
 		return;
 
-	intel_hdmi_set_edid(connector, true);
+	intel_hdmi_set_edid(connector);
 	hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
 }
 
@@ -2011,6 +1997,50 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 	intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 }
 
+static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
+			     enum port port)
+{
+	const struct ddi_vbt_port_info *info =
+		&dev_priv->vbt.ddi_port_info[port];
+	u8 ddc_pin;
+
+	if (info->alternate_ddc_pin) {
+		DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (VBT)\n",
+			      info->alternate_ddc_pin, port_name(port));
+		return info->alternate_ddc_pin;
+	}
+
+	switch (port) {
+	case PORT_B:
+		if (IS_BROXTON(dev_priv))
+			ddc_pin = GMBUS_PIN_1_BXT;
+		else
+			ddc_pin = GMBUS_PIN_DPB;
+		break;
+	case PORT_C:
+		if (IS_BROXTON(dev_priv))
+			ddc_pin = GMBUS_PIN_2_BXT;
+		else
+			ddc_pin = GMBUS_PIN_DPC;
+		break;
+	case PORT_D:
+		if (IS_CHERRYVIEW(dev_priv))
+			ddc_pin = GMBUS_PIN_DPD_CHV;
+		else
+			ddc_pin = GMBUS_PIN_DPD;
+		break;
+	default:
+		MISSING_CASE(port);
+		ddc_pin = GMBUS_PIN_DPB;
+		break;
+	}
+
+	DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (platform default)\n",
+		      ddc_pin, port_name(port));
+
+	return ddc_pin;
+}
+
 void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 			       struct intel_connector *intel_connector)
 {
@@ -2020,7 +2050,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum port port = intel_dig_port->port;
-	uint8_t alternate_ddc_pin;
+
+	DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
+		      port_name(port));
 
 	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
@@ -2030,12 +2062,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	connector->doublescan_allowed = 0;
 	connector->stereo_allowed = 1;
 
+	intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
+
 	switch (port) {
 	case PORT_B:
-		if (IS_BROXTON(dev_priv))
-			intel_hdmi->ddc_bus = GMBUS_PIN_1_BXT;
-		else
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
 		/*
 		 * On BXT A0/A1, sw needs to activate DDIA HPD logic and
 		 * interrupts to check the external panel connection.
@@ -2046,46 +2076,17 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 			intel_encoder->hpd_pin = HPD_PORT_B;
 		break;
 	case PORT_C:
-		if (IS_BROXTON(dev_priv))
-			intel_hdmi->ddc_bus = GMBUS_PIN_2_BXT;
-		else
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPC;
 		intel_encoder->hpd_pin = HPD_PORT_C;
 		break;
 	case PORT_D:
-		if (WARN_ON(IS_BROXTON(dev_priv)))
-			intel_hdmi->ddc_bus = GMBUS_PIN_DISABLED;
-		else if (IS_CHERRYVIEW(dev_priv))
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPD_CHV;
-		else
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPD;
 		intel_encoder->hpd_pin = HPD_PORT_D;
 		break;
 	case PORT_E:
-		/* On SKL PORT E doesn't have seperate GMBUS pin
-		 *  We rely on VBT to set a proper alternate GMBUS pin. */
-		alternate_ddc_pin =
-			dev_priv->vbt.ddi_port_info[PORT_E].alternate_ddc_pin;
-		switch (alternate_ddc_pin) {
-		case DDC_PIN_B:
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
-			break;
-		case DDC_PIN_C:
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPC;
-			break;
-		case DDC_PIN_D:
-			intel_hdmi->ddc_bus = GMBUS_PIN_DPD;
-			break;
-		default:
-			MISSING_CASE(alternate_ddc_pin);
-		}
 		intel_encoder->hpd_pin = HPD_PORT_E;
 		break;
-	case PORT_A:
-		intel_encoder->hpd_pin = HPD_PORT_A;
-		/* Internal port only for eDP. */
 	default:
-		BUG();
+		MISSING_CASE(port);
+		return;
 	}
 
 	if (IS_VALLEYVIEW(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d69547a65dbb..7058f75c7b42 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -776,11 +776,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 6dc13c02c28e..e362a30776fa 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -682,7 +682,7 @@ static void intel_didl_outputs(struct drm_device *dev)
 	}
 
 	if (!acpi_video_bus) {
-		DRM_ERROR("No ACPI video bus found\n");
+		DRM_DEBUG_KMS("No ACPI video bus found\n");
 		return;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f091ad12d694..fd4690ed93c0 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1789,16 +1789,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
 				   const struct intel_plane_state *pstate,
 				   uint32_t mem_value)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	/*
+	 * We treat the cursor plane as always-on for the purposes of watermark
+	 * calculation.  Until we have two-stage watermark programming merged,
+	 * this is necessary to avoid flickering.
+	 */
+	int cpp = 4;
+	int width = pstate->visible ? pstate->base.crtc_w : 64;
 
-	if (!cstate->base.active || !pstate->visible)
+	if (!cstate->base.active)
 		return 0;
 
 	return ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 			      cstate->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&pstate->dst),
-			      bpp,
-			      mem_value);
+			      width, cpp, mem_value);
 }
 
 /* Only for WM_LP. */
@@ -2093,32 +2097,34 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 				GEN9_MEM_LATENCY_LEVEL_MASK;
 
 		/*
+		 * If a level n (n > 1) has a 0us latency, all levels m (m >= n)
+		 * need to be disabled. We make sure to sanitize the values out
+		 * of the punit to satisfy this requirement.
+		 */
+		for (level = 1; level <= max_level; level++) {
+			if (wm[level] == 0) {
+				for (i = level + 1; i <= max_level; i++)
+					wm[i] = 0;
+				break;
+			}
+		}
+
+		/*
 		 * WaWmMemoryReadLatency:skl
 		 *
 		 * punit doesn't take into account the read latency so we need
-		 * to add 2us to the various latency levels we retrieve from
-		 * the punit.
-		 *   - W0 is a bit special in that it's the only level that
-		 *   can't be disabled if we want to have display working, so
-		 *   we always add 2us there.
-		 *   - For levels >=1, punit returns 0us latency when they are
-		 *   disabled, so we respect that and don't add 2us then
-		 *
-		 * Additionally, if a level n (n > 1) has a 0us latency, all
-		 * levels m (m >= n) need to be disabled. We make sure to
-		 * sanitize the values out of the punit to satisfy this
-		 * requirement.
+		 * to add 2us to the various latency levels we retrieve from the
+		 * punit when level 0 response data us 0us.
 		 */
-		wm[0] += 2;
-		for (level = 1; level <= max_level; level++)
-			if (wm[level] != 0)
+		if (wm[0] == 0) {
+			wm[0] += 2;
+			for (level = 1; level <= max_level; level++) {
+				if (wm[level] == 0)
+					break;
 				wm[level] += 2;
-			else {
-				for (i = level + 1; i <= max_level; i++)
-					wm[i] = 0;
-
-				break;
 			}
+		}
+
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		uint64_t sskpd = I915_READ64(MCH_SSKPD);
 
@@ -3880,6 +3886,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
 
+	memset(active, 0, sizeof(*active));
+
 	active->pipe_enabled = intel_crtc->active;
 
 	if (active->pipe_enabled) {
@@ -4368,6 +4376,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		break;
 	}
 
+	/* When byt can survive without system hang with dynamic
+	 * sw freq adjustments, this restriction can be lifted.
+	 */
+	if (IS_VALLEYVIEW(dev_priv))
+		goto skip_hw_write;
+
 	I915_WRITE(GEN6_RP_UP_EI,
 		GT_INTERVAL_FROM_US(dev_priv, ei_up));
 	I915_WRITE(GEN6_RP_UP_THRESHOLD,
@@ -4386,6 +4400,7 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		    GEN6_RP_UP_BUSY_AVG |
 		    GEN6_RP_DOWN_IDLE_AVG);
 
+skip_hw_write:
 	dev_priv->rps.power = new_power;
 	dev_priv->rps.up_threshold = threshold_up;
 	dev_priv->rps.down_threshold = threshold_down;
@@ -4396,8 +4411,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 {
 	u32 mask = 0;
 
+	/* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
 	if (val > dev_priv->rps.min_freq_softlimit)
-		mask |= GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
+		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
 	if (val < dev_priv->rps.max_freq_softlimit)
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
 
@@ -4501,7 +4517,7 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED))
+		if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
 			gen6_rps_reset_ei(dev_priv);
 		I915_WRITE(GEN6_PMINTRMSK,
 			   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
@@ -4520,7 +4536,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 		else
 			gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
 		dev_priv->rps.last_adj = 0;
-		I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
+		I915_WRITE(GEN6_PMINTRMSK,
+			   gen6_sanitize_rps_pm_mask(dev_priv, ~0));
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -6620,6 +6637,12 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 	I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT);
+	/*
+	 * Wait at least 100 clocks before re-enabling clock gating. See
+	 * the definition of L3SQCREG1 in BSpec.
+	 */
+	POSTING_READ(GEN8_L3SQCREG1);
+	udelay(1);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	/*
@@ -6788,7 +6811,18 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 
 static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
+        u32 val;
+
+        /*
+        * On driver load, a pipe may be active and driving a DSI display.
+        * Preserve DPOUNIT_CLOCK_GATE_DISABLE to avoid the pipe getting stuck
+        * (and never recovering) in this case. intel_dsi_post_disable() will
+        * clear it when we turn off the display.
+        */
+        val = I915_READ(DSPCLK_GATE_D);
+        val &= DPOUNIT_CLOCK_GATE_DISABLE;
+        val |= VRHUNIT_CLOCK_GATE_DISABLE;
+        I915_WRITE(DSPCLK_GATE_D, val);
 
 	/*
 	 * Disable trickle feed and enable pnd deadline calculation
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index f6b2a814e629..9d48443bca2e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1922,6 +1922,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
 	return 0;
 }
 
+static void cleanup_phys_status_page(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+
+	if (!dev_priv->status_page_dmah)
+		return;
+
+	drm_pci_free(ring->dev, dev_priv->status_page_dmah);
+	ring->status_page.page_addr = NULL;
+}
+
 static void cleanup_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_object *obj;
@@ -1938,9 +1949,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring)
 
 static int init_status_page(struct intel_engine_cs *ring)
 {
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj = ring->status_page.obj;
 
-	if ((obj = ring->status_page.obj) == NULL) {
+	if (obj == NULL) {
 		unsigned flags;
 		int ret;
 
@@ -2134,7 +2145,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		if (ret)
 			goto error;
 	} else {
-		BUG_ON(ring->id != RCS);
+		WARN_ON(ring->id != RCS);
 		ret = init_phys_status_page(ring);
 		if (ret)
 			goto error;
@@ -2179,7 +2190,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
 	if (ring->cleanup)
 		ring->cleanup(ring);
 
-	cleanup_status_page(ring);
+	if (I915_NEED_GFX_HWS(ring->dev)) {
+		cleanup_status_page(ring);
+	} else {
+		WARN_ON(ring->id != RCS);
+		cleanup_phys_status_page(ring);
+	}
 
 	i915_cmd_parser_fini_ring(ring);
 	i915_gem_batch_pool_fini(&ring->batch_pool);
@@ -2341,11 +2357,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 56dc132e8e20..2cc6aa072f4c 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -195,7 +195,7 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
 	const struct drm_intel_sprite_colorkey *key =
 		&to_intel_plane_state(drm_plane->state)->ckey;
-	unsigned long surf_addr;
+	u32 surf_addr;
 	u32 tile_height, plane_offset, plane_size;
 	unsigned int rotation;
 	int x_offset, y_offset;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 43cba129a0c0..6fd7b50c5747 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -635,7 +635,8 @@ hsw_unclaimed_reg_detect(struct drm_i915_private *dev_priv)
 			  "enabling oneshot unclaimed register reporting. "
 			  "Please use i915.mmio_debug=N for more information.\n");
 		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-		i915.mmio_debug = mmio_debug_once--;
+		i915.mmio_debug = mmio_debug_once;
+		mmio_debug_once = false;
 	}
 }
 
@@ -1132,7 +1133,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		dev_priv->uncore.funcs.force_wake_get =
 			fw_domains_get_with_thread_status;
-		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
+		if (IS_HASWELL(dev))
+			dev_priv->uncore.funcs.force_wake_put =
+				fw_domains_put_with_fifo;
+		else
+			dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_ACK_HSW);
 	} else if (IS_IVYBRIDGE(dev)) {
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 7b990b4e96d2..5378bdc3bbf9 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -26,6 +26,7 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_of.h>
+#include <video/imx-ipu-v3.h>
 
 #include "imx-drm.h"
 
@@ -504,6 +505,13 @@ static int compare_of(struct device *dev, void *data)
 {
 	struct device_node *np = data;
 
+	/* Special case for DI, dev->of_node may not be set yet */
+	if (strcmp(dev->driver->name, "imx-ipuv3-crtc") == 0) {
+		struct ipu_client_platformdata *pdata = dev->platform_data;
+
+		return pdata->of_node == np;
+	}
+
 	/* Special case for LDB, one device for two channels */
 	if (of_node_cmp(np->name, "lvds-channel") == 0) {
 		np = of_get_parent(np);
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 4ab841eebee1..9b0abd44b751 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -369,7 +369,7 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 
 	ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc,
 			&ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs,
-			ipu_crtc->dev->of_node);
+			pdata->of_node);
 	if (ret) {
 		dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret);
 		goto err_put_resources;
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index c99d3fe12881..e5bb40e58020 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -194,7 +194,7 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
 			}
 		}
 
-		fvv = pllreffreq * testn / testm;
+		fvv = pllreffreq * (n + 1) / (m + 1);
 		fvv = (fvv - 800000) / 50000;
 
 		if (fvv > 15)
@@ -214,6 +214,14 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
 	WREG_DAC(MGA1064_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_PIX_PLLC_N, n);
 	WREG_DAC(MGA1064_PIX_PLLC_P, p);
+
+	if (mdev->unique_rev_id >= 0x04) {
+		WREG_DAC(0x1a, 0x09);
+		msleep(20);
+		WREG_DAC(0x1a, 0x01);
+
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index a3b54cc76495..b66ffd44ff26 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -204,7 +204,14 @@ int adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 void adreno_flush(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	uint32_t wptr = get_wptr(gpu->rb);
+	uint32_t wptr;
+
+	/*
+	 * Mask wptr value that we calculate to fit in the HW range. This is
+	 * to account for the possibility that the last command fit exactly into
+	 * the ringbuffer and rb->next hasn't wrapped to zero yet
+	 */
+	wptr = get_wptr(gpu->rb) & ((gpu->rb->size / 4) - 1);
 
 	/* ensure writes to ringbuffer have hit system memory: */
 	mb();
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b88ce514eb8e..24d45fc7716c 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -986,6 +986,7 @@ static struct drm_driver msm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export   = drm_gem_prime_export,
 	.gem_prime_import   = drm_gem_prime_import,
+	.gem_prime_res_obj  = msm_gem_prime_res_obj,
 	.gem_prime_pin      = msm_gem_prime_pin,
 	.gem_prime_unpin    = msm_gem_prime_unpin,
 	.gem_prime_get_sg_table = msm_gem_prime_get_sg_table,
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 3be7a56b14f1..026e156e519c 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -212,6 +212,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *msm_gem_prime_vmap(struct drm_gem_object *obj);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 121975b07cd4..1fbddc5c7281 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -70,3 +70,10 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj)
 	if (!obj->import_attach)
 		msm_gem_put_pages(obj);
 }
+
+struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	return msm_obj->resv;
+}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 6d7cd3fe21e7..fed44d4e5b72 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -55,6 +55,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	return submit;
 }
 
+static inline unsigned long __must_check
+copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_from_user_inatomic(to, from, n);
+	return -EFAULT;
+}
+
 static int submit_lookup_objects(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
@@ -62,6 +70,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	int ret = 0;
 
 	spin_lock(&file->table_lock);
+	pagefault_disable();
 
 	for (i = 0; i < args->nr_bos; i++) {
 		struct drm_msm_gem_submit_bo submit_bo;
@@ -70,13 +79,19 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 		void __user *userptr =
 			to_user_ptr(args->bos + (i * sizeof(submit_bo)));
 
-		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
-		if (ret) {
-			ret = -EFAULT;
-			goto out_unlock;
+		ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo));
+		if (unlikely(ret)) {
+			pagefault_enable();
+			spin_unlock(&file->table_lock);
+			ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+			if (ret)
+				goto out;
+			spin_lock(&file->table_lock);
+			pagefault_disable();
 		}
 
-		if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
+		if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) ||
+			!(submit_bo.flags & MSM_SUBMIT_BO_FLAGS)) {
 			DRM_ERROR("invalid flags: %x\n", submit_bo.flags);
 			ret = -EINVAL;
 			goto out_unlock;
@@ -113,9 +128,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	}
 
 out_unlock:
-	submit->nr_bos = i;
+	pagefault_enable();
 	spin_unlock(&file->table_lock);
 
+out:
+	submit->nr_bos = i;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 1f14b908b221..ae317271cf81 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -23,7 +23,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
 	struct msm_ringbuffer *ring;
 	int ret;
 
-	size = ALIGN(size, 4);   /* size should be dword aligned */
+	if (WARN_ON(!is_power_of_2(size)))
+		return ERR_PTR(-EINVAL);
 
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
 	if (!ring) {
diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c
index 956a833b8200..57c7389feee4 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/hw.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c
@@ -222,6 +222,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t mpllP;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
+		mpllP = (mpllP >> 8) & 0xf;
 		if (!mpllP)
 			mpllP = 4;
 
@@ -232,7 +233,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t clock;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
-		return clock;
+		return clock / 1000;
 	}
 
 	ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
index 82d3e28918fd..7e4f24ae7de8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
@@ -4,6 +4,7 @@
 
 struct nvkm_alarm {
 	struct list_head head;
+	struct list_head exec;
 	u64 timestamp;
 	void (*func)(struct nvkm_alarm *);
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 4dca65a63b92..af224fafa21f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -333,6 +333,9 @@ get_fp_strap(struct drm_device *dev, struct nvbios *bios)
 	if (bios->major_version < 5 && bios->data[0x48] & 0x4)
 		return NVReadVgaCrtc5758(dev, 0, 0xf) & 0xf;
 
+	if (drm->device.info.family >= NV_DEVICE_INFO_V0_MAXWELL)
+		return nvif_rd32(device, 0x001800) & 0x0000000f;
+	else
 	if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA)
 		return (nvif_rd32(device, NV_PEXTDEV_BOOT_0) >> 24) & 0xf;
 	else
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 58a3f7cf2fb3..00de1bf81519 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -370,7 +370,8 @@ nouveau_display_init(struct drm_device *dev)
 		return ret;
 
 	/* enable polling for external displays */
-	drm_kms_helper_poll_enable(dev);
+	if (!dev->mode_config.poll_enabled)
+		drm_kms_helper_poll_enable(dev);
 
 	/* enable hotplug interrupts */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 1d3ee5179ab8..91a61d2cca88 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -308,7 +308,16 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	bool boot = false;
 	int ret;
 
-	/* remove conflicting drivers (vesafb, efifb etc) */
+	/* We need to check that the chipset is supported before booting
+	 * fbdev off the hardware, as there's no way to put it back.
+	 */
+	ret = nvkm_device_pci_new(pdev, NULL, "error", true, false, 0, &device);
+	if (ret)
+		return ret;
+
+	nvkm_device_del(&device);
+
+	/* Remove conflicting drivers (vesafb, efifb etc). */
 	aper = alloc_apertures(3);
 	if (!aper)
 		return -ENOMEM;
@@ -734,7 +743,10 @@ nouveau_pmops_runtime_resume(struct device *dev)
 	pci_set_master(pdev);
 
 	ret = nouveau_do_resume(drm_dev, true);
-	drm_kms_helper_poll_enable(drm_dev);
+
+	if (!drm_dev->mode_config.poll_enabled)
+		drm_kms_helper_poll_enable(drm_dev);
+
 	/* do magic */
 	nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
 	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 59f27e774acb..e40a1b07a014 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -557,6 +557,8 @@ nouveau_fbcon_init(struct drm_device *dev)
 	if (ret)
 		goto fini;
 
+	if (fbcon->helper.fbdev)
+		fbcon->helper.fbdev->pixmap.buf_align = 4;
 	return 0;
 
 fini:
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 2e3a62d38fe9..1621c8ae0fa0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -99,6 +99,7 @@ struct nv84_fence_priv {
 	struct nouveau_bo *bo;
 	struct nouveau_bo *bo_gart;
 	u32 *suspend;
+	struct mutex mutex;
 };
 
 u64  nv84_fence_crtc(struct nouveau_channel *, int);
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 6ae1b3494bcd..b7b961233949 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,8 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc)
 	if (nvif_unpack(argv->v0, 0, 0, true)) {
 		/* block access to objects not created via this interface */
 		owner = argv->v0.owner;
-		if (argv->v0.object == 0ULL)
+		if (argv->v0.object == 0ULL &&
+		    argv->v0.type != NVIF_IOCTL_V0_DEL)
 			argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
 		else
 			argv->v0.owner = NVDRM_OBJECT_USIF;
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 789dc2993b0d..f90568327468 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -82,7 +82,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	uint32_t fg;
 	uint32_t bg;
 	uint32_t dsize;
-	uint32_t width;
 	uint32_t *data = (uint32_t *)image->data;
 	int ret;
 
@@ -93,9 +92,6 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 8);
-	dsize = ALIGN(width * image->height, 32) >> 5;
-
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
 		fg = ((uint32_t *) info->pseudo_palette)[image->fg_color];
@@ -111,10 +107,11 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 			 ((image->dx + image->width) & 0xffff));
 	OUT_RING(chan, bg);
 	OUT_RING(chan, fg);
-	OUT_RING(chan, (image->height << 16) | width);
+	OUT_RING(chan, (image->height << 16) | ALIGN(image->width, 8));
 	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->dy << 16) | (image->dx & 0xffff));
 
+	dsize = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dsize) {
 		int iter_len = dsize > 128 ? 128 : dsize;
 
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index e05499d6ed83..c8e096533f60 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -95,7 +95,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NV04(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING(chan, 0);
 	OUT_RING(chan, image->dy);
 
+	dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 412c5be5a9ca..7bc26eceda66 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -121,8 +121,10 @@ nv84_fence_context_del(struct nouveau_channel *chan)
 	}
 
 	nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence);
+	mutex_lock(&priv->mutex);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma_gart);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma);
+	mutex_unlock(&priv->mutex);
 	nouveau_fence_context_del(&fctx->base);
 	chan->fence = NULL;
 	nouveau_fence_context_free(&fctx->base);
@@ -148,11 +150,13 @@ nv84_fence_context_new(struct nouveau_channel *chan)
 	fctx->base.sync32 = nv84_fence_sync32;
 	fctx->base.sequence = nv84_fence_read(chan);
 
+	mutex_lock(&priv->mutex);
 	ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma);
 	if (ret == 0) {
 		ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm,
 					&fctx->vma_gart);
 	}
+	mutex_unlock(&priv->mutex);
 
 	/* map display semaphore buffers into channel's vm */
 	for (i = 0; !ret && i < chan->drm->dev->mode_config.num_crtc; i++) {
@@ -232,6 +236,8 @@ nv84_fence_create(struct nouveau_drm *drm)
 	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	priv->base.uevent = true;
 
+	mutex_init(&priv->mutex);
+
 	/* Use VRAM if there is any ; otherwise fallback to system memory */
 	domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM :
 			 /*
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index c97395b4a312..22d32578dafd 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -95,7 +95,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NVC0(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING  (chan, 0);
 	OUT_RING  (chan, image->dy);
 
+	dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c
index 3216e157a8a0..89da47234016 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/ramht.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/ramht.c
@@ -131,7 +131,7 @@ nvkm_ramht_del(struct nvkm_ramht **pramht)
 	struct nvkm_ramht *ramht = *pramht;
 	if (ramht) {
 		nvkm_gpuobj_del(&ramht->gpuobj);
-		kfree(*pramht);
+		vfree(*pramht);
 		*pramht = NULL;
 	}
 }
@@ -143,8 +143,8 @@ nvkm_ramht_new(struct nvkm_device *device, u32 size, u32 align,
 	struct nvkm_ramht *ramht;
 	int ret, i;
 
-	if (!(ramht = *pramht = kzalloc(sizeof(*ramht) + (size >> 3) *
-					sizeof(*ramht->data), GFP_KERNEL)))
+	if (!(ramht = *pramht = vzalloc(sizeof(*ramht) +
+					(size >> 3) * sizeof(*ramht->data))))
 		return -ENOMEM;
 
 	ramht->device = device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index bbc9824af6e0..7f8acb3ebfcd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -714,7 +714,7 @@ nv4a_chipset = {
 	.i2c = nv04_i2c_new,
 	.imem = nv40_instmem_new,
 	.mc = nv44_mc_new,
-	.mmu = nv44_mmu_new,
+	.mmu = nv04_mmu_new,
 	.pci = nv40_pci_new,
 	.therm = nv40_therm_new,
 	.timer = nv41_timer_new,
@@ -1833,7 +1833,7 @@ nvf1_chipset = {
 	.fb = gk104_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gf119_i2c_new,
+	.i2c = gk104_i2c_new,
 	.ibus = gk104_ibus_new,
 	.imem = nv50_instmem_new,
 	.ltc = gk104_ltc_new,
@@ -1941,7 +1941,7 @@ nv117_chipset = {
 	.fb = gm107_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gf119_i2c_new,
+	.i2c = gk104_i2c_new,
 	.ibus = gk104_ibus_new,
 	.imem = nv50_instmem_new,
 	.ltc = gm107_ltc_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
index c1590b746f13..eb58cd7bfbc9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
@@ -59,7 +59,7 @@ gt215_hda_eld(NV50_DISP_MTHD_V1)
 			);
 		}
 		for (i = 0; i < size; i++)
-			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]);
+			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]);
 		for (; i < 0x60; i++)
 			nvkm_wr32(device, 0x61c440 + soff, (i << 8));
 		nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index b4b41b135643..2aaf0dd19a55 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -40,8 +40,8 @@ static int
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	const u32 loff = gf119_sor_loff(outp);
-	nvkm_mask(device, 0x61c110 + loff, 0x0f0f0f0f, 0x01010101 * pattern);
+	const u32 soff = gf119_sor_soff(outp);
+	nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
index bfcc6408a772..b7f4b826febe 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
@@ -36,7 +36,10 @@ nv04_fifo_dma_object_dtor(struct nvkm_fifo_chan *base, int cookie)
 {
 	struct nv04_fifo_chan *chan = nv04_fifo_chan(base);
 	struct nvkm_instmem *imem = chan->fifo->base.engine.subdev.device->imem;
+
+	mutex_lock(&chan->fifo->base.engine.subdev.mutex);
 	nvkm_ramht_remove(imem->ramht, cookie);
+	mutex_unlock(&chan->fifo->base.engine.subdev.mutex);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogf100.c
index e7cbc139c1d4..89976ff4b305 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogf100.c
@@ -59,6 +59,7 @@ gf100_fifo_gpfifo_engine_fini(struct nvkm_fifo_chan *base,
 	struct nvkm_gpuobj *inst = chan->base.inst;
 	int ret = 0;
 
+	mutex_lock(&subdev->mutex);
 	nvkm_wr32(device, 0x002634, chan->base.chid);
 	if (nvkm_msec(device, 2000,
 		if (nvkm_rd32(device, 0x002634) == chan->base.chid)
@@ -66,10 +67,12 @@ gf100_fifo_gpfifo_engine_fini(struct nvkm_fifo_chan *base,
 	) < 0) {
 		nvkm_error(subdev, "channel %d [%s] kick timeout\n",
 			   chan->base.chid, chan->base.object.client->name);
-		ret = -EBUSY;
-		if (suspend)
-			return ret;
+		ret = -ETIMEDOUT;
 	}
+	mutex_unlock(&subdev->mutex);
+
+	if (ret && suspend)
+		return ret;
 
 	if (offset) {
 		nvkm_kmap(inst);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
index 0b817540a9e4..aa1692e5669f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogk104.c
@@ -39,7 +39,9 @@ gk104_fifo_gpfifo_kick(struct gk104_fifo_chan *chan)
 	struct nvkm_subdev *subdev = &fifo->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	struct nvkm_client *client = chan->base.object.client;
+	int ret = 0;
 
+	mutex_lock(&subdev->mutex);
 	nvkm_wr32(device, 0x002634, chan->base.chid);
 	if (nvkm_msec(device, 2000,
 		if (!(nvkm_rd32(device, 0x002634) & 0x00100000))
@@ -47,10 +49,10 @@ gk104_fifo_gpfifo_kick(struct gk104_fifo_chan *chan)
 	) < 0) {
 		nvkm_error(subdev, "channel %d [%s] kick timeout\n",
 			   chan->base.chid, client->name);
-		return -EBUSY;
+		ret = -ETIMEDOUT;
 	}
-
-	return 0;
+	mutex_unlock(&subdev->mutex);
+	return ret;
 }
 
 static u32
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 9f5dfc85147a..eeeea1c2ca23 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -874,22 +874,41 @@ gf100_gr_trap_gpc_rop(struct gf100_gr *gr, int gpc)
 }
 
 static const struct nvkm_enum gf100_mp_warp_error[] = {
-	{ 0x00, "NO_ERROR" },
-	{ 0x01, "STACK_MISMATCH" },
+	{ 0x01, "STACK_ERROR" },
+	{ 0x02, "API_STACK_ERROR" },
+	{ 0x03, "RET_EMPTY_STACK_ERROR" },
+	{ 0x04, "PC_WRAP" },
 	{ 0x05, "MISALIGNED_PC" },
-	{ 0x08, "MISALIGNED_GPR" },
-	{ 0x09, "INVALID_OPCODE" },
-	{ 0x0d, "GPR_OUT_OF_BOUNDS" },
-	{ 0x0e, "MEM_OUT_OF_BOUNDS" },
-	{ 0x0f, "UNALIGNED_MEM_ACCESS" },
+	{ 0x06, "PC_OVERFLOW" },
+	{ 0x07, "MISALIGNED_IMMC_ADDR" },
+	{ 0x08, "MISALIGNED_REG" },
+	{ 0x09, "ILLEGAL_INSTR_ENCODING" },
+	{ 0x0a, "ILLEGAL_SPH_INSTR_COMBO" },
+	{ 0x0b, "ILLEGAL_INSTR_PARAM" },
+	{ 0x0c, "INVALID_CONST_ADDR" },
+	{ 0x0d, "OOR_REG" },
+	{ 0x0e, "OOR_ADDR" },
+	{ 0x0f, "MISALIGNED_ADDR" },
 	{ 0x10, "INVALID_ADDR_SPACE" },
-	{ 0x11, "INVALID_PARAM" },
+	{ 0x11, "ILLEGAL_INSTR_PARAM2" },
+	{ 0x12, "INVALID_CONST_ADDR_LDC" },
+	{ 0x13, "GEOMETRY_SM_ERROR" },
+	{ 0x14, "DIVERGENT" },
+	{ 0x15, "WARP_EXIT" },
 	{}
 };
 
 static const struct nvkm_bitfield gf100_mp_global_error[] = {
+	{ 0x00000001, "SM_TO_SM_FAULT" },
+	{ 0x00000002, "L1_ERROR" },
 	{ 0x00000004, "MULTIPLE_WARP_ERRORS" },
-	{ 0x00000008, "OUT_OF_STACK_SPACE" },
+	{ 0x00000008, "PHYSICAL_STACK_OVERFLOW" },
+	{ 0x00000010, "BPT_INT" },
+	{ 0x00000020, "BPT_PAUSE" },
+	{ 0x00000040, "SINGLE_STEP_COMPLETE" },
+	{ 0x20000000, "ECC_SEC_ERROR" },
+	{ 0x40000000, "ECC_DED_ERROR" },
+	{ 0x80000000, "TIMEOUT" },
 	{}
 };
 
@@ -1717,6 +1736,8 @@ gf100_gr_init(struct gf100_gr *gr)
 
 	gf100_gr_mmio(gr, gr->func->mmio);
 
+	nvkm_mask(device, TPC_UNIT(0, 0, 0x05c), 0x00000001, 0x00000001);
+
 	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
 	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
 		do {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
index 69de8c6259fe..f1e15a4d4f64 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
@@ -76,8 +76,8 @@ nv30_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch,
 		nvkm_wo32(chan->inst, i, 0x00040004);
 	for (i = 0x1f18; i <= 0x3088 ; i += 16) {
 		nvkm_wo32(chan->inst, i + 0, 0x10700ff9);
-		nvkm_wo32(chan->inst, i + 1, 0x0436086c);
-		nvkm_wo32(chan->inst, i + 2, 0x000c001b);
+		nvkm_wo32(chan->inst, i + 4, 0x0436086c);
+		nvkm_wo32(chan->inst, i + 8, 0x000c001b);
 	}
 	for (i = 0x30b8; i < 0x30c8; i += 4)
 		nvkm_wo32(chan->inst, i, 0x0000ffff);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
index 2207dac23981..300f5ed5de0b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
@@ -75,8 +75,8 @@ nv34_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch,
 		nvkm_wo32(chan->inst, i, 0x00040004);
 	for (i = 0x15ac; i <= 0x271c ; i += 16) {
 		nvkm_wo32(chan->inst, i + 0, 0x10700ff9);
-		nvkm_wo32(chan->inst, i + 1, 0x0436086c);
-		nvkm_wo32(chan->inst, i + 2, 0x000c001b);
+		nvkm_wo32(chan->inst, i + 4, 0x0436086c);
+		nvkm_wo32(chan->inst, i + 8, 0x000c001b);
 	}
 	for (i = 0x274c; i < 0x275c; i += 4)
 		nvkm_wo32(chan->inst, i, 0x0000ffff);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
index d4d8942b1347..e55f8302d08a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv31.c
@@ -198,7 +198,7 @@ nv31_mpeg_intr(struct nvkm_engine *engine)
 		}
 
 		if (type == 0x00000010) {
-			if (!nv31_mpeg_mthd(mpeg, mthd, data))
+			if (nv31_mpeg_mthd(mpeg, mthd, data))
 				show &= ~0x01000000;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
index d433cfa4a8ab..36af0a8927fc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/mpeg/nv44.c
@@ -172,7 +172,7 @@ nv44_mpeg_intr(struct nvkm_engine *engine)
 		}
 
 		if (type == 0x00000010) {
-			if (!nv44_mpeg_mthd(subdev->device, mthd, data))
+			if (nv44_mpeg_mthd(subdev->device, mthd, data))
 				show &= ~0x01000000;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c
index 4bef72a9d106..3fda594700e0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/nv40.c
@@ -59,9 +59,11 @@ static void
 nv40_perfctr_next(struct nvkm_pm *pm, struct nvkm_perfdom *dom)
 {
 	struct nvkm_device *device = pm->engine.subdev.device;
-	if (pm->sequence != pm->sequence) {
+	struct nv40_pm *nv40pm = container_of(pm, struct nv40_pm, base);
+
+	if (nv40pm->sequence != pm->sequence) {
 		nvkm_wr32(device, 0x400084, 0x00000020);
-		pm->sequence = pm->sequence;
+		nv40pm->sequence = pm->sequence;
 	}
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c
index c794b2c2d21e..6d8f21290aa2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/gf100.c
@@ -129,7 +129,7 @@ gf100_bar_init(struct nvkm_bar *base)
 
 	if (bar->bar[0].mem) {
 		addr = nvkm_memory_addr(bar->bar[0].mem) >> 12;
-		nvkm_wr32(device, 0x001714, 0xc0000000 | addr);
+		nvkm_wr32(device, 0x001714, 0x80000000 | addr);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h
index 212800ecdce9..7d1d3c6b4b72 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/priv.h
@@ -12,6 +12,7 @@ struct nvbios_source {
 	bool rw;
 	bool ignore_checksum;
 	bool no_pcir;
+	bool require_checksum;
 };
 
 int nvbios_extend(struct nvkm_bios *, u32 length);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index b2557e87afdd..7deb81b6dbac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -86,9 +86,12 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd)
 		    nvbios_checksum(&bios->data[image.base], image.size)) {
 			nvkm_debug(subdev, "%08x: checksum failed\n",
 				   image.base);
-			if (mthd->func->rw)
+			if (!mthd->func->require_checksum) {
+				if (mthd->func->rw)
+					score += 1;
 				score += 1;
-			score += 1;
+			} else
+				return 0;
 		} else {
 			score += 3;
 		}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowacpi.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowacpi.c
index 8fecb5ff22a0..06572f8ce914 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowacpi.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowacpi.c
@@ -99,6 +99,7 @@ nvbios_acpi_fast = {
 	.init = acpi_init,
 	.read = acpi_read_fast,
 	.rw = false,
+	.require_checksum = true,
 };
 
 const struct nvbios_source
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
index 85b1464c0194..587c52f08d3f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/base.c
@@ -47,8 +47,10 @@ nvkm_ltc_tags_clear(struct nvkm_ltc *ltc, u32 first, u32 count)
 
 	BUG_ON((first > limit) || (limit >= ltc->num_tags));
 
+	mutex_lock(&ltc->subdev.mutex);
 	ltc->func->cbc_clear(ltc, first, limit);
 	ltc->func->cbc_wait(ltc);
+	mutex_unlock(&ltc->subdev.mutex);
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
index d671dcfaff3c..4896474da320 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
@@ -180,6 +180,10 @@ nvkm_pci_new_(const struct nvkm_pci_func *func, struct nvkm_device *device,
 		}
 	}
 
+#ifdef __BIG_ENDIAN
+	pci->msi = false;
+#endif
+
 	pci->msi = nvkm_boolopt(device->cfgopt, "NvMSI", pci->msi);
 	if (pci->msi && func->msi_rearm) {
 		pci->msi = pci_enable_msi(pci->pdev) == 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
index 949dc6101a58..7c0b58613747 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
@@ -130,7 +130,7 @@ nvkm_therm_update(struct nvkm_therm *therm, int mode)
 		poll = false;
 	}
 
-	if (list_empty(&therm->alarm.head) && poll)
+	if (poll)
 		nvkm_timer_alarm(tmr, 1000000000ULL, &therm->alarm);
 	spin_unlock_irqrestore(&therm->lock, flags);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c
index 91198d79393a..e2feccec25f5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fan.c
@@ -83,7 +83,7 @@ nvkm_fan_update(struct nvkm_fan *fan, bool immediate, int target)
 	spin_unlock_irqrestore(&fan->lock, flags);
 
 	/* schedule next fan update, if not at target speed already */
-	if (list_empty(&fan->alarm.head) && target != duty) {
+	if (target != duty) {
 		u16 bump_period = fan->bios.bump_period;
 		u16 slow_down_period = fan->bios.slow_down_period;
 		u64 delay;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c
index 59701b7a6597..ff9fbe7950e5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/fantog.c
@@ -53,7 +53,7 @@ nvkm_fantog_update(struct nvkm_fantog *fan, int percent)
 	duty = !nvkm_gpio_get(gpio, 0, DCB_GPIO_FAN, 0xff);
 	nvkm_gpio_set(gpio, 0, DCB_GPIO_FAN, 0xff, duty);
 
-	if (list_empty(&fan->alarm.head) && percent != (duty * 100)) {
+	if (percent != (duty * 100)) {
 		u64 next_change = (percent * fan->period_us) / 100;
 		if (!duty)
 			next_change = fan->period_us - next_change;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c
index b9703c02d8ca..9a79e91fdfdc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c
@@ -185,7 +185,7 @@ alarm_timer_callback(struct nvkm_alarm *alarm)
 	spin_unlock_irqrestore(&therm->sensor.alarm_program_lock, flags);
 
 	/* schedule the next poll in one second */
-	if (therm->func->temp_get(therm) >= 0 && list_empty(&alarm->head))
+	if (therm->func->temp_get(therm) >= 0)
 		nvkm_timer_alarm(tmr, 1000000000ULL, alarm);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
index d4dae1f12d62..46033909d950 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
@@ -36,25 +36,32 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 	unsigned long flags;
 	LIST_HEAD(exec);
 
-	/* move any due alarms off the pending list */
+	/* Process pending alarms. */
 	spin_lock_irqsave(&tmr->lock, flags);
 	list_for_each_entry_safe(alarm, atemp, &tmr->alarms, head) {
-		if (alarm->timestamp <= nvkm_timer_read(tmr))
-			list_move_tail(&alarm->head, &exec);
+		/* Have we hit the earliest alarm that hasn't gone off? */
+		if (alarm->timestamp > nvkm_timer_read(tmr)) {
+			/* Schedule it.  If we didn't race, we're done. */
+			tmr->func->alarm_init(tmr, alarm->timestamp);
+			if (alarm->timestamp > nvkm_timer_read(tmr))
+				break;
+		}
+
+		/* Move to completed list.  We'll drop the lock before
+		 * executing the callback so it can reschedule itself.
+		 */
+		list_del_init(&alarm->head);
+		list_add(&alarm->exec, &exec);
 	}
 
-	/* reschedule interrupt for next alarm time */
-	if (!list_empty(&tmr->alarms)) {
-		alarm = list_first_entry(&tmr->alarms, typeof(*alarm), head);
-		tmr->func->alarm_init(tmr, alarm->timestamp);
-	} else {
+	/* Shut down interrupt if no more pending alarms. */
+	if (list_empty(&tmr->alarms))
 		tmr->func->alarm_fini(tmr);
-	}
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
-	/* execute any pending alarm handlers */
-	list_for_each_entry_safe(alarm, atemp, &exec, head) {
-		list_del_init(&alarm->head);
+	/* Execute completed callbacks. */
+	list_for_each_entry_safe(alarm, atemp, &exec, exec) {
+		list_del(&alarm->exec);
 		alarm->func(alarm);
 	}
 }
@@ -65,24 +72,37 @@ nvkm_timer_alarm(struct nvkm_timer *tmr, u32 nsec, struct nvkm_alarm *alarm)
 	struct nvkm_alarm *list;
 	unsigned long flags;
 
-	alarm->timestamp = nvkm_timer_read(tmr) + nsec;
-
-	/* append new alarm to list, in soonest-alarm-first order */
+	/* Remove alarm from pending list.
+	 *
+	 * This both protects against the corruption of the list,
+	 * and implements alarm rescheduling/cancellation.
+	 */
 	spin_lock_irqsave(&tmr->lock, flags);
-	if (!nsec) {
-		if (!list_empty(&alarm->head))
-			list_del(&alarm->head);
-	} else {
+	list_del_init(&alarm->head);
+
+	if (nsec) {
+		/* Insert into pending list, ordered earliest to latest. */
+		alarm->timestamp = nvkm_timer_read(tmr) + nsec;
 		list_for_each_entry(list, &tmr->alarms, head) {
 			if (list->timestamp > alarm->timestamp)
 				break;
 		}
+
 		list_add_tail(&alarm->head, &list->head);
+
+		/* Update HW if this is now the earliest alarm. */
+		list = list_first_entry(&tmr->alarms, typeof(*list), head);
+		if (list == alarm) {
+			tmr->func->alarm_init(tmr, alarm->timestamp);
+			/* This shouldn't happen if callers aren't stupid.
+			 *
+			 * Worst case scenario is that it'll take roughly
+			 * 4 seconds for the next alarm to trigger.
+			 */
+			WARN_ON(alarm->timestamp <= nvkm_timer_read(tmr));
+		}
 	}
 	spin_unlock_irqrestore(&tmr->lock, flags);
-
-	/* process pending alarms */
-	nvkm_timer_alarm_trigger(tmr);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c
index 7b9ce87f0617..7f48249f41de 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/nv04.c
@@ -76,8 +76,8 @@ nv04_timer_intr(struct nvkm_timer *tmr)
 	u32 stat = nvkm_rd32(device, NV04_PTIMER_INTR_0);
 
 	if (stat & 0x00000001) {
-		nvkm_timer_alarm_trigger(tmr);
 		nvkm_wr32(device, NV04_PTIMER_INTR_0, 0x00000001);
+		nvkm_timer_alarm_trigger(tmr);
 		stat &= ~0x00000001;
 	}
 
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 183aea1abebc..5edebf495c07 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -375,10 +375,15 @@ static int qxl_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	qxl_bo_kunmap(user_bo);
 
+	qcrtc->cur_x += qcrtc->hot_spot_x - hot_x;
+	qcrtc->cur_y += qcrtc->hot_spot_y - hot_y;
+	qcrtc->hot_spot_x = hot_x;
+	qcrtc->hot_spot_y = hot_y;
+
 	cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_CURSOR_SET;
-	cmd->u.set.position.x = qcrtc->cur_x;
-	cmd->u.set.position.y = qcrtc->cur_y;
+	cmd->u.set.position.x = qcrtc->cur_x + qcrtc->hot_spot_x;
+	cmd->u.set.position.y = qcrtc->cur_y + qcrtc->hot_spot_y;
 
 	cmd->u.set.shape = qxl_bo_physical_address(qdev, cursor_bo, 0);
 
@@ -441,8 +446,8 @@ static int qxl_crtc_cursor_move(struct drm_crtc *crtc,
 
 	cmd = (struct qxl_cursor_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_CURSOR_MOVE;
-	cmd->u.position.x = qcrtc->cur_x;
-	cmd->u.position.y = qcrtc->cur_y;
+	cmd->u.position.x = qcrtc->cur_x + qcrtc->hot_spot_x;
+	cmd->u.position.y = qcrtc->cur_y + qcrtc->hot_spot_y;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
 	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 56e1d633875e..6e6c76080d6a 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -136,6 +136,8 @@ static int qxl_palette_create_1bit(struct qxl_bo *palette_bo,
 				 * correctly globaly, since that would require
 				 * tracking all of our palettes. */
 	ret = qxl_bo_kmap(palette_bo, (void **)&pal);
+	if (ret)
+		return ret;
 	pal->num_ents = 2;
 	pal->unique = unique++;
 	if (visual == FB_VISUAL_TRUECOLOR || visual == FB_VISUAL_DIRECTCOLOR) {
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 01a86948eb8c..3ab90179e9ab 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -135,6 +135,8 @@ struct qxl_crtc {
 	int index;
 	int cur_x;
 	int cur_y;
+	int hot_spot_x;
+	int hot_spot_y;
 };
 
 struct qxl_output {
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index dac78ad24b31..6755d4768f59 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -275,6 +275,8 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 			atombios_enable_crtc_memreq(crtc, ATOM_ENABLE);
 		atombios_blank_crtc(crtc, ATOM_DISABLE);
 		drm_vblank_post_modeset(dev, radeon_crtc->crtc_id);
+		/* Make sure vblank interrupt is still enabled if needed */
+		radeon_irq_set(rdev);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
@@ -1739,6 +1741,7 @@ static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc)
 static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_crtc *test_crtc;
 	struct radeon_crtc *test_radeon_crtc;
 
@@ -1748,6 +1751,10 @@ static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc)
 		test_radeon_crtc = to_radeon_crtc(test_crtc);
 		if (test_radeon_crtc->encoder &&
 		    ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* PPLL2 is exclusive to UNIPHYA on DCE61 */
+			if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) &&
+			    test_radeon_crtc->pll_id == ATOM_PPLL2)
+				continue;
 			/* for DP use the same PLL for all */
 			if (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID)
 				return test_radeon_crtc->pll_id;
@@ -1769,6 +1776,7 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_crtc *test_crtc;
 	struct radeon_crtc *test_radeon_crtc;
 	u32 adjusted_clock, test_adjusted_clock;
@@ -1784,6 +1792,10 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
 		test_radeon_crtc = to_radeon_crtc(test_crtc);
 		if (test_radeon_crtc->encoder &&
 		    !ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_radeon_crtc->encoder))) {
+			/* PPLL2 is exclusive to UNIPHYA on DCE61 */
+			if (ASIC_IS_DCE61(rdev) && !ASIC_IS_DCE8(rdev) &&
+			    test_radeon_crtc->pll_id == ATOM_PPLL2)
+				continue;
 			/* check if we are already driving this connector with another crtc */
 			if (test_radeon_crtc->connector == radeon_crtc->connector) {
 				/* if we are, return that pll */
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index bd73b4069069..b5760851195c 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -302,77 +302,43 @@ static int convert_bpc_to_bpp(int bpc)
 		return bpc * 3;
 }
 
-/* get the max pix clock supported by the link rate and lane num */
-static int dp_get_max_dp_pix_clock(int link_rate,
-				   int lane_num,
-				   int bpp)
-{
-	return (link_rate * lane_num * 8) / bpp;
-}
-
 /***** radeon specific DP functions *****/
 
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				const 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.
- */
-static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
-					const u8 dpcd[DP_DPCD_SIZE],
-					int pix_clock)
+int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+				 const u8 dpcd[DP_DPCD_SIZE],
+				 unsigned pix_clock,
+				 unsigned *dp_lanes, unsigned *dp_rate)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	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;
-
-	for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) {
-		max_dp_pix_clock = dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp);
-		if (pix_clock <= max_dp_pix_clock)
-			break;
-	}
-
-	return lane_num;
-}
-
-static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
-				       const u8 dpcd[DP_DPCD_SIZE],
-				       int pix_clock)
-{
-	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int lane_num, max_pix_clock;
+	static const unsigned link_rates[3] = { 162000, 270000, 540000 };
+	unsigned max_link_rate = drm_dp_max_link_rate(dpcd);
+	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
+	unsigned lane_num, i, max_pix_clock;
 
 	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		return 270000;
-
-	lane_num = radeon_dp_get_dp_lane_number(connector, dpcd, pix_clock);
-	max_pix_clock = dp_get_max_dp_pix_clock(162000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 162000;
-	max_pix_clock = dp_get_max_dp_pix_clock(270000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 270000;
-	if (radeon_connector_is_dp12_capable(connector)) {
-		max_pix_clock = dp_get_max_dp_pix_clock(540000, lane_num, bpp);
-		if (pix_clock <= max_pix_clock)
-			return 540000;
+	    ENCODER_OBJECT_ID_NUTMEG) {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			max_pix_clock = (lane_num * 270000 * 8) / bpp;
+			if (max_pix_clock >= pix_clock) {
+				*dp_lanes = lane_num;
+				*dp_rate = 270000;
+				return 0;
+			}
+		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+			for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+				max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+				if (max_pix_clock >= pix_clock) {
+					*dp_lanes = lane_num;
+					*dp_rate = link_rates[i];
+					return 0;
+				}
+			}
+		}
 	}
 
-	return radeon_dp_get_max_link_rate(connector, dpcd);
+	return -EINVAL;
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -491,6 +457,7 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
+	int ret;
 
 	if (!radeon_connector->con_priv)
 		return;
@@ -498,10 +465,14 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 
 	if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 	    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-		dig_connector->dp_clock =
-			radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
-		dig_connector->dp_lane_count =
-			radeon_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock);
+		ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+						   mode->clock,
+						   &dig_connector->dp_lane_count,
+						   &dig_connector->dp_clock);
+		if (ret) {
+			dig_connector->dp_clock = 0;
+			dig_connector->dp_lane_count = 0;
+		}
 	}
 }
 
@@ -510,7 +481,8 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
-	int dp_clock;
+	unsigned dp_clock, dp_lanes;
+	int ret;
 
 	if ((mode->clock > 340000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
@@ -520,8 +492,12 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
 
-	dp_clock =
-		radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
+	ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+					   mode->clock,
+					   &dp_lanes,
+					   &dp_clock);
+	if (ret)
+		return MODE_CLOCK_HIGH;
 
 	if ((dp_clock == 540000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index bb292143997e..8e86cf7da614 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -30,6 +30,7 @@
 #include "radeon_audio.h"
 #include "atom.h"
 #include <linux/backlight.h>
+#include <linux/dmi.h>
 
 extern int atom_debug;
 
@@ -120,6 +121,7 @@ atombios_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level)
 		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
 			if (dig->backlight_level == 0)
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
 			else {
@@ -310,6 +312,10 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder,
 	    && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2)))
 		adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2;
 
+	/* vertical FP must be at least 1 */
+	if (mode->crtc_vsync_start == mode->crtc_vdisplay)
+		adjusted_mode->crtc_vsync_start++;
+
 	/* get the native mode for scaling */
 	if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) {
 		radeon_panel_mode_fixup(encoder, adjusted_mode);
@@ -892,8 +898,6 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m
 			else
 				args.v1.ucLaneNum = 4;
 
-			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000))
-				args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ;
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 				args.v1.ucConfig = ATOM_ENCODER_CONFIG_V2_TRANSMITTER1;
@@ -910,6 +914,10 @@ atombios_dig_encoder_setup2(struct drm_encoder *encoder, int action, int panel_m
 				args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKB;
 			else
 				args.v1.ucConfig |= ATOM_ENCODER_CONFIG_LINKA;
+
+			if (ENCODER_MODE_IS_DP(args.v1.ucEncoderMode) && (dp_clock == 270000))
+				args.v1.ucConfig |= ATOM_ENCODER_CONFIG_DPLINKRATE_2_70GHZ;
+
 			break;
 		case 2:
 		case 3:
@@ -2176,9 +2184,17 @@ int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder, int fe_idx)
 		goto assigned;
 	}
 
-	/* on DCE32 and encoder can driver any block so just crtc id */
+	/*
+	 * On DCE32 any encoder can drive any block so usually just use crtc id,
+	 * but Apple thinks different at least on iMac10,1, so there use linkb,
+	 * otherwise the internal eDP panel will stay dark.
+	 */
 	if (ASIC_IS_DCE32(rdev)) {
-		enc_idx = radeon_crtc->crtc_id;
+		if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1"))
+			enc_idx = (dig->linkb) ? 1 : 0;
+		else
+			enc_idx = radeon_crtc->crtc_id;
+
 		goto assigned;
 	}
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 4a09947be244..2ccf81168d1e 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -776,6 +776,18 @@ bool ci_dpm_vblank_too_short(struct radeon_device *rdev)
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
 	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
 
+	/* disable mclk switching if the refresh is >120Hz, even if the
+        * blanking period would allow it
+        */
+	if (r600_dpm_get_vrefresh(rdev) > 120)
+		return true;
+
+	/* disable mclk switching if the refresh is >120Hz, even if the
+        * blanking period would allow it
+        */
+	if (r600_dpm_get_vrefresh(rdev) > 120)
+		return true;
+
 	if (vblank_time < switch_limit)
 		return true;
 	else
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index f81fb2641097..134874cab4c7 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -7762,7 +7762,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -7792,7 +7792,7 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 2ad462896896..ba9e6ed4ae54 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2608,10 +2608,152 @@ static void evergreen_agp_enable(struct radeon_device *rdev)
 	WREG32(VM_CONTEXT1_CNTL, 0);
 }
 
+static const unsigned ni_dig_offsets[] =
+{
+	NI_DIG0_REGISTER_OFFSET,
+	NI_DIG1_REGISTER_OFFSET,
+	NI_DIG2_REGISTER_OFFSET,
+	NI_DIG3_REGISTER_OFFSET,
+	NI_DIG4_REGISTER_OFFSET,
+	NI_DIG5_REGISTER_OFFSET
+};
+
+static const unsigned ni_tx_offsets[] =
+{
+	NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1,
+	NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1,
+	NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1,
+	NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1,
+	NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1,
+	NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1
+};
+
+static const unsigned evergreen_dp_offsets[] =
+{
+	EVERGREEN_DP0_REGISTER_OFFSET,
+	EVERGREEN_DP1_REGISTER_OFFSET,
+	EVERGREEN_DP2_REGISTER_OFFSET,
+	EVERGREEN_DP3_REGISTER_OFFSET,
+	EVERGREEN_DP4_REGISTER_OFFSET,
+	EVERGREEN_DP5_REGISTER_OFFSET
+};
+
+
+/*
+ * Assumption is that EVERGREEN_CRTC_MASTER_EN enable for requested crtc
+ * We go from crtc to connector and it is not relible  since it
+ * should be an opposite direction .If crtc is enable then
+ * find the dig_fe which selects this crtc and insure that it enable.
+ * if such dig_fe is found then find dig_be which selects found dig_be and
+ * insure that it enable and in DP_SST mode.
+ * if UNIPHY_PLL_CONTROL1.enable then we should disconnect timing
+ * from dp symbols clocks .
+ */
+static bool evergreen_is_dp_sst_stream_enabled(struct radeon_device *rdev,
+					       unsigned crtc_id, unsigned *ret_dig_fe)
+{
+	unsigned i;
+	unsigned dig_fe;
+	unsigned dig_be;
+	unsigned dig_en_be;
+	unsigned uniphy_pll;
+	unsigned digs_fe_selected;
+	unsigned dig_be_mode;
+	unsigned dig_fe_mask;
+	bool is_enabled = false;
+	bool found_crtc = false;
+
+	/* loop through all running dig_fe to find selected crtc */
+	for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) {
+		dig_fe = RREG32(NI_DIG_FE_CNTL + ni_dig_offsets[i]);
+		if (dig_fe & NI_DIG_FE_CNTL_SYMCLK_FE_ON &&
+		    crtc_id == NI_DIG_FE_CNTL_SOURCE_SELECT(dig_fe)) {
+			/* found running pipe */
+			found_crtc = true;
+			dig_fe_mask = 1 << i;
+			dig_fe = i;
+			break;
+		}
+	}
+
+	if (found_crtc) {
+		/* loop through all running dig_be to find selected dig_fe */
+		for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) {
+			dig_be = RREG32(NI_DIG_BE_CNTL + ni_dig_offsets[i]);
+			/* if dig_fe_selected by dig_be? */
+			digs_fe_selected = NI_DIG_BE_CNTL_FE_SOURCE_SELECT(dig_be);
+			dig_be_mode = NI_DIG_FE_CNTL_MODE(dig_be);
+			if (dig_fe_mask &  digs_fe_selected &&
+			    /* if dig_be in sst mode? */
+			    dig_be_mode == NI_DIG_BE_DPSST) {
+				dig_en_be = RREG32(NI_DIG_BE_EN_CNTL +
+						   ni_dig_offsets[i]);
+				uniphy_pll = RREG32(NI_DCIO_UNIPHY0_PLL_CONTROL1 +
+						    ni_tx_offsets[i]);
+				/* dig_be enable and tx is running */
+				if (dig_en_be & NI_DIG_BE_EN_CNTL_ENABLE &&
+				    dig_en_be & NI_DIG_BE_EN_CNTL_SYMBCLK_ON &&
+				    uniphy_pll & NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE) {
+					is_enabled = true;
+					*ret_dig_fe = dig_fe;
+					break;
+				}
+			}
+		}
+	}
+
+	return is_enabled;
+}
+
+/*
+ * Blank dig when in dp sst mode
+ * Dig ignores crtc timing
+ */
+static void evergreen_blank_dp_output(struct radeon_device *rdev,
+				      unsigned dig_fe)
+{
+	unsigned stream_ctrl;
+	unsigned fifo_ctrl;
+	unsigned counter = 0;
+
+	if (dig_fe >= ARRAY_SIZE(evergreen_dp_offsets)) {
+		DRM_ERROR("invalid dig_fe %d\n", dig_fe);
+		return;
+	}
+
+	stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL +
+			     evergreen_dp_offsets[dig_fe]);
+	if (!(stream_ctrl & EVERGREEN_DP_VID_STREAM_CNTL_ENABLE)) {
+		DRM_ERROR("dig %d , should be enable\n", dig_fe);
+		return;
+	}
+
+	stream_ctrl &=~EVERGREEN_DP_VID_STREAM_CNTL_ENABLE;
+	WREG32(EVERGREEN_DP_VID_STREAM_CNTL +
+	       evergreen_dp_offsets[dig_fe], stream_ctrl);
+
+	stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL +
+			     evergreen_dp_offsets[dig_fe]);
+	while (counter < 32 && stream_ctrl & EVERGREEN_DP_VID_STREAM_STATUS) {
+		msleep(1);
+		counter++;
+		stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL +
+				     evergreen_dp_offsets[dig_fe]);
+	}
+	if (counter >= 32 )
+		DRM_ERROR("counter exceeds %d\n", counter);
+
+	fifo_ctrl = RREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe]);
+	fifo_ctrl |= EVERGREEN_DP_STEER_FIFO_RESET;
+	WREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe], fifo_ctrl);
+
+}
+
 void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save)
 {
 	u32 crtc_enabled, tmp, frame_count, blackout;
 	int i, j;
+	unsigned dig_fe;
 
 	if (!ASIC_IS_NODCE(rdev)) {
 		save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
@@ -2651,7 +2793,17 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 					break;
 				udelay(1);
 			}
-
+			/*we should disable dig if it drives dp sst*/
+			/*but we are in radeon_device_init and the topology is unknown*/
+			/*and it is available after radeon_modeset_init*/
+			/*the following method radeon_atom_encoder_dpms_dig*/
+			/*does the job if we initialize it properly*/
+			/*for now we do it this manually*/
+			/**/
+			if (ASIC_IS_DCE5(rdev) &&
+			    evergreen_is_dp_sst_stream_enabled(rdev, i ,&dig_fe))
+				evergreen_blank_dp_output(rdev, dig_fe);
+			/*we could remove 6 lines below*/
 			/* XXX this is a hack to avoid strange behavior with EFI on certain systems */
 			WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 			tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
@@ -4772,7 +4924,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -4803,7 +4955,7 @@ static void evergreen_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index aa939dfed3a3..b436badf9efa 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -250,8 +250,43 @@
 
 /* HDMI blocks at 0x7030, 0x7c30, 0x10830, 0x11430, 0x12030, 0x12c30 */
 #define EVERGREEN_HDMI_BASE				0x7030
+/*DIG block*/
+#define NI_DIG0_REGISTER_OFFSET                 (0x7000  - 0x7000)
+#define NI_DIG1_REGISTER_OFFSET                 (0x7C00  - 0x7000)
+#define NI_DIG2_REGISTER_OFFSET                 (0x10800 - 0x7000)
+#define NI_DIG3_REGISTER_OFFSET                 (0x11400 - 0x7000)
+#define NI_DIG4_REGISTER_OFFSET                 (0x12000 - 0x7000)
+#define NI_DIG5_REGISTER_OFFSET                 (0x12C00 - 0x7000)
+
+
+#define NI_DIG_FE_CNTL                               0x7000
+#       define NI_DIG_FE_CNTL_SOURCE_SELECT(x)        ((x) & 0x3)
+#       define NI_DIG_FE_CNTL_SYMCLK_FE_ON            (1<<24)
+
+
+#define NI_DIG_BE_CNTL                    0x7140
+#       define NI_DIG_BE_CNTL_FE_SOURCE_SELECT(x)     (((x) >> 8 ) & 0x3F)
+#       define NI_DIG_FE_CNTL_MODE(x)                 (((x) >> 16) & 0x7 )
+
+#define NI_DIG_BE_EN_CNTL                              0x7144
+#       define NI_DIG_BE_EN_CNTL_ENABLE               (1 << 0)
+#       define NI_DIG_BE_EN_CNTL_SYMBCLK_ON           (1 << 8)
+#       define NI_DIG_BE_DPSST 0
 
 /* Display Port block */
+#define EVERGREEN_DP0_REGISTER_OFFSET                 (0x730C  - 0x730C)
+#define EVERGREEN_DP1_REGISTER_OFFSET                 (0x7F0C  - 0x730C)
+#define EVERGREEN_DP2_REGISTER_OFFSET                 (0x10B0C - 0x730C)
+#define EVERGREEN_DP3_REGISTER_OFFSET                 (0x1170C - 0x730C)
+#define EVERGREEN_DP4_REGISTER_OFFSET                 (0x1230C - 0x730C)
+#define EVERGREEN_DP5_REGISTER_OFFSET                 (0x12F0C - 0x730C)
+
+
+#define EVERGREEN_DP_VID_STREAM_CNTL                    0x730C
+#       define EVERGREEN_DP_VID_STREAM_CNTL_ENABLE     (1 << 0)
+#       define EVERGREEN_DP_VID_STREAM_STATUS          (1 <<16)
+#define EVERGREEN_DP_STEER_FIFO                         0x7310
+#       define EVERGREEN_DP_STEER_FIFO_RESET           (1 << 0)
 #define EVERGREEN_DP_SEC_CNTL                           0x7280
 #       define EVERGREEN_DP_SEC_STREAM_ENABLE           (1 << 0)
 #       define EVERGREEN_DP_SEC_ASP_ENABLE              (1 << 4)
@@ -266,4 +301,15 @@
 #       define EVERGREEN_DP_SEC_N_BASE_MULTIPLE(x)      (((x) & 0xf) << 24)
 #       define EVERGREEN_DP_SEC_SS_EN                   (1 << 28)
 
+/*DCIO_UNIPHY block*/
+#define NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1            (0x6600  -0x6600)
+#define NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1            (0x6640  -0x6600)
+#define NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1            (0x6680 - 0x6600)
+#define NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1            (0x66C0 - 0x6600)
+#define NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1            (0x6700 - 0x6600)
+#define NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1            (0x6740 - 0x6600)
+
+#define NI_DCIO_UNIPHY0_PLL_CONTROL1                   0x6618
+#       define NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE     (1 << 0)
+
 #endif
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 158872eb78e4..a3a321208fd8 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1396,9 +1396,7 @@ static void cayman_pcie_gart_fini(struct radeon_device *rdev)
 void cayman_cp_int_cntl_setup(struct radeon_device *rdev,
 			      int ring, u32 cp_int_cntl)
 {
-	u32 srbm_gfx_cntl = RREG32(SRBM_GFX_CNTL) & ~3;
-
-	WREG32(SRBM_GFX_CNTL, srbm_gfx_cntl | (ring & 3));
+	WREG32(SRBM_GFX_CNTL, RINGID(ring));
 	WREG32(CP_INT_CNTL, cp_int_cntl);
 }
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index cc2fdf0be37a..0e20c08f8977 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3945,7 +3945,7 @@ static void r600_irq_ack(struct radeon_device *rdev)
 			WREG32(DC_HPD5_INT_CONTROL, tmp);
 		}
 		if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
-			tmp = RREG32(DC_HPD5_INT_CONTROL);
+			tmp = RREG32(DC_HPD6_INT_CONTROL);
 			tmp |= DC_HPDx_INT_ACK;
 			WREG32(DC_HPD6_INT_CONTROL, tmp);
 		}
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index fa2154493cf1..470af4aa4a6a 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -156,19 +156,20 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
 	struct drm_device *dev = rdev->ddev;
 	struct drm_crtc *crtc;
 	struct radeon_crtc *radeon_crtc;
-	u32 line_time_us, vblank_lines;
+	u32 vblank_in_pixels;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
 	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			radeon_crtc = to_radeon_crtc(crtc);
 			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-				line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
-					radeon_crtc->hw_mode.clock;
-				vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
-					radeon_crtc->hw_mode.crtc_vdisplay +
-					(radeon_crtc->v_border * 2);
-				vblank_time_us = vblank_lines * line_time_us;
+				vblank_in_pixels =
+					radeon_crtc->hw_mode.crtc_htotal *
+					(radeon_crtc->hw_mode.crtc_vblank_end -
+					 radeon_crtc->hw_mode.crtc_vdisplay +
+					 (radeon_crtc->v_border * 2));
+
+				vblank_time_us = vblank_in_pixels * 1000 / radeon_crtc->hw_mode.clock;
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index de9a2ffcf5f7..0c5b3eeff82d 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1155,7 +1155,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		    le16_to_cpu(firmware_info->info.usReferenceClock);
 		p1pll->reference_div = 0;
 
-		if (crev < 2)
+		if ((frev < 2) && (crev < 2))
 			p1pll->pll_out_min =
 				le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output);
 		else
@@ -1164,7 +1164,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		p1pll->pll_out_max =
 		    le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output);
 
-		if (crev >= 4) {
+		if (((frev < 2) && (crev >= 4)) || (frev >= 2)) {
 			p1pll->lcd_pll_out_min =
 				le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
 			if (p1pll->lcd_pll_out_min == 0)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index c4b4f298a283..69ce95571136 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 
 #include "radeon_acpi.h"
 
@@ -255,6 +256,10 @@ static int radeon_atpx_set_discrete_state(struct radeon_atpx *atpx, u8 state)
 		if (!info)
 			return -EIO;
 		kfree(info);
+
+		/* 200ms delay is required after off */
+		if (state == 0)
+			msleep(200);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index a9b01bcf7d0a..fcecaf5b5526 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -3394,6 +3394,13 @@ void radeon_combios_asic_init(struct drm_device *dev)
 	    rdev->pdev->subsystem_vendor == 0x103c &&
 	    rdev->pdev->subsystem_device == 0x280a)
 		return;
+	/* quirk for rs4xx Toshiba Sattellite L20-183 latop to make it resume
+	 * - it hangs on resume inside the dynclk 1 table.
+	 */
+	if (rdev->family == CHIP_RS400 &&
+	    rdev->pdev->subsystem_vendor == 0x1179 &&
+	    rdev->pdev->subsystem_device == 0xff31)
+	        return;
 
 	/* DYN CLK 1 */
 	table = combios_get_table_offset(dev, COMBIOS_DYN_CLK_1_TABLE);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 340f3f549f29..30f00748ed37 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1996,10 +1996,12 @@ radeon_add_atom_connector(struct drm_device *dev,
 						   rdev->mode_info.dither_property,
 						   RADEON_FMT_DITHER_DISABLE);
 
-			if (radeon_audio != 0)
+			if (radeon_audio != 0) {
 				drm_object_attach_property(&radeon_connector->base.base,
 							   rdev->mode_info.audio_property,
 							   RADEON_AUDIO_AUTO);
+				radeon_connector->audio = RADEON_AUDIO_AUTO;
+			}
 			if (ASIC_IS_DCE5(rdev))
 				drm_object_attach_property(&radeon_connector->base.base,
 							   rdev->mode_info.output_csc_property,
@@ -2056,7 +2058,6 @@ radeon_add_atom_connector(struct drm_device *dev,
 							   RADEON_OUTPUT_CSC_BYPASS);
 			/* no HPD on analog connectors */
 			radeon_connector->hpd.hpd = RADEON_HPD_NONE;
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			break;
@@ -2124,6 +2125,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				drm_object_attach_property(&radeon_connector->base.base,
 							   rdev->mode_info.audio_property,
 							   RADEON_AUDIO_AUTO);
+				radeon_connector->audio = RADEON_AUDIO_AUTO;
 			}
 			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 				radeon_connector->dac_load_detect = true;
@@ -2179,6 +2181,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				drm_object_attach_property(&radeon_connector->base.base,
 							   rdev->mode_info.audio_property,
 							   RADEON_AUDIO_AUTO);
+				radeon_connector->audio = RADEON_AUDIO_AUTO;
 			}
 			if (ASIC_IS_DCE5(rdev))
 				drm_object_attach_property(&radeon_connector->base.base,
@@ -2231,6 +2234,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				drm_object_attach_property(&radeon_connector->base.base,
 							   rdev->mode_info.audio_property,
 							   RADEON_AUDIO_AUTO);
+				radeon_connector->audio = RADEON_AUDIO_AUTO;
 			}
 			if (ASIC_IS_DCE5(rdev))
 				drm_object_attach_property(&radeon_connector->base.base,
@@ -2303,8 +2307,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 	}
 
 	if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 
@@ -2380,7 +2386,6 @@ radeon_add_legacy_connector(struct drm_device *dev,
 					      1);
 		/* no HPD on analog connectors */
 		radeon_connector->hpd.hpd = RADEON_HPD_NONE;
-		connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 		connector->interlace_allowed = true;
 		connector->doublescan_allowed = true;
 		break;
@@ -2465,10 +2470,13 @@ radeon_add_legacy_connector(struct drm_device *dev,
 	}
 
 	if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
+
 	connector->display_info.subpixel_order = subpixel_order;
 	drm_connector_register(connector);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index afaf346bd50e..8901228b5d5d 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -90,6 +90,9 @@ static void radeon_show_cursor(struct drm_crtc *crtc)
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct radeon_device *rdev = crtc->dev->dev_private;
 
+	if (radeon_crtc->cursor_out_of_bounds)
+		return;
+
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
 		       upper_32_bits(radeon_crtc->cursor_addr));
@@ -143,21 +146,25 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 	int xorigin = 0, yorigin = 0;
 	int w = radeon_crtc->cursor_width;
 
+	radeon_crtc->cursor_x = x;
+	radeon_crtc->cursor_y = y;
+
 	if (ASIC_IS_AVIVO(rdev)) {
 		/* avivo cursor are offset into the total surface */
 		x += crtc->x;
 		y += crtc->y;
 	}
-	DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
 
-	if (x < 0) {
+	if (x < 0)
 		xorigin = min(-x, radeon_crtc->max_cursor_width - 1);
-		x = 0;
-	}
-	if (y < 0) {
+	if (y < 0)
 		yorigin = min(-y, radeon_crtc->max_cursor_height - 1);
-		y = 0;
+
+	if (!ASIC_IS_AVIVO(rdev)) {
+		x += crtc->x;
+		y += crtc->y;
 	}
+	DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
 
 	/* fixed on DCE6 and newer */
 	if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE6(rdev)) {
@@ -180,27 +187,31 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 		if (i > 1) {
 			int cursor_end, frame_end;
 
-			cursor_end = x - xorigin + w;
+			cursor_end = x + w;
 			frame_end = crtc->x + crtc->mode.crtc_hdisplay;
 			if (cursor_end >= frame_end) {
 				w = w - (cursor_end - frame_end);
 				if (!(frame_end & 0x7f))
 					w--;
-			} else {
-				if (!(cursor_end & 0x7f))
-					w--;
+			} else if (cursor_end <= 0) {
+				goto out_of_bounds;
+			} else if (!(cursor_end & 0x7f)) {
+				w--;
 			}
 			if (w <= 0) {
-				w = 1;
-				cursor_end = x - xorigin + w;
-				if (!(cursor_end & 0x7f)) {
-					x--;
-					WARN_ON_ONCE(x < 0);
-				}
+				goto out_of_bounds;
 			}
 		}
 	}
 
+	if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) ||
+	    x >= (crtc->x + crtc->mode.hdisplay) ||
+	    y >= (crtc->y + crtc->mode.vdisplay))
+		goto out_of_bounds;
+
+	x += xorigin;
+	y += yorigin;
+
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset, (x << 16) | y);
 		WREG32(EVERGREEN_CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
@@ -212,6 +223,9 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 		WREG32(AVIVO_D1CUR_SIZE + radeon_crtc->crtc_offset,
 		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
 	} else {
+		x -= crtc->x;
+		y -= crtc->y;
+
 		if (crtc->mode.flags & DRM_MODE_FLAG_DBLSCAN)
 			y *= 2;
 
@@ -229,10 +243,20 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 		       yorigin * 256);
 	}
 
-	radeon_crtc->cursor_x = x;
-	radeon_crtc->cursor_y = y;
+	if (radeon_crtc->cursor_out_of_bounds) {
+		radeon_crtc->cursor_out_of_bounds = false;
+		if (radeon_crtc->cursor_bo)
+			radeon_show_cursor(crtc);
+	}
 
 	return 0;
+
+ out_of_bounds:
+	if (!radeon_crtc->cursor_out_of_bounds) {
+		radeon_hide_cursor(crtc);
+		radeon_crtc->cursor_out_of_bounds = true;
+	}
+	return 0;
 }
 
 int radeon_crtc_cursor_move(struct drm_crtc *crtc,
@@ -297,22 +321,23 @@ int radeon_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	radeon_crtc->cursor_width = width;
-	radeon_crtc->cursor_height = height;
-
 	radeon_lock_cursor(crtc, true);
 
-	if (hot_x != radeon_crtc->cursor_hot_x ||
+	if (width != radeon_crtc->cursor_width ||
+	    height != radeon_crtc->cursor_height ||
+	    hot_x != radeon_crtc->cursor_hot_x ||
 	    hot_y != radeon_crtc->cursor_hot_y) {
 		int x, y;
 
 		x = radeon_crtc->cursor_x + radeon_crtc->cursor_hot_x - hot_x;
 		y = radeon_crtc->cursor_y + radeon_crtc->cursor_hot_y - hot_y;
 
-		radeon_cursor_move_locked(crtc, x, y);
-
+		radeon_crtc->cursor_width = width;
+		radeon_crtc->cursor_height = height;
 		radeon_crtc->cursor_hot_x = hot_x;
 		radeon_crtc->cursor_hot_y = hot_y;
+
+		radeon_cursor_move_locked(crtc, x, y);
 	}
 
 	radeon_show_cursor(crtc);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index c566993a2ec3..a77521695c9a 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -127,6 +127,10 @@ static struct radeon_px_quirk radeon_px_quirk_list[] = {
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=51381
 	 */
 	{ PCI_VENDOR_ID_ATI, 0x6840, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX },
+	/* Asus K53TK laptop with AMD A6-3420M APU and Radeon 7670m GPU
+	 * https://bugs.freedesktop.org/show_bug.cgi?id=101491
+	 */
+	{ PCI_VENDOR_ID_ATI, 0x6741, 0x1043, 0x2122, RADEON_PX_QUIRK_DISABLE_PX },
 	/* macbook pro 8.2 */
 	{ PCI_VENDOR_ID_ATI, 0x6741, PCI_VENDOR_ID_APPLE, 0x00e2, RADEON_PX_QUIRK_LONG_WAKEUP },
 	{ 0, 0, 0, 0, 0 },
@@ -630,6 +634,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
 /*
  * GPU helpers function.
  */
+
+/**
+ * radeon_device_is_virtual - check if we are running is a virtual environment
+ *
+ * Check if the asic has been passed through to a VM (all asics).
+ * Used at driver startup.
+ * Returns true if virtual or false if not.
+ */
+static bool radeon_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false;
+#endif
+}
+
 /**
  * radeon_card_posted - check if the hw has already been initialized
  *
@@ -643,6 +664,11 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
+	/* for pass through, always force asic_init for CI */
+	if (rdev->family >= CHIP_BONAIRE &&
+	    radeon_device_is_virtual())
+		return false;
+
 	/* required for EFI mode on macbook2,1 which uses an r5xx asic */
 	if (efi_enabled(EFI_BOOT) &&
 	    (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 744f5c49c664..6dd39bdedb97 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -525,11 +525,9 @@ static bool radeon_mst_mode_fixup(struct drm_encoder *encoder,
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 	{
 	  struct radeon_connector_atom_dig *dig_connector;
-
 	  dig_connector = mst_enc->connector->con_priv;
 	  dig_connector->dp_lane_count = drm_dp_max_lane_count(dig_connector->dpcd);
-	  dig_connector->dp_clock = radeon_dp_get_max_link_rate(&mst_enc->connector->base,
-								dig_connector->dpcd);
+	  dig_connector->dp_clock = drm_dp_max_link_rate(dig_connector->dpcd);
 	  DRM_DEBUG_KMS("dig clock %p %d %d\n", dig_connector,
 			dig_connector->dp_lane_count, dig_connector->dp_clock);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 678b4386540d..89f22bdde298 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -331,6 +331,8 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode)
 			WREG32_P(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl, ~(mask | crtc_ext_cntl));
 		}
 		drm_vblank_post_modeset(dev, radeon_crtc->crtc_id);
+		/* Make sure vblank interrupt is still enabled if needed */
+		radeon_irq_set(rdev);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index bba112628b47..d8f8be608c19 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -330,6 +330,7 @@ struct radeon_crtc {
 	u16 lut_r[256], lut_g[256], lut_b[256];
 	bool enabled;
 	bool can_tile;
+	bool cursor_out_of_bounds;
 	uint32_t crtc_offset;
 	struct drm_gem_object *cursor_bo;
 	uint64_t cursor_addr;
@@ -757,8 +758,10 @@ extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector);
 extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector);
 extern int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 				    struct drm_connector *connector);
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				const u8 *dpcd);
+extern int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+					const u8 *dpcd,
+					unsigned pix_clock,
+					unsigned *dp_lanes, unsigned *dp_rate);
 extern void radeon_dp_set_rx_power_state(struct drm_connector *connector,
 					 u8 power_state);
 extern void radeon_dp_aux_init(struct radeon_connector *radeon_connector);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index e06ac546a90f..d684e2b79d2b 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -213,8 +213,8 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 			rbo->placement.num_busy_placement = 0;
 			for (i = 0; i < rbo->placement.num_placement; i++) {
 				if (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) {
-					if (rbo->placements[0].fpfn < fpfn)
-						rbo->placements[0].fpfn = fpfn;
+					if (rbo->placements[i].fpfn < fpfn)
+						rbo->placements[i].fpfn = fpfn;
 				} else {
 					rbo->placement.busy_placement =
 						&rbo->placements[i];
@@ -235,6 +235,8 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
 	struct radeon_bo *rbo = container_of(bo, struct radeon_bo, tbo);
 
+	if (radeon_ttm_tt_has_userptr(bo->ttm))
+		return -EPERM;
 	return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp);
 }
 
@@ -261,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
 	rdev = radeon_get_rdev(bo->bdev);
 	ridx = radeon_copy_ring_index(rdev);
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;
 
 	switch (old_mem->mem_type) {
 	case TTM_PL_VRAM:
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index f878d6962da5..5cf3a2cbc07e 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6335,7 +6335,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
@@ -6366,7 +6366,7 @@ static inline void si_irq_ack(struct radeon_device *rdev)
 		WREG32(DC_HPD5_INT_CONTROL, tmp);
 	}
 	if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-		tmp = RREG32(DC_HPD5_INT_CONTROL);
+		tmp = RREG32(DC_HPD6_INT_CONTROL);
 		tmp |= DC_HPDx_RX_INT_ACK;
 		WREG32(DC_HPD6_INT_CONTROL, tmp);
 	}
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index a82b891ae1fe..b6f16804e73b 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2926,9 +2926,12 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x148c, 0x2015, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1682, 0x9275, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };
 
@@ -2996,6 +2999,37 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	int i;
 	struct si_dpm_quirk *p = si_dpm_quirk_list;
 
+	/* limit all SI kickers */
+	if (rdev->family == CHIP_PITCAIRN) {
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->device == 0x6810) ||
+		    (rdev->pdev->device == 0x6811) ||
+		    (rdev->pdev->device == 0x6816) ||
+		    (rdev->pdev->device == 0x6817) ||
+		    (rdev->pdev->device == 0x6806))
+			max_mclk = 120000;
+	} else if (rdev->family == CHIP_OLAND) {
+		if ((rdev->pdev->revision == 0xC7) ||
+		    (rdev->pdev->revision == 0x80) ||
+		    (rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0x87) ||
+		    (rdev->pdev->device == 0x6604) ||
+		    (rdev->pdev->device == 0x6605)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	} else if (rdev->family == CHIP_HAINAN) {
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0xC3) ||
+		    (rdev->pdev->device == 0x6664) ||
+		    (rdev->pdev->device == 0x6665) ||
+		    (rdev->pdev->device == 0x6667)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	}
 	/* Apply dpm quirks */
 	while (p && p->chip_device != 0) {
 		if (rdev->pdev->vendor == p->chip_vendor &&
@@ -4099,7 +4133,7 @@ static int si_populate_smc_voltage_tables(struct radeon_device *rdev,
 							      &rdev->pm.dpm.dyn_state.phase_shedding_limits_table)) {
 				si_populate_smc_voltage_table(rdev, &si_pi->vddc_phase_shed_table, table);
 
-				table->phaseMaskTable.lowMask[SISLANDS_SMC_VOLTAGEMASK_VDDC] =
+				table->phaseMaskTable.lowMask[SISLANDS_SMC_VOLTAGEMASK_VDDC_PHASE_SHEDDING] =
 					cpu_to_be32(si_pi->vddc_phase_shed_table.mask_low);
 
 				si_write_smc_soft_register(rdev, SI_SMC_SOFT_REGISTER_phase_shedding_delay,
diff --git a/drivers/gpu/drm/radeon/sislands_smc.h b/drivers/gpu/drm/radeon/sislands_smc.h
index 3c779838d9ab..966e3a556011 100644
--- a/drivers/gpu/drm/radeon/sislands_smc.h
+++ b/drivers/gpu/drm/radeon/sislands_smc.h
@@ -194,6 +194,7 @@ typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE;
 #define SISLANDS_SMC_VOLTAGEMASK_VDDC  0
 #define SISLANDS_SMC_VOLTAGEMASK_MVDD  1
 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2
+#define SISLANDS_SMC_VOLTAGEMASK_VDDC_PHASE_SHEDDING 3
 #define SISLANDS_SMC_VOLTAGEMASK_MAX   4
 
 struct SISLANDS_SMC_VOLTAGEMASKTABLE
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 48cb19949ca3..9befd624a5f0 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -148,8 +148,8 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? OTAR2 : OTAR, 0);
 
 	/* Signal polarities */
-	value = ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? 0 : DSMR_VSL)
-	      | ((mode->flags & DRM_MODE_FLAG_PHSYNC) ? 0 : DSMR_HSL)
+	value = ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? DSMR_VSL : 0)
+	      | ((mode->flags & DRM_MODE_FLAG_PHSYNC) ? DSMR_HSL : 0)
 	      | DSMR_DIPM_DE | DSMR_CSPM;
 	rcar_du_crtc_write(rcrtc, DSMR, value);
 
@@ -171,7 +171,7 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 					mode->crtc_vsync_start - 1);
 	rcar_du_crtc_write(rcrtc, VCR,  mode->crtc_vtotal - 1);
 
-	rcar_du_crtc_write(rcrtc, DESR,  mode->htotal - mode->hsync_start);
+	rcar_du_crtc_write(rcrtc, DESR,  mode->htotal - mode->hsync_start - 1);
 	rcar_du_crtc_write(rcrtc, DEWR,  mode->hdisplay);
 }
 
@@ -282,26 +282,6 @@ static void rcar_du_crtc_update_planes(struct rcar_du_crtc *rcrtc)
  * Page Flip
  */
 
-void rcar_du_crtc_cancel_page_flip(struct rcar_du_crtc *rcrtc,
-				   struct drm_file *file)
-{
-	struct drm_pending_vblank_event *event;
-	struct drm_device *dev = rcrtc->crtc.dev;
-	unsigned long flags;
-
-	/* Destroy the pending vertical blanking event associated with the
-	 * pending page flip, if any, and disable vertical blanking interrupts.
-	 */
-	spin_lock_irqsave(&dev->event_lock, flags);
-	event = rcrtc->event;
-	if (event && event->base.file_priv == file) {
-		rcrtc->event = NULL;
-		event->base.destroy(&event->base);
-		drm_crtc_vblank_put(&rcrtc->crtc);
-	}
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-}
-
 static void rcar_du_crtc_finish_page_flip(struct rcar_du_crtc *rcrtc)
 {
 	struct drm_pending_vblank_event *event;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index 4b95d9d08c49..2bbe3f5aab65 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -67,8 +67,6 @@ enum rcar_du_output {
 
 int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index);
 void rcar_du_crtc_enable_vblank(struct rcar_du_crtc *rcrtc, bool enable);
-void rcar_du_crtc_cancel_page_flip(struct rcar_du_crtc *rcrtc,
-				   struct drm_file *file);
 void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc);
 void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index 40422f6b645e..bb9cd35d7fdf 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -144,91 +144,6 @@ MODULE_DEVICE_TABLE(of, rcar_du_of_table);
  * DRM operations
  */
 
-static int rcar_du_unload(struct drm_device *dev)
-{
-	struct rcar_du_device *rcdu = dev->dev_private;
-
-	if (rcdu->fbdev)
-		drm_fbdev_cma_fini(rcdu->fbdev);
-
-	drm_kms_helper_poll_fini(dev);
-	drm_mode_config_cleanup(dev);
-	drm_vblank_cleanup(dev);
-
-	dev->irq_enabled = 0;
-	dev->dev_private = NULL;
-
-	return 0;
-}
-
-static int rcar_du_load(struct drm_device *dev, unsigned long flags)
-{
-	struct platform_device *pdev = dev->platformdev;
-	struct device_node *np = pdev->dev.of_node;
-	struct rcar_du_device *rcdu;
-	struct resource *mem;
-	int ret;
-
-	if (np == NULL) {
-		dev_err(dev->dev, "no platform data\n");
-		return -ENODEV;
-	}
-
-	rcdu = devm_kzalloc(&pdev->dev, sizeof(*rcdu), GFP_KERNEL);
-	if (rcdu == NULL) {
-		dev_err(dev->dev, "failed to allocate private data\n");
-		return -ENOMEM;
-	}
-
-	init_waitqueue_head(&rcdu->commit.wait);
-
-	rcdu->dev = &pdev->dev;
-	rcdu->info = of_match_device(rcar_du_of_table, rcdu->dev)->data;
-	rcdu->ddev = dev;
-	dev->dev_private = rcdu;
-
-	/* I/O resources */
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rcdu->mmio = devm_ioremap_resource(&pdev->dev, mem);
-	if (IS_ERR(rcdu->mmio))
-		return PTR_ERR(rcdu->mmio);
-
-	/* Initialize vertical blanking interrupts handling. Start with vblank
-	 * disabled for all CRTCs.
-	 */
-	ret = drm_vblank_init(dev, (1 << rcdu->info->num_crtcs) - 1);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to initialize vblank\n");
-		goto done;
-	}
-
-	/* DRM/KMS objects */
-	ret = rcar_du_modeset_init(rcdu);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to initialize DRM/KMS (%d)\n", ret);
-		goto done;
-	}
-
-	dev->irq_enabled = 1;
-
-	platform_set_drvdata(pdev, rcdu);
-
-done:
-	if (ret)
-		rcar_du_unload(dev);
-
-	return ret;
-}
-
-static void rcar_du_preclose(struct drm_device *dev, struct drm_file *file)
-{
-	struct rcar_du_device *rcdu = dev->dev_private;
-	unsigned int i;
-
-	for (i = 0; i < rcdu->num_crtcs; ++i)
-		rcar_du_crtc_cancel_page_flip(&rcdu->crtcs[i], file);
-}
-
 static void rcar_du_lastclose(struct drm_device *dev)
 {
 	struct rcar_du_device *rcdu = dev->dev_private;
@@ -269,11 +184,7 @@ static const struct file_operations rcar_du_fops = {
 static struct drm_driver rcar_du_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME
 				| DRIVER_ATOMIC,
-	.load			= rcar_du_load,
-	.unload			= rcar_du_unload,
-	.preclose		= rcar_du_preclose,
 	.lastclose		= rcar_du_lastclose,
-	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= rcar_du_enable_vblank,
 	.disable_vblank		= rcar_du_disable_vblank,
@@ -333,18 +244,104 @@ static const struct dev_pm_ops rcar_du_pm_ops = {
  * Platform driver
  */
 
-static int rcar_du_probe(struct platform_device *pdev)
+static int rcar_du_remove(struct platform_device *pdev)
 {
-	return drm_platform_init(&rcar_du_driver, pdev);
+	struct rcar_du_device *rcdu = platform_get_drvdata(pdev);
+	struct drm_device *ddev = rcdu->ddev;
+
+	mutex_lock(&ddev->mode_config.mutex);
+	drm_connector_unplug_all(ddev);
+	mutex_unlock(&ddev->mode_config.mutex);
+
+	drm_dev_unregister(ddev);
+
+	if (rcdu->fbdev)
+		drm_fbdev_cma_fini(rcdu->fbdev);
+
+	drm_kms_helper_poll_fini(ddev);
+	drm_mode_config_cleanup(ddev);
+
+	drm_dev_unref(ddev);
+
+	return 0;
 }
 
-static int rcar_du_remove(struct platform_device *pdev)
+static int rcar_du_probe(struct platform_device *pdev)
 {
-	struct rcar_du_device *rcdu = platform_get_drvdata(pdev);
+	struct device_node *np = pdev->dev.of_node;
+	struct rcar_du_device *rcdu;
+	struct drm_connector *connector;
+	struct drm_device *ddev;
+	struct resource *mem;
+	int ret;
+
+	if (np == NULL) {
+		dev_err(&pdev->dev, "no device tree node\n");
+		return -ENODEV;
+	}
 
-	drm_put_dev(rcdu->ddev);
+	/* Allocate and initialize the DRM and R-Car device structures. */
+	rcdu = devm_kzalloc(&pdev->dev, sizeof(*rcdu), GFP_KERNEL);
+	if (rcdu == NULL)
+		return -ENOMEM;
+
+	init_waitqueue_head(&rcdu->commit.wait);
+
+	rcdu->dev = &pdev->dev;
+	rcdu->info = of_match_device(rcar_du_of_table, rcdu->dev)->data;
+
+	platform_set_drvdata(pdev, rcdu);
+
+	/* I/O resources */
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rcdu->mmio = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(rcdu->mmio))
+		return PTR_ERR(rcdu->mmio);
+
+	/* DRM/KMS objects */
+	ddev = drm_dev_alloc(&rcar_du_driver, &pdev->dev);
+	if (!ddev)
+		return -ENOMEM;
+
+	drm_dev_set_unique(ddev, dev_name(&pdev->dev));
+
+	rcdu->ddev = ddev;
+	ddev->dev_private = rcdu;
+
+	ret = rcar_du_modeset_init(rcdu);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to initialize DRM/KMS (%d)\n", ret);
+		goto error;
+	}
+
+	ddev->irq_enabled = 1;
+
+	/* Register the DRM device with the core and the connectors with
+	 * sysfs.
+	 */
+	ret = drm_dev_register(ddev, 0);
+	if (ret)
+		goto error;
+
+	mutex_lock(&ddev->mode_config.mutex);
+	drm_for_each_connector(connector, ddev) {
+		ret = drm_connector_register(connector);
+		if (ret < 0)
+			break;
+	}
+	mutex_unlock(&ddev->mode_config.mutex);
+
+	if (ret < 0)
+		goto error;
+
+	DRM_INFO("Device %s probed\n", dev_name(&pdev->dev));
 
 	return 0;
+
+error:
+	rcar_du_remove(pdev);
+
+	return ret;
 }
 
 static struct platform_driver rcar_du_platform_driver = {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c
index 96f2eb43713c..6038be93c58d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c
@@ -55,12 +55,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.best_encoder = rcar_du_connector_best_encoder,
 };
 
-static void rcar_du_hdmi_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static enum drm_connector_status
 rcar_du_hdmi_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -79,7 +73,7 @@ static const struct drm_connector_funcs connector_funcs = {
 	.reset = drm_atomic_helper_connector_reset,
 	.detect = rcar_du_hdmi_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = rcar_du_hdmi_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
@@ -108,9 +102,6 @@ int rcar_du_hdmi_connector_init(struct rcar_du_device *rcdu,
 		return ret;
 
 	drm_connector_helper_add(connector, &connector_helper_funcs);
-	ret = drm_connector_register(connector);
-	if (ret < 0)
-		return ret;
 
 	connector->dpms = DRM_MODE_DPMS_OFF;
 	drm_object_property_set_value(&connector->base,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index ca12e8ca5552..2b75a4891dec 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -642,13 +642,13 @@ static int rcar_du_encoders_init_one(struct rcar_du_device *rcdu,
 	}
 
 	ret = rcar_du_encoder_init(rcdu, enc_type, output, encoder, connector);
-	of_node_put(encoder);
-	of_node_put(connector);
-
 	if (ret && ret != -EPROBE_DEFER)
 		dev_warn(rcdu->dev,
-			 "failed to initialize encoder %s (%d), skipping\n",
-			 encoder->full_name, ret);
+			 "failed to initialize encoder %s on output %u (%d), skipping\n",
+			 of_node_full_name(encoder), output, ret);
+
+	of_node_put(encoder);
+	of_node_put(connector);
 
 	return ret;
 }
@@ -761,6 +761,13 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	if (ret < 0)
 		return ret;
 
+	/* Initialize vertical blanking interrupts handling. Start with vblank
+	* disabled for all CRTCs.
+	*/
+	ret = drm_vblank_init(dev, (1 << rcdu->info->num_crtcs) - 1);
+	if (ret < 0)
+		return ret;
+
 	/* Initialize the groups. */
 	num_groups = DIV_ROUND_UP(rcdu->num_crtcs, 2);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index 0c43032fc693..e905f5da7aaa 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -62,12 +62,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.best_encoder = rcar_du_connector_best_encoder,
 };
 
-static void rcar_du_lvds_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static enum drm_connector_status
 rcar_du_lvds_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -79,7 +73,7 @@ static const struct drm_connector_funcs connector_funcs = {
 	.reset = drm_atomic_helper_connector_reset,
 	.detect = rcar_du_lvds_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = rcar_du_lvds_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
@@ -117,9 +111,6 @@ int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
 		return ret;
 
 	drm_connector_helper_add(connector, &connector_helper_funcs);
-	ret = drm_connector_register(connector);
-	if (ret < 0)
-		return ret;
 
 	connector->dpms = DRM_MODE_DPMS_OFF;
 	drm_object_property_set_value(&connector->base,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
index 85043c5bad03..873e04aa9352 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
@@ -56,11 +56,11 @@ static int rcar_du_lvdsenc_start(struct rcar_du_lvdsenc *lvds,
 		return ret;
 
 	/* PLL clock configuration */
-	if (freq <= 38000)
+	if (freq < 39000)
 		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_38M;
-	else if (freq <= 60000)
+	else if (freq < 61000)
 		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_60M;
-	else if (freq <= 121000)
+	else if (freq < 121000)
 		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_121M;
 	else
 		pllcr = LVDPLLCR_PLLDLYCNT_150M;
@@ -102,7 +102,7 @@ static int rcar_du_lvdsenc_start(struct rcar_du_lvdsenc *lvds,
 	/* Turn the PLL on, wait for the startup delay, and turn the output
 	 * on.
 	 */
-	lvdcr0 |= LVDCR0_PLLEN;
+	lvdcr0 |= LVDCR0_PLLON;
 	rcar_lvds_write(lvds, LVDCR0, lvdcr0);
 
 	usleep_range(100, 150);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
index e0a5d8f93963..9d7e5c99caf6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
@@ -31,12 +31,6 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.best_encoder = rcar_du_connector_best_encoder,
 };
 
-static void rcar_du_vga_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
 static enum drm_connector_status
 rcar_du_vga_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -48,7 +42,7 @@ static const struct drm_connector_funcs connector_funcs = {
 	.reset = drm_atomic_helper_connector_reset,
 	.detect = rcar_du_vga_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = rcar_du_vga_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
@@ -76,9 +70,6 @@ int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
 		return ret;
 
 	drm_connector_helper_add(connector, &connector_helper_funcs);
-	ret = drm_connector_register(connector);
-	if (ret < 0)
-		return ret;
 
 	connector->dpms = DRM_MODE_DPMS_OFF;
 	drm_object_property_set_value(&connector->base,
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h b/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h
index 77cf9289ab65..b1eafd097a79 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h
@@ -18,7 +18,7 @@
 #define LVDCR0_DMD			(1 << 12)
 #define LVDCR0_LVMD_MASK		(0xf << 8)
 #define LVDCR0_LVMD_SHIFT		8
-#define LVDCR0_PLLEN			(1 << 4)
+#define LVDCR0_PLLON			(1 << 4)
 #define LVDCR0_BEN			(1 << 2)
 #define LVDCR0_LVEN			(1 << 1)
 #define LVDCR0_LVRES			(1 << 0)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 745e996d2dbc..037c38bb5333 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1004,9 +1004,9 @@ out_unlock:
 	return ret;
 }
 
-static bool ttm_bo_mem_compat(struct ttm_placement *placement,
-			      struct ttm_mem_reg *mem,
-			      uint32_t *new_flags)
+bool ttm_bo_mem_compat(struct ttm_placement *placement,
+		       struct ttm_mem_reg *mem,
+		       uint32_t *new_flags)
 {
 	int i;
 
@@ -1038,6 +1038,7 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement,
 
 	return false;
 }
+EXPORT_SYMBOL(ttm_bo_mem_compat);
 
 int ttm_bo_validate(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
@@ -1620,7 +1621,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	struct ttm_buffer_object *bo;
 	int ret = -EBUSY;
 	int put_count;
-	uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM);
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &glob->swap_lru, swap) {
@@ -1656,7 +1656,8 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	if (unlikely(ret != 0))
 		goto out;
 
-	if ((bo->mem.placement & swap_placement) != swap_placement) {
+	if (bo->mem.mem_type != TTM_PL_SYSTEM ||
+	    bo->ttm->caching_state != tt_cached) {
 		struct ttm_mem_reg evict_mem;
 
 		evict_mem = bo->mem;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 8fb7213277cc..b75391495778 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -66,8 +66,11 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;
 
+		ttm_bo_reference(bo);
 		up_read(&vma->vm_mm->mmap_sem);
 		(void) ttm_bo_wait(bo, false, true, false);
+		ttm_bo_unreserve(bo);
+		ttm_bo_unref(&bo);
 		goto out_unlock;
 	}
 
@@ -114,8 +117,10 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				ttm_bo_reference(bo);
 				up_read(&vma->vm_mm->mmap_sem);
 				(void) ttm_bo_wait_unreserved(bo);
+				ttm_bo_unref(&bo);
 			}
 
 			return VM_FAULT_RETRY;
@@ -160,6 +165,13 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = ttm_bo_vm_fault_idle(bo, vma, vmf);
 	if (unlikely(ret != 0)) {
 		retval = ret;
+
+		if (retval == VM_FAULT_RETRY &&
+		    !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+			/* The BO has already been unreserved. */
+			return retval;
+		}
+
 		goto out_unlock;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 4f5fa8d65fe9..144367c0c28f 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -179,7 +179,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
 	if (unlikely(ret != 0))
 		goto out_err0;
 
-	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
 	if (unlikely(ret != 0))
 		goto out_err1;
 
@@ -318,7 +318,8 @@ EXPORT_SYMBOL(ttm_ref_object_exists);
 
 int ttm_ref_object_add(struct ttm_object_file *tfile,
 		       struct ttm_base_object *base,
-		       enum ttm_ref_type ref_type, bool *existed)
+		       enum ttm_ref_type ref_type, bool *existed,
+		       bool require_existed)
 {
 	struct drm_open_hash *ht = &tfile->ref_hash[ref_type];
 	struct ttm_ref_object *ref;
@@ -345,6 +346,9 @@ int ttm_ref_object_add(struct ttm_object_file *tfile,
 		}
 
 		rcu_read_unlock();
+		if (require_existed)
+			return -EPERM;
+
 		ret = ttm_mem_global_alloc(mem_glob, sizeof(*ref),
 					   false, false);
 		if (unlikely(ret != 0))
@@ -635,7 +639,7 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
 	prime = (struct ttm_prime_object *) dma_buf->priv;
 	base = &prime->base;
 	*handle = base->hash.key;
-	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL, false);
 
 	dma_buf_put(dma_buf);
 
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 025c429050c0..5d8dfe027b30 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -612,7 +612,7 @@ static void ttm_page_pool_fill_locked(struct ttm_page_pool *pool,
 		} else {
 			pr_err("Failed to fill pool (%p)\n", pool);
 			/* If we have any pages left put them to the pool. */
-			list_for_each_entry(p, &pool->list, lru) {
+			list_for_each_entry(p, &new_pages, lru) {
 				++cpages;
 			}
 			list_splice(&new_pages, &pool->list);
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 62c7b1dafaa4..73e41a8613da 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -539,7 +539,7 @@ static int udlfb_create(struct drm_fb_helper *helper,
 out_destroy_fbi:
 	drm_fb_helper_release_fbi(helper);
 out_gfree:
-	drm_gem_object_unreference(&ufbdev->ufb.obj->base);
+	drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 2a0a784ab6ee..d7528e0d8442 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -52,7 +52,7 @@ udl_gem_create(struct drm_file *file,
 		return ret;
 	}
 
-	drm_gem_object_unreference(&obj->base);
+	drm_gem_object_unreference_unlocked(&obj->base);
 	*handle_p = handle;
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index 6a81e084593b..2b59d80a09b8 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -338,7 +338,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
 	info->fbops = &virtio_gpufb_ops;
 	info->pixmap.flags = FB_PIXMAP_SYSTEM;
 
-	info->screen_base = obj->vmap;
+	info->screen_buffer = obj->vmap;
 	info->screen_size = obj->gem_base.size;
 	drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth);
 	drm_fb_helper_fill_var(info, &vfbdev->helper,
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index f300eba95bb1..1244cdf52859 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -81,8 +81,10 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 		return -ENOMEM;
 	size = roundup(size, PAGE_SIZE);
 	ret = drm_gem_object_init(vgdev->ddev, &bo->gem_base, size);
-	if (ret != 0)
+	if (ret != 0) {
+		kfree(bo);
 		return ret;
+	}
 	bo->dumb = false;
 	virtio_gpu_init_ttm_placement(bo, pinned);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 13db8a2851ed..1f013d45c9e9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -321,6 +321,7 @@ void vmw_cmdbuf_res_man_destroy(struct vmw_cmdbuf_res_manager *man)
 	list_for_each_entry_safe(entry, next, &man->list, head)
 		vmw_cmdbuf_res_free(man, entry);
 
+	drm_ht_remove(&man->resources);
 	kfree(man);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index 299925a1f6c6..eadc981ee79a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -49,6 +49,7 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv,
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	int ret;
+	uint32_t new_flags;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -60,7 +61,12 @@ int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		goto err;
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false);
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, interruptible, false);
+
 	if (!ret)
 		vmw_bo_pin_reserved(buf, true);
 
@@ -91,6 +97,7 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	int ret;
+	uint32_t new_flags;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -102,6 +109,12 @@ int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		goto err;
 
+	if (buf->pin_count > 0) {
+		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
 	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, interruptible,
 			      false);
 	if (likely(ret == 0) || ret == -ERESTARTSYS)
@@ -161,6 +174,7 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv,
 	struct ttm_placement placement;
 	struct ttm_place place;
 	int ret = 0;
+	uint32_t new_flags;
 
 	place = vmw_vram_placement.placement[0];
 	place.lpfn = bo->num_pages;
@@ -185,10 +199,15 @@ int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv,
 	 */
 	if (bo->mem.mem_type == TTM_PL_VRAM &&
 	    bo->mem.start < bo->num_pages &&
-	    bo->mem.start > 0)
+	    bo->mem.start > 0 &&
+	    buf->pin_count == 0)
 		(void) ttm_bo_validate(bo, &vmw_sys_placement, false, false);
 
-	ret = ttm_bo_validate(bo, &placement, interruptible, false);
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(&placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, interruptible, false);
 
 	/* For some reason we didn't end up at the start of vram */
 	WARN_ON(ret == 0 && bo->offset != 0);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 24fb348a44e1..f3f31f995878 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -227,6 +227,7 @@ static int vmw_force_iommu;
 static int vmw_restrict_iommu;
 static int vmw_force_coherent;
 static int vmw_restrict_dma_mask;
+static int vmw_assume_16bpp;
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
 static void vmw_master_init(struct vmw_master *);
@@ -243,6 +244,8 @@ MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
 module_param_named(force_coherent, vmw_force_coherent, int, 0600);
 MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU");
 module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600);
+MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
+module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
 static void vmw_print_capabilities(uint32_t capabilities)
@@ -652,6 +655,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	dev_priv->vram_start = pci_resource_start(dev->pdev, 1);
 	dev_priv->mmio_start = pci_resource_start(dev->pdev, 2);
 
+	dev_priv->assume_16bpp = !!vmw_assume_16bpp;
+
 	dev_priv->enable_fb = enable_fbdev;
 
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
@@ -698,6 +703,13 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 			vmw_read(dev_priv,
 				 SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB);
 
+		/*
+		 * Workaround for low memory 2D VMs to compensate for the
+		 * allocation taken by fbdev
+		 */
+		if (!(dev_priv->capabilities & SVGA_CAP_3D))
+			mem_size *= 2;
+
 		dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE;
 		dev_priv->prim_bb_mem =
 			vmw_read(dev_priv,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 469cdd520615..2e94fe27b3f6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -387,6 +387,7 @@ struct vmw_private {
 	spinlock_t hw_lock;
 	spinlock_t cap_lock;
 	bool has_dx;
+	bool assume_16bpp;
 
 	/*
 	 * VGA registers.
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 5da5de0cb522..04fd0f2b6af0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -471,7 +471,7 @@ static int vmw_cmd_invalid(struct vmw_private *dev_priv,
 			   struct vmw_sw_context *sw_context,
 			   SVGA3dCmdHeader *header)
 {
-	return capable(CAP_SYS_ADMIN) ? : -EINVAL;
+	return -EINVAL;
 }
 
 static int vmw_cmd_ok(struct vmw_private *dev_priv,
@@ -3273,19 +3273,19 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 		    &vmw_cmd_dx_cid_check, true, false, true),
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_DEFINE_QUERY, &vmw_cmd_dx_define_query,
 		    true, false, true),
-	VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_ok,
+	VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_dx_cid_check,
 		    true, false, true),
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_BIND_QUERY, &vmw_cmd_dx_bind_query,
 		    true, false, true),
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_QUERY_OFFSET,
-		    &vmw_cmd_ok, true, false, true),
-	VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_ok,
+		    &vmw_cmd_dx_cid_check, true, false, true),
+	VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_dx_cid_check,
 		    true, false, true),
-	VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_ok,
+	VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_dx_cid_check,
 		    true, false, true),
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_READBACK_QUERY, &vmw_cmd_invalid,
 		    true, false, true),
-	VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_dx_cid_check,
 		    true, false, true),
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_VIEWPORTS, &vmw_cmd_dx_cid_check,
 		    true, false, true),
@@ -3830,14 +3830,14 @@ static void *vmw_execbuf_cmdbuf(struct vmw_private *dev_priv,
 	int ret;
 
 	*header = NULL;
-	if (!dev_priv->cman || kernel_commands)
-		return kernel_commands;
-
 	if (command_size > SVGA_CB_MAX_SIZE) {
 		DRM_ERROR("Command buffer is too large.\n");
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (!dev_priv->cman || kernel_commands)
+		return kernel_commands;
+
 	/* If possible, add a little space for fencing. */
 	cmdbuf_size = command_size + 512;
 	cmdbuf_size = min_t(size_t, cmdbuf_size, SVGA_CB_MAX_SIZE);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 3b1faf7862a5..d2d93959b119 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -517,28 +517,6 @@ static int vmw_fb_kms_framebuffer(struct fb_info *info)
 
 	par->set_fb = &vfb->base;
 
-	if (!par->bo_ptr) {
-		/*
-		 * Pin before mapping. Since we don't know in what placement
-		 * to pin, call into KMS to do it for us.
-		 */
-		ret = vfb->pin(vfb);
-		if (ret) {
-			DRM_ERROR("Could not pin the fbdev framebuffer.\n");
-			return ret;
-		}
-
-		ret = ttm_bo_kmap(&par->vmw_bo->base, 0,
-				  par->vmw_bo->base.num_pages, &par->map);
-		if (ret) {
-			vfb->unpin(vfb);
-			DRM_ERROR("Could not map the fbdev framebuffer.\n");
-			return ret;
-		}
-
-		par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite);
-	}
-
 	return 0;
 }
 
@@ -573,9 +551,9 @@ static int vmw_fb_set_par(struct fb_info *info)
 		mode = old_mode;
 		old_mode = NULL;
 	} else if (!vmw_kms_validate_mode_vram(vmw_priv,
-					       mode->hdisplay *
-					       (var->bits_per_pixel + 7) / 8,
-					       mode->vdisplay)) {
+					mode->hdisplay *
+					DIV_ROUND_UP(var->bits_per_pixel, 8),
+					mode->vdisplay)) {
 		drm_mode_destroy(vmw_priv->dev, mode);
 		return -EINVAL;
 	}
@@ -601,6 +579,31 @@ static int vmw_fb_set_par(struct fb_info *info)
 	if (ret)
 		goto out_unlock;
 
+	if (!par->bo_ptr) {
+		struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(set.fb);
+
+		/*
+		 * Pin before mapping. Since we don't know in what placement
+		 * to pin, call into KMS to do it for us.
+		 */
+		ret = vfb->pin(vfb);
+		if (ret) {
+			DRM_ERROR("Could not pin the fbdev framebuffer.\n");
+			goto out_unlock;
+		}
+
+		ret = ttm_bo_kmap(&par->vmw_bo->base, 0,
+				  par->vmw_bo->base.num_pages, &par->map);
+		if (ret) {
+			vfb->unpin(vfb);
+			DRM_ERROR("Could not map the fbdev framebuffer.\n");
+			goto out_unlock;
+		}
+
+		par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite);
+	}
+
+
 	vmw_fb_dirty_mark(par, par->fb_x, par->fb_y,
 			  par->set_fb->width, par->set_fb->height);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 8e689b439890..6c649f7b5929 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -539,7 +539,7 @@ int vmw_fence_create(struct vmw_fence_manager *fman,
 		     struct vmw_fence_obj **p_fence)
 {
 	struct vmw_fence_obj *fence;
-	int ret;
+ 	int ret;
 
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
 	if (unlikely(fence == NULL))
@@ -702,6 +702,41 @@ void vmw_fence_fifo_up(struct vmw_fence_manager *fman)
 }
 
 
+/**
+ * vmw_fence_obj_lookup - Look up a user-space fence object
+ *
+ * @tfile: A struct ttm_object_file identifying the caller.
+ * @handle: A handle identifying the fence object.
+ * @return: A struct vmw_user_fence base ttm object on success or
+ * an error pointer on failure.
+ *
+ * The fence object is looked up and type-checked. The caller needs
+ * to have opened the fence object first, but since that happens on
+ * creation and fence objects aren't shareable, that's not an
+ * issue currently.
+ */
+static struct ttm_base_object *
+vmw_fence_obj_lookup(struct ttm_object_file *tfile, u32 handle)
+{
+	struct ttm_base_object *base = ttm_base_object_lookup(tfile, handle);
+
+	if (!base) {
+		pr_err("Invalid fence object handle 0x%08lx.\n",
+		       (unsigned long)handle);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (base->refcount_release != vmw_user_fence_base_release) {
+		pr_err("Invalid fence object handle 0x%08lx.\n",
+		       (unsigned long)handle);
+		ttm_base_object_unref(&base);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return base;
+}
+
+
 int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv)
 {
@@ -727,13 +762,9 @@ int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
 		arg->kernel_cookie = jiffies + wait_timeout;
 	}
 
-	base = ttm_base_object_lookup(tfile, arg->handle);
-	if (unlikely(base == NULL)) {
-		printk(KERN_ERR "Wait invalid fence object handle "
-		       "0x%08lx.\n",
-		       (unsigned long)arg->handle);
-		return -EINVAL;
-	}
+	base = vmw_fence_obj_lookup(tfile, arg->handle);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	fence = &(container_of(base, struct vmw_user_fence, base)->fence);
 
@@ -772,13 +803,9 @@ int vmw_fence_obj_signaled_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct vmw_private *dev_priv = vmw_priv(dev);
 
-	base = ttm_base_object_lookup(tfile, arg->handle);
-	if (unlikely(base == NULL)) {
-		printk(KERN_ERR "Fence signaled invalid fence object handle "
-		       "0x%08lx.\n",
-		       (unsigned long)arg->handle);
-		return -EINVAL;
-	}
+	base = vmw_fence_obj_lookup(tfile, arg->handle);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	fence = &(container_of(base, struct vmw_user_fence, base)->fence);
 	fman = fman_from_fence(fence);
@@ -1093,6 +1120,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_fence_event_arg *) data;
 	struct vmw_fence_obj *fence = NULL;
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
+	struct ttm_object_file *tfile = vmw_fp->tfile;
 	struct drm_vmw_fence_rep __user *user_fence_rep =
 		(struct drm_vmw_fence_rep __user *)(unsigned long)
 		arg->fence_rep;
@@ -1106,24 +1134,18 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 	 */
 	if (arg->handle) {
 		struct ttm_base_object *base =
-			ttm_base_object_lookup_for_ref(dev_priv->tdev,
-						       arg->handle);
-
-		if (unlikely(base == NULL)) {
-			DRM_ERROR("Fence event invalid fence object handle "
-				  "0x%08lx.\n",
-				  (unsigned long)arg->handle);
-			return -EINVAL;
-		}
+			vmw_fence_obj_lookup(tfile, arg->handle);
+
+		if (IS_ERR(base))
+			return PTR_ERR(base);
+
 		fence = &(container_of(base, struct vmw_user_fence,
 				       base)->fence);
 		(void) vmw_fence_obj_reference(fence);
 
 		if (user_fence_rep != NULL) {
-			bool existed;
-
 			ret = ttm_ref_object_add(vmw_fp->tfile, base,
-						 TTM_REF_USAGE, &existed);
+						 TTM_REF_USAGE, NULL, false);
 			if (unlikely(ret != 0)) {
 				DRM_ERROR("Failed to reference a fence "
 					  "object.\n");
@@ -1166,8 +1188,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 	return 0;
 out_no_create:
 	if (user_fence_rep != NULL)
-		ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					  handle, TTM_REF_USAGE);
+		ttm_ref_object_base_unref(tfile, handle, TTM_REF_USAGE);
 out_no_ref_obj:
 	vmw_fence_obj_unreference(&fence);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index b6a0806b06bf..a1c68e6a689e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv,
 				return fifo_state->static_buffer;
 			else {
 				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
 				return fifo_state->dynamic_buffer;
 			}
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index b8c6a03c8c54..5ec24fd801cd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -114,8 +114,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 		param->value = dev_priv->has_dx;
 		break;
 	default:
-		DRM_ERROR("Illegal vmwgfx get param request: %d\n",
-			  param->param);
 		return -EINVAL;
 	}
 
@@ -186,7 +184,7 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
 	bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS);
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
-	if (unlikely(arg->pad64 != 0)) {
+	if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) {
 		DRM_ERROR("Illegal GET_3D_CAP argument.\n");
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 7c2e118a77b0..060e5c6f4446 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1538,14 +1538,10 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC)
 	};
 	int i;
-	u32 assumed_bpp = 2;
+	u32 assumed_bpp = 4;
 
-	/*
-	 * If using screen objects, then assume 32-bpp because that's what the
-	 * SVGA device is assuming
-	 */
-	if (dev_priv->active_display_unit == vmw_du_screen_object)
-		assumed_bpp = 4;
+	if (dev_priv->assume_16bpp)
+		assumed_bpp = 2;
 
 	if (dev_priv->active_display_unit == vmw_du_screen_target) {
 		max_width  = min(max_width,  dev_priv->stdu_max_width);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index e57667ca7557..dbca128a9aa6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -591,7 +591,7 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
 		return ret;
 
 	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
-				 TTM_REF_SYNCCPU_WRITE, &existed);
+				 TTM_REF_SYNCCPU_WRITE, &existed, false);
 	if (ret != 0 || existed)
 		ttm_bo_synccpu_write_release(&user_bo->dma.base);
 
@@ -775,7 +775,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
 
 	*handle = user_bo->prime.base.hash.key;
 	return ttm_ref_object_add(tfile, &user_bo->prime.base,
-				  TTM_REF_USAGE, NULL);
+				  TTM_REF_USAGE, NULL, false);
 }
 
 /*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 7d620e82e000..027987023400 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -715,11 +715,14 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 			128;
 
 	num_sizes = 0;
-	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
+	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) {
+		if (req->mip_levels[i] > DRM_VMW_MAX_MIP_LEVELS)
+			return -EINVAL;
 		num_sizes += req->mip_levels[i];
+	}
 
-	if (num_sizes > DRM_VMW_MAX_SURFACE_FACES *
-	    DRM_VMW_MAX_MIP_LEVELS)
+	if (num_sizes > DRM_VMW_MAX_SURFACE_FACES * DRM_VMW_MAX_MIP_LEVELS ||
+	    num_sizes == 0)
 		return -EINVAL;
 
 	size = vmw_user_surface_size + 128 +
@@ -904,17 +907,16 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 	uint32_t handle;
 	struct ttm_base_object *base;
 	int ret;
+	bool require_exist = false;
 
 	if (handle_type == DRM_VMW_HANDLE_PRIME) {
 		ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
 		if (unlikely(ret != 0))
 			return ret;
 	} else {
-		if (unlikely(drm_is_render_client(file_priv))) {
-			DRM_ERROR("Render client refused legacy "
-				  "surface reference.\n");
-			return -EACCES;
-		}
+		if (unlikely(drm_is_render_client(file_priv)))
+			require_exist = true;
+
 		if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) {
 			DRM_ERROR("Locked master refused legacy "
 				  "surface reference.\n");
@@ -942,17 +944,14 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 
 		/*
 		 * Make sure the surface creator has the same
-		 * authenticating master.
+		 * authenticating master, or is already registered with us.
 		 */
 		if (drm_is_primary_client(file_priv) &&
-		    user_srf->master != file_priv->master) {
-			DRM_ERROR("Trying to reference surface outside of"
-				  " master domain.\n");
-			ret = -EACCES;
-			goto out_bad_resource;
-		}
+		    user_srf->master != file_priv->master)
+			require_exist = true;
 
-		ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+		ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL,
+					 require_exist);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not add a reference to a surface.\n");
 			goto out_bad_resource;
@@ -1289,11 +1288,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	int ret;
 	uint32_t size;
-	uint32_t backup_handle;
+	uint32_t backup_handle = 0;
 
 	if (req->multisample_count != 0)
 		return -EINVAL;
 
+	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
 			128;
@@ -1329,12 +1331,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
 					     &res->backup,
 					     &user_srf->backup_base);
-		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
-		    res->backup_size) {
-			DRM_ERROR("Surface backup buffer is too small.\n");
-			vmw_dmabuf_unreference(&res->backup);
-			ret = -EINVAL;
-			goto out_unlock;
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer is too small.\n");
+				vmw_dmabuf_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->buffer_handle;
+			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
 		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index a0e28f3a278d..5030cba4a581 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -997,7 +997,7 @@ struct ipu_platform_reg {
 };
 
 /* These must be in the order of the corresponding device tree port nodes */
-static const struct ipu_platform_reg client_reg[] = {
+static struct ipu_platform_reg client_reg[] = {
 	{
 		.pdata = {
 			.csi = 0,
@@ -1048,7 +1048,7 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 	mutex_unlock(&ipu_client_id_mutex);
 
 	for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
-		const struct ipu_platform_reg *reg = &client_reg[i];
+		struct ipu_platform_reg *reg = &client_reg[i];
 		struct platform_device *pdev;
 		struct device_node *of_node;
 
@@ -1068,9 +1068,9 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 			goto err_register;
 		}
 
-		pdev->dev.of_node = of_node;
 		pdev->dev.parent = dev;
 
+		reg->pdata.of_node = of_node;
 		ret = platform_device_add_data(pdev, &reg->pdata,
 					       sizeof(reg->pdata));
 		if (!ret)
@@ -1079,6 +1079,12 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 			platform_device_put(pdev);
 			goto err_register;
 		}
+
+		/*
+		 * Set of_node only after calling platform_device_add. Otherwise
+		 * the platform:imx-ipuv3-crtc modalias won't be used.
+		 */
+		pdev->dev.of_node = of_node;
 	}
 
 	return 0;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index c6f7a694f67a..11a051bd8a8b 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1251,6 +1251,7 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 		/* Ignore report if ErrorRollOver */
 		if (!(field->flags & HID_MAIN_ITEM_VARIABLE) &&
 		    value[n] >= min && value[n] <= max &&
+		    value[n] - min < field->maxusage &&
 		    field->usage[value[n] - min].hid == HID_UP_KEYBOARD + 1)
 			goto exit;
 	}
@@ -1263,11 +1264,13 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 		}
 
 		if (field->value[n] >= min && field->value[n] <= max
+			&& field->value[n] - min < field->maxusage
 			&& field->usage[field->value[n] - min].hid
 			&& search(value, field->value[n], count))
 				hid_process_event(hid, field, &field->usage[field->value[n] - min], 0, interrupt);
 
 		if (value[n] >= min && value[n] <= max
+			&& value[n] - min < field->maxusage
 			&& field->usage[value[n] - min].hid
 			&& search(field->value, value[n], count))
 				hid_process_event(hid, field, &field->usage[value[n] - min], 1, interrupt);
@@ -1897,6 +1900,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_EXTREME_3D) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DUAL_ACTION) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WHEEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD) },
@@ -2423,6 +2427,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0002) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0003) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PANJIT, 0x0004) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) },
 #if defined(CONFIG_MOUSE_SYNAPTICS_USB) || defined(CONFIG_MOUSE_SYNAPTICS_USB_MODULE)
@@ -2615,9 +2620,10 @@ int hid_add_device(struct hid_device *hdev)
 	/*
 	 * Scan generic devices for group information
 	 */
-	if (hid_ignore_special_drivers ||
-	    (!hdev->group &&
-	     !hid_match_id(hdev, hid_have_special_driver))) {
+	if (hid_ignore_special_drivers) {
+		hdev->group = HID_GROUP_GENERIC;
+	} else if (!hdev->group &&
+		   !hid_match_id(hdev, hid_have_special_driver)) {
 		ret = hid_scan_report(hdev);
 		if (ret)
 			hid_warn(hdev, "bad device descriptor (%d)\n", ret);
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index bcefb9ebb026..88be56321610 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -148,26 +148,36 @@ static enum led_brightness k90_backlight_get(struct led_classdev *led_cdev)
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	int brightness;
-	char data[8];
+	char *data;
+
+	data = kmalloc(8, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_STATUS,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 8,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 5) {
 		dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	brightness = data[4];
 	if (brightness < 0 || brightness > 3) {
 		dev_warn(dev,
 			 "Read invalid backlight brightness: %02hhx.\n",
 			 data[4]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
-	return brightness;
+	ret = brightness;
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static enum led_brightness k90_record_led_get(struct led_classdev *led_cdev)
@@ -253,17 +263,22 @@ static ssize_t k90_show_macro_mode(struct device *dev,
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	const char *macro_mode;
-	char data[8];
+	char *data;
+
+	data = kmalloc(2, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_GET_MODE,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 2,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 1) {
 		dev_warn(dev, "Failed to get K90 initial mode (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	switch (data[0]) {
@@ -277,10 +292,15 @@ static ssize_t k90_show_macro_mode(struct device *dev,
 	default:
 		dev_warn(dev, "K90 in unknown mode: %02hhx.\n",
 			 data[0]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+	ret = snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static ssize_t k90_store_macro_mode(struct device *dev,
@@ -320,26 +340,36 @@ static ssize_t k90_show_current_profile(struct device *dev,
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	int current_profile;
-	char data[8];
+	char *data;
+
+	data = kmalloc(8, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_STATUS,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 8,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 8) {
 		dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	current_profile = data[7];
 	if (current_profile < 1 || current_profile > 3) {
 		dev_warn(dev, "Read invalid current profile: %02hhx.\n",
 			 data[7]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+	ret = snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static ssize_t k90_store_current_profile(struct device *dev,
diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c
index 1b764d1745f3..1689568b597d 100644
--- a/drivers/hid/hid-cypress.c
+++ b/drivers/hid/hid-cypress.c
@@ -39,6 +39,9 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX))
 		return rdesc;
 
+	if (*rsize < 4)
+		return rdesc;
+
 	for (i = 0; i < *rsize - 4; i++)
 		if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) {
 			rdesc[i] = 0x19;
diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c
index aad8c162a825..0cd4f7216239 100644
--- a/drivers/hid/hid-elo.c
+++ b/drivers/hid/hid-elo.c
@@ -261,7 +261,7 @@ static void elo_remove(struct hid_device *hdev)
 	struct elo_priv *priv = hid_get_drvdata(hdev);
 
 	hid_hw_stop(hdev);
-	flush_workqueue(wq);
+	cancel_delayed_work_sync(&priv->work);
 	kfree(priv);
 }
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 8b78a7f1f779..37cbc2ecfc5f 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -168,6 +168,7 @@
 #define USB_DEVICE_ID_ATEN_4PORTKVM	0x2205
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
 #define USB_DEVICE_ID_ATEN_CS682	0x2213
+#define USB_DEVICE_ID_ATEN_CS692	0x8021
 
 #define USB_VENDOR_ID_ATMEL		0x03eb
 #define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
@@ -255,6 +256,7 @@
 #define USB_DEVICE_ID_CORSAIR_K90	0x1b02
 
 #define USB_VENDOR_ID_CREATIVELABS	0x041e
+#define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51	0x322c
 #define USB_DEVICE_ID_PRODIKEYS_PCMIDI	0x2801
 
 #define USB_VENDOR_ID_CVTOUCH		0x1ff7
@@ -283,6 +285,9 @@
 #define USB_VENDOR_ID_DEALEXTREAME	0x10c5
 #define USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701	0x819a
 
+#define USB_VENDOR_ID_DELL				0x413c
+#define USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE	0x301a
+
 #define USB_VENDOR_ID_DELORME		0x1163
 #define USB_DEVICE_ID_DELORME_EARTHMATE	0x0100
 #define USB_DEVICE_ID_DELORME_EM_LT20	0x0200
@@ -772,6 +777,9 @@
 #define USB_VENDOR_ID_PETALYNX		0x18b1
 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE	0x0037
 
+#define USB_VENDOR_ID_PETZL		0x2122
+#define USB_DEVICE_ID_PETZL_HEADLAMP	0x1234
+
 #define USB_VENDOR_ID_PHILIPS		0x0471
 #define USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE 0x0617
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 2b8ff18d3713..f62a9d6601cc 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -61,6 +61,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_ALWAYS_VALID		(1 << 4)
 #define MT_QUIRK_VALID_IS_INRANGE	(1 << 5)
 #define MT_QUIRK_VALID_IS_CONFIDENCE	(1 << 6)
+#define MT_QUIRK_CONFIDENCE		(1 << 7)
 #define MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE	(1 << 8)
 #define MT_QUIRK_NO_AREA		(1 << 9)
 #define MT_QUIRK_IGNORE_DUPLICATES	(1 << 10)
@@ -78,6 +79,7 @@ struct mt_slot {
 	__s32 contactid;	/* the device ContactID assigned to this slot */
 	bool touch_state;	/* is the touch valid? */
 	bool inrange_state;	/* is the finger in proximity of the sensor? */
+	bool confidence_state;  /* is the touch made by a finger? */
 };
 
 struct mt_class {
@@ -396,6 +398,11 @@ static void mt_feature_mapping(struct hid_device *hdev,
 			td->is_buttonpad = true;
 
 		break;
+	case 0xff0000c5:
+		/* Retrieve the Win8 blob once to enable some devices */
+		if (usage->usage_index == 0)
+			mt_get_feature(hdev, field->report);
+		break;
 	}
 }
 
@@ -497,6 +504,9 @@ 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_CONFIDENCE:
+			if (cls->name == MT_CLS_WIN_8 &&
+				field->application == HID_DG_TOUCHPAD)
+				cls->quirks |= MT_QUIRK_CONFIDENCE;
 			mt_store_field(usage, td, hi);
 			return 1;
 		case HID_DG_TIPSWITCH:
@@ -609,6 +619,7 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
 		return;
 
 	if (td->curvalid || (td->mtclass.quirks & MT_QUIRK_ALWAYS_VALID)) {
+		int active;
 		int slotnum = mt_compute_slot(td, input);
 		struct mt_slot *s = &td->curdata;
 		struct input_mt *mt = input->mt;
@@ -623,10 +634,14 @@ static void mt_complete_slot(struct mt_device *td, struct input_dev *input)
 				return;
 		}
 
+		if (!(td->mtclass.quirks & MT_QUIRK_CONFIDENCE))
+			s->confidence_state = 1;
+		active = (s->touch_state || s->inrange_state) &&
+							s->confidence_state;
+
 		input_mt_slot(input, slotnum);
-		input_mt_report_slot_state(input, MT_TOOL_FINGER,
-			s->touch_state || s->inrange_state);
-		if (s->touch_state || s->inrange_state) {
+		input_mt_report_slot_state(input, MT_TOOL_FINGER, active);
+		if (active) {
 			/* this finger is in proximity of the sensor */
 			int wide = (s->w > s->h);
 			/* divided by two to match visual scale of touch */
@@ -691,6 +706,8 @@ static void mt_process_mt_event(struct hid_device *hid, struct hid_field *field,
 			td->curdata.touch_state = value;
 			break;
 		case HID_DG_CONFIDENCE:
+			if (quirks & MT_QUIRK_CONFIDENCE)
+				td->curdata.confidence_state = value;
 			if (quirks & MT_QUIRK_VALID_IS_CONFIDENCE)
 				td->curvalid = value;
 			break;
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 774cd2210566..21febbb0d84e 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -1418,8 +1418,10 @@ static int sixaxis_set_operational_usb(struct hid_device *hdev)
 	}
 
 	ret = hid_hw_output_report(hdev, buf, 1);
-	if (ret < 0)
-		hid_err(hdev, "can't set operational mode: step 3\n");
+	if (ret < 0) {
+		hid_info(hdev, "can't set operational mode: step 3, ignoring\n");
+		ret = 0;
+	}
 
 out:
 	kfree(buf);
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 10bd8e6e4c9c..d4d655a10df1 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -282,17 +282,21 @@ static int i2c_hid_set_or_send_report(struct i2c_client *client, u8 reportType,
 	u16 dataRegister = le16_to_cpu(ihid->hdesc.wDataRegister);
 	u16 outputRegister = le16_to_cpu(ihid->hdesc.wOutputRegister);
 	u16 maxOutputLength = le16_to_cpu(ihid->hdesc.wMaxOutputLength);
+	u16 size;
+	int args_len;
+	int index = 0;
+
+	i2c_hid_dbg(ihid, "%s\n", __func__);
 
-	/* hid_hw_* already checked that data_len < HID_MAX_BUFFER_SIZE */
-	u16 size =	2			/* size */ +
+	if (data_len > ihid->bufsize)
+		return -EINVAL;
+
+	size =		2			/* size */ +
 			(reportID ? 1 : 0)	/* reportID */ +
 			data_len		/* buf */;
-	int args_len =	(reportID >= 0x0F ? 1 : 0) /* optional third byte */ +
+	args_len =	(reportID >= 0x0F ? 1 : 0) /* optional third byte */ +
 			2			/* dataRegister */ +
 			size			/* args */;
-	int index = 0;
-
-	i2c_hid_dbg(ihid, "%s\n", __func__);
 
 	if (!use_data && maxOutputLength == 0)
 		return -ENOSYS;
@@ -360,6 +364,15 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret)
 		return ret;
 
+	/*
+	 * The HID over I2C specification states that if a DEVICE needs time
+	 * after the PWR_ON request, it should utilise CLOCK stretching.
+	 * However, it has been observered that the Windows driver provides a
+	 * 1ms sleep between the PWR_ON and RESET requests and that some devices
+	 * rely on this.
+	 */
+	usleep_range(1000, 5000);
+
 	i2c_hid_dbg(ihid, "resetting...\n");
 
 	ret = i2c_hid_command(client, &hid_reset_cmd, NULL, 0);
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index e094c572b86e..1a2032c2c1fb 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -51,10 +51,26 @@ struct uhid_device {
 	u32 report_id;
 	u32 report_type;
 	struct uhid_event report_buf;
+	struct work_struct worker;
 };
 
 static struct miscdevice uhid_misc;
 
+static void uhid_device_add_worker(struct work_struct *work)
+{
+	struct uhid_device *uhid = container_of(work, struct uhid_device, worker);
+	int ret;
+
+	ret = hid_add_device(uhid->hid);
+	if (ret) {
+		hid_err(uhid->hid, "Cannot register HID device: error %d\n", ret);
+
+		hid_destroy_device(uhid->hid);
+		uhid->hid = NULL;
+		uhid->running = false;
+	}
+}
+
 static void uhid_queue(struct uhid_device *uhid, struct uhid_event *ev)
 {
 	__u8 newhead;
@@ -498,18 +514,14 @@ static int uhid_dev_create2(struct uhid_device *uhid,
 	uhid->hid = hid;
 	uhid->running = true;
 
-	ret = hid_add_device(hid);
-	if (ret) {
-		hid_err(hid, "Cannot register HID device\n");
-		goto err_hid;
-	}
+	/* Adding of a HID device is done through a worker, to allow HID drivers
+	 * which use feature requests during .probe to work, without they would
+	 * be blocked on devlock, which is held by uhid_char_write.
+	 */
+	schedule_work(&uhid->worker);
 
 	return 0;
 
-err_hid:
-	hid_destroy_device(hid);
-	uhid->hid = NULL;
-	uhid->running = false;
 err_free:
 	kfree(uhid->rd_data);
 	uhid->rd_data = NULL;
@@ -550,6 +562,8 @@ static int uhid_dev_destroy(struct uhid_device *uhid)
 	uhid->running = false;
 	wake_up_interruptible(&uhid->report_wait);
 
+	cancel_work_sync(&uhid->worker);
+
 	hid_destroy_device(uhid->hid);
 	kfree(uhid->rd_data);
 
@@ -612,6 +626,7 @@ static int uhid_char_open(struct inode *inode, struct file *file)
 	init_waitqueue_head(&uhid->waitq);
 	init_waitqueue_head(&uhid->report_wait);
 	uhid->running = false;
+	INIT_WORK(&uhid->worker, uhid_device_add_worker);
 
 	file->private_data = uhid;
 	nonseekable_open(inode, file);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 5dd426fee8cc..0df32fe0e345 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -951,14 +951,6 @@ static int usbhid_output_report(struct hid_device *hid, __u8 *buf, size_t count)
 	return ret;
 }
 
-static void usbhid_restart_queues(struct usbhid_device *usbhid)
-{
-	if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl))
-		usbhid_restart_out_queue(usbhid);
-	if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl))
-		usbhid_restart_ctrl_queue(usbhid);
-}
-
 static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
@@ -1404,6 +1396,37 @@ static void hid_cease_io(struct usbhid_device *usbhid)
 	usb_kill_urb(usbhid->urbout);
 }
 
+static void hid_restart_io(struct hid_device *hid)
+{
+	struct usbhid_device *usbhid = hid->driver_data;
+	int clear_halt = test_bit(HID_CLEAR_HALT, &usbhid->iofl);
+	int reset_pending = test_bit(HID_RESET_PENDING, &usbhid->iofl);
+
+	spin_lock_irq(&usbhid->lock);
+	clear_bit(HID_SUSPENDED, &usbhid->iofl);
+	usbhid_mark_busy(usbhid);
+
+	if (clear_halt || reset_pending)
+		schedule_work(&usbhid->reset_work);
+	usbhid->retry_delay = 0;
+	spin_unlock_irq(&usbhid->lock);
+
+	if (reset_pending || !test_bit(HID_STARTED, &usbhid->iofl))
+		return;
+
+	if (!clear_halt) {
+		if (hid_start_in(hid) < 0)
+			hid_io_error(hid);
+	}
+
+	spin_lock_irq(&usbhid->lock);
+	if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl))
+		usbhid_restart_out_queue(usbhid);
+	if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl))
+		usbhid_restart_ctrl_queue(usbhid);
+	spin_unlock_irq(&usbhid->lock);
+}
+
 /* Treat USB reset pretty much the same as suspend/resume */
 static int hid_pre_reset(struct usb_interface *intf)
 {
@@ -1453,14 +1476,14 @@ static int hid_post_reset(struct usb_interface *intf)
 		return 1;
 	}
 
+	/* No need to do another reset or clear a halted endpoint */
 	spin_lock_irq(&usbhid->lock);
 	clear_bit(HID_RESET_PENDING, &usbhid->iofl);
+	clear_bit(HID_CLEAR_HALT, &usbhid->iofl);
 	spin_unlock_irq(&usbhid->lock);
 	hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0);
-	status = hid_start_in(hid);
-	if (status < 0)
-		hid_io_error(hid);
-	usbhid_restart_queues(usbhid);
+
+	hid_restart_io(hid);
 
 	return 0;
 }
@@ -1483,25 +1506,9 @@ void usbhid_put_power(struct hid_device *hid)
 #ifdef CONFIG_PM
 static int hid_resume_common(struct hid_device *hid, bool driver_suspended)
 {
-	struct usbhid_device *usbhid = hid->driver_data;
-	int status;
-
-	spin_lock_irq(&usbhid->lock);
-	clear_bit(HID_SUSPENDED, &usbhid->iofl);
-	usbhid_mark_busy(usbhid);
-
-	if (test_bit(HID_CLEAR_HALT, &usbhid->iofl) ||
-			test_bit(HID_RESET_PENDING, &usbhid->iofl))
-		schedule_work(&usbhid->reset_work);
-	usbhid->retry_delay = 0;
-
-	usbhid_restart_queues(usbhid);
-	spin_unlock_irq(&usbhid->lock);
-
-	status = hid_start_in(hid);
-	if (status < 0)
-		hid_io_error(hid);
+	int status = 0;
 
+	hid_restart_io(hid);
 	if (driver_suspended && hid->driver && hid->driver->resume)
 		status = hid->driver->resume(hid);
 	return status;
@@ -1570,12 +1577,8 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message)
 static int hid_resume(struct usb_interface *intf)
 {
 	struct hid_device *hid = usb_get_intfdata (intf);
-	struct usbhid_device *usbhid = hid->driver_data;
 	int status;
 
-	if (!test_bit(HID_STARTED, &usbhid->iofl))
-		return 0;
-
 	status = hid_resume_common(hid, true);
 	dev_dbg(&intf->dev, "resume status %d\n", status);
 	return 0;
@@ -1584,10 +1587,8 @@ static int hid_resume(struct usb_interface *intf)
 static int hid_reset_resume(struct usb_interface *intf)
 {
 	struct hid_device *hid = usb_get_intfdata(intf);
-	struct usbhid_device *usbhid = hid->driver_data;
 	int status;
 
-	clear_bit(HID_SUSPENDED, &usbhid->iofl);
 	status = hid_post_reset(intf);
 	if (status >= 0 && hid->driver && hid->driver->reset_resume) {
 		int ret = hid->driver->reset_resume(hid);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 7dd0953cd70f..ce1543d69acb 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -61,6 +61,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS692, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
@@ -70,6 +71,8 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 2f1ddca6f2e0..700145b15088 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -516,13 +516,13 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 					goto inval;
 			} else if (uref->usage_index >= field->report_count)
 				goto inval;
-
-			else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
-				 (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
-				  uref->usage_index + uref_multi->num_values > field->report_count))
-				goto inval;
 		}
 
+		if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+		    (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+		     uref->usage_index + uref_multi->num_values > field->report_count))
+			goto inval;
+
 		switch (cmd) {
 		case HIDIOCGUSAGE:
 			uref->value = field->value[uref->usage_index];
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 01a4f05c1642..b62c50d1b1e4 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -148,19 +148,21 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 		wacom->id[0] = STYLUS_DEVICE_ID;
 	}
 
-	pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
-	if (features->pressure_max > 255)
-		pressure = (pressure << 1) | ((data[4] >> 6) & 1);
-	pressure += (features->pressure_max + 1) / 2;
+	if (prox) {
+		pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
+		if (features->pressure_max > 255)
+			pressure = (pressure << 1) | ((data[4] >> 6) & 1);
+		pressure += (features->pressure_max + 1) / 2;
 
-	input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
-	input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
-	input_report_abs(input, ABS_PRESSURE, pressure);
+		input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
+		input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
+		input_report_abs(input, ABS_PRESSURE, pressure);
 
-	input_report_key(input, BTN_TOUCH, data[4] & 0x08);
-	input_report_key(input, BTN_STYLUS, data[4] & 0x10);
-	/* Only allow the stylus2 button to be reported for the pen tool. */
-	input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+		input_report_key(input, BTN_TOUCH, data[4] & 0x08);
+		input_report_key(input, BTN_STYLUS, data[4] & 0x10);
+		/* Only allow the stylus2 button to be reported for the pen tool. */
+		input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+	}
 
 	if (!prox)
 		wacom->id[0] = 0;
@@ -1438,37 +1440,38 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
 
-	if (wacom->pen_input)
+	if (wacom->pen_input) {
 		dev_dbg(wacom->pen_input->dev.parent,
 			"%s: received report #%d\n", __func__, data[0]);
-	else if (wacom->touch_input)
+
+		if (len == WACOM_PKGLEN_PENABLED ||
+		    data[0] == WACOM_REPORT_PENABLED)
+			return wacom_tpc_pen(wacom);
+	}
+	else if (wacom->touch_input) {
 		dev_dbg(wacom->touch_input->dev.parent,
 			"%s: received report #%d\n", __func__, data[0]);
 
-	switch (len) {
-	case WACOM_PKGLEN_TPC1FG:
-		return wacom_tpc_single_touch(wacom, len);
+		switch (len) {
+		case WACOM_PKGLEN_TPC1FG:
+			return wacom_tpc_single_touch(wacom, len);
 
-	case WACOM_PKGLEN_TPC2FG:
-		return wacom_tpc_mt_touch(wacom);
+		case WACOM_PKGLEN_TPC2FG:
+			return wacom_tpc_mt_touch(wacom);
 
-	case WACOM_PKGLEN_PENABLED:
-		return wacom_tpc_pen(wacom);
+		default:
+			switch (data[0]) {
+			case WACOM_REPORT_TPC1FG:
+			case WACOM_REPORT_TPCHID:
+			case WACOM_REPORT_TPCST:
+			case WACOM_REPORT_TPC1FGE:
+				return wacom_tpc_single_touch(wacom, len);
 
-	default:
-		switch (data[0]) {
-		case WACOM_REPORT_TPC1FG:
-		case WACOM_REPORT_TPCHID:
-		case WACOM_REPORT_TPCST:
-		case WACOM_REPORT_TPC1FGE:
-			return wacom_tpc_single_touch(wacom, len);
+			case WACOM_REPORT_TPCMT:
+			case WACOM_REPORT_TPCMT2:
+				return wacom_mt_touch(wacom);
 
-		case WACOM_REPORT_TPCMT:
-		case WACOM_REPORT_TPCMT2:
-			return wacom_mt_touch(wacom);
-
-		case WACOM_REPORT_PENABLED:
-			return wacom_tpc_pen(wacom);
+			}
 		}
 	}
 
@@ -2493,6 +2496,17 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 	}
 
 	/*
+	 * Hack for the Bamboo One:
+	 * the device presents a PAD/Touch interface as most Bamboos and even
+	 * sends ghosts PAD data on it. However, later, we must disable this
+	 * ghost interface, and we can not detect it unless we set it here
+	 * to WACOM_DEVICETYPE_PAD or WACOM_DEVICETYPE_TOUCH.
+	 */
+	if (features->type == BAMBOO_PEN &&
+	    features->pktlen == WACOM_PKGLEN_BBTOUCH3)
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+
+	/*
 	 * Raw Wacom-mode pen and touch events both come from interface
 	 * 0, whose HID descriptor has an application usage of 0xFF0D
 	 * (i.e., WACOM_VENDORDEFINED_PEN). We route pen packets back
@@ -3438,6 +3452,10 @@ static const struct wacom_features wacom_features_0x33E =
 	{ "Wacom Intuos PT M 2", 21600, 13500, 2047, 63,
 	  INTUOSHT2, WACOM_INTUOS_RES, WACOM_INTUOS_RES, .touch_max = 16,
 	  .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE };
+static const struct wacom_features wacom_features_0x343 =
+	{ "Wacom DTK1651", 34616, 19559, 1023, 0,
+	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4,
+	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 
 static const struct wacom_features wacom_features_HID_ANY_ID =
 	{ "Wacom HID", .type = HID_GENERIC };
@@ -3603,6 +3621,7 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x33C) },
 	{ USB_DEVICE_WACOM(0x33D) },
 	{ USB_DEVICE_WACOM(0x33E) },
+	{ USB_DEVICE_WACOM(0x343) },
 	{ USB_DEVICE_WACOM(0x4001) },
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 9098f13f2f44..d037454fe7b8 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/hyperv.h>
 #include <linux/uio.h>
+#include <linux/interrupt.h>
 
 #include "hyperv_vmbus.h"
 
@@ -72,7 +73,6 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	void *in, *out;
 	unsigned long flags;
 	int ret, err = 0;
-	unsigned long t;
 	struct page *page;
 
 	spin_lock_irqsave(&newchannel->lock, flags);
@@ -182,11 +182,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 		goto error1;
 	}
 
-	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
-	if (t == 0) {
-		err = -ETIMEDOUT;
-		goto error1;
-	}
+	wait_for_completion(&open_info->waitevent);
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&open_info->msglistentry);
@@ -374,7 +370,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
 	struct vmbus_channel_msginfo *msginfo = NULL;
-	struct vmbus_channel_msginfo *submsginfo;
+	struct vmbus_channel_msginfo *submsginfo, *tmp;
 	u32 msgcount;
 	struct list_head *curr;
 	u32 next_gpadl_handle;
@@ -436,6 +432,13 @@ cleanup:
 	list_del(&msginfo->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+	if (msgcount > 1) {
+		list_for_each_entry_safe(submsginfo, tmp, &msginfo->submsglist,
+			 msglistentry) {
+			kfree(submsginfo);
+		}
+	}
+
 	kfree(msginfo);
 	return ret;
 }
@@ -496,8 +499,21 @@ static void reset_channel_cb(void *arg)
 static int vmbus_close_internal(struct vmbus_channel *channel)
 {
 	struct vmbus_channel_close_channel *msg;
+	struct tasklet_struct *tasklet;
 	int ret;
 
+	/*
+	 * process_chn_event(), running in the tasklet, can race
+	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
+	 * the former is accessing channel->inbound.ring_buffer, the latter
+	 * could be freeing the ring_buffer pages.
+	 *
+	 * To resolve the race, we can serialize them by disabling the
+	 * tasklet when the latter is running here.
+	 */
+	tasklet = hv_context.event_dpc[channel->target_cpu];
+	tasklet_disable(tasklet);
+
 	channel->state = CHANNEL_OPEN_STATE;
 	channel->sc_creation_callback = NULL;
 	/* Stop callback and cancel the timer asap */
@@ -525,7 +541,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 		 * If we failed to post the close msg,
 		 * it is perhaps better to leak memory.
 		 */
-		return ret;
+		goto out;
 	}
 
 	/* Tear down the gpadl for the channel's ring buffer */
@@ -538,7 +554,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 			 * If we failed to teardown gpadl,
 			 * it is perhaps better to leak memory.
 			 */
-			return ret;
+			goto out;
 		}
 	}
 
@@ -549,12 +565,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	free_pages((unsigned long)channel->ringbuffer_pages,
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
-	/*
-	 * If the channel has been rescinded; process device removal.
-	 */
-	if (channel->rescind)
-		hv_process_channel_removal(channel,
-					   channel->offermsg.child_relid);
+out:
+	tasklet_enable(tasklet);
+
 	return ret;
 }
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 652afd11a9ef..37238dffd947 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include <linux/hyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -191,6 +192,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 	if (channel == NULL)
 		return;
 
+	BUG_ON(!channel->rescind);
+
 	if (channel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(channel->target_cpu,
@@ -230,9 +233,7 @@ void vmbus_free_channels(void)
 
 	list_for_each_entry_safe(channel, tmp, &vmbus_connection.chn_list,
 		listentry) {
-		/* if we don't set rescind to true, vmbus_close_internal()
-		 * won't invoke hv_process_channel_removal().
-		 */
+		/* hv_process_channel_removal() needs this */
 		channel->rescind = true;
 
 		vmbus_device_unregister(channel->device_obj);
@@ -459,6 +460,17 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 		    cpumask_of_node(primary->numa_node));
 
 	cur_cpu = -1;
+
+	/*
+	 * Normally Hyper-V host doesn't create more subchannels than there
+	 * are VCPUs on the node but it is possible when not all present VCPUs
+	 * on the node are initialized by guest. Clear the alloced_cpus_in_node
+	 * to start over.
+	 */
+	if (cpumask_equal(&primary->alloced_cpus_in_node,
+			  cpumask_of_node(primary->numa_node)))
+		cpumask_clear(&primary->alloced_cpus_in_node);
+
 	while (true) {
 		cur_cpu = cpumask_next(cur_cpu, &available_mask);
 		if (cur_cpu >= nr_cpu_ids) {
@@ -488,6 +500,40 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 	channel->target_vp = hv_context.vp_index[cur_cpu];
 }
 
+static void vmbus_wait_for_unload(void)
+{
+	int cpu = smp_processor_id();
+	void *page_addr = hv_context.synic_message_page[cpu];
+	struct hv_message *msg = (struct hv_message *)page_addr +
+				  VMBUS_MESSAGE_SINT;
+	struct vmbus_channel_message_header *hdr;
+	bool unloaded = false;
+
+	while (1) {
+		if (msg->header.message_type == HVMSG_NONE) {
+			mdelay(10);
+			continue;
+		}
+
+		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+			unloaded = true;
+
+		msg->header.message_type = HVMSG_NONE;
+		/*
+		 * header.message_type needs to be written before we do
+		 * wrmsrl() below.
+		 */
+		mb();
+
+		if (msg->header.message_flags.msg_pending)
+			wrmsrl(HV_X64_MSR_EOM, 0);
+
+		if (unloaded)
+			break;
+	}
+}
+
 /*
  * vmbus_unload_response - Handler for the unload response.
  */
@@ -513,7 +559,14 @@ void vmbus_initiate_unload(void)
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
 
-	wait_for_completion(&vmbus_connection.unload_event);
+	/*
+	 * vmbus_initiate_unload() is also called on crash and the crash can be
+	 * happening in an interrupt context, where scheduling is impossible.
+	 */
+	if (!in_interrupt())
+		wait_for_completion(&vmbus_connection.unload_event);
+	else
+		vmbus_wait_for_unload();
 }
 
 /*
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 4fc2e8836e60..2bbc53025549 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -429,7 +429,7 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	union hv_connection_id conn_id;
 	int ret = 0;
 	int retries = 0;
-	u32 msec = 1;
+	u32 usec = 1;
 
 	conn_id.asu32 = 0;
 	conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID;
@@ -462,9 +462,9 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		}
 
 		retries++;
-		msleep(msec);
-		if (msec < 2048)
-			msec *= 2;
+		udelay(usec);
+		if (usec < 2048)
+			usec *= 2;
 	}
 	return ret;
 }
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 6341be8739ae..8ce1f2e22912 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -219,7 +219,7 @@ int hv_init(void)
 	/* See if the hypercall page is already set */
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_EXEC);
+	virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
 
 	if (!virtaddr)
 		goto cleanup;
@@ -274,7 +274,7 @@ cleanup:
  *
  * This routine is called normally during driver unloading or exiting.
  */
-void hv_cleanup(void)
+void hv_cleanup(bool crash)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 
@@ -284,7 +284,8 @@ void hv_cleanup(void)
 	if (hv_context.hypercall_page) {
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		vfree(hv_context.hypercall_page);
+		if (!crash)
+			vfree(hv_context.hypercall_page);
 		hv_context.hypercall_page = NULL;
 	}
 
@@ -293,13 +294,21 @@ void hv_cleanup(void)
 	 * Cleanup the TSC page based CS.
 	 */
 	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		clocksource_change_rating(&hyperv_cs_tsc, 10);
-		clocksource_unregister(&hyperv_cs_tsc);
+		/*
+		 * Crash can happen in an interrupt context and unregistering
+		 * a clocksource is impossible and redundant in this case.
+		 */
+		if (!oops_in_progress) {
+			clocksource_change_rating(&hyperv_cs_tsc, 10);
+			clocksource_unregister(&hyperv_cs_tsc);
+		}
 
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-		vfree(hv_context.tsc_page);
-		hv_context.tsc_page = NULL;
+		if (!crash) {
+			vfree(hv_context.tsc_page);
+			hv_context.tsc_page = NULL;
+		}
 	}
 #endif
 }
@@ -416,7 +425,7 @@ int hv_synic_alloc(void)
 		goto err;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		hv_context.event_dpc[cpu] = kmalloc(size, GFP_ATOMIC);
 		if (hv_context.event_dpc[cpu] == NULL) {
 			pr_err("Unable to allocate event dpc\n");
@@ -455,6 +464,8 @@ int hv_synic_alloc(void)
 			pr_err("Unable to allocate post msg page\n");
 			goto err;
 		}
+
+		INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
 	}
 
 	return 0;
@@ -479,7 +490,7 @@ void hv_synic_free(void)
 	int cpu;
 
 	kfree(hv_context.hv_numa_map);
-	for_each_online_cpu(cpu)
+	for_each_present_cpu(cpu)
 		hv_synic_free_cpu(cpu);
 }
 
@@ -549,8 +560,6 @@ void hv_synic_init(void *arg)
 	rdmsrl(HV_X64_MSR_VP_INDEX, vp_index);
 	hv_context.vp_index[cpu] = (u32)vp_index;
 
-	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
-
 	/*
 	 * Register the per-cpu clockevent source.
 	 */
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b853b4b083bd..354da7f207b7 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -430,16 +430,27 @@ struct dm_info_msg {
  * currently hot added. We hot add in multiples of 128M
  * chunks; it is possible that we may not be able to bring
  * online all the pages in the region. The range
- * covered_end_pfn defines the pages that can
+ * covered_start_pfn:covered_end_pfn defines the pages that can
  * be brough online.
  */
 
 struct hv_hotadd_state {
 	struct list_head list;
 	unsigned long start_pfn;
+	unsigned long covered_start_pfn;
 	unsigned long covered_end_pfn;
 	unsigned long ha_end_pfn;
 	unsigned long end_pfn;
+	/*
+	 * A list of gaps.
+	 */
+	struct list_head gap_list;
+};
+
+struct hv_hotadd_gap {
+	struct list_head list;
+	unsigned long start_pfn;
+	unsigned long end_pfn;
 };
 
 struct balloon_state {
@@ -595,18 +606,46 @@ static struct notifier_block hv_memory_nb = {
 	.priority = 0
 };
 
+/* Check if the particular page is backed and can be onlined and online it. */
+static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg)
+{
+	unsigned long cur_start_pgp;
+	unsigned long cur_end_pgp;
+	struct hv_hotadd_gap *gap;
+
+	cur_start_pgp = (unsigned long)pfn_to_page(has->covered_start_pfn);
+	cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn);
+
+	/* The page is not backed. */
+	if (((unsigned long)pg < cur_start_pgp) ||
+	    ((unsigned long)pg >= cur_end_pgp))
+		return;
+
+	/* Check for gaps. */
+	list_for_each_entry(gap, &has->gap_list, list) {
+		cur_start_pgp = (unsigned long)
+			pfn_to_page(gap->start_pfn);
+		cur_end_pgp = (unsigned long)
+			pfn_to_page(gap->end_pfn);
+		if (((unsigned long)pg >= cur_start_pgp) &&
+		    ((unsigned long)pg < cur_end_pgp)) {
+			return;
+		}
+	}
 
-static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
+	/* This frame is currently backed; online the page. */
+	__online_page_set_limits(pg);
+	__online_page_increment_counters(pg);
+	__online_page_free(pg);
+}
+
+static void hv_bring_pgs_online(struct hv_hotadd_state *has,
+				unsigned long start_pfn, unsigned long size)
 {
 	int i;
 
-	for (i = 0; i < size; i++) {
-		struct page *pg;
-		pg = pfn_to_page(start_pfn + i);
-		__online_page_set_limits(pg);
-		__online_page_increment_counters(pg);
-		__online_page_free(pg);
-	}
+	for (i = 0; i < size; i++)
+		hv_page_online_one(has, pfn_to_page(start_pfn + i));
 }
 
 static void hv_mem_hot_add(unsigned long start, unsigned long size,
@@ -682,26 +721,25 @@ static void hv_online_page(struct page *pg)
 
 	list_for_each(cur, &dm_device.ha_region_list) {
 		has = list_entry(cur, struct hv_hotadd_state, list);
-		cur_start_pgp = (unsigned long)pfn_to_page(has->start_pfn);
-		cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn);
+		cur_start_pgp = (unsigned long)
+			pfn_to_page(has->start_pfn);
+		cur_end_pgp = (unsigned long)pfn_to_page(has->end_pfn);
 
-		if (((unsigned long)pg >= cur_start_pgp) &&
-			((unsigned long)pg < cur_end_pgp)) {
-			/*
-			 * This frame is currently backed; online the
-			 * page.
-			 */
-			__online_page_set_limits(pg);
-			__online_page_increment_counters(pg);
-			__online_page_free(pg);
-		}
+		/* The page belongs to a different HAS. */
+		if (((unsigned long)pg < cur_start_pgp) ||
+		    ((unsigned long)pg >= cur_end_pgp))
+			continue;
+
+		hv_page_online_one(has, pg);
+		break;
 	}
 }
 
-static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
+static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 {
 	struct list_head *cur;
 	struct hv_hotadd_state *has;
+	struct hv_hotadd_gap *gap;
 	unsigned long residual, new_inc;
 
 	if (list_empty(&dm_device.ha_region_list))
@@ -714,8 +752,26 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
+
+		/*
+		 * If the current start pfn is not where the covered_end
+		 * is, create a gap and update covered_end_pfn.
+		 */
+		if (has->covered_end_pfn != start_pfn) {
+			gap = kzalloc(sizeof(struct hv_hotadd_gap), GFP_ATOMIC);
+			if (!gap)
+				return -ENOMEM;
+
+			INIT_LIST_HEAD(&gap->list);
+			gap->start_pfn = has->covered_end_pfn;
+			gap->end_pfn = start_pfn;
+			list_add_tail(&gap->list, &has->gap_list);
+
+			has->covered_end_pfn = start_pfn;
+		}
+
 		/*
 		 * If the current hot add-request extends beyond
 		 * our current limit; extend it.
@@ -732,19 +788,10 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 			has->end_pfn += new_inc;
 		}
 
-		/*
-		 * If the current start pfn is not where the covered_end
-		 * is, update it.
-		 */
-
-		if (has->covered_end_pfn != start_pfn)
-			has->covered_end_pfn = start_pfn;
-
-		return true;
-
+		return 1;
 	}
 
-	return false;
+	return 0;
 }
 
 static unsigned long handle_pg_range(unsigned long pg_start,
@@ -768,7 +815,7 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
 
 		old_covered_state = has->covered_end_pfn;
@@ -783,6 +830,8 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 			if (pgs_ol > pfn_cnt)
 				pgs_ol = pfn_cnt;
 
+			has->covered_end_pfn +=  pgs_ol;
+			pfn_cnt -= pgs_ol;
 			/*
 			 * Check if the corresponding memory block is already
 			 * online by checking its last previously backed page.
@@ -791,10 +840,8 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 			 */
 			if (start_pfn > has->start_pfn &&
 			    !PageReserved(pfn_to_page(start_pfn - 1)))
-				hv_bring_pgs_online(start_pfn, pgs_ol);
+				hv_bring_pgs_online(has, start_pfn, pgs_ol);
 
-			has->covered_end_pfn +=  pgs_ol;
-			pfn_cnt -= pgs_ol;
 		}
 
 		if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) {
@@ -832,13 +879,19 @@ static unsigned long process_hot_add(unsigned long pg_start,
 					unsigned long rg_size)
 {
 	struct hv_hotadd_state *ha_region = NULL;
+	int covered;
 
 	if (pfn_cnt == 0)
 		return 0;
 
-	if (!dm_device.host_specified_ha_region)
-		if (pfn_covered(pg_start, pfn_cnt))
+	if (!dm_device.host_specified_ha_region) {
+		covered = pfn_covered(pg_start, pfn_cnt);
+		if (covered < 0)
+			return 0;
+
+		if (covered)
 			goto do_pg_range;
+	}
 
 	/*
 	 * If the host has specified a hot-add range; deal with it first.
@@ -850,10 +903,12 @@ static unsigned long process_hot_add(unsigned long pg_start,
 			return 0;
 
 		INIT_LIST_HEAD(&ha_region->list);
+		INIT_LIST_HEAD(&ha_region->gap_list);
 
 		list_add_tail(&ha_region->list, &dm_device.ha_region_list);
 		ha_region->start_pfn = rg_start;
 		ha_region->ha_end_pfn = rg_start;
+		ha_region->covered_start_pfn = pg_start;
 		ha_region->covered_end_pfn = pg_start;
 		ha_region->end_pfn = rg_start + rg_size;
 	}
@@ -1581,6 +1636,7 @@ static int balloon_remove(struct hv_device *dev)
 	struct hv_dynmem_device *dm = hv_get_drvdata(dev);
 	struct list_head *cur, *tmp;
 	struct hv_hotadd_state *has;
+	struct hv_hotadd_gap *gap, *tmp_gap;
 
 	if (dm->num_pages_ballooned != 0)
 		pr_warn("Ballooned pages: %d\n", dm->num_pages_ballooned);
@@ -1597,6 +1653,10 @@ static int balloon_remove(struct hv_device *dev)
 #endif
 	list_for_each_safe(cur, tmp, &dm->ha_region_list) {
 		has = list_entry(cur, struct hv_hotadd_state, list);
+		list_for_each_entry_safe(gap, tmp_gap, &has->gap_list, list) {
+			list_del(&gap->list);
+			kfree(gap);
+		}
 		list_del(&has->list);
 		kfree(has);
 	}
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index db4b887b889d..1fb02dcbc500 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -51,7 +51,6 @@ static struct {
 	struct hv_fcopy_hdr  *fcopy_msg; /* current message */
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
-	void *fcopy_context; /* for the channel callback */
 } fcopy_transaction;
 
 static void fcopy_respond_to_host(int error);
@@ -62,11 +61,19 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
 static const char fcopy_devname[] = "vmbus/hv_fcopy";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 /*
  * This state maintains the version number registered by the daemon.
  */
 static int dm_reg_value;
 
+static void fcopy_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	fcopy_transaction.state = HVUTIL_READY;
+	hv_fcopy_onchannelcallback(channel);
+}
+
 static void fcopy_timeout_func(struct work_struct *dummy)
 {
 	/*
@@ -74,13 +81,7 @@ static void fcopy_timeout_func(struct work_struct *dummy)
 	 * process the pending transaction.
 	 */
 	fcopy_respond_to_host(HV_E_FAIL);
-
-	/* Transaction is finished, reset the state. */
-	if (fcopy_transaction.state > HVUTIL_READY)
-		fcopy_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(fcopy_transaction.fcopy_context,
-			hv_fcopy_onchannelcallback);
+	hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
 }
 
 static int fcopy_handle_handshake(u32 version)
@@ -108,9 +109,7 @@ static int fcopy_handle_handshake(u32 version)
 		return -EINVAL;
 	}
 	pr_debug("FCP: userspace daemon ver. %d registered\n", version);
-	fcopy_transaction.state = HVUTIL_READY;
-	hv_poll_channel(fcopy_transaction.fcopy_context,
-			hv_fcopy_onchannelcallback);
+	hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
 	return 0;
 }
 
@@ -227,15 +226,8 @@ void hv_fcopy_onchannelcallback(void *context)
 	int util_fw_version;
 	int fcopy_srv_version;
 
-	if (fcopy_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		fcopy_transaction.fcopy_context = context;
+	if (fcopy_transaction.state > HVUTIL_READY)
 		return;
-	}
-	fcopy_transaction.fcopy_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
 			 &requestid);
@@ -275,7 +267,8 @@ void hv_fcopy_onchannelcallback(void *context)
 		 * Send the information to the user-level daemon.
 		 */
 		schedule_work(&fcopy_send_work);
-		schedule_delayed_work(&fcopy_timeout_work, 5*HZ);
+		schedule_delayed_work(&fcopy_timeout_work,
+				      HV_UTIL_TIMEOUT * HZ);
 		return;
 	}
 	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
@@ -304,9 +297,8 @@ static int fcopy_on_msg(void *msg, int len)
 	if (cancel_delayed_work_sync(&fcopy_timeout_work)) {
 		fcopy_transaction.state = HVUTIL_USERSPACE_RECV;
 		fcopy_respond_to_host(*val);
-		fcopy_transaction.state = HVUTIL_READY;
-		hv_poll_channel(fcopy_transaction.fcopy_context,
-				hv_fcopy_onchannelcallback);
+		hv_poll_channel(fcopy_transaction.recv_channel,
+				fcopy_poll_wrapper);
 	}
 
 	return 0;
@@ -321,12 +313,14 @@ static void fcopy_on_reset(void)
 
 	if (cancel_delayed_work_sync(&fcopy_timeout_work))
 		fcopy_respond_to_host(HV_E_FAIL);
+	complete(&release_event);
 }
 
 int hv_fcopy_init(struct hv_util_service *srv)
 {
 	recv_buffer = srv->recv_buffer;
 
+	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -348,4 +342,5 @@ void hv_fcopy_deinit(void)
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&fcopy_timeout_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 74c38a9f34a6..ce4d3a935491 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -66,7 +66,6 @@ static struct {
 	struct hv_kvp_msg  *kvp_msg; /* current message */
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
-	void *kvp_context; /* for the channel callback */
 } kvp_transaction;
 
 /*
@@ -87,6 +86,7 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
 static const char kvp_devname[] = "vmbus/hv_kvp";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 /*
  * Register the kernel component with the user-level daemon.
  * As part of this registration, pass the LIC version number.
@@ -94,6 +94,13 @@ static struct hvutil_transport *hvt;
  */
 #define HV_DRV_VERSION           "3.1"
 
+static void kvp_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	kvp_transaction.state = HVUTIL_READY;
+	hv_kvp_onchannelcallback(channel);
+}
+
 static void
 kvp_register(int reg_value)
 {
@@ -121,12 +128,7 @@ static void kvp_timeout_func(struct work_struct *dummy)
 	 */
 	kvp_respond_to_host(NULL, HV_E_FAIL);
 
-	/* Transaction is finished, reset the state. */
-	if (kvp_transaction.state > HVUTIL_READY)
-		kvp_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(kvp_transaction.kvp_context,
-			hv_kvp_onchannelcallback);
+	hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 }
 
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
@@ -218,9 +220,7 @@ static int kvp_on_msg(void *msg, int len)
 	 */
 	if (cancel_delayed_work_sync(&kvp_timeout_work)) {
 		kvp_respond_to_host(message, error);
-		kvp_transaction.state = HVUTIL_READY;
-		hv_poll_channel(kvp_transaction.kvp_context,
-				hv_kvp_onchannelcallback);
+		hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 	}
 
 	return 0;
@@ -596,15 +596,8 @@ void hv_kvp_onchannelcallback(void *context)
 	int util_fw_version;
 	int kvp_srv_version;
 
-	if (kvp_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		kvp_transaction.kvp_context = context;
+	if (kvp_transaction.state > HVUTIL_READY)
 		return;
-	}
-	kvp_transaction.kvp_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
 			 &requestid);
@@ -668,7 +661,8 @@ void hv_kvp_onchannelcallback(void *context)
 			 * user-mode not responding.
 			 */
 			schedule_work(&kvp_sendkey_work);
-			schedule_delayed_work(&kvp_timeout_work, 5*HZ);
+			schedule_delayed_work(&kvp_timeout_work,
+					      HV_UTIL_TIMEOUT * HZ);
 
 			return;
 
@@ -689,6 +683,7 @@ static void kvp_on_reset(void)
 	if (cancel_delayed_work_sync(&kvp_timeout_work))
 		kvp_respond_to_host(NULL, HV_E_FAIL);
 	kvp_transaction.state = HVUTIL_DEVICE_INIT;
+	complete(&release_event);
 }
 
 int
@@ -696,6 +691,7 @@ hv_kvp_init(struct hv_util_service *srv)
 {
 	recv_buffer = srv->recv_buffer;
 
+	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -718,4 +714,5 @@ void hv_kvp_deinit(void)
 	cancel_delayed_work_sync(&kvp_timeout_work);
 	cancel_work_sync(&kvp_sendkey_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 815405f2e777..faad79ae318a 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -53,7 +53,6 @@ static struct {
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
 	struct hv_vss_msg  *msg; /* current message */
-	void *vss_context; /* for the channel callback */
 } vss_transaction;
 
 
@@ -67,6 +66,7 @@ static int dm_reg_value;
 static const char vss_devname[] = "vmbus/hv_vss";
 static __u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 
 static void vss_send_op(struct work_struct *dummy);
 static void vss_timeout_func(struct work_struct *dummy);
@@ -74,6 +74,13 @@ static void vss_timeout_func(struct work_struct *dummy);
 static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
 static DECLARE_WORK(vss_send_op_work, vss_send_op);
 
+static void vss_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	vss_transaction.state = HVUTIL_READY;
+	hv_vss_onchannelcallback(channel);
+}
+
 /*
  * Callback when data is received from user mode.
  */
@@ -86,12 +93,7 @@ static void vss_timeout_func(struct work_struct *dummy)
 	pr_warn("VSS: timeout waiting for daemon to reply\n");
 	vss_respond_to_host(HV_E_FAIL);
 
-	/* Transaction is finished, reset the state. */
-	if (vss_transaction.state > HVUTIL_READY)
-		vss_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(vss_transaction.vss_context,
-			hv_vss_onchannelcallback);
+	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
 }
 
 static int vss_handle_handshake(struct hv_vss_msg *vss_msg)
@@ -138,9 +140,8 @@ static int vss_on_msg(void *msg, int len)
 		if (cancel_delayed_work_sync(&vss_timeout_work)) {
 			vss_respond_to_host(vss_msg->error);
 			/* Transaction is finished, reset the state. */
-			vss_transaction.state = HVUTIL_READY;
-			hv_poll_channel(vss_transaction.vss_context,
-					hv_vss_onchannelcallback);
+			hv_poll_channel(vss_transaction.recv_channel,
+					vss_poll_wrapper);
 		}
 	} else {
 		/* This is a spurious call! */
@@ -238,15 +239,8 @@ void hv_vss_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct icmsg_negotiate *negop = NULL;
 
-	if (vss_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		vss_transaction.vss_context = context;
+	if (vss_transaction.state > HVUTIL_READY)
 		return;
-	}
-	vss_transaction.vss_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
 			 &requestid);
@@ -333,11 +327,18 @@ static void vss_on_reset(void)
 	if (cancel_delayed_work_sync(&vss_timeout_work))
 		vss_respond_to_host(HV_E_FAIL);
 	vss_transaction.state = HVUTIL_DEVICE_INIT;
+	complete(&release_event);
 }
 
 int
 hv_vss_init(struct hv_util_service *srv)
 {
+	init_completion(&release_event);
+	if (vmbus_proto_version < VERSION_WIN8_1) {
+		pr_warn("Integration service 'Backup (volume snapshot)'"
+			" not supported on this host version.\n");
+		return -ENOTSUPP;
+	}
 	recv_buffer = srv->recv_buffer;
 
 	/*
@@ -362,4 +363,5 @@ void hv_vss_deinit(void)
 	cancel_delayed_work_sync(&vss_timeout_work);
 	cancel_work_sync(&vss_send_op_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 7994ec2e4151..41f5896224bd 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -283,10 +283,14 @@ static void heartbeat_onchannelcallback(void *context)
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
 	struct icmsg_negotiate *negop = NULL;
 
-	vmbus_recvpacket(channel, hbeat_txf_buf,
-			 PAGE_SIZE, &recvlen, &requestid);
+	while (1) {
+
+		vmbus_recvpacket(channel, hbeat_txf_buf,
+				 PAGE_SIZE, &recvlen, &requestid);
+
+		if (!recvlen)
+			break;
 
-	if (recvlen > 0) {
 		icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];
 
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index 6a9d80a5332d..1505ee6e6605 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -204,9 +204,12 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len)
 		goto out_unlock;
 	}
 	hvt->outmsg = kzalloc(len, GFP_KERNEL);
-	memcpy(hvt->outmsg, msg, len);
-	hvt->outmsg_len = len;
-	wake_up_interruptible(&hvt->outmsg_q);
+	if (hvt->outmsg) {
+		memcpy(hvt->outmsg, msg, len);
+		hvt->outmsg_len = len;
+		wake_up_interruptible(&hvt->outmsg_q);
+	} else
+		ret = -ENOMEM;
 out_unlock:
 	mutex_unlock(&hvt->outmsg_lock);
 	return ret;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 3782636562a1..75e383e6d03d 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -31,6 +31,11 @@
 #include <linux/hyperv.h>
 
 /*
+ * Timeout for services such as KVP and fcopy.
+ */
+#define HV_UTIL_TIMEOUT 30
+
+/*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
  * is set by CPUID(HVCPUID_VERSION_FEATURES).
  */
@@ -576,7 +581,7 @@ struct hv_ring_buffer_debug_info {
 
 extern int hv_init(void);
 
-extern void hv_cleanup(void);
+extern void hv_cleanup(bool crash);
 
 extern int hv_post_message(union hv_connection_id connection_id,
 			 enum hv_message_type message_type,
@@ -759,11 +764,7 @@ static inline void hv_poll_channel(struct vmbus_channel *channel,
 	if (!channel)
 		return;
 
-	if (channel->target_cpu != smp_processor_id())
-		smp_call_function_single(channel->target_cpu,
-					 cb, channel, true);
-	else
-		cb(channel);
+	smp_call_function_single(channel->target_cpu, cb, channel, true);
 }
 
 enum hvutil_device_state {
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index f19b6f7a467a..802dcb409030 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -41,6 +41,7 @@
 #include <linux/ptrace.h>
 #include <linux/screen_info.h>
 #include <linux/kdebug.h>
+#include <linux/random.h>
 #include "hyperv_vmbus.h"
 
 static struct acpi_device  *hv_acpi_dev;
@@ -104,6 +105,7 @@ static struct notifier_block hyperv_panic_block = {
 };
 
 struct resource *hyperv_mmio;
+DEFINE_SEMAPHORE(hyperv_mmio_lock);
 
 static int vmbus_exists(void)
 {
@@ -602,23 +604,11 @@ static int vmbus_remove(struct device *child_device)
 {
 	struct hv_driver *drv;
 	struct hv_device *dev = device_to_hv_device(child_device);
-	u32 relid = dev->channel->offermsg.child_relid;
 
 	if (child_device->driver) {
 		drv = drv_to_hv_drv(child_device->driver);
 		if (drv->remove)
 			drv->remove(dev);
-		else {
-			hv_process_channel_removal(dev->channel, relid);
-			pr_err("remove not set for driver %s\n",
-				dev_name(child_device));
-		}
-	} else {
-		/*
-		 * We don't have a driver for this device; deal with the
-		 * rescind message by removing the channel.
-		 */
-		hv_process_channel_removal(dev->channel, relid);
 	}
 
 	return 0;
@@ -653,7 +643,10 @@ static void vmbus_shutdown(struct device *child_device)
 static void vmbus_device_release(struct device *device)
 {
 	struct hv_device *hv_dev = device_to_hv_device(device);
+	struct vmbus_channel *channel = hv_dev->channel;
 
+	hv_process_channel_removal(channel,
+				   channel->offermsg.child_relid);
 	kfree(hv_dev);
 
 }
@@ -826,6 +819,8 @@ static void vmbus_isr(void)
 		else
 			tasklet_schedule(&msg_dpc);
 	}
+
+	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
 }
 
 
@@ -867,7 +862,7 @@ static int vmbus_bus_init(int irq)
 	on_each_cpu(hv_synic_init, NULL, 1);
 	ret = vmbus_connect();
 	if (ret)
-		goto err_alloc;
+		goto err_connect;
 
 	if (vmbus_proto_version > VERSION_WIN7)
 		cpu_hotplug_disable();
@@ -885,6 +880,8 @@ static int vmbus_bus_init(int irq)
 
 	return 0;
 
+err_connect:
+	on_each_cpu(hv_synic_cleanup, NULL, 1);
 err_alloc:
 	hv_synic_free();
 	hv_remove_vmbus_irq();
@@ -892,7 +889,7 @@ err_alloc:
 	bus_unregister(&hv_bus);
 
 err_cleanup:
-	hv_cleanup();
+	hv_cleanup(false);
 
 	return ret;
 }
@@ -1144,7 +1141,10 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 	resource_size_t range_min, range_max, start, local_min, local_max;
 	const char *dev_n = dev_name(&device_obj->device);
 	u32 fb_end = screen_info.lfb_base + (screen_info.lfb_size << 1);
-	int i;
+	int i, retval;
+
+	retval = -ENXIO;
+	down(&hyperv_mmio_lock);
 
 	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
 		if ((iter->start >= max) || (iter->end <= min))
@@ -1181,13 +1181,17 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			for (; start + size - 1 <= local_max; start += align) {
 				*new = request_mem_region_exclusive(start, size,
 								    dev_n);
-				if (*new)
-					return 0;
+				if (*new) {
+					retval = 0;
+					goto exit;
+				}
 			}
 		}
 	}
 
-	return -ENXIO;
+exit:
+	up(&hyperv_mmio_lock);
+	return retval;
 }
 EXPORT_SYMBOL_GPL(vmbus_allocate_mmio);
 
@@ -1250,7 +1254,7 @@ static void hv_kexec_handler(void)
 	vmbus_initiate_unload();
 	for_each_online_cpu(cpu)
 		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
-	hv_cleanup();
+	hv_cleanup(false);
 };
 
 static void hv_crash_handler(struct pt_regs *regs)
@@ -1262,7 +1266,7 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * for kdump.
 	 */
 	hv_synic_cleanup(NULL);
-	hv_cleanup();
+	hv_cleanup(true);
 };
 
 static int __init hv_acpi_init(void)
@@ -1326,7 +1330,7 @@ static void __exit vmbus_exit(void)
 						 &hyperv_panic_block);
 	}
 	bus_unregister(&hv_bus);
-	hv_cleanup();
+	hv_cleanup(false);
 	for_each_online_cpu(cpu) {
 		tasklet_kill(hv_context.event_dpc[cpu]);
 		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index 6c99ee7bafa3..ee396ff167d9 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -120,6 +120,7 @@ static int ads7828_probe(struct i2c_client *client,
 	unsigned int vref_mv = ADS7828_INT_VREF_MV;
 	bool diff_input = false;
 	bool ext_vref = false;
+	unsigned int regval;
 
 	data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
 	if (!data)
@@ -154,6 +155,15 @@ static int ads7828_probe(struct i2c_client *client,
 	if (!diff_input)
 		data->cmd_byte |= ADS7828_CMD_SD_SE;
 
+	/*
+	 * Datasheet specifies internal reference voltage is disabled by
+	 * default. The internal reference voltage needs to be enabled and
+	 * voltage needs to settle before getting valid ADC data. So perform a
+	 * dummy read to enable the internal reference voltage.
+	 */
+	if (!ext_vref)
+		regmap_read(data->regmap, data->cmd_byte, &regval);
+
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
 							   data,
 							   ads7828_groups);
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index 827c03703128..a7f886961830 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -30,6 +30,7 @@
 
 #define ADT7411_REG_CFG1			0x18
 #define ADT7411_CFG1_START_MONITOR		(1 << 0)
+#define ADT7411_CFG1_RESERVED_BIT3		(1 << 3)
 
 #define ADT7411_REG_CFG2			0x19
 #define ADT7411_CFG2_DISABLE_AVG		(1 << 5)
@@ -296,8 +297,10 @@ static int adt7411_probe(struct i2c_client *client,
 	mutex_init(&data->device_lock);
 	mutex_init(&data->update_lock);
 
+	/* According to the datasheet, we must only write 1 to bit 3 */
 	ret = adt7411_modify_bit(client, ADT7411_REG_CFG1,
-				 ADT7411_CFG1_START_MONITOR, 1);
+				 ADT7411_CFG1_RESERVED_BIT3
+				 | ADT7411_CFG1_START_MONITOR, 1);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 12e851a5af48..46b4e35fd555 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -188,8 +188,8 @@ static struct amc6821_data *amc6821_update_device(struct device *dev)
 			!data->valid) {
 
 		for (i = 0; i < TEMP_IDX_LEN; i++)
-			data->temp[i] = i2c_smbus_read_byte_data(client,
-				temp_reg[i]);
+			data->temp[i] = (int8_t)i2c_smbus_read_byte_data(
+				client, temp_reg[i]);
 
 		data->stat1 = i2c_smbus_read_byte_data(client,
 			AMC6821_REG_STAT1);
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index c43318d3416e..a9356a3dea92 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -66,11 +66,13 @@
 
 static DEFINE_MUTEX(i8k_mutex);
 static char bios_version[4];
+static char bios_machineid[16];
 static struct device *i8k_hwmon_dev;
 static u32 i8k_hwmon_flags;
 static uint i8k_fan_mult = I8K_FAN_MULT;
 static uint i8k_pwm_mult;
 static uint i8k_fan_max = I8K_FAN_HIGH;
+static bool disallow_fan_type_call;
 
 #define I8K_HWMON_HAVE_TEMP1	(1 << 0)
 #define I8K_HWMON_HAVE_TEMP2	(1 << 1)
@@ -94,13 +96,13 @@ module_param(ignore_dmi, bool, 0);
 MODULE_PARM_DESC(ignore_dmi, "Continue probing hardware even if DMI data does not match");
 
 #if IS_ENABLED(CONFIG_I8K)
-static bool restricted;
+static bool restricted = true;
 module_param(restricted, bool, 0);
-MODULE_PARM_DESC(restricted, "Allow fan control if SYS_ADMIN capability set");
+MODULE_PARM_DESC(restricted, "Restrict fan control and serial number to CAP_SYS_ADMIN (default: 1)");
 
 static bool power_status;
 module_param(power_status, bool, 0600);
-MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k");
+MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k (default: 0)");
 #endif
 
 static uint fan_mult;
@@ -235,14 +237,28 @@ static int i8k_get_fan_speed(int fan)
 /*
  * Read the fan type.
  */
-static int i8k_get_fan_type(int fan)
+static int _i8k_get_fan_type(int fan)
 {
 	struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, };
 
+	if (disallow_fan_type_call)
+		return -EINVAL;
+
 	regs.ebx = fan & 0xff;
 	return i8k_smm(&regs) ? : regs.eax & 0xff;
 }
 
+static int i8k_get_fan_type(int fan)
+{
+	/* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */
+	static int types[2] = { INT_MIN, INT_MIN };
+
+	if (types[fan] == INT_MIN)
+		types[fan] = _i8k_get_fan_type(fan);
+
+	return types[fan];
+}
+
 /*
  * Read the fan nominal rpm for specific fan speed.
  */
@@ -392,9 +408,11 @@ i8k_ioctl_unlocked(struct file *fp, unsigned int cmd, unsigned long arg)
 		break;
 
 	case I8K_MACHINE_ID:
-		memset(buff, 0, 16);
-		strlcpy(buff, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
-			sizeof(buff));
+		if (restricted && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		memset(buff, 0, sizeof(buff));
+		strlcpy(buff, bios_machineid, sizeof(buff));
 		break;
 
 	case I8K_FN_STATUS:
@@ -511,7 +529,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset)
 	seq_printf(seq, "%s %s %s %d %d %d %d %d %d %d\n",
 		   I8K_PROC_FMT,
 		   bios_version,
-		   i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		   (restricted && !capable(CAP_SYS_ADMIN)) ? "-1" : bios_machineid,
 		   cpu_temp,
 		   left_fan, right_fan, left_speed, right_speed,
 		   ac_power, fn_key);
@@ -718,6 +736,9 @@ static struct attribute *i8k_attrs[] = {
 static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr,
 			      int index)
 {
+	if (disallow_fan_type_call &&
+	    (index == 9 || index == 12))
+		return 0;
 	if (index >= 0 && index <= 1 &&
 	    !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1))
 		return 0;
@@ -767,13 +788,17 @@ static int __init i8k_init_hwmon(void)
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4;
 
-	/* First fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(0);
+	/* First fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(0);
+	if (err < 0)
+		err = i8k_get_fan_type(0);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1;
 
-	/* Second fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(1);
+	/* Second fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(1);
+	if (err < 0)
+		err = i8k_get_fan_type(1);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
 
@@ -929,12 +954,14 @@ static struct dmi_system_id i8k_dmi_table[] __initdata = {
 
 MODULE_DEVICE_TABLE(dmi, i8k_dmi_table);
 
-static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
+/*
+ * On some machines once I8K_SMM_GET_FAN_TYPE is issued then CPU fan speed
+ * randomly going up and down due to bug in Dell SMM or BIOS. Here is blacklist
+ * of affected Dell machines for which we disallow I8K_SMM_GET_FAN_TYPE call.
+ * See bug: https://bugzilla.kernel.org/show_bug.cgi?id=100121
+ */
+static struct dmi_system_id i8k_blacklist_fan_type_dmi_table[] __initdata = {
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8000
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8000",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -942,16 +969,19 @@ static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
 		},
 	},
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8100
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8100",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"),
 		},
 	},
+	{
+		.ident = "Dell Inspiron 580",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Inspiron 580 "),
+		},
+	},
 	{ }
 };
 
@@ -966,8 +996,7 @@ static int __init i8k_probe(void)
 	/*
 	 * Get DMI information
 	 */
-	if (!dmi_check_system(i8k_dmi_table) ||
-	    dmi_check_system(i8k_blacklist_dmi_table)) {
+	if (!dmi_check_system(i8k_dmi_table)) {
 		if (!ignore_dmi && !force)
 			return -ENODEV;
 
@@ -978,8 +1007,13 @@ static int __init i8k_probe(void)
 			i8k_get_dmi_data(DMI_BIOS_VERSION));
 	}
 
+	if (dmi_check_system(i8k_blacklist_fan_type_dmi_table))
+		disallow_fan_type_call = true;
+
 	strlcpy(bios_version, i8k_get_dmi_data(DMI_BIOS_VERSION),
 		sizeof(bios_version));
+	strlcpy(bios_machineid, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		sizeof(bios_machineid));
 
 	/*
 	 * Get SMM Dell signature
diff --git a/drivers/hwmon/ds620.c b/drivers/hwmon/ds620.c
index edf550fc4eef..0043a4c02b85 100644
--- a/drivers/hwmon/ds620.c
+++ b/drivers/hwmon/ds620.c
@@ -166,7 +166,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *da,
 	if (res)
 		return res;
 
-	val = (val * 10 / 625) * 8;
+	val = (clamp_val(val, -128000, 128000) * 10 / 625) * 8;
 
 	mutex_lock(&data->update_lock);
 	data->temp[attr->index] = val;
diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c
index b96a2a9e4df7..628be9c95ff9 100644
--- a/drivers/hwmon/g762.c
+++ b/drivers/hwmon/g762.c
@@ -193,14 +193,17 @@ static inline unsigned int rpm_from_cnt(u8 cnt, u32 clk_freq, u16 p,
  * Convert fan RPM value from sysfs into count value for fan controller
  * register (FAN_SET_CNT).
  */
-static inline unsigned char cnt_from_rpm(u32 rpm, u32 clk_freq, u16 p,
+static inline unsigned char cnt_from_rpm(unsigned long rpm, u32 clk_freq, u16 p,
 					 u8 clk_div, u8 gear_mult)
 {
-	if (!rpm)         /* to stop the fan, set cnt to 255 */
+	unsigned long f1 = clk_freq * 30 * gear_mult;
+	unsigned long f2 = p * clk_div;
+
+	if (!rpm)	/* to stop the fan, set cnt to 255 */
 		return 0xff;
 
-	return clamp_val(((clk_freq * 30 * gear_mult) / (rpm * p * clk_div)),
-			 0, 255);
+	rpm = clamp_val(rpm, f1 / (255 * f2), ULONG_MAX / f2);
+	return DIV_ROUND_CLOSEST(f1, rpm * f2);
 }
 
 /* helper to grab and cache data, at most one time per second */
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 17ae2eb26ce2..d5c06f2764f4 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -109,24 +109,24 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 
 		switch (type) {
 		case IIO_VOLTAGE:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "in%d_input",
-							  in_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "in%d_input",
+							       in_i++);
 			break;
 		case IIO_TEMP:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "temp%d_input",
-							  temp_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "temp%d_input",
+							       temp_i++);
 			break;
 		case IIO_CURRENT:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "curr%d_input",
-							  curr_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "curr%d_input",
+							       curr_i++);
 			break;
 		case IIO_HUMIDITYRELATIVE:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "humidity%d_input",
-							  humidity_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "humidity%d_input",
+							       humidity_i++);
 			break;
 		default:
 			ret = -EINVAL;
diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c
index 36544c4f653c..303d0c9df907 100644
--- a/drivers/hwmon/max1111.c
+++ b/drivers/hwmon/max1111.c
@@ -85,6 +85,9 @@ static struct max1111_data *the_max1111;
 
 int max1111_read_channel(int channel)
 {
+	if (!the_max1111 || !the_max1111->spi)
+		return -ENODEV;
+
 	return max1111_read(&the_max1111->spi->dev, channel);
 }
 EXPORT_SYMBOL(max1111_read_channel);
@@ -258,6 +261,9 @@ static int max1111_remove(struct spi_device *spi)
 {
 	struct max1111_data *data = spi_get_drvdata(spi);
 
+#ifdef CONFIG_SHARPSL_PM
+	the_max1111 = NULL;
+#endif
 	hwmon_device_unregister(data->hwmon_dev);
 	sysfs_remove_group(&spi->dev.kobj, &max1110_attr_group);
 	sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group);
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 3ce33d244cc0..12b94b094c0d 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -259,13 +259,15 @@ static int nct7802_read_fan_min(struct nct7802_data *data, u8 reg_fan_low,
 		ret = 0;
 	else if (ret)
 		ret = DIV_ROUND_CLOSEST(1350000U, ret);
+	else
+		ret = 1350000U;
 abort:
 	mutex_unlock(&data->access_lock);
 	return ret;
 }
 
 static int nct7802_write_fan_min(struct nct7802_data *data, u8 reg_fan_low,
-				 u8 reg_fan_high, unsigned int limit)
+				 u8 reg_fan_high, unsigned long limit)
 {
 	int err;
 
@@ -326,8 +328,8 @@ static int nct7802_write_voltage(struct nct7802_data *data, int nr, int index,
 	int shift = 8 - REG_VOLTAGE_LIMIT_MSB_SHIFT[index - 1][nr];
 	int err;
 
+	voltage = clamp_val(voltage, 0, 0x3ff * nct7802_vmul[nr]);
 	voltage = DIV_ROUND_CLOSEST(voltage, nct7802_vmul[nr]);
-	voltage = clamp_val(voltage, 0, 0x3ff);
 
 	mutex_lock(&data->access_lock);
 	err = regmap_write(data->regmap,
@@ -402,7 +404,7 @@ static ssize_t store_temp(struct device *dev, struct device_attribute *attr,
 	if (err < 0)
 		return err;
 
-	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -128, 127);
+	val = DIV_ROUND_CLOSEST(clamp_val(val, -128000, 127000), 1000);
 
 	err = regmap_write(data->regmap, nr, val & 0xff);
 	return err ? : count;
diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c
index 7e20567bc369..6827169c82d4 100644
--- a/drivers/hwmon/scpi-hwmon.c
+++ b/drivers/hwmon/scpi-hwmon.c
@@ -272,6 +272,7 @@ static const struct of_device_id scpi_of_match[] = {
 	{.compatible = "arm,scpi-sensors"},
 	{},
 };
+MODULE_DEVICE_TABLE(of, scpi_of_match);
 
 static struct platform_driver scpi_hwmon_platdrv = {
 	.driver = {
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index 165d3001c301..c6ec5c62b7a9 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -419,6 +419,38 @@ static struct intel_th_subdevice {
 	},
 };
 
+#ifdef CONFIG_MODULES
+static void __intel_th_request_hub_module(struct work_struct *work)
+{
+	struct intel_th *th = container_of(work, struct intel_th,
+					   request_module_work);
+
+	request_module("intel_th_%s", th->hub->name);
+}
+
+static int intel_th_request_hub_module(struct intel_th *th)
+{
+	INIT_WORK(&th->request_module_work, __intel_th_request_hub_module);
+	schedule_work(&th->request_module_work);
+
+	return 0;
+}
+
+static void intel_th_request_hub_module_flush(struct intel_th *th)
+{
+	flush_work(&th->request_module_work);
+}
+#else
+static inline int intel_th_request_hub_module(struct intel_th *th)
+{
+	return -EINVAL;
+}
+
+static inline void intel_th_request_hub_module_flush(struct intel_th *th)
+{
+}
+#endif /* CONFIG_MODULES */
+
 static int intel_th_populate(struct intel_th *th, struct resource *devres,
 			     unsigned int ndevres, int irq)
 {
@@ -488,7 +520,7 @@ static int intel_th_populate(struct intel_th *th, struct resource *devres,
 		/* need switch driver to be loaded to enumerate the rest */
 		if (subdev->type == INTEL_TH_SWITCH && !req) {
 			th->hub = thdev;
-			err = request_module("intel_th_%s", subdev->name);
+			err = intel_th_request_hub_module(th);
 			if (!err)
 				req++;
 		}
@@ -603,6 +635,7 @@ void intel_th_free(struct intel_th *th)
 {
 	int i;
 
+	intel_th_request_hub_module_flush(th);
 	for (i = 0; i < TH_SUBDEVICE_MAX; i++)
 		if (th->thdev[i] != th->hub)
 			intel_th_device_remove(th->thdev[i]);
diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h
index 57fd72b20fae..d03a6cd1c65d 100644
--- a/drivers/hwtracing/intel_th/intel_th.h
+++ b/drivers/hwtracing/intel_th/intel_th.h
@@ -197,6 +197,9 @@ struct intel_th {
 
 	int			id;
 	int			major;
+#ifdef CONFIG_MODULES
+	struct work_struct	request_module_work;
+#endif /* CONFIG_MODULES */
 #ifdef CONFIG_INTEL_TH_DEBUG
 	struct dentry		*dbg;
 #endif
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 641e87936064..32c6a40a408f 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -67,6 +67,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa126),
 		.driver_data = (kernel_ulong_t)0,
 	},
+	{
+		/* Kaby Lake PCH-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Cannon Lake H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa326),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Cannon Lake LP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6),
+		.driver_data = (kernel_ulong_t)0,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/hwtracing/stm/Kconfig b/drivers/hwtracing/stm/Kconfig
index 83e9f591a54b..e7a348807f0c 100644
--- a/drivers/hwtracing/stm/Kconfig
+++ b/drivers/hwtracing/stm/Kconfig
@@ -1,6 +1,7 @@
 config STM
 	tristate "System Trace Module devices"
 	select CONFIGFS_FS
+	select SRCU
 	help
 	  A System Trace Module (STM) is a device exporting data in System
 	  Trace Protocol (STP) format as defined by MIPI STP standards.
diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig
index 78fbee463628..65dbde778181 100644
--- a/drivers/i2c/Kconfig
+++ b/drivers/i2c/Kconfig
@@ -59,7 +59,6 @@ config I2C_CHARDEV
 
 config I2C_MUX
 	tristate "I2C bus multiplexing support"
-	depends on HAS_IOMEM
 	help
 	  Say Y here if you want the I2C core to support the ability to
 	  handle multiplexed I2C bus topologies, by presenting each
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index 714bdc837769..b167ab25310a 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -116,8 +116,8 @@ struct cpm_i2c {
 	cbd_t __iomem *rbase;
 	u_char *txbuf[CPM_MAXBD];
 	u_char *rxbuf[CPM_MAXBD];
-	u32 txdma[CPM_MAXBD];
-	u32 rxdma[CPM_MAXBD];
+	dma_addr_t txdma[CPM_MAXBD];
+	dma_addr_t rxdma[CPM_MAXBD];
 };
 
 static irqreturn_t cpm_i2c_interrupt(int irq, void *dev_id)
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index a0d95ff682ae..2d5ff86398d0 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -215,7 +215,7 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 	msg->outsize = request_len;
 	msg->insize = response_len;
 
-	result = cros_ec_cmd_xfer(bus->ec, msg);
+	result = cros_ec_cmd_xfer_status(bus->ec, msg);
 	if (result < 0) {
 		dev_err(dev, "Error transferring EC i2c message %d\n", result);
 		goto exit;
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 6b00061c3746..a2ae2213ef3e 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -294,7 +294,7 @@ static void dw_i2c_plat_complete(struct device *dev)
 #endif
 
 #ifdef CONFIG_PM
-static int dw_i2c_plat_suspend(struct device *dev)
+static int dw_i2c_plat_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_i2c_dev *i_dev = platform_get_drvdata(pdev);
@@ -318,11 +318,21 @@ static int dw_i2c_plat_resume(struct device *dev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int dw_i2c_plat_suspend(struct device *dev)
+{
+	pm_runtime_resume(dev);
+	return dw_i2c_plat_runtime_suspend(dev);
+}
+#endif
+
 static const struct dev_pm_ops dw_i2c_dev_pm_ops = {
 	.prepare = dw_i2c_plat_prepare,
 	.complete = dw_i2c_plat_complete,
 	SET_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume)
-	SET_RUNTIME_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume, NULL)
+	SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend,
+			   dw_i2c_plat_resume,
+			   NULL)
 };
 
 #define DW_I2C_DEV_PMOPS (&dw_i2c_dev_pm_ops)
diff --git a/drivers/i2c/busses/i2c-efm32.c b/drivers/i2c/busses/i2c-efm32.c
index 8eff62738877..e253598d764c 100644
--- a/drivers/i2c/busses/i2c-efm32.c
+++ b/drivers/i2c/busses/i2c-efm32.c
@@ -433,7 +433,7 @@ static int efm32_i2c_probe(struct platform_device *pdev)
 	ret = request_irq(ddata->irq, efm32_i2c_irq, 0, DRIVER_NAME, ddata);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to request irq (%d)\n", ret);
-		return ret;
+		goto err_disable_clk;
 	}
 
 	ret = i2c_add_adapter(&ddata->adapter);
diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c
index 76e699f9ed97..eef3aa6007f1 100644
--- a/drivers/i2c/busses/i2c-eg20t.c
+++ b/drivers/i2c/busses/i2c-eg20t.c
@@ -773,13 +773,6 @@ static int pch_i2c_probe(struct pci_dev *pdev,
 	/* Set the number of I2C channel instance */
 	adap_info->ch_num = id->driver_data;
 
-	ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
-		  KBUILD_MODNAME, adap_info);
-	if (ret) {
-		pch_pci_err(pdev, "request_irq FAILED\n");
-		goto err_request_irq;
-	}
-
 	for (i = 0; i < adap_info->ch_num; i++) {
 		pch_adap = &adap_info->pch_data[i].pch_adapter;
 		adap_info->pch_i2c_suspended = false;
@@ -796,6 +789,17 @@ static int pch_i2c_probe(struct pci_dev *pdev,
 		adap_info->pch_data[i].pch_base_address = base_addr + 0x100 * i;
 
 		pch_adap->dev.parent = &pdev->dev;
+	}
+
+	ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
+		  KBUILD_MODNAME, adap_info);
+	if (ret) {
+		pch_pci_err(pdev, "request_irq FAILED\n");
+		goto err_request_irq;
+	}
+
+	for (i = 0; i < adap_info->ch_num; i++) {
+		pch_adap = &adap_info->pch_data[i].pch_adapter;
 
 		pch_i2c_init(&adap_info->pch_data[i]);
 
diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index b29c7500461a..f54ece8fce78 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -671,7 +671,9 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap,
 		return -EIO;
 	}
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < num; i++, msgs++) {
 		stop = (i == num - 1);
@@ -695,7 +697,7 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap,
 	}
 
  out:
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	return ret;
 }
 
@@ -747,7 +749,9 @@ static int exynos5_i2c_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	i2c->regs = devm_ioremap_resource(&pdev->dev, mem);
@@ -799,6 +803,10 @@ static int exynos5_i2c_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, i2c);
 
+	clk_disable(i2c->clk);
+
+	return 0;
+
  err_clk:
 	clk_disable_unprepare(i2c->clk);
 	return ret;
@@ -810,6 +818,8 @@ static int exynos5_i2c_remove(struct platform_device *pdev)
 
 	i2c_del_adapter(&i2c->adap);
 
+	clk_unprepare(i2c->clk);
+
 	return 0;
 }
 
@@ -821,6 +831,8 @@ static int exynos5_i2c_suspend_noirq(struct device *dev)
 
 	i2c->suspended = 1;
 
+	clk_unprepare(i2c->clk);
+
 	return 0;
 }
 
@@ -830,7 +842,9 @@ static int exynos5_i2c_resume_noirq(struct device *dev)
 	struct exynos5_i2c *i2c = platform_get_drvdata(pdev);
 	int ret = 0;
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	ret = exynos5_hsi2c_clock_setup(i2c);
 	if (ret) {
@@ -839,7 +853,7 @@ static int exynos5_i2c_resume_noirq(struct device *dev)
 	}
 
 	exynos5_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	i2c->suspended = 0;
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 27fa0cb09538..85f39cc3e276 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -244,6 +244,13 @@ struct i801_priv {
 	struct platform_device *mux_pdev;
 #endif
 	struct platform_device *tco_pdev;
+
+	/*
+	 * If set to true the host controller registers are reserved for
+	 * ACPI AML use. Protected by acpi_lock.
+	 */
+	bool acpi_reserved;
+	struct mutex acpi_lock;
 };
 
 #define FEATURE_SMBUS_PEC	(1 << 0)
@@ -714,9 +721,15 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 {
 	int hwpec;
 	int block = 0;
-	int ret, xact = 0;
+	int ret = 0, xact = 0;
 	struct i801_priv *priv = i2c_get_adapdata(adap);
 
+	mutex_lock(&priv->acpi_lock);
+	if (priv->acpi_reserved) {
+		mutex_unlock(&priv->acpi_lock);
+		return -EBUSY;
+	}
+
 	hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC)
 		&& size != I2C_SMBUS_QUICK
 		&& size != I2C_SMBUS_I2C_BLOCK_DATA;
@@ -773,7 +786,8 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 	default:
 		dev_err(&priv->pci_dev->dev, "Unsupported transaction %d\n",
 			size);
-		return -EOPNOTSUPP;
+		ret = -EOPNOTSUPP;
+		goto out;
 	}
 
 	if (hwpec)	/* enable/disable hardware PEC */
@@ -796,11 +810,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 		       ~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv));
 
 	if (block)
-		return ret;
+		goto out;
 	if (ret)
-		return ret;
+		goto out;
 	if ((read_write == I2C_SMBUS_WRITE) || (xact == I801_QUICK))
-		return 0;
+		goto out;
 
 	switch (xact & 0x7f) {
 	case I801_BYTE:	/* Result put in SMBHSTDAT0 */
@@ -812,7 +826,10 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 			     (inb_p(SMBHSTDAT1(priv)) << 8);
 		break;
 	}
-	return 0;
+
+out:
+	mutex_unlock(&priv->acpi_lock);
+	return ret;
 }
 
 
@@ -1249,6 +1266,72 @@ static void i801_add_tco(struct i801_priv *priv)
 	priv->tco_pdev = pdev;
 }
 
+#ifdef CONFIG_ACPI
+static acpi_status
+i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
+		     u64 *value, void *handler_context, void *region_context)
+{
+	struct i801_priv *priv = handler_context;
+	struct pci_dev *pdev = priv->pci_dev;
+	acpi_status status;
+
+	/*
+	 * Once BIOS AML code touches the OpRegion we warn and inhibit any
+	 * further access from the driver itself. This device is now owned
+	 * by the system firmware.
+	 */
+	mutex_lock(&priv->acpi_lock);
+
+	if (!priv->acpi_reserved) {
+		priv->acpi_reserved = true;
+
+		dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n");
+		dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n");
+	}
+
+	if ((function & ACPI_IO_MASK) == ACPI_READ)
+		status = acpi_os_read_port(address, (u32 *)value, bits);
+	else
+		status = acpi_os_write_port(address, (u32)*value, bits);
+
+	mutex_unlock(&priv->acpi_lock);
+
+	return status;
+}
+
+static int i801_acpi_probe(struct i801_priv *priv)
+{
+	struct acpi_device *adev;
+	acpi_status status;
+
+	adev = ACPI_COMPANION(&priv->pci_dev->dev);
+	if (adev) {
+		status = acpi_install_address_space_handler(adev->handle,
+				ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler,
+				NULL, priv);
+		if (ACPI_SUCCESS(status))
+			return 0;
+	}
+
+	return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]);
+}
+
+static void i801_acpi_remove(struct i801_priv *priv)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(&priv->pci_dev->dev);
+	if (!adev)
+		return;
+
+	acpi_remove_address_space_handler(adev->handle,
+		ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler);
+}
+#else
+static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
+static inline void i801_acpi_remove(struct i801_priv *priv) { }
+#endif
+
 static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	unsigned char temp;
@@ -1266,6 +1349,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	priv->adapter.dev.parent = &dev->dev;
 	ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev));
 	priv->adapter.retries = 3;
+	mutex_init(&priv->acpi_lock);
 
 	priv->pci_dev = dev;
 	switch (dev->device) {
@@ -1328,10 +1412,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENODEV;
 	}
 
-	err = acpi_check_resource_conflict(&dev->resource[SMBBAR]);
-	if (err) {
+	if (i801_acpi_probe(priv))
 		return -ENODEV;
-	}
 
 	err = pcim_iomap_regions(dev, 1 << SMBBAR,
 				 dev_driver_string(&dev->dev));
@@ -1340,6 +1422,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			"Failed to request SMBus region 0x%lx-0x%Lx\n",
 			priv->smba,
 			(unsigned long long)pci_resource_end(dev, SMBBAR));
+		i801_acpi_remove(priv);
 		return err;
 	}
 
@@ -1404,6 +1487,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	err = i2c_add_adapter(&priv->adapter);
 	if (err) {
 		dev_err(&dev->dev, "Failed to add SMBus adapter\n");
+		i801_acpi_remove(priv);
 		return err;
 	}
 
@@ -1422,6 +1506,7 @@ static void i801_remove(struct pci_dev *dev)
 
 	i801_del_mux(priv);
 	i2c_del_adapter(&priv->adapter);
+	i801_acpi_remove(priv);
 	pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg);
 
 	platform_device_unregister(priv->tco_pdev);
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index 7ba795b24e75..639d1a9c8793 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -339,8 +339,10 @@ static int ismt_process_desc(const struct ismt_desc *desc,
 			break;
 		case I2C_SMBUS_BLOCK_DATA:
 		case I2C_SMBUS_I2C_BLOCK_DATA:
-			memcpy(&data->block[1], dma_buffer, desc->rxbytes);
-			data->block[0] = desc->rxbytes;
+			if (desc->rxbytes != dma_buffer[0] + 1)
+				return -EMSGSIZE;
+
+			memcpy(data->block, dma_buffer, desc->rxbytes);
 			break;
 		}
 		return 0;
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index f325663c27c5..4b58e8aaf5c5 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -786,10 +786,6 @@ static int jz4780_i2c_probe(struct platform_device *pdev)
 
 	jz4780_i2c_writew(i2c, JZ4780_I2C_INTM, 0x0);
 
-	i2c->cmd = 0;
-	memset(i2c->cmd_buf, 0, BUFSIZE);
-	memset(i2c->data_buf, 0, BUFSIZE);
-
 	i2c->irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, i2c->irq, jz4780_i2c_irq, 0,
 			       dev_name(&pdev->dev), i2c);
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 630bce68bf38..b61db9db3ca5 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -54,7 +54,7 @@
 #define SMBSLVDAT	(0xC + piix4_smba)
 
 /* count for request_region */
-#define SMBIOSIZE	8
+#define SMBIOSIZE	9
 
 /* PCI Address Constants */
 #define SMBBA		0x090
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index fdcbdab808e9..33b11563cde7 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -727,7 +727,8 @@ static int qup_i2c_pm_resume_runtime(struct device *device)
 #ifdef CONFIG_PM_SLEEP
 static int qup_i2c_suspend(struct device *device)
 {
-	qup_i2c_pm_suspend_runtime(device);
+	if (!pm_runtime_suspended(device))
+		return qup_i2c_pm_suspend_runtime(device);
 	return 0;
 }
 
diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c
index 0ed77eeff31e..a2e3dd715380 100644
--- a/drivers/i2c/busses/i2c-tiny-usb.c
+++ b/drivers/i2c/busses/i2c-tiny-usb.c
@@ -178,22 +178,39 @@ static int usb_read(struct i2c_adapter *adapter, int cmd,
 		    int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmalloc(len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_rcvctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE |
-			       USB_DIR_IN, value, index, data, len, 2000);
+			       USB_DIR_IN, value, index, dmadata, len, 2000);
+
+	memcpy(data, dmadata, len);
+	kfree(dmadata);
+	return ret;
 }
 
 static int usb_write(struct i2c_adapter *adapter, int cmd,
 		     int value, int index, void *data, int len)
 {
 	struct i2c_tiny_usb *dev = (struct i2c_tiny_usb *)adapter->algo_data;
+	void *dmadata = kmemdup(data, len, GFP_KERNEL);
+	int ret;
+
+	if (!dmadata)
+		return -ENOMEM;
 
 	/* do control transfer */
-	return usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
+	ret = usb_control_msg(dev->usb_dev, usb_sndctrlpipe(dev->usb_dev, 0),
 			       cmd, USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
-			       value, index, data, len, 2000);
+			       value, index, dmadata, len, 2000);
+
+	kfree(dmadata);
+	return ret;
 }
 
 static void i2c_tiny_usb_free(struct i2c_tiny_usb *dev)
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index 4233f5695352..3c38029e3fe9 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -105,7 +105,7 @@ struct slimpro_i2c_dev {
 	struct mbox_chan *mbox_chan;
 	struct mbox_client mbox_client;
 	struct completion rd_complete;
-	u8 dma_buffer[I2C_SMBUS_BLOCK_MAX];
+	u8 dma_buffer[I2C_SMBUS_BLOCK_MAX + 1]; /* dma_buffer[0] is used for length */
 	u32 *resp_msg;
 };
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index ba8eb087f224..e4587411b447 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -1400,7 +1400,7 @@ static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
 
 	if (i2c_check_addr_validity(addr, info.flags)) {
 		dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n",
-			info.addr, node->full_name);
+			addr, node->full_name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1876,6 +1876,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 	/* add the driver to the list of i2c drivers in the driver core */
 	driver->driver.owner = owner;
 	driver->driver.bus = &i2c_bus_type;
+	INIT_LIST_HEAD(&driver->clients);
 
 	/* When registration returns, the driver core
 	 * will have called probe() for all matching-but-unbound devices.
@@ -1886,7 +1887,6 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 
 	pr_debug("i2c-core: driver [%s] registered\n", driver->driver.name);
 
-	INIT_LIST_HEAD(&driver->clients);
 	/* Walk the adapters that are already present */
 	i2c_for_each_dev(driver, __process_new_driver);
 
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 2413ec9f8207..94c837046786 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -329,7 +329,7 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client,
 		unsigned long arg)
 {
 	struct i2c_smbus_ioctl_data data_arg;
-	union i2c_smbus_data temp;
+	union i2c_smbus_data temp = {};
 	int datasize, res;
 
 	if (copy_from_user(&data_arg,
diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig
index f06b0e24673b..af2a63cb4056 100644
--- a/drivers/i2c/muxes/Kconfig
+++ b/drivers/i2c/muxes/Kconfig
@@ -63,6 +63,7 @@ config I2C_MUX_PINCTRL
 
 config I2C_MUX_REG
 	tristate "Register-based I2C multiplexer"
+	depends on HAS_IOMEM
 	help
 	  If you say yes to this option, support will be included for a
 	  register based I2C multiplexer. This driver provides access to
diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 5fbd5bd0878f..49fc2c7e560a 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -150,7 +150,7 @@ static int i2c_mux_reg_probe_dt(struct regmux *mux,
 		mux->data.idle_in_use = true;
 
 	/* map address from "reg" if exists */
-	if (of_address_to_resource(np, 0, &res)) {
+	if (of_address_to_resource(np, 0, &res) == 0) {
 		mux->data.reg_size = resource_size(&res);
 		mux->data.reg = devm_ioremap_resource(&pdev->dev, &res);
 		if (IS_ERR(mux->data.reg))
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index cd4510a63375..ba947df5a8c7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -65,7 +65,7 @@
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
-#define INTEL_IDLE_VERSION "0.4"
+#define INTEL_IDLE_VERSION "0.4.1"
 #define PREFIX "intel_idle: "
 
 static struct cpuidle_driver intel_idle_driver = {
@@ -716,6 +716,26 @@ static struct cpuidle_state avn_cstates[] = {
 	{
 		.enter = NULL }
 };
+static struct cpuidle_state knl_cstates[] = {
+	{
+		.name = "C1-KNL",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 1,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze },
+	{
+		.name = "C6-KNL",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 120,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze },
+	{
+		.enter = NULL }
+};
 
 /**
  * intel_idle
@@ -890,6 +910,10 @@ static const struct idle_cpu idle_cpu_avn = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_knl = {
+	.state_table = knl_cstates,
+};
+
 #define ICPU(model, cpu) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
 
@@ -921,6 +945,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(0x56, idle_cpu_bdw),
 	ICPU(0x4e, idle_cpu_skl),
 	ICPU(0x5e, idle_cpu_skl),
+	ICPU(0x57, idle_cpu_knl),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
@@ -994,36 +1019,92 @@ static void intel_idle_cpuidle_devices_uninit(void)
 }
 
 /*
- * intel_idle_state_table_update()
+ * ivt_idle_state_table_update(void)
  *
- * Update the default state_table for this CPU-id
- *
- * Currently used to access tuned IVT multi-socket targets
+ * Tune IVT multi-socket targets
  * Assumption: num_sockets == (max_package_num + 1)
  */
-void intel_idle_state_table_update(void)
+static void ivt_idle_state_table_update(void)
 {
 	/* IVT uses a different table for 1-2, 3-4, and > 4 sockets */
-	if (boot_cpu_data.x86_model == 0x3e) { /* IVT */
-		int cpu, package_num, num_sockets = 1;
-
-		for_each_online_cpu(cpu) {
-			package_num = topology_physical_package_id(cpu);
-			if (package_num + 1 > num_sockets) {
-				num_sockets = package_num + 1;
-
-				if (num_sockets > 4) {
-					cpuidle_state_table = ivt_cstates_8s;
-					return;
-				}
+	int cpu, package_num, num_sockets = 1;
+
+	for_each_online_cpu(cpu) {
+		package_num = topology_physical_package_id(cpu);
+		if (package_num + 1 > num_sockets) {
+			num_sockets = package_num + 1;
+
+			if (num_sockets > 4) {
+				cpuidle_state_table = ivt_cstates_8s;
+				return;
 			}
 		}
+	}
+
+	if (num_sockets > 2)
+		cpuidle_state_table = ivt_cstates_4s;
 
-		if (num_sockets > 2)
-			cpuidle_state_table = ivt_cstates_4s;
-		/* else, 1 and 2 socket systems use default ivt_cstates */
+	/* else, 1 and 2 socket systems use default ivt_cstates */
+}
+/*
+ * sklh_idle_state_table_update(void)
+ *
+ * On SKL-H (model 0x5e) disable C8 and C9 if:
+ * C10 is enabled and SGX disabled
+ */
+static void sklh_idle_state_table_update(void)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+
+
+	/* if PC10 disabled via cmdline intel_idle.max_cstate=7 or shallower */
+	if (max_cstate <= 7)
+		return;
+
+	/* if PC10 not present in CPUID.MWAIT.EDX */
+	if ((mwait_substates & (0xF << 28)) == 0)
+		return;
+
+	rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr);
+
+	/* PC10 is not enabled in PKG C-state limit */
+	if ((msr & 0xF) != 8)
+		return;
+
+	ecx = 0;
+	cpuid(7, &eax, &ebx, &ecx, &edx);
+
+	/* if SGX is present */
+	if (ebx & (1 << 2)) {
+
+		rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
+
+		/* if SGX is enabled */
+		if (msr & (1 << 18))
+			return;
+	}
+
+	skl_cstates[5].disabled = 1;	/* C8-SKL */
+	skl_cstates[6].disabled = 1;	/* C9-SKL */
+}
+/*
+ * intel_idle_state_table_update()
+ *
+ * Update the default state_table for this CPU-id
+ */
+
+static void intel_idle_state_table_update(void)
+{
+	switch (boot_cpu_data.x86_model) {
+
+	case 0x3e: /* IVT */
+		ivt_idle_state_table_update();
+		break;
+	case 0x5e: /* SKL-H */
+		sklh_idle_state_table_update();
+		break;
 	}
-	return;
 }
 
 /*
@@ -1063,6 +1144,14 @@ static int __init intel_idle_cpuidle_driver_init(void)
 		if (num_substates == 0)
 			continue;
 
+		/* if state marked as disabled, skip it */
+		if (cpuidle_state_table[cstate].disabled != 0) {
+			pr_debug(PREFIX "state %s is disabled",
+				cpuidle_state_table[cstate].name);
+			continue;
+		}
+
+
 		if (((mwait_cstate + 1) > 2) &&
 			!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 			mark_tsc_unstable("TSC halts in idle"
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 2d33f1e821db..c7122919a8c0 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -68,6 +68,9 @@
 #define BMC150_ACCEL_REG_PMU_BW		0x10
 #define BMC150_ACCEL_DEF_BW			125
 
+#define BMC150_ACCEL_REG_RESET			0x14
+#define BMC150_ACCEL_RESET_VAL			0xB6
+
 #define BMC150_ACCEL_REG_INT_MAP_0		0x19
 #define BMC150_ACCEL_INT_MAP_0_BIT_SLOPE	BIT(2)
 
@@ -191,7 +194,6 @@ struct bmc150_accel_data {
 	struct device *dev;
 	int irq;
 	struct bmc150_accel_interrupt interrupts[BMC150_ACCEL_INTERRUPTS];
-	atomic_t active_intr;
 	struct bmc150_accel_trigger triggers[BMC150_ACCEL_TRIGGERS];
 	struct mutex mutex;
 	u8 fifo_mode, watermark;
@@ -486,11 +488,6 @@ static int bmc150_accel_set_interrupt(struct bmc150_accel_data *data, int i,
 		goto out_fix_power_state;
 	}
 
-	if (state)
-		atomic_inc(&data->active_intr);
-	else
-		atomic_dec(&data->active_intr);
-
 	return 0;
 
 out_fix_power_state:
@@ -547,7 +544,7 @@ static int bmc150_accel_get_axis(struct bmc150_accel_data *data,
 {
 	int ret;
 	int axis = chan->scan_index;
-	unsigned int raw_val;
+	__le16 raw_val;
 
 	mutex_lock(&data->mutex);
 	ret = bmc150_accel_set_power_state(data, true);
@@ -557,14 +554,14 @@ static int bmc150_accel_get_axis(struct bmc150_accel_data *data,
 	}
 
 	ret = regmap_bulk_read(data->regmap, BMC150_ACCEL_AXIS_TO_REG(axis),
-			       &raw_val, 2);
+			       &raw_val, sizeof(raw_val));
 	if (ret < 0) {
 		dev_err(data->dev, "Error reading axis %d\n", axis);
 		bmc150_accel_set_power_state(data, false);
 		mutex_unlock(&data->mutex);
 		return ret;
 	}
-	*val = sign_extend32(raw_val >> chan->scan_type.shift,
+	*val = sign_extend32(le16_to_cpu(raw_val) >> chan->scan_type.shift,
 			     chan->scan_type.realbits - 1);
 	ret = bmc150_accel_set_power_state(data, false);
 	mutex_unlock(&data->mutex);
@@ -988,6 +985,7 @@ static const struct iio_event_spec bmc150_accel_event = {
 		.realbits = (bits),					\
 		.storagebits = 16,					\
 		.shift = 16 - (bits),					\
+		.endianness = IIO_LE,					\
 	},								\
 	.event_spec = &bmc150_accel_event,				\
 	.num_event_specs = 1						\
@@ -1486,6 +1484,14 @@ static int bmc150_accel_chip_init(struct bmc150_accel_data *data)
 	int ret, i;
 	unsigned int val;
 
+	/*
+	 * Reset chip to get it in a known good state. A delay of 1.8ms after
+	 * reset is required according to the data sheets of supported chips.
+	 */
+	regmap_write(data->regmap, BMC150_ACCEL_REG_RESET,
+		     BMC150_ACCEL_RESET_VAL);
+	usleep_range(1800, 2500);
+
 	ret = regmap_read(data->regmap, BMC150_ACCEL_REG_CHIP_ID, &val);
 	if (ret < 0) {
 		dev_err(data->dev,
@@ -1692,8 +1698,7 @@ static int bmc150_accel_resume(struct device *dev)
 	struct bmc150_accel_data *data = iio_priv(indio_dev);
 
 	mutex_lock(&data->mutex);
-	if (atomic_read(&data->active_intr))
-		bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0);
+	bmc150_accel_set_mode(data, BMC150_ACCEL_SLEEP_MODE_NORMAL, 0);
 	bmc150_accel_fifo_set_mode(data);
 	mutex_unlock(&data->mutex);
 
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 923f56598d4b..9d72d4bcf5e9 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -81,7 +81,7 @@ static int kxsd9_write_scale(struct iio_dev *indio_dev, int micro)
 
 	mutex_lock(&st->buf_lock);
 	ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C);
 	st->tx[1] = (ret & ~KXSD9_FS_MASK) | i;
@@ -160,11 +160,13 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev,
 		if (ret < 0)
 			goto error_ret;
 		*val = ret;
+		ret = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SCALE:
 		ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-		if (ret)
+		if (ret < 0)
 			goto error_ret;
+		*val = 0;
 		*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
 		ret = IIO_VAL_INT_PLUS_MICRO;
 		break;
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 1e7aded53117..bda6bbe4479c 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -306,6 +306,7 @@ config QCOM_SPMI_VADC
 config ROCKCHIP_SARADC
 	tristate "Rockchip SARADC driver"
 	depends on ARCH_ROCKCHIP || (ARM && COMPILE_TEST)
+	depends on RESET_CONTROLLER
 	help
 	  Say yes here to build support for the SARADC found in SoCs from
 	  Rockchip.
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 21e19b60e2b9..2123f0ac2e2a 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -396,8 +396,8 @@ static int ad7266_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	st->reg = devm_regulator_get(&spi->dev, "vref");
-	if (!IS_ERR_OR_NULL(st->reg)) {
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
@@ -408,6 +408,9 @@ static int ad7266_probe(struct spi_device *spi)
 
 		st->vref_mv = ret / 1000;
 	} else {
+		/* Any other error indicates that the regulator does exist */
+		if (PTR_ERR(st->reg) != -ENODEV)
+			return PTR_ERR(st->reg);
 		/* Use internal reference */
 		st->vref_mv = 2500;
 	}
diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c
index 01d71588d752..ba82de25a797 100644
--- a/drivers/iio/adc/ad799x.c
+++ b/drivers/iio/adc/ad799x.c
@@ -533,6 +533,7 @@ static struct attribute_group ad799x_event_attrs_group = {
 static const struct iio_info ad7991_info = {
 	.read_raw = &ad799x_read_raw,
 	.driver_module = THIS_MODULE,
+	.update_scan_mode = ad799x_update_scan_mode,
 };
 
 static const struct iio_info ad7993_4_7_8_noirq_info = {
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 7b40925dd4ff..93986f0590ef 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -381,8 +381,8 @@ static irqreturn_t at91_adc_rl_interrupt(int irq, void *private)
 		st->ts_bufferedmeasure = false;
 		input_report_key(st->ts_input, BTN_TOUCH, 0);
 		input_sync(st->ts_input);
-	} else if (status & AT91_ADC_EOC(3)) {
-		/* Conversion finished */
+	} else if (status & AT91_ADC_EOC(3) && st->ts_input) {
+		/* Conversion finished and we've a touchscreen */
 		if (st->ts_bufferedmeasure) {
 			/*
 			 * Last measurement is always discarded, since it can
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index 9c311c1e1ac7..dffff64b5989 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -21,6 +21,8 @@
 #include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/reset.h>
 #include <linux/regulator/consumer.h>
 #include <linux/iio/iio.h>
 
@@ -53,6 +55,7 @@ struct rockchip_saradc {
 	struct clk		*clk;
 	struct completion	completion;
 	struct regulator	*vref;
+	struct reset_control	*reset;
 	const struct rockchip_saradc_data *data;
 	u16			last_val;
 };
@@ -171,6 +174,16 @@ static const struct of_device_id rockchip_saradc_match[] = {
 };
 MODULE_DEVICE_TABLE(of, rockchip_saradc_match);
 
+/**
+ * Reset SARADC Controller.
+ */
+static void rockchip_saradc_reset_controller(struct reset_control *reset)
+{
+	reset_control_assert(reset);
+	usleep_range(10, 20);
+	reset_control_deassert(reset);
+}
+
 static int rockchip_saradc_probe(struct platform_device *pdev)
 {
 	struct rockchip_saradc *info = NULL;
@@ -199,6 +212,20 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 	if (IS_ERR(info->regs))
 		return PTR_ERR(info->regs);
 
+	/*
+	 * The reset should be an optional property, as it should work
+	 * with old devicetrees as well
+	 */
+	info->reset = devm_reset_control_get(&pdev->dev, "saradc-apb");
+	if (IS_ERR(info->reset)) {
+		ret = PTR_ERR(info->reset);
+		if (ret != -ENOENT)
+			return ret;
+
+		dev_dbg(&pdev->dev, "no reset control found\n");
+		info->reset = NULL;
+	}
+
 	init_completion(&info->completion);
 
 	irq = platform_get_irq(pdev, 0);
@@ -233,6 +260,9 @@ static int rockchip_saradc_probe(struct platform_device *pdev)
 		return PTR_ERR(info->vref);
 	}
 
+	if (info->reset)
+		rockchip_saradc_reset_controller(info->reset);
+
 	/*
 	 * Use a default value for the converter clock.
 	 * This may become user-configurable in the future.
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index c1e05532d437..9b6854607d73 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -32,6 +32,7 @@
 
 struct tiadc_device {
 	struct ti_tscadc_dev *mfd_tscadc;
+	struct mutex fifo1_lock; /* to protect fifo access */
 	int channels;
 	u8 channel_line[8];
 	u8 channel_step[8];
@@ -150,7 +151,9 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
 {
 	struct iio_dev *indio_dev = private;
 	struct tiadc_device *adc_dev = iio_priv(indio_dev);
-	unsigned int status, config;
+	unsigned int status, config, adc_fsm;
+	unsigned short count = 0;
+
 	status = tiadc_readl(adc_dev, REG_IRQSTATUS);
 
 	/*
@@ -164,6 +167,15 @@ static irqreturn_t tiadc_irq_h(int irq, void *private)
 		tiadc_writel(adc_dev, REG_CTRL, config);
 		tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN
 				| IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES);
+
+		/* wait for idle state.
+		 * ADC needs to finish the current conversion
+		 * before disabling the module
+		 */
+		do {
+			adc_fsm = tiadc_readl(adc_dev, REG_ADCFSM);
+		} while (adc_fsm != 0x10 && count++ < 100);
+
 		tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB));
 		return IRQ_HANDLED;
 	} else if (status & IRQENB_FIFO1THRES) {
@@ -360,6 +372,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 		int *val, int *val2, long mask)
 {
 	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	int ret = IIO_VAL_INT;
 	int i, map_val;
 	unsigned int fifo1count, read, stepid;
 	bool found = false;
@@ -373,13 +386,14 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 	if (!step_en)
 		return -EINVAL;
 
+	mutex_lock(&adc_dev->fifo1_lock);
 	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
 	while (fifo1count--)
 		tiadc_readl(adc_dev, REG_FIFO1);
 
 	am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en);
 
-	timeout = jiffies + usecs_to_jiffies
+	timeout = jiffies + msecs_to_jiffies
 				(IDLE_TIMEOUT * adc_dev->channels);
 	/* Wait for Fifo threshold interrupt */
 	while (1) {
@@ -389,7 +403,8 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 
 		if (time_after(jiffies, timeout)) {
 			am335x_tsc_se_adc_done(adc_dev->mfd_tscadc);
-			return -EAGAIN;
+			ret = -EAGAIN;
+			goto err_unlock;
 		}
 	}
 	map_val = adc_dev->channel_step[chan->scan_index];
@@ -415,8 +430,11 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 	am335x_tsc_se_adc_done(adc_dev->mfd_tscadc);
 
 	if (found == false)
-		return -EBUSY;
-	return IIO_VAL_INT;
+		ret =  -EBUSY;
+
+err_unlock:
+	mutex_unlock(&adc_dev->fifo1_lock);
+	return ret;
 }
 
 static const struct iio_info tiadc_info = {
@@ -485,6 +503,7 @@ static int tiadc_probe(struct platform_device *pdev)
 
 	tiadc_step_config(indio_dev);
 	tiadc_writel(adc_dev, REG_FIFO1THR, FIFO1_THRESHOLD);
+	mutex_init(&adc_dev->fifo1_lock);
 
 	err = tiadc_channel_init(indio_dev, adc_dev->channels);
 	if (err < 0)
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index b10f629cc44b..1dbc2143cdfc 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -77,7 +77,7 @@
 #define VF610_ADC_ADSTS_MASK		0x300
 #define VF610_ADC_ADLPC_EN		0x80
 #define VF610_ADC_ADHSC_EN		0x400
-#define VF610_ADC_REFSEL_VALT		0x100
+#define VF610_ADC_REFSEL_VALT		0x800
 #define VF610_ADC_REFSEL_VBG		0x1000
 #define VF610_ADC_ADTRG_HARD		0x2000
 #define VF610_ADC_AVGS_8		0x4000
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index e81f434760f4..b5beea53d6f6 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -30,34 +30,34 @@ static struct {
 	u32 usage_id;
 	int unit; /* 0 for default others from HID sensor spec */
 	int scale_val0; /* scale, whole number */
-	int scale_val1; /* scale, fraction in micros */
+	int scale_val1; /* scale, fraction in nanos */
 } unit_conversion[] = {
-	{HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650},
+	{HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650000},
 	{HID_USAGE_SENSOR_ACCEL_3D,
 		HID_USAGE_SENSOR_UNITS_METERS_PER_SEC_SQRD, 1, 0},
 	{HID_USAGE_SENSOR_ACCEL_3D,
-		HID_USAGE_SENSOR_UNITS_G, 9, 806650},
+		HID_USAGE_SENSOR_UNITS_G, 9, 806650000},
 
-	{HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453},
+	{HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453293},
 	{HID_USAGE_SENSOR_GYRO_3D,
 		HID_USAGE_SENSOR_UNITS_RADIANS_PER_SECOND, 1, 0},
 	{HID_USAGE_SENSOR_GYRO_3D,
-		HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453},
+		HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453293},
 
-	{HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000},
+	{HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000000},
 	{HID_USAGE_SENSOR_COMPASS_3D, HID_USAGE_SENSOR_UNITS_GAUSS, 1, 0},
 
-	{HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453},
+	{HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453293},
 	{HID_USAGE_SENSOR_INCLINOMETER_3D,
-		HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453},
+		HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293},
 	{HID_USAGE_SENSOR_INCLINOMETER_3D,
 		HID_USAGE_SENSOR_UNITS_RADIANS, 1, 0},
 
 	{HID_USAGE_SENSOR_ALS, 0, 1, 0},
 	{HID_USAGE_SENSOR_ALS, HID_USAGE_SENSOR_UNITS_LUX, 1, 0},
 
-	{HID_USAGE_SENSOR_PRESSURE, 0, 100000, 0},
-	{HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 1, 0},
+	{HID_USAGE_SENSOR_PRESSURE, 0, 100, 0},
+	{HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000000},
 };
 
 static int pow_10(unsigned power)
@@ -266,15 +266,15 @@ EXPORT_SYMBOL(hid_sensor_write_raw_hyst_value);
 /*
  * This fuction applies the unit exponent to the scale.
  * For example:
- * 9.806650 ->exp:2-> val0[980]val1[665000]
- * 9.000806 ->exp:2-> val0[900]val1[80600]
- * 0.174535 ->exp:2-> val0[17]val1[453500]
- * 1.001745 ->exp:0-> val0[1]val1[1745]
- * 1.001745 ->exp:2-> val0[100]val1[174500]
- * 1.001745 ->exp:4-> val0[10017]val1[450000]
- * 9.806650 ->exp:-2-> val0[0]val1[98066]
+ * 9.806650000 ->exp:2-> val0[980]val1[665000000]
+ * 9.000806000 ->exp:2-> val0[900]val1[80600000]
+ * 0.174535293 ->exp:2-> val0[17]val1[453529300]
+ * 1.001745329 ->exp:0-> val0[1]val1[1745329]
+ * 1.001745329 ->exp:2-> val0[100]val1[174532900]
+ * 1.001745329 ->exp:4-> val0[10017]val1[453290000]
+ * 9.806650000 ->exp:-2-> val0[0]val1[98066500]
  */
-static void adjust_exponent_micro(int *val0, int *val1, int scale0,
+static void adjust_exponent_nano(int *val0, int *val1, int scale0,
 				  int scale1, int exp)
 {
 	int i;
@@ -285,32 +285,32 @@ static void adjust_exponent_micro(int *val0, int *val1, int scale0,
 	if (exp > 0) {
 		*val0 = scale0 * pow_10(exp);
 		res = 0;
-		if (exp > 6) {
+		if (exp > 9) {
 			*val1 = 0;
 			return;
 		}
 		for (i = 0; i < exp; ++i) {
-			x = scale1 / pow_10(5 - i);
+			x = scale1 / pow_10(8 - i);
 			res += (pow_10(exp - 1 - i) * x);
-			scale1 = scale1 % pow_10(5 - i);
+			scale1 = scale1 % pow_10(8 - i);
 		}
 		*val0 += res;
 			*val1 = scale1 * pow_10(exp);
 	} else if (exp < 0) {
 		exp = abs(exp);
-		if (exp > 6) {
+		if (exp > 9) {
 			*val0 = *val1 = 0;
 			return;
 		}
 		*val0 = scale0 / pow_10(exp);
 		rem = scale0 % pow_10(exp);
 		res = 0;
-		for (i = 0; i < (6 - exp); ++i) {
-			x = scale1 / pow_10(5 - i);
-			res += (pow_10(5 - exp - i) * x);
-			scale1 = scale1 % pow_10(5 - i);
+		for (i = 0; i < (9 - exp); ++i) {
+			x = scale1 / pow_10(8 - i);
+			res += (pow_10(8 - exp - i) * x);
+			scale1 = scale1 % pow_10(8 - i);
 		}
-		*val1 = rem * pow_10(6 - exp) + res;
+		*val1 = rem * pow_10(9 - exp) + res;
 	} else {
 		*val0 = scale0;
 		*val1 = scale1;
@@ -332,14 +332,14 @@ int hid_sensor_format_scale(u32 usage_id,
 			unit_conversion[i].unit == attr_info->units) {
 			exp  = hid_sensor_convert_exponent(
 						attr_info->unit_expo);
-			adjust_exponent_micro(val0, val1,
+			adjust_exponent_nano(val0, val1,
 					unit_conversion[i].scale_val0,
 					unit_conversion[i].scale_val1, exp);
 			break;
 		}
 	}
 
-	return IIO_VAL_INT_PLUS_MICRO;
+	return IIO_VAL_INT_PLUS_NANO;
 }
 EXPORT_SYMBOL(hid_sensor_format_scale);
 
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 595511022795..a8db38db622e 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -36,8 +36,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 	s32 poll_value = 0;
 
 	if (state) {
-		if (!atomic_read(&st->user_requested_state))
-			return 0;
 		if (sensor_hub_device_open(st->hsdev))
 			return -EIO;
 
@@ -51,8 +49,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 			st->report_state.report_id,
 			st->report_state.index,
 			HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM);
-
-		poll_value = hid_sensor_read_poll_value(st);
 	} else {
 		int val;
 
@@ -86,10 +82,15 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 				       &report_val);
 	}
 
+	pr_debug("HID_SENSOR %s set power_state %d report_state %d\n",
+		 st->pdev->name, state_val, report_val);
+
 	sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
 			       st->power_state.index,
 			       sizeof(state_val), &state_val);
-	if (state && poll_value)
+	if (state)
+		poll_value = hid_sensor_read_poll_value(st);
+	if (poll_value > 0)
 		msleep_interruptible(poll_value * 2);
 
 	return 0;
@@ -107,6 +108,7 @@ int hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 		ret = pm_runtime_get_sync(&st->pdev->dev);
 	else {
 		pm_runtime_mark_last_busy(&st->pdev->dev);
+		pm_runtime_use_autosuspend(&st->pdev->dev);
 		ret = pm_runtime_put_autosuspend(&st->pdev->dev);
 	}
 	if (ret < 0) {
@@ -175,8 +177,6 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name,
 	/* Default to 3 seconds, but can be changed from sysfs */
 	pm_runtime_set_autosuspend_delay(&attrb->pdev->dev,
 					 3000);
-	pm_runtime_use_autosuspend(&attrb->pdev->dev);
-
 	return ret;
 error_unreg_trigger:
 	iio_trigger_unregister(trig);
diff --git a/drivers/iio/dac/ad7303.c b/drivers/iio/dac/ad7303.c
index e690dd11e99f..4b0f942b8914 100644
--- a/drivers/iio/dac/ad7303.c
+++ b/drivers/iio/dac/ad7303.c
@@ -184,9 +184,9 @@ static const struct iio_chan_spec_ext_info ad7303_ext_info[] = {
 	.address = (chan),					\
 	.scan_type = {						\
 		.sign = 'u',					\
-		.realbits = '8',				\
-		.storagebits = '8',				\
-		.shift = '0',					\
+		.realbits = 8,					\
+		.storagebits = 8,				\
+		.shift = 0,					\
 	},							\
 	.ext_info = ad7303_ext_info,				\
 }
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index 02ff789852a0..90841abd3ce4 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -28,6 +28,7 @@
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/regmap.h>
+#include <linux/delay.h>
 #include "bmg160.h"
 
 #define BMG160_IRQ_NAME		"bmg160_event"
@@ -53,6 +54,9 @@
 #define BMG160_NO_FILTER		0
 #define BMG160_DEF_BW			100
 
+#define BMG160_GYRO_REG_RESET		0x14
+#define BMG160_GYRO_RESET_VAL		0xb6
+
 #define BMG160_REG_INT_MAP_0		0x17
 #define BMG160_INT_MAP_0_BIT_ANY	BIT(1)
 
@@ -186,6 +190,14 @@ static int bmg160_chip_init(struct bmg160_data *data)
 	int ret;
 	unsigned int val;
 
+	/*
+	 * Reset chip to get it in a known good state. A delay of 30ms after
+	 * reset is required according to the datasheet.
+	 */
+	regmap_write(data->regmap, BMG160_GYRO_REG_RESET,
+		     BMG160_GYRO_RESET_VAL);
+	usleep_range(30000, 30700);
+
 	ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val);
 	if (ret < 0) {
 		dev_err(data->dev, "Error reading reg_chip_id\n");
@@ -452,7 +464,7 @@ static int bmg160_get_temp(struct bmg160_data *data, int *val)
 static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val)
 {
 	int ret;
-	unsigned int raw_val;
+	__le16 raw_val;
 
 	mutex_lock(&data->mutex);
 	ret = bmg160_set_power_state(data, true);
@@ -462,7 +474,7 @@ static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val)
 	}
 
 	ret = regmap_bulk_read(data->regmap, BMG160_AXIS_TO_REG(axis), &raw_val,
-			       2);
+			       sizeof(raw_val));
 	if (ret < 0) {
 		dev_err(data->dev, "Error reading axis %d\n", axis);
 		bmg160_set_power_state(data, false);
@@ -470,7 +482,7 @@ static int bmg160_get_axis(struct bmg160_data *data, int axis, int *val)
 		return ret;
 	}
 
-	*val = sign_extend32(raw_val, 15);
+	*val = sign_extend32(le16_to_cpu(raw_val), 15);
 	ret = bmg160_set_power_state(data, false);
 	mutex_unlock(&data->mutex);
 	if (ret < 0)
@@ -733,6 +745,7 @@ static const struct iio_event_spec bmg160_event = {
 		.sign = 's',						\
 		.realbits = 16,					\
 		.storagebits = 16,					\
+		.endianness = IIO_LE,					\
 	},								\
 	.event_spec = &bmg160_event,					\
 	.num_event_specs = 1						\
@@ -780,7 +793,7 @@ static irqreturn_t bmg160_trigger_handler(int irq, void *p)
 			mutex_unlock(&data->mutex);
 			goto err;
 		}
-		data->buffer[i++] = ret;
+		data->buffer[i++] = val;
 	}
 	mutex_unlock(&data->mutex);
 
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index a7f61e881a49..dc5e7e70f951 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -55,7 +55,7 @@ static const struct {
 	},
 	{ /* IIO_HUMIDITYRELATIVE channel */
 		.shift = 8,
-		.mask = 2,
+		.mask = 3,
 	},
 };
 
@@ -164,14 +164,14 @@ static int hdc100x_get_measurement(struct hdc100x_data *data,
 		dev_err(&client->dev, "cannot read high byte measurement");
 		return ret;
 	}
-	val = ret << 6;
+	val = ret << 8;
 
 	ret = i2c_smbus_read_byte(client);
 	if (ret < 0) {
 		dev_err(&client->dev, "cannot read low byte measurement");
 		return ret;
 	}
-	val |= ret >> 2;
+	val |= ret;
 
 	return val;
 }
@@ -211,18 +211,18 @@ static int hdc100x_read_raw(struct iio_dev *indio_dev,
 		return IIO_VAL_INT_PLUS_MICRO;
 	case IIO_CHAN_INFO_SCALE:
 		if (chan->type == IIO_TEMP) {
-			*val = 165;
-			*val2 = 65536 >> 2;
+			*val = 165000;
+			*val2 = 65536;
 			return IIO_VAL_FRACTIONAL;
 		} else {
-			*val = 0;
-			*val2 = 10000;
-			return IIO_VAL_INT_PLUS_MICRO;
+			*val = 100;
+			*val2 = 65536;
+			return IIO_VAL_FRACTIONAL;
 		}
 		break;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = -3971;
-		*val2 = 879096;
+		*val = -15887;
+		*val2 = 515151;
 		return IIO_VAL_INT_PLUS_MICRO;
 	default:
 		return -EINVAL;
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
index 2485b88ee1b6..1880105cc8c4 100644
--- a/drivers/iio/imu/adis16480.c
+++ b/drivers/iio/imu/adis16480.c
@@ -696,7 +696,7 @@ static const struct adis16480_chip_info adis16480_chip_info[] = {
 		.gyro_max_val = IIO_RAD_TO_DEGREE(22500),
 		.gyro_max_scale = 450,
 		.accel_max_val = IIO_M_S_2_TO_G(12500),
-		.accel_max_scale = 5,
+		.accel_max_scale = 10,
 	},
 	[ADIS16485] = {
 		.channels = adis16485_channels,
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 0f6f63b20263..32bb036069eb 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -107,9 +107,10 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf,
 {
 	struct iio_dev *indio_dev = filp->private_data;
 	struct iio_buffer *rb = indio_dev->buffer;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	size_t datum_size;
 	size_t to_wait;
-	int ret;
+	int ret = 0;
 
 	if (!indio_dev->info)
 		return -ENODEV;
@@ -131,19 +132,29 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf,
 	else
 		to_wait = min_t(size_t, n / datum_size, rb->watermark);
 
+	add_wait_queue(&rb->pollq, &wait);
 	do {
-		ret = wait_event_interruptible(rb->pollq,
-		      iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size));
-		if (ret)
-			return ret;
+		if (!indio_dev->info) {
+			ret = -ENODEV;
+			break;
+		}
 
-		if (!indio_dev->info)
-			return -ENODEV;
+		if (!iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size)) {
+			if (signal_pending(current)) {
+				ret = -ERESTARTSYS;
+				break;
+			}
+
+			wait_woken(&wait, TASK_INTERRUPTIBLE,
+				   MAX_SCHEDULE_TIMEOUT);
+			continue;
+		}
 
 		ret = rb->access->read_first_n(rb, n, buf);
 		if (ret == 0 && (filp->f_flags & O_NONBLOCK))
 			ret = -EAGAIN;
-	 } while (ret == 0);
+	} while (ret == 0);
+	remove_wait_queue(&rb->pollq, &wait);
 
 	return ret;
 }
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 159ede61f793..131b434af994 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -433,23 +433,21 @@ ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals)
 		scale_db = true;
 	case IIO_VAL_INT_PLUS_MICRO:
 		if (vals[1] < 0)
-			return sprintf(buf, "-%ld.%06u%s\n", abs(vals[0]),
-					-vals[1],
-				scale_db ? " dB" : "");
+			return sprintf(buf, "-%d.%06u%s\n", abs(vals[0]),
+				       -vals[1], scale_db ? " dB" : "");
 		else
 			return sprintf(buf, "%d.%06u%s\n", vals[0], vals[1],
 				scale_db ? " dB" : "");
 	case IIO_VAL_INT_PLUS_NANO:
 		if (vals[1] < 0)
-			return sprintf(buf, "-%ld.%09u\n", abs(vals[0]),
-					-vals[1]);
+			return sprintf(buf, "-%d.%09u\n", abs(vals[0]),
+				       -vals[1]);
 		else
 			return sprintf(buf, "%d.%09u\n", vals[0], vals[1]);
 	case IIO_VAL_FRACTIONAL:
 		tmp = div_s64((s64)vals[0] * 1000000000LL, vals[1]);
-		vals[1] = do_div(tmp, 1000000000LL);
-		vals[0] = tmp;
-		return sprintf(buf, "%d.%09u\n", vals[0], vals[1]);
+		vals[0] = (int)div_s64_rem(tmp, 1000000000, &vals[1]);
+		return sprintf(buf, "%d.%09u\n", vals[0], abs(vals[1]));
 	case IIO_VAL_FRACTIONAL_LOG2:
 		tmp = (s64)vals[0] * 1000000000LL >> vals[1];
 		vals[1] = do_div(tmp, 1000000000LL);
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index ae2806aafb72..0c52dfe64977 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -210,22 +210,35 @@ static int iio_trigger_attach_poll_func(struct iio_trigger *trig,
 
 	/* Prevent the module from being removed whilst attached to a trigger */
 	__module_get(pf->indio_dev->info->driver_module);
+
+	/* Get irq number */
 	pf->irq = iio_trigger_get_irq(trig);
+	if (pf->irq < 0)
+		goto out_put_module;
+
+	/* Request irq */
 	ret = request_threaded_irq(pf->irq, pf->h, pf->thread,
 				   pf->type, pf->name,
 				   pf);
-	if (ret < 0) {
-		module_put(pf->indio_dev->info->driver_module);
-		return ret;
-	}
+	if (ret < 0)
+		goto out_put_irq;
 
+	/* Enable trigger in driver */
 	if (trig->ops && trig->ops->set_trigger_state && notinuse) {
 		ret = trig->ops->set_trigger_state(trig, true);
 		if (ret < 0)
-			module_put(pf->indio_dev->info->driver_module);
+			goto out_free_irq;
 	}
 
 	return ret;
+
+out_free_irq:
+	free_irq(pf->irq, pf);
+out_put_irq:
+	iio_trigger_put_irq(trig, pf->irq);
+out_put_module:
+	module_put(pf->indio_dev->info->driver_module);
+	return ret;
 }
 
 static int iio_trigger_detach_poll_func(struct iio_trigger *trig,
diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c
index f6a07dc32ae4..4a6d9670e4cd 100644
--- a/drivers/iio/light/apds9960.c
+++ b/drivers/iio/light/apds9960.c
@@ -1005,6 +1005,7 @@ static int apds9960_probe(struct i2c_client *client,
 
 	iio_device_attach_buffer(indio_dev, buffer);
 
+	indio_dev->dev.parent = &client->dev;
 	indio_dev->info = &apds9960_info;
 	indio_dev->name = APDS9960_DRV_NAME;
 	indio_dev->channels = apds9960_channels;
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 6bf89d8f3741..b9d1e5c58ec5 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -74,9 +74,9 @@ static const int int_time_mapping[] = {100000, 50000, 200000, 400000};
 static const struct reg_field reg_field_it =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4);
 static const struct reg_field reg_field_als_intr =
-				REG_FIELD(LTR501_INTR, 0, 0);
-static const struct reg_field reg_field_ps_intr =
 				REG_FIELD(LTR501_INTR, 1, 1);
+static const struct reg_field reg_field_ps_intr =
+				REG_FIELD(LTR501_INTR, 0, 0);
 static const struct reg_field reg_field_als_rate =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2);
 static const struct reg_field reg_field_ps_rate =
diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c
index 12731d6b89ec..ec1b2e798cc1 100644
--- a/drivers/iio/light/tsl2563.c
+++ b/drivers/iio/light/tsl2563.c
@@ -626,7 +626,7 @@ static irqreturn_t tsl2563_event_handler(int irq, void *private)
 	struct tsl2563_chip *chip = iio_priv(dev_info);
 
 	iio_push_event(dev_info,
-		       IIO_UNMOD_EVENT_CODE(IIO_LIGHT,
+		       IIO_UNMOD_EVENT_CODE(IIO_INTENSITY,
 					    0,
 					    IIO_EV_TYPE_THRESH,
 					    IIO_EV_DIR_EITHER),
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index b13936dacc78..f2a7f72f7aa6 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -462,6 +462,8 @@ static int ak8975_setup_irq(struct ak8975_data *data)
 	int rc;
 	int irq;
 
+	init_waitqueue_head(&data->data_ready_queue);
+	clear_bit(0, &data->flags);
 	if (client->irq)
 		irq = client->irq;
 	else
@@ -477,8 +479,6 @@ static int ak8975_setup_irq(struct ak8975_data *data)
 		return rc;
 	}
 
-	init_waitqueue_head(&data->data_ready_queue);
-	clear_bit(0, &data->flags);
 	data->eoc_irq = irq;
 
 	return rc;
@@ -732,7 +732,7 @@ static int ak8975_probe(struct i2c_client *client,
 	int eoc_gpio;
 	int err;
 	const char *name = NULL;
-	enum asahi_compass_chipset chipset;
+	enum asahi_compass_chipset chipset = AK_MAX_TYPE;
 
 	/* Grab and set up the supplied GPIO. */
 	if (client->dev.platform_data)
diff --git a/drivers/iio/magnetometer/st_magn.h b/drivers/iio/magnetometer/st_magn.h
index 06a4d9c35581..9daca4681922 100644
--- a/drivers/iio/magnetometer/st_magn.h
+++ b/drivers/iio/magnetometer/st_magn.h
@@ -44,6 +44,7 @@ static inline int st_magn_allocate_ring(struct iio_dev *indio_dev)
 static inline void st_magn_deallocate_ring(struct iio_dev *indio_dev)
 {
 }
+#define ST_MAGN_TRIGGER_SET_STATE NULL
 #endif /* CONFIG_IIO_BUFFER */
 
 #endif /* ST_MAGN_H */
diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c
index b98b9d94d184..a97e802ca523 100644
--- a/drivers/iio/orientation/hid-sensor-rotation.c
+++ b/drivers/iio/orientation/hid-sensor-rotation.c
@@ -335,6 +335,7 @@ static struct platform_driver hid_dev_rot_platform_driver = {
 	.id_table = hid_dev_rot_ids,
 	.driver = {
 		.name	= KBUILD_MODNAME,
+		.pm     = &hid_sensor_pm_ops,
 	},
 	.probe		= hid_dev_rot_probe,
 	.remove		= hid_dev_rot_remove,
diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c
index a0d7deeac62f..3f90985d545e 100644
--- a/drivers/iio/pressure/mpl115.c
+++ b/drivers/iio/pressure/mpl115.c
@@ -136,6 +136,7 @@ static const struct iio_chan_spec mpl115_channels[] = {
 	{
 		.type = IIO_TEMP,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_shared_by_type =
 			BIT(IIO_CHAN_INFO_OFFSET) | BIT(IIO_CHAN_INFO_SCALE),
 	},
 };
diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c
index 01b2e0b18878..0f5b8767ec2e 100644
--- a/drivers/iio/pressure/mpl3115.c
+++ b/drivers/iio/pressure/mpl3115.c
@@ -182,7 +182,7 @@ static const struct iio_chan_spec mpl3115_channels[] = {
 	{
 		.type = IIO_PRESSURE,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = 0,
 		.scan_type = {
 			.sign = 'u',
@@ -195,7 +195,7 @@ static const struct iio_chan_spec mpl3115_channels[] = {
 	{
 		.type = IIO_TEMP,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-			BIT(IIO_CHAN_INFO_SCALE),
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = 1,
 		.scan_type = {
 			.sign = 's',
diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index b39a2fb0671c..5056bd68573f 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -28,15 +28,21 @@
 #include <linux/iio/common/st_sensors.h>
 #include "st_pressure.h"
 
+#define MCELSIUS_PER_CELSIUS			1000
+
+/* Default pressure sensitivity */
 #define ST_PRESS_LSB_PER_MBAR			4096UL
 #define ST_PRESS_KPASCAL_NANO_SCALE		(100000000UL / \
 						 ST_PRESS_LSB_PER_MBAR)
+
+/* Default temperature sensitivity */
 #define ST_PRESS_LSB_PER_CELSIUS		480UL
-#define ST_PRESS_CELSIUS_NANO_SCALE		(1000000000UL / \
-						 ST_PRESS_LSB_PER_CELSIUS)
+#define ST_PRESS_MILLI_CELSIUS_OFFSET		42500UL
+
 #define ST_PRESS_NUMBER_DATA_CHANNELS		1
 
 /* FULLSCALE */
+#define ST_PRESS_FS_AVL_1100MB			1100
 #define ST_PRESS_FS_AVL_1260MB			1260
 
 #define ST_PRESS_1_OUT_XL_ADDR			0x28
@@ -54,18 +60,20 @@
 #define ST_PRESS_LPS331AP_PW_MASK		0x80
 #define ST_PRESS_LPS331AP_FS_ADDR		0x23
 #define ST_PRESS_LPS331AP_FS_MASK		0x30
-#define ST_PRESS_LPS331AP_FS_AVL_1260_VAL	0x00
-#define ST_PRESS_LPS331AP_FS_AVL_1260_GAIN	ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN	ST_PRESS_CELSIUS_NANO_SCALE
 #define ST_PRESS_LPS331AP_BDU_ADDR		0x20
 #define ST_PRESS_LPS331AP_BDU_MASK		0x04
 #define ST_PRESS_LPS331AP_DRDY_IRQ_ADDR		0x22
 #define ST_PRESS_LPS331AP_DRDY_IRQ_INT1_MASK	0x04
 #define ST_PRESS_LPS331AP_DRDY_IRQ_INT2_MASK	0x20
 #define ST_PRESS_LPS331AP_MULTIREAD_BIT		true
-#define ST_PRESS_LPS331AP_TEMP_OFFSET		42500
 
 /* CUSTOM VALUES FOR LPS001WP SENSOR */
+
+/* LPS001WP pressure resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_MBAR		16UL
+/* LPS001WP temperature resolution */
+#define ST_PRESS_LPS001WP_LSB_PER_CELSIUS	64UL
+
 #define ST_PRESS_LPS001WP_WAI_EXP		0xba
 #define ST_PRESS_LPS001WP_ODR_ADDR		0x20
 #define ST_PRESS_LPS001WP_ODR_MASK		0x30
@@ -74,6 +82,8 @@
 #define ST_PRESS_LPS001WP_ODR_AVL_13HZ_VAL	0x03
 #define ST_PRESS_LPS001WP_PW_ADDR		0x20
 #define ST_PRESS_LPS001WP_PW_MASK		0x40
+#define ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN \
+	(100000000UL / ST_PRESS_LPS001WP_LSB_PER_MBAR)
 #define ST_PRESS_LPS001WP_BDU_ADDR		0x20
 #define ST_PRESS_LPS001WP_BDU_MASK		0x04
 #define ST_PRESS_LPS001WP_MULTIREAD_BIT		true
@@ -90,18 +100,12 @@
 #define ST_PRESS_LPS25H_ODR_AVL_25HZ_VAL	0x04
 #define ST_PRESS_LPS25H_PW_ADDR			0x20
 #define ST_PRESS_LPS25H_PW_MASK			0x80
-#define ST_PRESS_LPS25H_FS_ADDR			0x00
-#define ST_PRESS_LPS25H_FS_MASK			0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_VAL		0x00
-#define ST_PRESS_LPS25H_FS_AVL_1260_GAIN	ST_PRESS_KPASCAL_NANO_SCALE
-#define ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN	ST_PRESS_CELSIUS_NANO_SCALE
 #define ST_PRESS_LPS25H_BDU_ADDR		0x20
 #define ST_PRESS_LPS25H_BDU_MASK		0x04
 #define ST_PRESS_LPS25H_DRDY_IRQ_ADDR		0x23
 #define ST_PRESS_LPS25H_DRDY_IRQ_INT1_MASK	0x01
 #define ST_PRESS_LPS25H_DRDY_IRQ_INT2_MASK	0x10
 #define ST_PRESS_LPS25H_MULTIREAD_BIT		true
-#define ST_PRESS_LPS25H_TEMP_OFFSET		42500
 #define ST_PRESS_LPS25H_OUT_XL_ADDR		0x28
 #define ST_TEMP_LPS25H_OUT_L_ADDR		0x2b
 
@@ -153,7 +157,9 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
 			.storagebits = 16,
 			.endianness = IIO_LE,
 		},
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) |
+			BIT(IIO_CHAN_INFO_SCALE),
 		.modified = 0,
 	},
 	{
@@ -169,7 +175,7 @@ static const struct iio_chan_spec st_press_lps001wp_channels[] = {
 		},
 		.info_mask_separate =
 			BIT(IIO_CHAN_INFO_RAW) |
-			BIT(IIO_CHAN_INFO_OFFSET),
+			BIT(IIO_CHAN_INFO_SCALE),
 		.modified = 0,
 	},
 	IIO_CHAN_SOFT_TIMESTAMP(1)
@@ -204,11 +210,14 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.addr = ST_PRESS_LPS331AP_FS_ADDR,
 			.mask = ST_PRESS_LPS331AP_FS_MASK,
 			.fs_avl = {
+				/*
+				 * Pressure and temperature sensitivity values
+				 * as defined in table 3 of LPS331AP datasheet.
+				 */
 				[0] = {
 					.num = ST_PRESS_FS_AVL_1260MB,
-					.value = ST_PRESS_LPS331AP_FS_AVL_1260_VAL,
-					.gain = ST_PRESS_LPS331AP_FS_AVL_1260_GAIN,
-					.gain2 = ST_PRESS_LPS331AP_FS_AVL_TEMP_GAIN,
+					.gain = ST_PRESS_KPASCAL_NANO_SCALE,
+					.gain2 = ST_PRESS_LSB_PER_CELSIUS,
 				},
 			},
 		},
@@ -248,7 +257,17 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
 		},
 		.fs = {
-			.addr = 0,
+			.fs_avl = {
+				/*
+				 * Pressure and temperature resolution values
+				 * as defined in table 3 of LPS001WP datasheet.
+				 */
+				[0] = {
+					.num = ST_PRESS_FS_AVL_1100MB,
+					.gain = ST_PRESS_LPS001WP_FS_AVL_PRESS_GAIN,
+					.gain2 = ST_PRESS_LPS001WP_LSB_PER_CELSIUS,
+				},
+			},
 		},
 		.bdu = {
 			.addr = ST_PRESS_LPS001WP_BDU_ADDR,
@@ -285,14 +304,15 @@ static const struct st_sensor_settings st_press_sensors_settings[] = {
 			.value_off = ST_SENSORS_DEFAULT_POWER_OFF_VALUE,
 		},
 		.fs = {
-			.addr = ST_PRESS_LPS25H_FS_ADDR,
-			.mask = ST_PRESS_LPS25H_FS_MASK,
 			.fs_avl = {
+				/*
+				 * Pressure and temperature sensitivity values
+				 * as defined in table 3 of LPS25H datasheet.
+				 */
 				[0] = {
 					.num = ST_PRESS_FS_AVL_1260MB,
-					.value = ST_PRESS_LPS25H_FS_AVL_1260_VAL,
-					.gain = ST_PRESS_LPS25H_FS_AVL_1260_GAIN,
-					.gain2 = ST_PRESS_LPS25H_FS_AVL_TEMP_GAIN,
+					.gain = ST_PRESS_KPASCAL_NANO_SCALE,
+					.gain2 = ST_PRESS_LSB_PER_CELSIUS,
 				},
 			},
 		},
@@ -346,26 +366,26 @@ static int st_press_read_raw(struct iio_dev *indio_dev,
 
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
-		*val = 0;
-
 		switch (ch->type) {
 		case IIO_PRESSURE:
+			*val = 0;
 			*val2 = press_data->current_fullscale->gain;
-			break;
+			return IIO_VAL_INT_PLUS_NANO;
 		case IIO_TEMP:
+			*val = MCELSIUS_PER_CELSIUS;
 			*val2 = press_data->current_fullscale->gain2;
-			break;
+			return IIO_VAL_FRACTIONAL;
 		default:
 			err = -EINVAL;
 			goto read_error;
 		}
 
-		return IIO_VAL_INT_PLUS_NANO;
 	case IIO_CHAN_INFO_OFFSET:
 		switch (ch->type) {
 		case IIO_TEMP:
-			*val = 425;
-			*val2 = 10;
+			*val = ST_PRESS_MILLI_CELSIUS_OFFSET *
+			       press_data->current_fullscale->gain2;
+			*val2 = MCELSIUS_PER_CELSIUS;
 			break;
 		default:
 			err = -EINVAL;
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index f4d29d5dbd5f..420478924a0c 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -40,9 +40,9 @@
 #define AS3935_AFE_PWR_BIT	BIT(0)
 
 #define AS3935_INT		0x03
-#define AS3935_INT_MASK		0x07
+#define AS3935_INT_MASK		0x0f
 #define AS3935_EVENT_INT	BIT(3)
-#define AS3935_NOISE_INT	BIT(1)
+#define AS3935_NOISE_INT	BIT(0)
 
 #define AS3935_DATA		0x07
 #define AS3935_DATA_MASK	0x3F
@@ -50,7 +50,6 @@
 #define AS3935_TUNE_CAP		0x08
 #define AS3935_CALIBRATE	0x3D
 
-#define AS3935_WRITE_DATA	BIT(15)
 #define AS3935_READ_DATA	BIT(14)
 #define AS3935_ADDRESS(x)	((x) << 8)
 
@@ -64,6 +63,7 @@ struct as3935_state {
 	struct delayed_work work;
 
 	u32 tune_cap;
+	u8 buffer[16]; /* 8-bit data + 56-bit padding + 64-bit timestamp */
 	u8 buf[2] ____cacheline_aligned;
 };
 
@@ -72,7 +72,8 @@ static const struct iio_chan_spec as3935_channels[] = {
 		.type           = IIO_PROXIMITY,
 		.info_mask_separate =
 			BIT(IIO_CHAN_INFO_RAW) |
-			BIT(IIO_CHAN_INFO_PROCESSED),
+			BIT(IIO_CHAN_INFO_PROCESSED) |
+			BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index     = 0,
 		.scan_type = {
 			.sign           = 'u',
@@ -103,7 +104,7 @@ static int as3935_write(struct as3935_state *st,
 {
 	u8 *buf = st->buf;
 
-	buf[0] = (AS3935_WRITE_DATA | AS3935_ADDRESS(reg)) >> 8;
+	buf[0] = AS3935_ADDRESS(reg) >> 8;
 	buf[1] = val;
 
 	return spi_write(st->spi, buf, 2);
@@ -181,7 +182,12 @@ static int as3935_read_raw(struct iio_dev *indio_dev,
 		/* storm out of range */
 		if (*val == AS3935_DATA_MASK)
 			return -EINVAL;
-		*val *= 1000;
+
+		if (m == IIO_CHAN_INFO_PROCESSED)
+			*val *= 1000;
+		break;
+	case IIO_CHAN_INFO_SCALE:
+		*val = 1000;
 		break;
 	default:
 		return -EINVAL;
@@ -206,10 +212,10 @@ static irqreturn_t as3935_trigger_handler(int irq, void *private)
 	ret = as3935_read(st, AS3935_DATA, &val);
 	if (ret)
 		goto err_read;
-	val &= AS3935_DATA_MASK;
-	val *= 1000;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, &val, pf->timestamp);
+	st->buffer[0] = val & AS3935_DATA_MASK;
+	iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
+					   pf->timestamp);
 err_read:
 	iio_trigger_notify_done(indio_dev->trig);
 
@@ -257,8 +263,6 @@ static irqreturn_t as3935_interrupt_handler(int irq, void *private)
 
 static void calibrate_as3935(struct as3935_state *st)
 {
-	mutex_lock(&st->lock);
-
 	/* mask disturber interrupt bit */
 	as3935_write(st, AS3935_INT, BIT(5));
 
@@ -268,8 +272,6 @@ static void calibrate_as3935(struct as3935_state *st)
 
 	mdelay(2);
 	as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV));
-
-	mutex_unlock(&st->lock);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -306,6 +308,8 @@ static int as3935_resume(struct device *dev)
 	val &= ~AS3935_AFE_PWR_BIT;
 	ret = as3935_write(st, AS3935_AFE_GAIN, val);
 
+	calibrate_as3935(st);
+
 err_resume:
 	mutex_unlock(&st->lock);
 
@@ -385,7 +389,7 @@ static int as3935_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	ret = iio_triggered_buffer_setup(indio_dev, NULL,
+	ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time,
 		&as3935_trigger_handler, NULL);
 
 	if (ret) {
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 34b1adad07aa..6a8024d9d742 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -277,8 +277,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 	fl6.saddr = src_in->sin6_addr;
 	fl6.flowi6_oif = addr->bound_dev_if;
 
-	dst = ip6_route_output(addr->net, NULL, &fl6);
-	if ((ret = dst->error))
+	ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6);
+	if (ret < 0)
 		goto put;
 
 	if (ipv6_addr_any(&fl6.saddr)) {
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index d6d2b3582910..941cd9b83941 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -80,6 +80,8 @@ static struct ib_cm {
 	__be32 random_id_operand;
 	struct list_head timewait_list;
 	struct workqueue_struct *wq;
+	/* Sync on cm change port state */
+	spinlock_t state_lock;
 } cm;
 
 /* Counter indexes ordered by attribute ID */
@@ -161,6 +163,8 @@ struct cm_port {
 	struct ib_mad_agent *mad_agent;
 	struct kobject port_obj;
 	u8 port_num;
+	struct list_head cm_priv_prim_list;
+	struct list_head cm_priv_altr_list;
 	struct cm_counter_group counter_group[CM_COUNTER_GROUPS];
 };
 
@@ -241,6 +245,12 @@ struct cm_id_private {
 	u8 service_timeout;
 	u8 target_ack_delay;
 
+	struct list_head prim_list;
+	struct list_head altr_list;
+	/* Indicates that the send port mad is registered and av is set */
+	int prim_send_port_not_ready;
+	int altr_send_port_not_ready;
+
 	struct list_head work_list;
 	atomic_t work_count;
 };
@@ -259,20 +269,47 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	struct ib_mad_agent *mad_agent;
 	struct ib_mad_send_buf *m;
 	struct ib_ah *ah;
+	struct cm_av *av;
+	unsigned long flags, flags2;
+	int ret = 0;
 
+	/* don't let the port to be released till the agent is down */
+	spin_lock_irqsave(&cm.state_lock, flags2);
+	spin_lock_irqsave(&cm.lock, flags);
+	if (!cm_id_priv->prim_send_port_not_ready)
+		av = &cm_id_priv->av;
+	else if (!cm_id_priv->altr_send_port_not_ready &&
+		 (cm_id_priv->alt_av.port))
+		av = &cm_id_priv->alt_av;
+	else {
+		pr_info("%s: not valid CM id\n", __func__);
+		ret = -ENODEV;
+		spin_unlock_irqrestore(&cm.lock, flags);
+		goto out;
+	}
+	spin_unlock_irqrestore(&cm.lock, flags);
+	/* Make sure the port haven't released the mad yet */
 	mad_agent = cm_id_priv->av.port->mad_agent;
-	ah = ib_create_ah(mad_agent->qp->pd, &cm_id_priv->av.ah_attr);
-	if (IS_ERR(ah))
-		return PTR_ERR(ah);
+	if (!mad_agent) {
+		pr_info("%s: not a valid MAD agent\n", __func__);
+		ret = -ENODEV;
+		goto out;
+	}
+	ah = ib_create_ah(mad_agent->qp->pd, &av->ah_attr);
+	if (IS_ERR(ah)) {
+		ret = PTR_ERR(ah);
+		goto out;
+	}
 
 	m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
-			       cm_id_priv->av.pkey_index,
+			       av->pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
 			       GFP_ATOMIC,
 			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
-		return PTR_ERR(m);
+		ret = PTR_ERR(m);
+		goto out;
 	}
 
 	/* Timeout set by caller if response is expected. */
@@ -282,7 +319,10 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	atomic_inc(&cm_id_priv->refcount);
 	m->context[0] = cm_id_priv;
 	*msg = m;
-	return 0;
+
+out:
+	spin_unlock_irqrestore(&cm.state_lock, flags2);
+	return ret;
 }
 
 static int cm_alloc_response_msg(struct cm_port *port,
@@ -352,7 +392,8 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
 			   grh, &av->ah_attr);
 }
 
-static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
+static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av,
+			      struct cm_id_private *cm_id_priv)
 {
 	struct cm_device *cm_dev;
 	struct cm_port *port = NULL;
@@ -387,7 +428,17 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 			     &av->ah_attr);
 	av->timeout = path->packet_life_time + 1;
 
-	return 0;
+	spin_lock_irqsave(&cm.lock, flags);
+	if (&cm_id_priv->av == av)
+		list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
+	else if (&cm_id_priv->alt_av == av)
+		list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
+	else
+		ret = -EINVAL;
+
+	spin_unlock_irqrestore(&cm.lock, flags);
+
+	return ret;
 }
 
 static int cm_alloc_id(struct cm_id_private *cm_id_priv)
@@ -677,6 +728,8 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 	spin_lock_init(&cm_id_priv->lock);
 	init_completion(&cm_id_priv->comp);
 	INIT_LIST_HEAD(&cm_id_priv->work_list);
+	INIT_LIST_HEAD(&cm_id_priv->prim_list);
+	INIT_LIST_HEAD(&cm_id_priv->altr_list);
 	atomic_set(&cm_id_priv->work_count, -1);
 	atomic_set(&cm_id_priv->refcount, 1);
 	return &cm_id_priv->id;
@@ -892,6 +945,15 @@ retest:
 		break;
 	}
 
+	spin_lock_irq(&cm.lock);
+	if (!list_empty(&cm_id_priv->altr_list) &&
+	    (!cm_id_priv->altr_send_port_not_ready))
+		list_del(&cm_id_priv->altr_list);
+	if (!list_empty(&cm_id_priv->prim_list) &&
+	    (!cm_id_priv->prim_send_port_not_ready))
+		list_del(&cm_id_priv->prim_list);
+	spin_unlock_irq(&cm.lock);
+
 	cm_free_id(cm_id->local_id);
 	cm_deref_id(cm_id_priv);
 	wait_for_completion(&cm_id_priv->comp);
@@ -1192,12 +1254,13 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av,
+				 cm_id_priv);
 	if (ret)
 		goto error1;
 	if (param->alternate_path) {
 		ret = cm_init_av_by_path(param->alternate_path,
-					 &cm_id_priv->alt_av);
+					 &cm_id_priv->alt_av, cm_id_priv);
 		if (ret)
 			goto error1;
 	}
@@ -1639,7 +1702,8 @@ static int cm_req_handler(struct cm_work *work)
 	cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
 
 	memcpy(work->path[0].dmac, cm_id_priv->av.ah_attr.dmac, ETH_ALEN);
-	ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
+	ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av,
+				 cm_id_priv);
 	if (ret) {
 		ib_get_cached_gid(work->port->cm_dev->ib_device,
 				  work->port->port_num, 0, &work->path[0].sgid,
@@ -1650,7 +1714,8 @@ static int cm_req_handler(struct cm_work *work)
 		goto rejected;
 	}
 	if (req_msg->alt_local_lid) {
-		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av);
+		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
+					 cm_id_priv);
 		if (ret) {
 			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
 				       &work->path[0].sgid,
@@ -2705,7 +2770,8 @@ int ib_send_cm_lap(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av);
+	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av,
+				 cm_id_priv);
 	if (ret)
 		goto out;
 	cm_id_priv->alt_av.timeout =
@@ -2817,7 +2883,8 @@ static int cm_lap_handler(struct cm_work *work)
 	cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
 				work->mad_recv_wc->recv_buf.grh,
 				&cm_id_priv->av);
-	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av);
+	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av,
+			   cm_id_priv);
 	ret = atomic_inc_and_test(&cm_id_priv->work_count);
 	if (!ret)
 		list_add_tail(&work->list, &cm_id_priv->work_list);
@@ -3009,7 +3076,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
 		return -EINVAL;
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	ret = cm_init_av_by_path(param->path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->path, &cm_id_priv->av, cm_id_priv);
 	if (ret)
 		goto out;
 
@@ -3430,14 +3497,14 @@ static int cm_establish(struct ib_cm_id *cm_id)
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
 
 	/* Check if the device started its remove_one */
-	spin_lock_irq(&cm.lock);
+	spin_lock_irqsave(&cm.lock, flags);
 	if (!cm_dev->going_down) {
 		queue_delayed_work(cm.wq, &work->work, 0);
 	} else {
 		kfree(work);
 		ret = -ENODEV;
 	}
-	spin_unlock_irq(&cm.lock);
+	spin_unlock_irqrestore(&cm.lock, flags);
 
 out:
 	return ret;
@@ -3446,7 +3513,9 @@ out:
 static int cm_migrate(struct ib_cm_id *cm_id)
 {
 	struct cm_id_private *cm_id_priv;
+	struct cm_av tmp_av;
 	unsigned long flags;
+	int tmp_send_port_not_ready;
 	int ret = 0;
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
@@ -3455,7 +3524,14 @@ static int cm_migrate(struct ib_cm_id *cm_id)
 	    (cm_id->lap_state == IB_CM_LAP_UNINIT ||
 	     cm_id->lap_state == IB_CM_LAP_IDLE)) {
 		cm_id->lap_state = IB_CM_LAP_IDLE;
+		/* Swap address vector */
+		tmp_av = cm_id_priv->av;
 		cm_id_priv->av = cm_id_priv->alt_av;
+		cm_id_priv->alt_av = tmp_av;
+		/* Swap port send ready state */
+		tmp_send_port_not_ready = cm_id_priv->prim_send_port_not_ready;
+		cm_id_priv->prim_send_port_not_ready = cm_id_priv->altr_send_port_not_ready;
+		cm_id_priv->altr_send_port_not_ready = tmp_send_port_not_ready;
 	} else
 		ret = -EINVAL;
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -3875,6 +3951,9 @@ static void cm_add_one(struct ib_device *ib_device)
 		port->cm_dev = cm_dev;
 		port->port_num = i;
 
+		INIT_LIST_HEAD(&port->cm_priv_prim_list);
+		INIT_LIST_HEAD(&port->cm_priv_altr_list);
+
 		ret = cm_create_port_fs(port);
 		if (ret)
 			goto error1;
@@ -3932,6 +4011,8 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 {
 	struct cm_device *cm_dev = client_data;
 	struct cm_port *port;
+	struct cm_id_private *cm_id_priv;
+	struct ib_mad_agent *cur_mad_agent;
 	struct ib_port_modify port_modify = {
 		.clr_port_cap_mask = IB_PORT_CM_SUP
 	};
@@ -3955,15 +4036,27 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
+		/* Mark all the cm_id's as not valid */
+		spin_lock_irq(&cm.lock);
+		list_for_each_entry(cm_id_priv, &port->cm_priv_altr_list, altr_list)
+			cm_id_priv->altr_send_port_not_ready = 1;
+		list_for_each_entry(cm_id_priv, &port->cm_priv_prim_list, prim_list)
+			cm_id_priv->prim_send_port_not_ready = 1;
+		spin_unlock_irq(&cm.lock);
 		/*
 		 * We flush the queue here after the going_down set, this
 		 * verify that no new works will be queued in the recv handler,
 		 * after that we can call the unregister_mad_agent
 		 */
 		flush_workqueue(cm.wq);
-		ib_unregister_mad_agent(port->mad_agent);
+		spin_lock_irq(&cm.state_lock);
+		cur_mad_agent = port->mad_agent;
+		port->mad_agent = NULL;
+		spin_unlock_irq(&cm.state_lock);
+		ib_unregister_mad_agent(cur_mad_agent);
 		cm_remove_port_fs(port);
 	}
+
 	device_unregister(cm_dev->device);
 	kfree(cm_dev);
 }
@@ -3976,6 +4069,7 @@ static int __init ib_cm_init(void)
 	INIT_LIST_HEAD(&cm.device_list);
 	rwlock_init(&cm.device_lock);
 	spin_lock_init(&cm.lock);
+	spin_lock_init(&cm.state_lock);
 	cm.listen_service_table = RB_ROOT;
 	cm.listen_service_id = be64_to_cpu(IB_CM_ASSIGN_SERVICE_ID);
 	cm.remote_id_table = RB_ROOT;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 17a15c56028c..43d5166db4c6 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -857,6 +857,8 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 		} else
 			ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr,
 						 qp_attr_mask);
+		qp_attr->port_num = id_priv->id.port_num;
+		*qp_attr_mask |= IB_QP_PORT;
 	} else
 		ret = -ENOSYS;
 
@@ -2578,7 +2580,8 @@ static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
 	if (!src_addr || !src_addr->sa_family) {
 		src_addr = (struct sockaddr *) &id->route.addr.src_addr;
 		src_addr->sa_family = dst_addr->sa_family;
-		if (dst_addr->sa_family == AF_INET6) {
+		if (IS_ENABLED(CONFIG_IPV6) &&
+		    dst_addr->sa_family == AF_INET6) {
 			struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr;
 			struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr;
 			src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id;
@@ -3348,6 +3351,9 @@ static int cma_accept_iw(struct rdma_id_private *id_priv,
 	struct iw_cm_conn_param iw_param;
 	int ret;
 
+	if (!conn_param)
+		return -EINVAL;
+
 	ret = cma_modify_qp_rtr(id_priv, conn_param);
 	if (ret)
 		return ret;
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 5fb089e91353..fb43a242847b 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -634,6 +634,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 	if (!(ibnl_put_msg(skb, &nlh, 0, 0, nl_client,
 			   RDMA_NL_IWPM_MAPINFO, NLM_F_MULTI))) {
 		pr_warn("%s Unable to put NLMSG_DONE\n", __func__);
+		dev_kfree_skb(skb);
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 2281de122038..8d84c563ba75 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -1745,7 +1745,7 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 			if (!class)
 				goto out;
 			if (convert_mgmt_class(mad_hdr->mgmt_class) >=
-			    IB_MGMT_MAX_METHODS)
+			    ARRAY_SIZE(class->method_table))
 				goto out;
 			method = class->method_table[convert_mgmt_class(
 							mad_hdr->mgmt_class)];
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index bb6685fb08c6..2cd97977b988 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -106,7 +106,6 @@ struct mcast_group {
 	atomic_t		refcount;
 	enum mcast_group_state	state;
 	struct ib_sa_query	*query;
-	int			query_id;
 	u16			pkey_index;
 	u8			leave_state;
 	int			retries;
@@ -339,11 +338,7 @@ static int send_join(struct mcast_group *group, struct mcast_member *member)
 				       member->multicast.comp_mask,
 				       3000, GFP_KERNEL, join_handler, group,
 				       &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }
 
 static int send_leave(struct mcast_group *group, u8 leave_state)
@@ -363,11 +358,7 @@ static int send_leave(struct mcast_group *group, u8 leave_state)
 				       IB_SA_MCMEMBER_REC_JOIN_STATE,
 				       3000, GFP_KERNEL, leave_handler,
 				       group, &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }
 
 static void join_group(struct mcast_group *group, struct mcast_member *member,
@@ -526,8 +517,11 @@ static void join_handler(int status, struct ib_sa_mcmember_rec *rec,
 		process_join_error(group, status);
 	else {
 		int mgids_changed, is_mgid0;
-		ib_find_pkey(group->port->dev->device, group->port->port_num,
-			     be16_to_cpu(rec->pkey), &pkey_index);
+
+		if (ib_find_pkey(group->port->dev->device,
+				 group->port->port_num, be16_to_cpu(rec->pkey),
+				 &pkey_index))
+			pkey_index = MCAST_INVALID_PKEY_INDEX;
 
 		spin_lock_irq(&group->port->lock);
 		if (group->state == MCAST_BUSY &&
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index a95a32ba596e..d3b7ecd106f7 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -534,7 +534,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	data = ibnl_put_msg(skb, &nlh, query->seq, 0, RDMA_NL_LS,
 			    RDMA_NL_LS_OP_RESOLVE, NLM_F_REQUEST);
 	if (!data) {
-		kfree_skb(skb);
+		nlmsg_free(skb);
 		return -EMSGSIZE;
 	}
 
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index b1f37d4095fa..e76d52a203a7 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -863,7 +863,7 @@ err_put:
 	free_port_list_attributes(device);
 
 err_unregister:
-	device_unregister(class_dev);
+	device_del(class_dev);
 
 err:
 	return ret;
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 6b4e8a008bc0..564adf3116e8 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -48,6 +48,7 @@
 
 #include <asm/uaccess.h>
 
+#include <rdma/ib.h>
 #include <rdma/ib_cm.h>
 #include <rdma/ib_user_cm.h>
 #include <rdma/ib_marshall.h>
@@ -1103,6 +1104,9 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf,
 	struct ib_ucm_cmd_hdr hdr;
 	ssize_t result;
 
+	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+		return -EACCES;
+
 	if (len < sizeof(hdr))
 		return -EINVAL;
 
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 8b5a934e1133..886f61ea6cc7 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1574,6 +1574,9 @@ static ssize_t ucma_write(struct file *filp, const char __user *buf,
 	struct rdma_ucm_cmd_hdr hdr;
 	ssize_t ret;
 
+	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+		return -EACCES;
+
 	if (len < sizeof(hdr))
 		return -EINVAL;
 
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 38acb3cfc545..0ae337bec4f2 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -134,6 +134,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
 	if (access & IB_ACCESS_ON_DEMAND) {
+		put_pid(umem->pid);
 		ret = ib_umem_odp_get(context, umem);
 		if (ret) {
 			kfree(umem);
@@ -149,6 +150,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list) {
+		put_pid(umem->pid);
 		kfree(umem);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -175,7 +177,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	cur_base = addr & PAGE_MASK;
 
-	if (npages == 0) {
+	if (npages == 0 || npages > UINT_MAX) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 94bbd8c155fc..a2d19d136099 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -116,6 +116,7 @@ struct ib_uverbs_event_file {
 struct ib_uverbs_file {
 	struct kref				ref;
 	struct mutex				mutex;
+	struct mutex                            cleanup_mutex; /* protect cleanup */
 	struct ib_uverbs_device		       *device;
 	struct ib_ucontext		       *ucontext;
 	struct ib_event_handler			event_handler;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 1c02deab068f..b7a73f1a8beb 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2287,6 +2287,11 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	if ((cmd.attr_mask & IB_QP_PORT) &&
+	    (cmd.port_num < rdma_start_port(ib_dev) ||
+	     cmd.port_num > rdma_end_port(ib_dev)))
+		return -EINVAL;
+
 	INIT_UDATA(&udata, buf + sizeof cmd, NULL, in_len - sizeof cmd,
 		   out_len);
 
@@ -2827,6 +2832,10 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	if (cmd.attr.port_num < rdma_start_port(ib_dev) ||
+	    cmd.attr.port_num > rdma_end_port(ib_dev))
+		return -EINVAL;
+
 	uobj = kmalloc(sizeof *uobj, GFP_KERNEL);
 	if (!uobj)
 		return -ENOMEM;
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index e3ef28861be6..7becef27cbbe 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -48,6 +48,8 @@
 
 #include <asm/uaccess.h>
 
+#include <rdma/ib.h>
+
 #include "uverbs.h"
 
 MODULE_AUTHOR("Roland Dreier");
@@ -242,12 +244,9 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 			container_of(uobj, struct ib_uqp_object, uevent.uobject);
 
 		idr_remove_uobj(&ib_uverbs_qp_idr, uobj);
-		if (qp != qp->real_qp) {
-			ib_close_qp(qp);
-		} else {
+		if (qp == qp->real_qp)
 			ib_uverbs_detach_umcast(qp, uqp);
-			ib_destroy_qp(qp);
-		}
+		ib_destroy_qp(qp);
 		ib_uverbs_release_uevent(file, &uqp->uevent);
 		kfree(uqp);
 	}
@@ -682,6 +681,9 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 	int srcu_key;
 	ssize_t ret;
 
+	if (WARN_ON_ONCE(!ib_safe_file_access(filp)))
+		return -EACCES;
+
 	if (count < sizeof hdr)
 		return -EINVAL;
 
@@ -917,6 +919,7 @@ static int ib_uverbs_open(struct inode *inode, struct file *filp)
 	file->async_file = NULL;
 	kref_init(&file->ref);
 	mutex_init(&file->mutex);
+	mutex_init(&file->cleanup_mutex);
 
 	filp->private_data = file;
 	kobject_get(&dev->kobj);
@@ -942,18 +945,20 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp)
 {
 	struct ib_uverbs_file *file = filp->private_data;
 	struct ib_uverbs_device *dev = file->device;
-	struct ib_ucontext *ucontext = NULL;
+
+	mutex_lock(&file->cleanup_mutex);
+	if (file->ucontext) {
+		ib_uverbs_cleanup_ucontext(file, file->ucontext);
+		file->ucontext = NULL;
+	}
+	mutex_unlock(&file->cleanup_mutex);
 
 	mutex_lock(&file->device->lists_mutex);
-	ucontext = file->ucontext;
-	file->ucontext = NULL;
 	if (!file->is_closed) {
 		list_del(&file->list);
 		file->is_closed = 1;
 	}
 	mutex_unlock(&file->device->lists_mutex);
-	if (ucontext)
-		ib_uverbs_cleanup_ucontext(file, ucontext);
 
 	if (file->async_file)
 		kref_put(&file->async_file->ref, ib_uverbs_release_event_file);
@@ -1167,22 +1172,30 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 	mutex_lock(&uverbs_dev->lists_mutex);
 	while (!list_empty(&uverbs_dev->uverbs_file_list)) {
 		struct ib_ucontext *ucontext;
-
 		file = list_first_entry(&uverbs_dev->uverbs_file_list,
 					struct ib_uverbs_file, list);
 		file->is_closed = 1;
-		ucontext = file->ucontext;
 		list_del(&file->list);
-		file->ucontext = NULL;
 		kref_get(&file->ref);
 		mutex_unlock(&uverbs_dev->lists_mutex);
-		/* We must release the mutex before going ahead and calling
-		 * disassociate_ucontext. disassociate_ucontext might end up
-		 * indirectly calling uverbs_close, for example due to freeing
-		 * the resources (e.g mmput).
-		 */
+
 		ib_uverbs_event_handler(&file->event_handler, &event);
+
+		mutex_lock(&file->cleanup_mutex);
+		ucontext = file->ucontext;
+		file->ucontext = NULL;
+		mutex_unlock(&file->cleanup_mutex);
+
+		/* At this point ib_uverbs_close cannot be running
+		 * ib_uverbs_cleanup_ucontext
+		 */
 		if (ucontext) {
+			/* We must release the mutex before going ahead and
+			 * calling disassociate_ucontext. disassociate_ucontext
+			 * might end up indirectly calling uverbs_close,
+			 * for example due to freeing the resources
+			 * (e.g mmput).
+			 */
 			ib_dev->disassociate_ucontext(ucontext);
 			ib_uverbs_cleanup_ucontext(file, ucontext);
 		}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index de9cd6901752..bc147582bed9 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -162,7 +162,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS,
 				      &cq->bar2_qid,
 				      user ? &cq->bar2_pa : NULL);
-	if (user && !cq->bar2_va) {
+	if (user && !cq->bar2_pa) {
 		pr_warn(MOD "%s: cqid %u not in BAR2 range.\n",
 			pci_name(rdev->lldi.pdev), cq->cqid);
 		ret = -EINVAL;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index aa515afee724..53aa7515f542 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -185,6 +185,10 @@ void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid,
 
 	if (pbar2_pa)
 		*pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK;
+
+	if (is_t4(rdev->lldi.adapter_type))
+		return NULL;
+
 	return rdev->bar2_kva + bar2_qoffset;
 }
 
@@ -270,7 +274,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	/*
 	 * User mode must have bar2 access.
 	 */
-	if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) {
+	if (user && (!wq->sq.bar2_pa || !wq->rq.bar2_pa)) {
 		pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n",
 			pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid);
 		goto free_dma;
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 86af71351d9a..fc21bdbb8b32 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 
 	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
 	ah->av.ib.g_slid  = ah_attr->src_path_bits;
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		ah->av.ib.g_slid   |= 0x80;
 		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.ib.stat_rate;
 	}
-	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
@@ -102,7 +102,10 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 	if (vlan_tag < 0x1000)
 		vlan_tag |= (ah_attr->sl & 7) << 13;
 	ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
-	ah->av.eth.gid_index = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
+	ret = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
+	if (ret < 0)
+		return ERR_PTR(ret);
+	ah->av.eth.gid_index = ret;
 	ah->av.eth.vlan = cpu_to_be16(vlan_tag);
 	if (ah_attr->static_rate) {
 		ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
@@ -110,7 +113,9 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		       !(1 << ah->av.eth.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.eth.stat_rate;
 	}
-
+	ah->av.eth.sl_tclass_flowlabel |=
+			cpu_to_be32((ah_attr->grh.traffic_class << 20) |
+				    ah_attr->grh.flow_label);
 	/*
 	 * HW requires multicast LID so we just choose one.
 	 */
@@ -118,7 +123,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		ah->av.ib.dlid = cpu_to_be16(0xc000);
 
 	memcpy(ah->av.eth.dgid, ah_attr->grh.dgid.raw, 16);
-	ah->av.eth.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 29);
+	ah->av.eth.sl_tclass_flowlabel |= cpu_to_be32(ah_attr->sl << 29);
 
 	return &ah->ibah;
 }
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index b88fc8f5ab18..57e1a08925d9 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -253,11 +253,14 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 	if (context)
 		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof (__u32))) {
 			err = -EFAULT;
-			goto err_dbmap;
+			goto err_cq_free;
 		}
 
 	return &cq->ibcq;
 
+err_cq_free:
+	mlx4_cq_free(dev->dev, &cq->mcq);
+
 err_dbmap:
 	if (context)
 		mlx4_ib_db_unmap_user(to_mucontext(context), &cq->db);
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 870e56b6b25f..d862b9b7910e 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -526,7 +526,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
 	spin_unlock(&tun_qp->tx_lock);
 	if (ret)
-		goto out;
+		goto end;
 
 	tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
 	if (tun_qp->tx_ring[tun_tx_ix].ah)
@@ -595,9 +595,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	wr.wr.send_flags = IB_SEND_SIGNALED;
 
 	ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
-	if (ret)
-		ib_destroy_ah(ah);
+	if (!ret)
+		return 0;
+ out:
+	spin_lock(&tun_qp->tx_lock);
+	tun_qp->tx_ix_tail++;
+	spin_unlock(&tun_qp->tx_lock);
+	tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+	ib_destroy_ah(ah);
 	return ret;
 }
 
@@ -1074,6 +1080,27 @@ void handle_port_mgmt_change_event(struct work_struct *work)
 
 		/* Generate GUID changed event */
 		if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) {
+			if (mlx4_is_master(dev->dev)) {
+				union ib_gid gid;
+				int err = 0;
+
+				if (!eqe->event.port_mgmt_change.params.port_info.gid_prefix)
+					err = __mlx4_ib_query_gid(&dev->ib_dev, port, 0, &gid, 1);
+				else
+					gid.global.subnet_prefix =
+						eqe->event.port_mgmt_change.params.port_info.gid_prefix;
+				if (err) {
+					pr_warn("Could not change QP1 subnet prefix for port %d: query_gid error (%d)\n",
+						port, err);
+				} else {
+					pr_debug("Changing QP1 subnet prefix for port %d. old=0x%llx. new=0x%llx\n",
+						 port,
+						 (u64)atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix),
+						 be64_to_cpu(gid.global.subnet_prefix));
+					atomic64_set(&dev->sriov.demux[port - 1].subnet_prefix,
+						     be64_to_cpu(gid.global.subnet_prefix));
+				}
+			}
 			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
 			/*if master, notify all slaves*/
 			if (mlx4_is_master(dev->dev))
@@ -1278,9 +1305,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 
 	ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+	if (!ret)
+		return 0;
+
+	spin_lock(&sqp->tx_lock);
+	sqp->tx_ix_tail++;
+	spin_unlock(&sqp->tx_lock);
+	sqp->tx_ring[wire_tx_ix].ah = NULL;
 out:
-	if (ret)
-		ib_destroy_ah(ah);
+	ib_destroy_ah(ah);
 	return ret;
 }
 
@@ -2142,6 +2175,8 @@ int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev)
 		if (err)
 			goto demux_err;
 		dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id;
+		atomic64_set(&dev->sriov.demux[i].subnet_prefix,
+			     be64_to_cpu(gid.global.subnet_prefix));
 		err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1,
 				      &dev->sriov.sqps[i]);
 		if (err)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 97d6878f9938..8763fb832b01 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -630,9 +630,11 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	if (err)
 		goto out;
 
-	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ?
-						IB_WIDTH_4X : IB_WIDTH_1X;
-	props->active_speed	= IB_SPEED_QDR;
+	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ||
+				   (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_WIDTH_4X : IB_WIDTH_1X;
+	props->active_speed	=  (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_SPEED_FDR : IB_SPEED_QDR;
 	props->port_cap_flags	= IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
@@ -2401,14 +2403,19 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			goto err_steer_qp_release;
 		}
 
-		bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count);
-
-		err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
-				dev, ibdev->steer_qpn_base,
-				ibdev->steer_qpn_base +
-				ibdev->steer_qpn_count - 1);
-		if (err)
-			goto err_steer_free_bitmap;
+		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
+			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+			err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
+					dev, ibdev->steer_qpn_base,
+					ibdev->steer_qpn_base +
+					ibdev->steer_qpn_count - 1);
+			if (err)
+				goto err_steer_free_bitmap;
+		} else {
+			bitmap_fill(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+		}
 	}
 
 	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
@@ -2484,6 +2491,7 @@ err_counter:
 		mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[i]);
 
 err_map:
+	mlx4_ib_free_eqs(dev, ibdev);
 	iounmap(ibdev->uar_map);
 
 err_uar:
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index 99451d887266..0b5bb0cee6f9 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -489,7 +489,7 @@ static u8 get_leave_state(struct mcast_group *group)
 		if (!group->members[i])
 			leave_state |= (1 << i);
 
-	return leave_state & (group->rec.scope_join_state & 7);
+	return leave_state & (group->rec.scope_join_state & 0xf);
 }
 
 static int join_group(struct mcast_group *group, int slave, u8 join_mask)
@@ -564,8 +564,8 @@ static void mlx4_ib_mcg_timeout_handler(struct work_struct *work)
 		} else
 			mcg_warn_group(group, "DRIVER BUG\n");
 	} else if (group->state == MCAST_LEAVE_SENT) {
-		if (group->rec.scope_join_state & 7)
-			group->rec.scope_join_state &= 0xf8;
+		if (group->rec.scope_join_state & 0xf)
+			group->rec.scope_join_state &= 0xf0;
 		group->state = MCAST_IDLE;
 		mutex_unlock(&group->lock);
 		if (release_group(group, 1))
@@ -605,7 +605,7 @@ static int handle_leave_req(struct mcast_group *group, u8 leave_mask,
 static int handle_join_req(struct mcast_group *group, u8 join_mask,
 			   struct mcast_req *req)
 {
-	u8 group_join_state = group->rec.scope_join_state & 7;
+	u8 group_join_state = group->rec.scope_join_state & 0xf;
 	int ref = 0;
 	u16 status;
 	struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
@@ -690,8 +690,8 @@ static void mlx4_ib_mcg_work_handler(struct work_struct *work)
 			u8 cur_join_state;
 
 			resp_join_state = ((struct ib_sa_mcmember_data *)
-						group->response_sa_mad.data)->scope_join_state & 7;
-			cur_join_state = group->rec.scope_join_state & 7;
+						group->response_sa_mad.data)->scope_join_state & 0xf;
+			cur_join_state = group->rec.scope_join_state & 0xf;
 
 			if (method == IB_MGMT_METHOD_GET_RESP) {
 				/* successfull join */
@@ -710,7 +710,7 @@ process_requests:
 		req = list_first_entry(&group->pending_list, struct mcast_req,
 				       group_list);
 		sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
-		req_join_state = sa_data->scope_join_state & 0x7;
+		req_join_state = sa_data->scope_join_state & 0xf;
 
 		/* For a leave request, we will immediately answer the VF, and
 		 * update our internal counters. The actual leave will be sent
@@ -1105,7 +1105,8 @@ static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy
 	while ((p = rb_first(&ctx->mcg_table)) != NULL) {
 		group = rb_entry(p, struct mcast_group, node);
 		if (atomic_read(&group->refcount))
-			mcg_warn_group(group, "group refcount %d!!! (pointer %p)\n", atomic_read(&group->refcount), group);
+			mcg_debug_group(group, "group refcount %d!!! (pointer %p)\n",
+					atomic_read(&group->refcount), group);
 
 		force_clean_group(group);
 	}
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 1caa11edac03..78f29e91653a 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -441,7 +441,7 @@ struct mlx4_ib_demux_ctx {
 	struct workqueue_struct *wq;
 	struct workqueue_struct *ud_wq;
 	spinlock_t ud_lock;
-	__be64 subnet_prefix;
+	atomic64_t subnet_prefix;
 	__be64 guid_cache[128];
 	struct mlx4_ib_dev *dev;
 	/* the following lock protects both mcg_table and mcg_mgid0_list */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 13eaaf45288f..1c8b7c22c822 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -357,7 +357,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_RC:
 		return sizeof (struct mlx4_wqe_ctrl_seg) +
-			sizeof (struct mlx4_wqe_atomic_seg) +
+			sizeof (struct mlx4_wqe_masked_atomic_seg) +
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_SMI:
 	case MLX4_IB_QPT_GSI:
@@ -1162,8 +1162,10 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
 				       udata, 0, &qp, gfp);
-		if (err)
+		if (err) {
+			kfree(qp);
 			return ERR_PTR(err);
+		}
 
 		qp->ibqp.qp_num = qp->mqp.qpn;
 		qp->xrcdn = xrcdn;
@@ -1205,7 +1207,8 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp)
 	if (is_qp0(dev, mqp))
 		mlx4_CLOSE_PORT(dev->dev, mqp->port);
 
-	if (dev->qp1_proxy[mqp->port - 1] == mqp) {
+	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI &&
+	    dev->qp1_proxy[mqp->port - 1] == mqp) {
 		mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
 		dev->qp1_proxy[mqp->port - 1] = NULL;
 		mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
@@ -2329,24 +2332,27 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
 		sqp->ud_header.grh.flow_label    =
 			ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
 		sqp->ud_header.grh.hop_limit     = ah->av.ib.hop_limit;
-		if (is_eth)
+		if (is_eth) {
 			memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
-		else {
-		if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
-			/* When multi-function is enabled, the ib_core gid
-			 * indexes don't necessarily match the hw ones, so
-			 * we must use our own cache */
-			sqp->ud_header.grh.source_gid.global.subnet_prefix =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-						       subnet_prefix;
-			sqp->ud_header.grh.source_gid.global.interface_id =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-					       guid_cache[ah->av.ib.gid_index];
-		} else
-			ib_get_cached_gid(ib_dev,
-					  be32_to_cpu(ah->av.ib.port_pd) >> 24,
-					  ah->av.ib.gid_index,
-					  &sqp->ud_header.grh.source_gid, NULL);
+		} else {
+			if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
+				/* When multi-function is enabled, the ib_core gid
+				 * indexes don't necessarily match the hw ones, so
+				 * we must use our own cache
+				 */
+				sqp->ud_header.grh.source_gid.global.subnet_prefix =
+					cpu_to_be64(atomic64_read(&(to_mdev(ib_dev)->sriov.
+								    demux[sqp->qp.port - 1].
+								    subnet_prefix)));
+				sqp->ud_header.grh.source_gid.global.interface_id =
+					to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
+						       guid_cache[ah->av.ib.gid_index];
+			} else {
+				ib_get_cached_gid(ib_dev,
+						  be32_to_cpu(ah->av.ib.port_pd) >> 24,
+						  ah->av.ib.gid_index,
+						  &sqp->ud_header.grh.source_gid, NULL);
+			}
 		}
 		memcpy(sqp->ud_header.grh.destination_gid.raw,
 		       ah->av.ib.dgid, 16);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 92ddae101ecc..02c8deab1fff 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -763,7 +763,8 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 	if (attr->flags)
 		return ERR_PTR(-EINVAL);
 
-	if (entries < 0)
+	if (entries < 0 ||
+	    (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
 		return ERR_PTR(-EINVAL);
 
 	entries = roundup_pow_of_two(entries + 1);
@@ -786,8 +787,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 		if (err)
 			goto err_create;
 	} else {
-		/* for now choose 64 bytes till we have a proper interface */
-		cqe_size = 64;
+		cqe_size = cache_line_size() == 128 ? 128 : 64;
 		err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb,
 				       &index, &inlen);
 		if (err)
@@ -1094,11 +1094,16 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		return -ENOSYS;
 	}
 
-	if (entries < 1)
+	if (entries < 1 ||
+	    entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
+		mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
+			     entries,
+			     1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
 		return -EINVAL;
+	}
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries >  (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
+	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
 		return -EINVAL;
 
 	if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c4e091528390..2a1fdcaa3044 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -273,7 +273,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		     sizeof(struct mlx5_wqe_ctrl_seg)) /
 		     sizeof(struct mlx5_wqe_data_seg);
 	props->max_sge = min(max_rq_sg, max_sq_sg);
-	props->max_sge_rd = props->max_sge;
+	props->max_sge_rd	   = MLX5_MAX_SGE_RD;
 	props->max_cq		   = 1 << MLX5_CAP_GEN(mdev, log_max_cq);
 	props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1;
 	props->max_mr		   = 1 << MLX5_CAP_GEN(mdev, log_max_mkey);
@@ -405,8 +405,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *rep;
-	int max_mtu;
-	int oper_mtu;
+	u16 max_mtu;
+	u16 oper_mtu;
 	int err;
 	u8 ib_link_width_oper;
 	u8 vl_hw_cap;
@@ -947,13 +947,13 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 {
 	struct mlx5_ib_dev *ibdev = (struct mlx5_ib_dev *)context;
 	struct ib_event ibev;
-
+	bool fatal = false;
 	u8 port = 0;
 
 	switch (event) {
 	case MLX5_DEV_EVENT_SYS_ERROR:
-		ibdev->ib_active = false;
 		ibev.event = IB_EVENT_DEVICE_FATAL;
+		fatal = true;
 		break;
 
 	case MLX5_DEV_EVENT_PORT_UP:
@@ -962,14 +962,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 		break;
 
 	case MLX5_DEV_EVENT_PORT_DOWN:
+	case MLX5_DEV_EVENT_PORT_INITIALIZED:
 		ibev.event = IB_EVENT_PORT_ERR;
 		port = (u8)param;
 		break;
 
-	case MLX5_DEV_EVENT_PORT_INITIALIZED:
-		/* not used by ULPs */
-		return;
-
 	case MLX5_DEV_EVENT_LID_CHANGE:
 		ibev.event = IB_EVENT_LID_CHANGE;
 		port = (u8)param;
@@ -1001,6 +998,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 	if (ibdev->ib_active)
 		ib_dispatch_event(&ibev);
+
+	if (fatal)
+		ibdev->ib_active = false;
 }
 
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 6000f7aeede9..3399271c235b 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -614,6 +614,33 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 	return 0;
 }
 
+static void wait_for_async_commands(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_mr_cache *cache = &dev->cache;
+	struct mlx5_cache_ent *ent;
+	int total = 0;
+	int i;
+	int j;
+
+	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
+		ent = &cache->ent[i];
+		for (j = 0 ; j < 1000; j++) {
+			if (!ent->pending)
+				break;
+			msleep(50);
+		}
+	}
+	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
+		ent = &cache->ent[i];
+		total += ent->pending;
+	}
+
+	if (total)
+		mlx5_ib_warn(dev, "aborted while there are %d pending mr requests\n", total);
+	else
+		mlx5_ib_warn(dev, "done with all pending requests\n");
+}
+
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 {
 	int i;
@@ -627,6 +654,7 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 		clean_keys(dev, i);
 
 	destroy_workqueue(dev->cache.wq);
+	wait_for_async_commands(dev);
 	del_timer_sync(&dev->delay_timer);
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 307bdbca8938..cfcfbb6b84d7 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -226,6 +226,8 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 		qp->rq.max_gs = 0;
 		qp->rq.wqe_cnt = 0;
 		qp->rq.wqe_shift = 0;
+		cap->max_recv_wr = 0;
+		cap->max_recv_sge = 0;
 	} else {
 		if (ucmd) {
 			qp->rq.wqe_cnt = ucmd->rq_wqe_count;
@@ -2525,10 +2527,11 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
 			return MLX5_FENCE_MODE_SMALL_AND_FENCE;
 		else
 			return fence;
-
-	} else {
-		return 0;
+	} else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+		return MLX5_FENCE_MODE_FENCE;
 	}
+
+	return 0;
 }
 
 static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
@@ -3092,17 +3095,19 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
 
 	if (!ibqp->uobject) {
-		qp_attr->cap.max_send_wr  = qp->sq.wqe_cnt;
+		qp_attr->cap.max_send_wr  = qp->sq.max_post;
 		qp_attr->cap.max_send_sge = qp->sq.max_gs;
+		qp_init_attr->qp_context = ibqp->qp_context;
 	} else {
 		qp_attr->cap.max_send_wr  = 0;
 		qp_attr->cap.max_send_sge = 0;
 	}
 
-	/* We don't support inline sends for kernel QPs (yet), and we
-	 * don't know what userspace's value should be.
-	 */
-	qp_attr->cap.max_inline_data = 0;
+	qp_init_attr->qp_type = ibqp->qp_type;
+	qp_init_attr->recv_cq = ibqp->recv_cq;
+	qp_init_attr->send_cq = ibqp->send_cq;
+	qp_init_attr->srq = ibqp->srq;
+	qp_attr->cap.max_inline_data = qp->max_inline_data;
 
 	qp_init_attr->cap	     = qp_attr->cap;
 
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index e449e394963f..24f4a782e0f4 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -45,6 +45,8 @@
 #include <linux/export.h>
 #include <linux/uio.h>
 
+#include <rdma/ib.h>
+
 #include "qib.h"
 #include "qib_common.h"
 #include "qib_user_sdma.h"
@@ -2067,6 +2069,9 @@ static ssize_t qib_write(struct file *fp, const char __user *data,
 	ssize_t ret = 0;
 	void *dest;
 
+	if (WARN_ON_ONCE(!ib_safe_file_access(fp)))
+		return -EACCES;
+
 	if (count < sizeof(cmd.type)) {
 		ret = -EINVAL;
 		goto bail;
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 3eff35c2d453..2684605fe67f 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -41,13 +41,13 @@
 
 #include "qib.h"
 
-#define BITS_PER_PAGE           (PAGE_SIZE*BITS_PER_BYTE)
-#define BITS_PER_PAGE_MASK      (BITS_PER_PAGE-1)
+#define RVT_BITS_PER_PAGE           (PAGE_SIZE*BITS_PER_BYTE)
+#define RVT_BITS_PER_PAGE_MASK      (RVT_BITS_PER_PAGE-1)
 
 static inline unsigned mk_qpn(struct qib_qpn_table *qpt,
 			      struct qpn_map *map, unsigned off)
 {
-	return (map - qpt->map) * BITS_PER_PAGE + off;
+	return (map - qpt->map) * RVT_BITS_PER_PAGE + off;
 }
 
 static inline unsigned find_next_offset(struct qib_qpn_table *qpt,
@@ -59,7 +59,7 @@ static inline unsigned find_next_offset(struct qib_qpn_table *qpt,
 		if (((off & qpt->mask) >> 1) >= n)
 			off = (off | qpt->mask) + 2;
 	} else
-		off = find_next_zero_bit(map->page, BITS_PER_PAGE, off);
+		off = find_next_zero_bit(map->page, RVT_BITS_PER_PAGE, off);
 	return off;
 }
 
@@ -147,8 +147,8 @@ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt,
 		qpn = 2;
 	if (qpt->mask && ((qpn & qpt->mask) >> 1) >= dd->n_krcv_queues)
 		qpn = (qpn | qpt->mask) + 2;
-	offset = qpn & BITS_PER_PAGE_MASK;
-	map = &qpt->map[qpn / BITS_PER_PAGE];
+	offset = qpn & RVT_BITS_PER_PAGE_MASK;
+	map = &qpt->map[qpn / RVT_BITS_PER_PAGE];
 	max_scan = qpt->nmaps - !offset;
 	for (i = 0;;) {
 		if (unlikely(!map->page)) {
@@ -173,7 +173,7 @@ static int alloc_qpn(struct qib_devdata *dd, struct qib_qpn_table *qpt,
 			 * We just need to be sure we don't loop
 			 * forever.
 			 */
-		} while (offset < BITS_PER_PAGE && qpn < QPN_MAX);
+		} while (offset < RVT_BITS_PER_PAGE && qpn < QPN_MAX);
 		/*
 		 * In order to keep the number of pages allocated to a
 		 * minimum, we scan the all existing pages before increasing
@@ -204,9 +204,9 @@ static void free_qpn(struct qib_qpn_table *qpt, u32 qpn)
 {
 	struct qpn_map *map;
 
-	map = qpt->map + qpn / BITS_PER_PAGE;
+	map = qpt->map + qpn / RVT_BITS_PER_PAGE;
 	if (map->page)
-		clear_bit(qpn & BITS_PER_PAGE_MASK, map->page);
+		clear_bit(qpn & RVT_BITS_PER_PAGE_MASK, map->page);
 }
 
 static inline unsigned qpn_hash(struct qib_ibdev *dev, u32 qpn)
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index e6b7556d5221..cbc4216091c9 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -2088,8 +2088,10 @@ send_last:
 		ret = qib_get_rwqe(qp, 1);
 		if (ret < 0)
 			goto nack_op_err;
-		if (!ret)
+		if (!ret) {
+			qib_put_ss(&qp->r_sge);
 			goto rnr_nak;
+		}
 		wc.ex.imm_data = ohdr->u.rc.imm_data;
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 3ede10309754..07cfcc326863 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
 
 enum {
 	IPOIB_ENCAP_LEN		  = 4,
+	IPOIB_PSEUDO_LEN	  = 20,
+	IPOIB_HARD_LEN		  = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
 
 	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
 	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */
@@ -131,15 +133,21 @@ struct ipoib_header {
 	u16	reserved;
 };
 
-struct ipoib_cb {
-	struct qdisc_skb_cb	qdisc_cb;
-	u8			hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+	u8	hwaddr[INFINIBAND_ALEN];
 };
 
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
-	return (struct ipoib_cb *)skb->cb;
+	char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+	/*
+	 * only the ipoib header is present now, make room for a dummy
+	 * pseudo header and set skb field accordingly
+	 */
+	memset(data, 0, IPOIB_PSEUDO_LEN);
+	skb_reset_mac_header(skb);
+	skb_pull(skb, IPOIB_HARD_LEN);
 }
 
 /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
@@ -472,6 +480,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		struct ipoib_ah *address, u32 qpn);
 void ipoib_reap_ah(struct work_struct *work);
 
+struct ipoib_path *__path_find(struct net_device *dev, void *gid);
 void ipoib_mark_paths_invalid(struct net_device *dev);
 void ipoib_flush_paths(struct net_device *dev);
 struct ipoib_dev_priv *ipoib_intf_alloc(const char *format);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 3ae9726efb98..2018d24344de 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
 #define IPOIB_CM_RX_DELAY       (3 * 256 * HZ)
 #define IPOIB_CM_RX_UPDATE_MASK (0x3)
 
+#define IPOIB_CM_RX_RESERVE     (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
 static struct ib_qp_attr ipoib_cm_err_attr = {
 	.qp_state = IB_QPS_ERR
 };
@@ -147,15 +149,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
 	struct sk_buff *skb;
 	int i;
 
-	skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+	skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+	 * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
 	 * IP header to a multiple of 16.
 	 */
-	skb_reserve(skb, 12);
+	skb_reserve(skb, IPOIB_CM_RX_RESERVE);
 
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
 				       DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	if (wc->byte_len < IPOIB_CM_COPYBREAK) {
 		int dlen = wc->byte_len;
 
-		small_skb = dev_alloc_skb(dlen + 12);
+		small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
 		if (small_skb) {
-			skb_reserve(small_skb, 12);
+			skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
 			ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
 						   dlen, DMA_FROM_DEVICE);
 			skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 copied:
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
@@ -1035,8 +1036,6 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 
 	tx_qp = ib_create_qp(priv->pd, &attr);
 	if (PTR_ERR(tx_qp) == -EINVAL) {
-		ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
-			   priv->ca->name);
 		attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
 		tx_qp = ib_create_qp(priv->pd, &attr);
 	}
@@ -1299,6 +1298,8 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx)
 	}
 }
 
+#define QPN_AND_OPTIONS_OFFSET	4
+
 static void ipoib_cm_tx_start(struct work_struct *work)
 {
 	struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
@@ -1307,6 +1308,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 	struct ipoib_neigh *neigh;
 	struct ipoib_cm_tx *p;
 	unsigned long flags;
+	struct ipoib_path *path;
 	int ret;
 
 	struct ib_sa_path_rec pathrec;
@@ -1319,7 +1321,19 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 		p = list_entry(priv->cm.start_list.next, typeof(*p), list);
 		list_del_init(&p->list);
 		neigh = p->neigh;
+
 		qpn = IPOIB_QPN(neigh->daddr);
+		/*
+		 * As long as the search is with these 2 locks,
+		 * path existence indicates its validity.
+		 */
+		path = __path_find(dev, neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+		if (!path) {
+			pr_info("%s ignore not valid path %pI6\n",
+				__func__,
+				neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+			goto free_neigh;
+		}
 		memcpy(&pathrec, &p->path->pathrec, sizeof pathrec);
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1331,6 +1345,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
 		spin_lock_irqsave(&priv->lock, flags);
 
 		if (ret) {
+free_neigh:
 			neigh = p->neigh;
 			if (neigh) {
 				neigh->cm = NULL;
@@ -1473,12 +1488,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 
 	ret = ipoib_set_mode(dev, buf);
 
-	rtnl_unlock();
-
-	if (!ret)
-		return count;
+	/* The assumption is that the function ipoib_set_mode returned
+	 * with the rtnl held by it, if not the value -EBUSY returned,
+	 * then no need to rtnl_unlock
+	 */
+	if (ret != -EBUSY)
+		rtnl_unlock();
 
-	return ret;
+	return (!ret || ret == -EBUSY) ? count : ret;
 }
 
 static DEVICE_ATTR(mode, S_IWUSR | S_IRUGO, show_mode, set_mode);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c
index 6bd5740e2691..09396bd7b02d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c
@@ -281,8 +281,11 @@ void ipoib_delete_debug_files(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	WARN_ONCE(!priv->mcg_dentry, "null mcg debug file\n");
+	WARN_ONCE(!priv->path_dentry, "null path debug file\n");
 	debugfs_remove(priv->mcg_dentry);
 	debugfs_remove(priv->path_dentry);
+	priv->mcg_dentry = priv->path_dentry = NULL;
 }
 
 int ipoib_register_debugfs(void)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5ea0c14070d1..8f8c3af9f4e8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -130,16 +130,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 
 	buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
 
-	skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+	skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
-	 * header.  So we need 4 more bytes to get to 48 and align the
-	 * IP header to a multiple of 16.
+	 * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+	 * 64 bytes aligned
 	 */
-	skb_reserve(skb, 4);
+	skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
 
 	mapping = priv->rx_ring[id].mapping;
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -242,10 +241,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
-
-	skb->truesize = SKB_TRUESIZE(skb->len);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
@@ -1030,8 +1026,17 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	}
 
 	if (level == IPOIB_FLUSH_LIGHT) {
+		int oper_up;
 		ipoib_mark_paths_invalid(dev);
+		/* Set IPoIB operation as down to prevent races between:
+		 * the flush flow which leaves MCG and on the fly joins
+		 * which can happen during that time. mcast restart task
+		 * should deal with join requests we missed.
+		 */
+		oper_up = test_and_clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 		ipoib_mcast_dev_flush(dev);
+		if (oper_up)
+			set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 		ipoib_flush_ah(dev);
 	}
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 7d3281866ffc..6699ecd855f0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -106,6 +106,33 @@ static struct ib_client ipoib_client = {
 	.get_net_dev_by_params = ipoib_get_net_dev_by_params,
 };
 
+#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
+static int ipoib_netdev_event(struct notifier_block *this,
+			      unsigned long event, void *ptr)
+{
+	struct netdev_notifier_info *ni = ptr;
+	struct net_device *dev = ni->dev;
+
+	if (dev->netdev_ops->ndo_open != ipoib_open)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		ipoib_create_debug_files(dev);
+		break;
+	case NETDEV_CHANGENAME:
+		ipoib_delete_debug_files(dev);
+		ipoib_create_debug_files(dev);
+		break;
+	case NETDEV_UNREGISTER:
+		ipoib_delete_debug_files(dev);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+#endif
+
 int ipoib_open(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -464,8 +491,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 
 		ipoib_flush_paths(dev);
-		rtnl_lock();
-		return 0;
+		return (!rtnl_trylock()) ? -EBUSY : 0;
 	}
 
 	if (!strcmp(buf, "datagram\n")) {
@@ -474,14 +500,13 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
 		rtnl_unlock();
 		ipoib_flush_paths(dev);
-		rtnl_lock();
-		return 0;
+		return (!rtnl_trylock()) ? -EBUSY : 0;
 	}
 
 	return -EINVAL;
 }
 
-static struct ipoib_path *__path_find(struct net_device *dev, void *gid)
+struct ipoib_path *__path_find(struct net_device *dev, void *gid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->path_tree.rb_node;
@@ -628,6 +653,14 @@ void ipoib_mark_paths_invalid(struct net_device *dev)
 	spin_unlock_irq(&priv->lock);
 }
 
+static void push_pseudo_header(struct sk_buff *skb, const char *daddr)
+{
+	struct ipoib_pseudo_header *phdr;
+
+	phdr = (struct ipoib_pseudo_header *)skb_push(skb, sizeof(*phdr));
+	memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
+}
+
 void ipoib_flush_paths(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -850,9 +883,11 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 				ipoib_neigh_free(neigh);
 				goto err_drop;
 			}
-			if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+			if (skb_queue_len(&neigh->queue) <
+			    IPOIB_MAX_PATH_REC_QUEUE) {
+				push_pseudo_header(skb, neigh->daddr);
 				__skb_queue_tail(&neigh->queue, skb);
-			else {
+			} else {
 				ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
 					   skb_queue_len(&neigh->queue));
 				goto err_drop;
@@ -868,10 +903,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 
 		if (!path->query && path_rec_start(dev, path))
 			goto err_path;
-		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+			push_pseudo_header(skb, neigh->daddr);
 			__skb_queue_tail(&neigh->queue, skb);
-		else
+		} else {
 			goto err_drop;
+		}
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
@@ -889,7 +926,7 @@ err_drop:
 }
 
 static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
-			     struct ipoib_cb *cb)
+			     struct ipoib_pseudo_header *phdr)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_path *path;
@@ -897,16 +934,17 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	path = __path_find(dev, cb->hwaddr + 4);
+	path = __path_find(dev, phdr->hwaddr + 4);
 	if (!path || !path->valid) {
 		int new_path = 0;
 
 		if (!path) {
-			path = path_rec_create(dev, cb->hwaddr + 4);
+			path = path_rec_create(dev, phdr->hwaddr + 4);
 			new_path = 1;
 		}
 		if (path) {
 			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+				push_pseudo_header(skb, phdr->hwaddr);
 				__skb_queue_tail(&path->queue, skb);
 			} else {
 				++dev->stats.tx_dropped;
@@ -934,10 +972,11 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			  be16_to_cpu(path->pathrec.dlid));
 
 		spin_unlock_irqrestore(&priv->lock, flags);
-		ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
 		return;
 	} else if ((path->query || !path_rec_start(dev, path)) &&
 		   skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		push_pseudo_header(skb, phdr->hwaddr);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
 		++dev->stats.tx_dropped;
@@ -951,13 +990,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_neigh *neigh;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
+	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
 	unsigned long flags;
 
+	phdr = (struct ipoib_pseudo_header *) skb->data;
+	skb_pull(skb, sizeof(*phdr));
 	header = (struct ipoib_header *) skb->data;
 
-	if (unlikely(cb->hwaddr[4] == 0xff)) {
+	if (unlikely(phdr->hwaddr[4] == 0xff)) {
 		/* multicast, arrange "if" according to probability */
 		if ((header->proto != htons(ETH_P_IP)) &&
 		    (header->proto != htons(ETH_P_IPV6)) &&
@@ -970,13 +1011,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_OK;
 		}
 		/* Add in the P_Key for multicast*/
-		cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
-		cb->hwaddr[9] = priv->pkey & 0xff;
+		phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+		phdr->hwaddr[9] = priv->pkey & 0xff;
 
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (likely(neigh))
 			goto send_using_neigh;
-		ipoib_mcast_send(dev, cb->hwaddr, skb);
+		ipoib_mcast_send(dev, phdr->hwaddr, skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -985,16 +1026,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_IP):
 	case htons(ETH_P_IPV6):
 	case htons(ETH_P_TIPC):
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (unlikely(!neigh)) {
-			neigh_add_path(skb, cb->hwaddr, dev);
+			neigh_add_path(skb, phdr->hwaddr, dev);
 			return NETDEV_TX_OK;
 		}
 		break;
 	case htons(ETH_P_ARP):
 	case htons(ETH_P_RARP):
 		/* for unicast ARP and RARP should always perform path find */
-		unicast_arp_send(skb, dev, cb);
+		unicast_arp_send(skb, dev, phdr);
 		return NETDEV_TX_OK;
 	default:
 		/* ethertype not supported by IPoIB */
@@ -1011,11 +1052,12 @@ send_using_neigh:
 			goto unref;
 		}
 	} else if (neigh->ah) {
-		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
 		goto unref;
 	}
 
 	if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		push_pseudo_header(skb, phdr->hwaddr);
 		spin_lock_irqsave(&priv->lock, flags);
 		__skb_queue_tail(&neigh->queue, skb);
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1048,7 +1090,6 @@ static int ipoib_hard_header(struct sk_buff *skb,
 			     const void *daddr, const void *saddr, unsigned len)
 {
 	struct ipoib_header *header;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
 
 	header = (struct ipoib_header *) skb_push(skb, sizeof *header);
 
@@ -1057,12 +1098,12 @@ static int ipoib_hard_header(struct sk_buff *skb,
 
 	/*
 	 * we don't rely on dst_entry structure,  always stuff the
-	 * destination address into skb->cb so we can figure out where
+	 * destination address into skb hard header so we can figure out where
 	 * to send the packet later.
 	 */
-	memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+	push_pseudo_header(skb, daddr);
 
-	return sizeof *header;
+	return IPOIB_HARD_LEN;
 }
 
 static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1131,7 +1172,9 @@ struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr)
 				neigh = NULL;
 				goto out_unlock;
 			}
-			neigh->alive = jiffies;
+
+			if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE))
+				neigh->alive = jiffies;
 			goto out_unlock;
 		}
 	}
@@ -1579,8 +1622,6 @@ void ipoib_dev_cleanup(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	ipoib_delete_debug_files(dev);
-
 	/* Delete any child interfaces first */
 	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
 		/* Stop GC on child */
@@ -1636,7 +1677,7 @@ void ipoib_setup(struct net_device *dev)
 
 	dev->flags		|= IFF_BROADCAST | IFF_MULTICAST;
 
-	dev->hard_header_len	 = IPOIB_ENCAP_LEN;
+	dev->hard_header_len	 = IPOIB_HARD_LEN;
 	dev->addr_len		 = INFINIBAND_ALEN;
 	dev->type		 = ARPHRD_INFINIBAND;
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
@@ -1892,8 +1933,6 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto register_failed;
 	}
 
-	ipoib_create_debug_files(priv->dev);
-
 	if (ipoib_cm_add_mode_attr(priv->dev))
 		goto sysfs_failed;
 	if (ipoib_add_pkey_attr(priv->dev))
@@ -1908,7 +1947,6 @@ static struct net_device *ipoib_add_port(const char *format,
 	return priv->dev;
 
 sysfs_failed:
-	ipoib_delete_debug_files(priv->dev);
 	unregister_netdev(priv->dev);
 
 register_failed:
@@ -1990,6 +2028,12 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data)
 	kfree(dev_list);
 }
 
+#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
+static struct notifier_block ipoib_netdev_notifier = {
+	.notifier_call = ipoib_netdev_event,
+};
+#endif
+
 static int __init ipoib_init_module(void)
 {
 	int ret;
@@ -2041,6 +2085,9 @@ static int __init ipoib_init_module(void)
 	if (ret)
 		goto err_client;
 
+#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
+	register_netdevice_notifier(&ipoib_netdev_notifier);
+#endif
 	return 0;
 
 err_client:
@@ -2058,6 +2105,9 @@ err_fs:
 
 static void __exit ipoib_cleanup_module(void)
 {
+#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
+	unregister_netdevice_notifier(&ipoib_netdev_notifier);
+#endif
 	ipoib_netlink_fini();
 	ib_unregister_client(&ipoib_client);
 	ib_sa_unregister_client(&ipoib_sa_client);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index f357ca67a41c..5580ab0b5781 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -456,7 +456,10 @@ out_locked:
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
+/*
+ * Caller must hold 'priv->lock'
+ */
+static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 	ib_sa_comp_mask comp_mask;
 	int ret = 0;
 
+	if (!priv->broadcast ||
+	    !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+		return -EINVAL;
+
 	ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);
 
 	rec.mgid     = mcast->mcmember.mgid;
@@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 			rec.join_state = 4;
 #endif
 	}
+	spin_unlock_irq(&priv->lock);
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
+	spin_lock_irq(&priv->lock);
 	if (IS_ERR(multicast)) {
 		ret = PTR_ERR(multicast);
 		ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
-		spin_lock_irq(&priv->lock);
 		/* Requeue this join task with a backoff delay */
 		__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 		spin_unlock_irq(&priv->lock);
 		complete(&mcast->done);
+		spin_lock_irq(&priv->lock);
 	}
+	return 0;
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -553,8 +563,11 @@ void ipoib_mcast_join_task(struct work_struct *work)
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
 		return;
 
-	if (ib_query_port(priv->ca, priv->port, &port_attr) ||
-	    port_attr.state != IB_PORT_ACTIVE) {
+	if (ib_query_port(priv->ca, priv->port, &port_attr)) {
+		ipoib_dbg(priv, "ib_query_port() failed\n");
+		return;
+	}
+	if (port_attr.state != IB_PORT_ACTIVE) {
 		ipoib_dbg(priv, "port state is not ACTIVE (state = %d) suspending join task\n",
 			  port_attr.state);
 		return;
@@ -620,9 +633,10 @@ void ipoib_mcast_join_task(struct work_struct *work)
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast);
-				spin_lock_irq(&priv->lock);
+				if (ipoib_mcast_join(dev, mcast)) {
+					spin_unlock_irq(&priv->lock);
+					return;
+				}
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
 				delay_until = mcast->delay_until;
@@ -641,10 +655,9 @@ out:
 	if (mcast) {
 		init_completion(&mcast->done);
 		set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+		ipoib_mcast_join(dev, mcast);
 	}
 	spin_unlock_irq(&priv->lock);
-	if (mcast)
-		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)
@@ -743,9 +756,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 			__ipoib_mcast_add(dev, mcast);
 			list_add_tail(&mcast->list, &priv->multicast_list);
 		}
-		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+			/* put pseudoheader back on for next time */
+			skb_push(skb, sizeof(struct ipoib_pseudo_header));
 			skb_queue_tail(&mcast->pkt_queue, skb);
-		else {
+		} else {
 			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index fca1a882de27..57a34f87dedf 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -85,8 +85,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 		goto register_failed;
 	}
 
-	ipoib_create_debug_files(priv->dev);
-
 	/* RTNL childs don't need proprietary sysfs entries */
 	if (type == IPOIB_LEGACY_CHILD) {
 		if (ipoib_cm_add_mode_attr(priv->dev))
@@ -107,7 +105,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 
 sysfs_failed:
 	result = -ENOMEM;
-	ipoib_delete_debug_files(priv->dev);
 	unregister_netdevice(priv->dev);
 
 register_failed:
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 8a51c3b5d657..0b7f5a701c60 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -66,6 +66,7 @@ isert_rdma_accept(struct isert_conn *isert_conn);
 struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
 
 static void isert_release_work(struct work_struct *work);
+static void isert_wait4flush(struct isert_conn *isert_conn);
 
 static inline bool
 isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
@@ -815,12 +816,31 @@ isert_put_conn(struct isert_conn *isert_conn)
 	kref_put(&isert_conn->kref, isert_release_kref);
 }
 
+static void
+isert_handle_unbound_conn(struct isert_conn *isert_conn)
+{
+	struct isert_np *isert_np = isert_conn->cm_id->context;
+
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		/*
+		 * This means iscsi doesn't know this connection
+		 * so schedule a cleanup ourselves
+		 */
+		list_del_init(&isert_conn->node);
+		isert_put_conn(isert_conn);
+		complete(&isert_conn->wait);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->mutex);
+}
+
 /**
  * isert_conn_terminate() - Initiate connection termination
  * @isert_conn: isert connection struct
  *
  * Notes:
- * In case the connection state is FULL_FEATURE, move state
+ * In case the connection state is BOUND, move state
  * to TEMINATING and start teardown sequence (rdma_disconnect).
  * In case the connection state is UP, complete flush as well.
  *
@@ -832,23 +852,19 @@ isert_conn_terminate(struct isert_conn *isert_conn)
 {
 	int err;
 
-	switch (isert_conn->state) {
-	case ISER_CONN_TERMINATING:
-		break;
-	case ISER_CONN_UP:
-	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
-		isert_info("Terminating conn %p state %d\n",
-			   isert_conn, isert_conn->state);
-		isert_conn->state = ISER_CONN_TERMINATING;
-		err = rdma_disconnect(isert_conn->cm_id);
-		if (err)
-			isert_warn("Failed rdma_disconnect isert_conn %p\n",
-				   isert_conn);
-		break;
-	default:
-		isert_warn("conn %p teminating in state %d\n",
-			   isert_conn, isert_conn->state);
-	}
+	if (isert_conn->state >= ISER_CONN_TERMINATING)
+		return;
+
+	isert_info("Terminating conn %p state %d\n",
+		   isert_conn, isert_conn->state);
+	isert_conn->state = ISER_CONN_TERMINATING;
+	err = rdma_disconnect(isert_conn->cm_id);
+	if (err)
+		isert_warn("Failed rdma_disconnect isert_conn %p\n",
+			   isert_conn);
+
+	isert_info("conn %p completing wait\n", isert_conn);
+	complete(&isert_conn->wait);
 }
 
 static int
@@ -882,35 +898,27 @@ static int
 isert_disconnected_handler(struct rdma_cm_id *cma_id,
 			   enum rdma_cm_event_type event)
 {
-	struct isert_np *isert_np = cma_id->context;
-	struct isert_conn *isert_conn;
-	bool terminating = false;
-
-	if (isert_np->cm_id == cma_id)
-		return isert_np_cma_handler(cma_id->context, event);
-
-	isert_conn = cma_id->qp->qp_context;
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
 	mutex_lock(&isert_conn->mutex);
-	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
-	isert_conn_terminate(isert_conn);
-	mutex_unlock(&isert_conn->mutex);
-
-	isert_info("conn %p completing wait\n", isert_conn);
-	complete(&isert_conn->wait);
-
-	if (terminating)
-		goto out;
-
-	mutex_lock(&isert_np->mutex);
-	if (!list_empty(&isert_conn->node)) {
-		list_del_init(&isert_conn->node);
-		isert_put_conn(isert_conn);
-		queue_work(isert_release_wq, &isert_conn->release_work);
+	switch (isert_conn->state) {
+	case ISER_CONN_TERMINATING:
+		break;
+	case ISER_CONN_UP:
+		isert_conn_terminate(isert_conn);
+		isert_wait4flush(isert_conn);
+		isert_handle_unbound_conn(isert_conn);
+		break;
+	case ISER_CONN_BOUND:
+	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
+		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+		break;
+	default:
+		isert_warn("conn %p teminating in state %d\n",
+			   isert_conn, isert_conn->state);
 	}
-	mutex_unlock(&isert_np->mutex);
+	mutex_unlock(&isert_conn->mutex);
 
-out:
 	return 0;
 }
 
@@ -929,12 +937,16 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
+	struct isert_np *isert_np = cma_id->context;
 	int ret = 0;
 
 	isert_info("%s (%d): status %d id %p np %p\n",
 		   rdma_event_msg(event->event), event->event,
 		   event->status, cma_id, cma_id->context);
 
+	if (isert_np->cm_id == cma_id)
+		return isert_np_cma_handler(cma_id->context, event->event);
+
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
 		ret = isert_connect_request(cma_id, event);
@@ -980,13 +992,10 @@ isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
-	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
 			   &rx_wr_failed);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
-		isert_conn->post_recv_buf_count -= count;
-	}
 
 	return ret;
 }
@@ -1002,12 +1011,9 @@ isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
 	rx_wr.num_sge = 1;
 	rx_wr.next = NULL;
 
-	isert_conn->post_recv_buf_count++;
 	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
-		isert_conn->post_recv_buf_count--;
-	}
 
 	return ret;
 }
@@ -1120,12 +1126,9 @@ isert_rdma_post_recvl(struct isert_conn *isert_conn)
 	rx_wr.sg_list = &sge;
 	rx_wr.num_sge = 1;
 
-	isert_conn->post_recv_buf_count++;
 	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_fail);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed: %d\n", ret);
-		isert_conn->post_recv_buf_count--;
-	}
 
 	return ret;
 }
@@ -1578,7 +1581,7 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 		     struct isert_conn *isert_conn,
 		     u32 xfer_len)
 {
-	struct ib_device *ib_dev = isert_conn->cm_id->device;
+	struct ib_device *ib_dev = isert_conn->device->ib_device;
 	struct iscsi_hdr *hdr;
 	u64 rx_dma;
 	int rx_buflen;
@@ -1620,7 +1623,6 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 	ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen,
 				      DMA_FROM_DEVICE);
 
-	isert_conn->post_recv_buf_count--;
 }
 
 static int
@@ -2035,7 +2037,8 @@ is_isert_tx_desc(struct isert_conn *isert_conn, void *wr_id)
 	void *start = isert_conn->rx_descs;
 	int len = ISERT_QP_MAX_RECV_DTOS * sizeof(*isert_conn->rx_descs);
 
-	if (wr_id >= start && wr_id < start + len)
+	if ((wr_id >= start && wr_id < start + len) ||
+	    (wr_id == isert_conn->login_req_buf))
 		return false;
 
 	return true;
@@ -2059,10 +2062,6 @@ isert_cq_comp_err(struct isert_conn *isert_conn, struct ib_wc *wc)
 			isert_unmap_tx_desc(desc, ib_dev);
 		else
 			isert_completion_put(desc, isert_cmd, ib_dev, true);
-	} else {
-		isert_conn->post_recv_buf_count--;
-		if (!isert_conn->post_recv_buf_count)
-			iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
 	}
 }
 
@@ -3193,6 +3192,7 @@ accept_wait:
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
+	isert_conn->state = ISER_CONN_BOUND;
 
 	isert_set_conn_info(np, conn, isert_conn);
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 3d7fbc47c343..1874d21daee0 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -50,6 +50,7 @@ enum iser_ib_op_code {
 enum iser_conn_state {
 	ISER_CONN_INIT,
 	ISER_CONN_UP,
+	ISER_CONN_BOUND,
 	ISER_CONN_FULL_FEATURE,
 	ISER_CONN_TERMINATING,
 	ISER_CONN_DOWN,
@@ -144,7 +145,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	int			post_recv_buf_count;
 	u32			responder_resources;
 	u32			initiator_depth;
 	bool			pi_support;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 3db9a659719b..e397f1b0af09 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1519,7 +1519,7 @@ static int srp_map_idb(struct srp_rdma_ch *ch, struct srp_request *req,
 
 	if (dev->use_fast_reg) {
 		state.sg = idb_sg;
-		sg_set_buf(idb_sg, req->indirect_desc, idb_len);
+		sg_init_one(idb_sg, req->indirect_desc, idb_len);
 		idb_sg->dma_address = req->indirect_dma_addr; /* hack! */
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 		idb_sg->dma_length = idb_sg->length;	      /* hack^2 */
@@ -1787,17 +1787,24 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp)
 	if (unlikely(rsp->tag & SRP_TAG_TSK_MGMT)) {
 		spin_lock_irqsave(&ch->lock, flags);
 		ch->req_lim += be32_to_cpu(rsp->req_lim_delta);
+		if (rsp->tag == ch->tsk_mgmt_tag) {
+			ch->tsk_mgmt_status = -1;
+			if (be32_to_cpu(rsp->resp_data_len) >= 4)
+				ch->tsk_mgmt_status = rsp->data[3];
+			complete(&ch->tsk_mgmt_done);
+		} else {
+			shost_printk(KERN_ERR, target->scsi_host,
+				     "Received tsk mgmt response too late for tag %#llx\n",
+				     rsp->tag);
+		}
 		spin_unlock_irqrestore(&ch->lock, flags);
-
-		ch->tsk_mgmt_status = -1;
-		if (be32_to_cpu(rsp->resp_data_len) >= 4)
-			ch->tsk_mgmt_status = rsp->data[3];
-		complete(&ch->tsk_mgmt_done);
 	} else {
 		scmnd = scsi_host_find_tag(target->scsi_host, rsp->tag);
-		if (scmnd) {
+		if (scmnd && scmnd->host_scribble) {
 			req = (void *)scmnd->host_scribble;
 			scmnd = srp_claim_req(ch, req, NULL, scmnd);
+		} else {
+			scmnd = NULL;
 		}
 		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
@@ -2469,19 +2476,18 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth)
 }
 
 static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
-			     u8 func)
+			     u8 func, u8 *status)
 {
 	struct srp_target_port *target = ch->target;
 	struct srp_rport *rport = target->rport;
 	struct ib_device *dev = target->srp_host->srp_dev->dev;
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;
+	int res;
 
 	if (!ch->connected || target->qp_in_error)
 		return -1;
 
-	init_completion(&ch->tsk_mgmt_done);
-
 	/*
 	 * Lock the rport mutex to avoid that srp_create_ch_ib() is
 	 * invoked while a task management function is being sent.
@@ -2504,10 +2510,16 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
 
 	tsk_mgmt->opcode 	= SRP_TSK_MGMT;
 	int_to_scsilun(lun, &tsk_mgmt->lun);
-	tsk_mgmt->tag		= req_tag | SRP_TAG_TSK_MGMT;
 	tsk_mgmt->tsk_mgmt_func = func;
 	tsk_mgmt->task_tag	= req_tag;
 
+	spin_lock_irq(&ch->lock);
+	ch->tsk_mgmt_tag = (ch->tsk_mgmt_tag + 1) | SRP_TAG_TSK_MGMT;
+	tsk_mgmt->tag = ch->tsk_mgmt_tag;
+	spin_unlock_irq(&ch->lock);
+
+	init_completion(&ch->tsk_mgmt_done);
+
 	ib_dma_sync_single_for_device(dev, iu->dma, sizeof *tsk_mgmt,
 				      DMA_TO_DEVICE);
 	if (srp_post_send(ch, iu, sizeof(*tsk_mgmt))) {
@@ -2516,13 +2528,15 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
 
 		return -1;
 	}
+	res = wait_for_completion_timeout(&ch->tsk_mgmt_done,
+					msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS));
+	if (res > 0 && status)
+		*status = ch->tsk_mgmt_status;
 	mutex_unlock(&rport->mutex);
 
-	if (!wait_for_completion_timeout(&ch->tsk_mgmt_done,
-					 msecs_to_jiffies(SRP_ABORT_TIMEOUT_MS)))
-		return -1;
+	WARN_ON_ONCE(res < 0);
 
-	return 0;
+	return res > 0 ? 0 : -1;
 }
 
 static int srp_abort(struct scsi_cmnd *scmnd)
@@ -2548,7 +2562,7 @@ static int srp_abort(struct scsi_cmnd *scmnd)
 	shost_printk(KERN_ERR, target->scsi_host,
 		     "Sending SRP abort for tag %#x\n", tag);
 	if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun,
-			      SRP_TSK_ABORT_TASK) == 0)
+			      SRP_TSK_ABORT_TASK, NULL) == 0)
 		ret = SUCCESS;
 	else if (target->rport->state == SRP_RPORT_LOST)
 		ret = FAST_IO_FAIL;
@@ -2566,14 +2580,15 @@ static int srp_reset_device(struct scsi_cmnd *scmnd)
 	struct srp_target_port *target = host_to_target(scmnd->device->host);
 	struct srp_rdma_ch *ch;
 	int i;
+	u8 status;
 
 	shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n");
 
 	ch = &target->ch[0];
 	if (srp_send_tsk_mgmt(ch, SRP_TAG_NO_REQ, scmnd->device->lun,
-			      SRP_TSK_LUN_RESET))
+			      SRP_TSK_LUN_RESET, &status))
 		return FAILED;
-	if (ch->tsk_mgmt_status)
+	if (status)
 		return FAILED;
 
 	for (i = 0; i < target->ch_count; i++) {
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index f6af531f9f32..109eea94d0f9 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -168,6 +168,7 @@ struct srp_rdma_ch {
 	int			max_ti_iu_len;
 	int			comp_vector;
 
+	u64			tsk_mgmt_tag;
 	struct completion	tsk_mgmt_done;
 	u8			tsk_mgmt_status;
 	bool			connected;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 2e2fe818ca9f..eaabf3125846 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1737,47 +1737,6 @@ send_sense:
 	return -1;
 }
 
-/**
- * srpt_rx_mgmt_fn_tag() - Process a task management function by tag.
- * @ch: RDMA channel of the task management request.
- * @fn: Task management function to perform.
- * @req_tag: Tag of the SRP task management request.
- * @mgmt_ioctx: I/O context of the task management request.
- *
- * Returns zero if the target core will process the task management
- * request asynchronously.
- *
- * Note: It is assumed that the initiator serializes tag-based task management
- * requests.
- */
-static int srpt_rx_mgmt_fn_tag(struct srpt_send_ioctx *ioctx, u64 tag)
-{
-	struct srpt_device *sdev;
-	struct srpt_rdma_ch *ch;
-	struct srpt_send_ioctx *target;
-	int ret, i;
-
-	ret = -EINVAL;
-	ch = ioctx->ch;
-	BUG_ON(!ch);
-	BUG_ON(!ch->sport);
-	sdev = ch->sport->sdev;
-	BUG_ON(!sdev);
-	spin_lock_irq(&sdev->spinlock);
-	for (i = 0; i < ch->rq_size; ++i) {
-		target = ch->ioctx_ring[i];
-		if (target->cmd.se_lun == ioctx->cmd.se_lun &&
-		    target->cmd.tag == tag &&
-		    srpt_get_cmd_state(target) != SRPT_STATE_DONE) {
-			ret = 0;
-			/* now let the target core abort &target->cmd; */
-			break;
-		}
-	}
-	spin_unlock_irq(&sdev->spinlock);
-	return ret;
-}
-
 static int srp_tmr_to_tcm(int fn)
 {
 	switch (fn) {
@@ -1812,7 +1771,6 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch,
 	struct se_cmd *cmd;
 	struct se_session *sess = ch->sess;
 	uint64_t unpacked_lun;
-	uint32_t tag = 0;
 	int tcm_tmr;
 	int rc;
 
@@ -1828,25 +1786,10 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch,
 	srpt_set_cmd_state(send_ioctx, SRPT_STATE_MGMT);
 	send_ioctx->cmd.tag = srp_tsk->tag;
 	tcm_tmr = srp_tmr_to_tcm(srp_tsk->tsk_mgmt_func);
-	if (tcm_tmr < 0) {
-		send_ioctx->cmd.se_tmr_req->response =
-			TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED;
-		goto fail;
-	}
 	unpacked_lun = srpt_unpack_lun((uint8_t *)&srp_tsk->lun,
 				       sizeof(srp_tsk->lun));
-
-	if (srp_tsk->tsk_mgmt_func == SRP_TSK_ABORT_TASK) {
-		rc = srpt_rx_mgmt_fn_tag(send_ioctx, srp_tsk->task_tag);
-		if (rc < 0) {
-			send_ioctx->cmd.se_tmr_req->response =
-					TMR_TASK_DOES_NOT_EXIST;
-			goto fail;
-		}
-		tag = srp_tsk->task_tag;
-	}
 	rc = target_submit_tmr(&send_ioctx->cmd, sess, NULL, unpacked_lun,
-				srp_tsk, tcm_tmr, GFP_KERNEL, tag,
+				srp_tsk, tcm_tmr, GFP_KERNEL, srp_tsk->task_tag,
 				TARGET_SCF_ACK_KREF);
 	if (rc != 0) {
 		send_ioctx->cmd.se_tmr_req->response = TMR_FUNCTION_REJECTED;
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index d96aa27dfcdc..db64adfbe1af 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -141,6 +141,9 @@ static int iforce_usb_probe(struct usb_interface *intf,
 
 	interface = intf->cur_altsetting;
 
+	if (interface->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	epirq = &interface->endpoint[0].desc;
 	epout = &interface->endpoint[1].desc;
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index fd4100d56d8c..3258baf3282e 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -189,6 +189,7 @@ 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 },
 	{ 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+	{ 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
 	{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
@@ -310,6 +311,7 @@ static struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
 	XPAD_XBOX360_VENDOR(0x24c6),		/* PowerA Controllers */
 	XPAD_XBOX360_VENDOR(0x1532),		/* Razer Sabertooth */
+	XPAD_XBOXONE_VENDOR(0x1532),		/* Razer Wildcat */
 	XPAD_XBOX360_VENDOR(0x15e4),		/* Numark X-Box 360 controllers */
 	XPAD_XBOX360_VENDOR(0x162e),		/* Joytech X-Box 360 controllers */
 	{ }
@@ -317,6 +319,19 @@ static struct usb_device_id xpad_table[] = {
 
 MODULE_DEVICE_TABLE(usb, xpad_table);
 
+struct xpad_output_packet {
+	u8 data[XPAD_PKT_LEN];
+	u8 len;
+	bool pending;
+};
+
+#define XPAD_OUT_CMD_IDX	0
+#define XPAD_OUT_FF_IDX		1
+#define XPAD_OUT_LED_IDX	(1 + IS_ENABLED(CONFIG_JOYSTICK_XPAD_FF))
+#define XPAD_NUM_OUT_PACKETS	(1 + \
+				 IS_ENABLED(CONFIG_JOYSTICK_XPAD_FF) + \
+				 IS_ENABLED(CONFIG_JOYSTICK_XPAD_LEDS))
+
 struct usb_xpad {
 	struct input_dev *dev;		/* input device interface */
 	struct usb_device *udev;	/* usb device */
@@ -329,9 +344,13 @@ struct usb_xpad {
 	dma_addr_t idata_dma;
 
 	struct urb *irq_out;		/* urb for interrupt out report */
+	bool irq_out_active;		/* we must not use an active URB */
 	unsigned char *odata;		/* output data */
 	dma_addr_t odata_dma;
-	struct mutex odata_mutex;
+	spinlock_t odata_lock;
+
+	struct xpad_output_packet out_packets[XPAD_NUM_OUT_PACKETS];
+	int last_out_packet;
 
 #if defined(CONFIG_JOYSTICK_XPAD_LEDS)
 	struct xpad_led *led;
@@ -678,18 +697,71 @@ exit:
 			__func__, retval);
 }
 
+/* Callers must hold xpad->odata_lock spinlock */
+static bool xpad_prepare_next_out_packet(struct usb_xpad *xpad)
+{
+	struct xpad_output_packet *pkt, *packet = NULL;
+	int i;
+
+	for (i = 0; i < XPAD_NUM_OUT_PACKETS; i++) {
+		if (++xpad->last_out_packet >= XPAD_NUM_OUT_PACKETS)
+			xpad->last_out_packet = 0;
+
+		pkt = &xpad->out_packets[xpad->last_out_packet];
+		if (pkt->pending) {
+			dev_dbg(&xpad->intf->dev,
+				"%s - found pending output packet %d\n",
+				__func__, xpad->last_out_packet);
+			packet = pkt;
+			break;
+		}
+	}
+
+	if (packet) {
+		memcpy(xpad->odata, packet->data, packet->len);
+		xpad->irq_out->transfer_buffer_length = packet->len;
+		packet->pending = false;
+		return true;
+	}
+
+	return false;
+}
+
+/* Callers must hold xpad->odata_lock spinlock */
+static int xpad_try_sending_next_out_packet(struct usb_xpad *xpad)
+{
+	int error;
+
+	if (!xpad->irq_out_active && xpad_prepare_next_out_packet(xpad)) {
+		error = usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+		if (error) {
+			dev_err(&xpad->intf->dev,
+				"%s - usb_submit_urb failed with result %d\n",
+				__func__, error);
+			return -EIO;
+		}
+
+		xpad->irq_out_active = true;
+	}
+
+	return 0;
+}
+
 static void xpad_irq_out(struct urb *urb)
 {
 	struct usb_xpad *xpad = urb->context;
 	struct device *dev = &xpad->intf->dev;
-	int retval, status;
+	int status = urb->status;
+	int error;
+	unsigned long flags;
 
-	status = urb->status;
+	spin_lock_irqsave(&xpad->odata_lock, flags);
 
 	switch (status) {
 	case 0:
 		/* success */
-		return;
+		xpad->irq_out_active = xpad_prepare_next_out_packet(xpad);
+		break;
 
 	case -ECONNRESET:
 	case -ENOENT:
@@ -697,19 +769,26 @@ static void xpad_irq_out(struct urb *urb)
 		/* this urb is terminated, clean up */
 		dev_dbg(dev, "%s - urb shutting down with status: %d\n",
 			__func__, status);
-		return;
+		xpad->irq_out_active = false;
+		break;
 
 	default:
 		dev_dbg(dev, "%s - nonzero urb status received: %d\n",
 			__func__, status);
-		goto exit;
+		break;
 	}
 
-exit:
-	retval = usb_submit_urb(urb, GFP_ATOMIC);
-	if (retval)
-		dev_err(dev, "%s - usb_submit_urb failed with result %d\n",
-			__func__, retval);
+	if (xpad->irq_out_active) {
+		error = usb_submit_urb(urb, GFP_ATOMIC);
+		if (error) {
+			dev_err(dev,
+				"%s - usb_submit_urb failed with result %d\n",
+				__func__, error);
+			xpad->irq_out_active = false;
+		}
+	}
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
@@ -728,7 +807,7 @@ static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
 		goto fail1;
 	}
 
-	mutex_init(&xpad->odata_mutex);
+	spin_lock_init(&xpad->odata_lock);
 
 	xpad->irq_out = usb_alloc_urb(0, GFP_KERNEL);
 	if (!xpad->irq_out) {
@@ -770,27 +849,57 @@ static void xpad_deinit_output(struct usb_xpad *xpad)
 
 static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 {
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_CMD_IDX];
+	unsigned long flags;
 	int retval;
 
-	mutex_lock(&xpad->odata_mutex);
+	spin_lock_irqsave(&xpad->odata_lock, flags);
+
+	packet->data[0] = 0x08;
+	packet->data[1] = 0x00;
+	packet->data[2] = 0x0F;
+	packet->data[3] = 0xC0;
+	packet->data[4] = 0x00;
+	packet->data[5] = 0x00;
+	packet->data[6] = 0x00;
+	packet->data[7] = 0x00;
+	packet->data[8] = 0x00;
+	packet->data[9] = 0x00;
+	packet->data[10] = 0x00;
+	packet->data[11] = 0x00;
+	packet->len = 12;
+	packet->pending = true;
+
+	/* Reset the sequence so we send out presence first */
+	xpad->last_out_packet = -1;
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 
-	xpad->odata[0] = 0x08;
-	xpad->odata[1] = 0x00;
-	xpad->odata[2] = 0x0F;
-	xpad->odata[3] = 0xC0;
-	xpad->odata[4] = 0x00;
-	xpad->odata[5] = 0x00;
-	xpad->odata[6] = 0x00;
-	xpad->odata[7] = 0x00;
-	xpad->odata[8] = 0x00;
-	xpad->odata[9] = 0x00;
-	xpad->odata[10] = 0x00;
-	xpad->odata[11] = 0x00;
-	xpad->irq_out->transfer_buffer_length = 12;
+	return retval;
+}
+
+static int xpad_start_xbox_one(struct usb_xpad *xpad)
+{
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_CMD_IDX];
+	unsigned long flags;
+	int retval;
 
-	retval = usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+	spin_lock_irqsave(&xpad->odata_lock, flags);
 
-	mutex_unlock(&xpad->odata_mutex);
+	/* Xbox one controller needs to be initialized. */
+	packet->data[0] = 0x05;
+	packet->data[1] = 0x20;
+	packet->len = 2;
+	packet->pending = true;
+
+	/* Reset the sequence so we send out start packet first */
+	xpad->last_out_packet = -1;
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 
 	return retval;
 }
@@ -799,8 +908,11 @@ static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect)
 {
 	struct usb_xpad *xpad = input_get_drvdata(dev);
+	struct xpad_output_packet *packet = &xpad->out_packets[XPAD_OUT_FF_IDX];
 	__u16 strong;
 	__u16 weak;
+	int retval;
+	unsigned long flags;
 
 	if (effect->type != FF_RUMBLE)
 		return 0;
@@ -808,69 +920,80 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 	strong = effect->u.rumble.strong_magnitude;
 	weak = effect->u.rumble.weak_magnitude;
 
+	spin_lock_irqsave(&xpad->odata_lock, flags);
+
 	switch (xpad->xtype) {
 	case XTYPE_XBOX:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x06;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = strong / 256;	/* left actuator */
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = weak / 256;	/* right actuator */
-		xpad->irq_out->transfer_buffer_length = 6;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x06;
+		packet->data[2] = 0x00;
+		packet->data[3] = strong / 256;	/* left actuator */
+		packet->data[4] = 0x00;
+		packet->data[5] = weak / 256;	/* right actuator */
+		packet->len = 6;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOX360:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x08;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = strong / 256;  /* left actuator? */
-		xpad->odata[4] = weak / 256;	/* right actuator? */
-		xpad->odata[5] = 0x00;
-		xpad->odata[6] = 0x00;
-		xpad->odata[7] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 8;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x08;
+		packet->data[2] = 0x00;
+		packet->data[3] = strong / 256;  /* left actuator? */
+		packet->data[4] = weak / 256;	/* right actuator? */
+		packet->data[5] = 0x00;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
+		packet->len = 8;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOX360W:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x01;
-		xpad->odata[2] = 0x0F;
-		xpad->odata[3] = 0xC0;
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = strong / 256;
-		xpad->odata[6] = weak / 256;
-		xpad->odata[7] = 0x00;
-		xpad->odata[8] = 0x00;
-		xpad->odata[9] = 0x00;
-		xpad->odata[10] = 0x00;
-		xpad->odata[11] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x01;
+		packet->data[2] = 0x0F;
+		packet->data[3] = 0xC0;
+		packet->data[4] = 0x00;
+		packet->data[5] = strong / 256;
+		packet->data[6] = weak / 256;
+		packet->data[7] = 0x00;
+		packet->data[8] = 0x00;
+		packet->data[9] = 0x00;
+		packet->data[10] = 0x00;
+		packet->data[11] = 0x00;
+		packet->len = 12;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOXONE:
-		xpad->odata[0] = 0x09; /* activate rumble */
-		xpad->odata[1] = 0x08;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = 0x08; /* continuous effect */
-		xpad->odata[4] = 0x00; /* simple rumble mode */
-		xpad->odata[5] = 0x03; /* L and R actuator only */
-		xpad->odata[6] = 0x00; /* TODO: LT actuator */
-		xpad->odata[7] = 0x00; /* TODO: RT actuator */
-		xpad->odata[8] = strong / 256;	/* left actuator */
-		xpad->odata[9] = weak / 256;	/* right actuator */
-		xpad->odata[10] = 0x80;	/* length of pulse */
-		xpad->odata[11] = 0x00;	/* stop period of pulse */
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x09; /* activate rumble */
+		packet->data[1] = 0x08;
+		packet->data[2] = 0x00;
+		packet->data[3] = 0x08; /* continuous effect */
+		packet->data[4] = 0x00; /* simple rumble mode */
+		packet->data[5] = 0x03; /* L and R actuator only */
+		packet->data[6] = 0x00; /* TODO: LT actuator */
+		packet->data[7] = 0x00; /* TODO: RT actuator */
+		packet->data[8] = strong / 256;	/* left actuator */
+		packet->data[9] = weak / 256;	/* right actuator */
+		packet->data[10] = 0x80;	/* length of pulse */
+		packet->data[11] = 0x00;	/* stop period of pulse */
+		packet->len = 12;
+		packet->pending = true;
 		break;
 
 	default:
 		dev_dbg(&xpad->dev->dev,
 			"%s - rumble command sent to unsupported xpad type: %d\n",
 			__func__, xpad->xtype);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto out;
 	}
 
-	return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+out:
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
+	return retval;
 }
 
 static int xpad_init_ff(struct usb_xpad *xpad)
@@ -921,36 +1044,44 @@ struct xpad_led {
  */
 static void xpad_send_led_command(struct usb_xpad *xpad, int command)
 {
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_LED_IDX];
+	unsigned long flags;
+
 	command %= 16;
 
-	mutex_lock(&xpad->odata_mutex);
+	spin_lock_irqsave(&xpad->odata_lock, flags);
 
 	switch (xpad->xtype) {
 	case XTYPE_XBOX360:
-		xpad->odata[0] = 0x01;
-		xpad->odata[1] = 0x03;
-		xpad->odata[2] = command;
-		xpad->irq_out->transfer_buffer_length = 3;
+		packet->data[0] = 0x01;
+		packet->data[1] = 0x03;
+		packet->data[2] = command;
+		packet->len = 3;
+		packet->pending = true;
 		break;
+
 	case XTYPE_XBOX360W:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x00;
-		xpad->odata[2] = 0x08;
-		xpad->odata[3] = 0x40 + command;
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = 0x00;
-		xpad->odata[6] = 0x00;
-		xpad->odata[7] = 0x00;
-		xpad->odata[8] = 0x00;
-		xpad->odata[9] = 0x00;
-		xpad->odata[10] = 0x00;
-		xpad->odata[11] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x00;
+		packet->data[2] = 0x08;
+		packet->data[3] = 0x40 + command;
+		packet->data[4] = 0x00;
+		packet->data[5] = 0x00;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
+		packet->data[8] = 0x00;
+		packet->data[9] = 0x00;
+		packet->data[10] = 0x00;
+		packet->data[11] = 0x00;
+		packet->len = 12;
+		packet->pending = true;
 		break;
 	}
 
-	usb_submit_urb(xpad->irq_out, GFP_KERNEL);
-	mutex_unlock(&xpad->odata_mutex);
+	xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 /*
@@ -1048,13 +1179,8 @@ static int xpad_open(struct input_dev *dev)
 	if (usb_submit_urb(xpad->irq_in, GFP_KERNEL))
 		return -EIO;
 
-	if (xpad->xtype == XTYPE_XBOXONE) {
-		/* Xbox one controller needs to be initialized. */
-		xpad->odata[0] = 0x05;
-		xpad->odata[1] = 0x20;
-		xpad->irq_out->transfer_buffer_length = 2;
-		return usb_submit_urb(xpad->irq_out, GFP_KERNEL);
-	}
+	if (xpad->xtype == XTYPE_XBOXONE)
+		return xpad_start_xbox_one(xpad);
 
 	return 0;
 }
@@ -1114,6 +1240,12 @@ static int xpad_init_input(struct usb_xpad *xpad)
 	input_dev->name = xpad->name;
 	input_dev->phys = xpad->phys;
 	usb_to_input_id(xpad->udev, &input_dev->id);
+
+	if (xpad->xtype == XTYPE_XBOX360W) {
+		/* x360w controllers and the receiver have different ids */
+		input_dev->id.product = 0x02a1;
+	}
+
 	input_dev->dev.parent = &xpad->intf->dev;
 
 	input_set_drvdata(input_dev, xpad);
@@ -1200,22 +1332,15 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 	int ep_irq_in_idx;
 	int i, error;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints != 2)
+		return -ENODEV;
+
 	for (i = 0; xpad_device[i].idVendor; i++) {
 		if ((le16_to_cpu(udev->descriptor.idVendor) == xpad_device[i].idVendor) &&
 		    (le16_to_cpu(udev->descriptor.idProduct) == xpad_device[i].idProduct))
 			break;
 	}
 
-	if (xpad_device[i].xtype == XTYPE_XBOXONE &&
-	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
-		/*
-		 * The Xbox One controller lists three interfaces all with the
-		 * same interface class, subclass and protocol. Differentiate by
-		 * interface number.
-		 */
-		return -ENODEV;
-	}
-
 	xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
 	if (!xpad)
 		return -ENOMEM;
@@ -1246,6 +1371,8 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 		if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) {
 			if (intf->cur_altsetting->desc.bInterfaceProtocol == 129)
 				xpad->xtype = XTYPE_XBOX360W;
+			else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208)
+				xpad->xtype = XTYPE_XBOXONE;
 			else
 				xpad->xtype = XTYPE_XBOX360;
 		} else {
@@ -1260,6 +1387,17 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 			xpad->mapping |= MAP_STICKS_TO_NULL;
 	}
 
+	if (xpad->xtype == XTYPE_XBOXONE &&
+	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+		/*
+		 * The Xbox One controller lists three interfaces all with the
+		 * same interface class, subclass and protocol. Differentiate by
+		 * interface number.
+		 */
+		error = -ENODEV;
+		goto err_free_in_urb;
+	}
+
 	error = xpad_init_output(intf, xpad);
 	if (error)
 		goto err_free_in_urb;
diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c
index acc5394afb03..29485bc4221c 100644
--- a/drivers/input/keyboard/tegra-kbc.c
+++ b/drivers/input/keyboard/tegra-kbc.c
@@ -376,7 +376,7 @@ static int tegra_kbc_start(struct tegra_kbc *kbc)
 	/* Reset the KBC controller to clear all previous status.*/
 	reset_control_assert(kbc->rst);
 	udelay(100);
-	reset_control_assert(kbc->rst);
+	reset_control_deassert(kbc->rst);
 	udelay(100);
 
 	tegra_kbc_config_pins(kbc);
diff --git a/drivers/input/misc/ati_remote2.c b/drivers/input/misc/ati_remote2.c
index cfd58e87da26..1c5914cae853 100644
--- a/drivers/input/misc/ati_remote2.c
+++ b/drivers/input/misc/ati_remote2.c
@@ -817,26 +817,49 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d
 
 	ar2->udev = udev;
 
+	/* Sanity check, first interface must have an endpoint */
+	if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) {
+		dev_err(&interface->dev,
+			"%s(): interface 0 must have an endpoint\n", __func__);
+		r = -ENODEV;
+		goto fail1;
+	}
 	ar2->intf[0] = interface;
 	ar2->ep[0] = &alt->endpoint[0].desc;
 
+	/* Sanity check, the device must have two interfaces */
 	ar2->intf[1] = usb_ifnum_to_if(udev, 1);
+	if ((udev->actconfig->desc.bNumInterfaces < 2) || !ar2->intf[1]) {
+		dev_err(&interface->dev, "%s(): need 2 interfaces, found %d\n",
+			__func__, udev->actconfig->desc.bNumInterfaces);
+		r = -ENODEV;
+		goto fail1;
+	}
+
 	r = usb_driver_claim_interface(&ati_remote2_driver, ar2->intf[1], ar2);
 	if (r)
 		goto fail1;
+
+	/* Sanity check, second interface must have an endpoint */
 	alt = ar2->intf[1]->cur_altsetting;
+	if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) {
+		dev_err(&interface->dev,
+			"%s(): interface 1 must have an endpoint\n", __func__);
+		r = -ENODEV;
+		goto fail2;
+	}
 	ar2->ep[1] = &alt->endpoint[0].desc;
 
 	r = ati_remote2_urb_init(ar2);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	ar2->channel_mask = channel_mask;
 	ar2->mode_mask = mode_mask;
 
 	r = ati_remote2_setup(ar2, ar2->channel_mask);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	usb_make_path(udev, ar2->phys, sizeof(ar2->phys));
 	strlcat(ar2->phys, "/input0", sizeof(ar2->phys));
@@ -845,11 +868,11 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d
 
 	r = sysfs_create_group(&udev->dev.kobj, &ati_remote2_attr_group);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	r = ati_remote2_input_init(ar2);
 	if (r)
-		goto fail3;
+		goto fail4;
 
 	usb_set_intfdata(interface, ar2);
 
@@ -857,10 +880,11 @@ static int ati_remote2_probe(struct usb_interface *interface, const struct usb_d
 
 	return 0;
 
- fail3:
+ fail4:
 	sysfs_remove_group(&udev->dev.kobj, &ati_remote2_attr_group);
- fail2:
+ fail3:
 	ati_remote2_urb_cleanup(ar2);
+ fail2:
 	usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]);
  fail1:
 	kfree(ar2);
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 9365535ba7f1..50a7faa504f7 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -675,6 +675,10 @@ static int cm109_usb_probe(struct usb_interface *intf,
 	int error = -ENOMEM;
 
 	interface = intf->cur_altsetting;
+
+	if (interface->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &interface->endpoint[0].desc;
 
 	if (!usb_endpoint_is_int_in(endpoint))
diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c
index 2adfd86c869a..930424e55439 100644
--- a/drivers/input/misc/drv260x.c
+++ b/drivers/input/misc/drv260x.c
@@ -592,7 +592,6 @@ static int drv260x_probe(struct i2c_client *client,
 	}
 
 	haptics->input_dev->name = "drv260x:haptics";
-	haptics->input_dev->dev.parent = client->dev.parent;
 	haptics->input_dev->close = drv260x_close;
 	input_set_drvdata(haptics->input_dev, haptics);
 	input_set_capability(haptics->input_dev, EV_FF, FF_RUMBLE);
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index ac1fa5f44580..f4e8fbec6a94 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1663,13 +1663,21 @@ static int ims_pcu_parse_cdc_data(struct usb_interface *intf, struct ims_pcu *pc
 
 	pcu->ctrl_intf = usb_ifnum_to_if(pcu->udev,
 					 union_desc->bMasterInterface0);
+	if (!pcu->ctrl_intf)
+		return -EINVAL;
 
 	alt = pcu->ctrl_intf->cur_altsetting;
+
+	if (alt->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	pcu->ep_ctrl = &alt->endpoint[0].desc;
 	pcu->max_ctrl_size = usb_endpoint_maxp(pcu->ep_ctrl);
 
 	pcu->data_intf = usb_ifnum_to_if(pcu->udev,
 					 union_desc->bSlaveInterface0);
+	if (!pcu->data_intf)
+		return -EINVAL;
 
 	alt = pcu->data_intf->cur_altsetting;
 	if (alt->desc.bNumEndpoints != 2) {
diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c
index a806ba3818f7..8d6326d7e7be 100644
--- a/drivers/input/misc/max8997_haptic.c
+++ b/drivers/input/misc/max8997_haptic.c
@@ -255,12 +255,14 @@ static int max8997_haptic_probe(struct platform_device *pdev)
 	struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	const struct max8997_platform_data *pdata =
 					dev_get_platdata(iodev->dev);
-	const struct max8997_haptic_platform_data *haptic_pdata =
-					pdata->haptic_pdata;
+	const struct max8997_haptic_platform_data *haptic_pdata = NULL;
 	struct max8997_haptic *chip;
 	struct input_dev *input_dev;
 	int error;
 
+	if (pdata)
+		haptic_pdata = pdata->haptic_pdata;
+
 	if (!haptic_pdata) {
 		dev_err(&pdev->dev, "no haptic platform data\n");
 		return -EINVAL;
diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c
index 3f02e0e03d12..67aab86048ad 100644
--- a/drivers/input/misc/pmic8xxx-pwrkey.c
+++ b/drivers/input/misc/pmic8xxx-pwrkey.c
@@ -353,7 +353,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	if (of_property_read_u32(pdev->dev.of_node, "debounce", &kpd_delay))
 		kpd_delay = 15625;
 
-	if (kpd_delay > 62500 || kpd_delay == 0) {
+	/* Valid range of pwr key trigger delay is 1/64 sec to 2 seconds. */
+	if (kpd_delay > USEC_PER_SEC * 2 || kpd_delay < USEC_PER_SEC / 64) {
 		dev_err(&pdev->dev, "invalid power key trigger delay\n");
 		return -EINVAL;
 	}
@@ -385,8 +386,8 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	pwr->name = "pmic8xxx_pwrkey";
 	pwr->phys = "pmic8xxx_pwrkey/input0";
 
-	delay = (kpd_delay << 10) / USEC_PER_SEC;
-	delay = 1 + ilog2(delay);
+	delay = (kpd_delay << 6) / USEC_PER_SEC;
+	delay = ilog2(delay);
 
 	err = regmap_read(regmap, PON_CNTL_1, &pon_cntl);
 	if (err < 0) {
diff --git a/drivers/input/misc/powermate.c b/drivers/input/misc/powermate.c
index 63b539d3daba..84909a12ff36 100644
--- a/drivers/input/misc/powermate.c
+++ b/drivers/input/misc/powermate.c
@@ -307,6 +307,9 @@ static int powermate_probe(struct usb_interface *intf, const struct usb_device_i
 	int error = -ENOMEM;
 
 	interface = intf->cur_altsetting;
+	if (interface->desc.bNumEndpoints < 1)
+		return -EINVAL;
+
 	endpoint = &interface->endpoint[0].desc;
 	if (!usb_endpoint_is_int_in(endpoint))
 		return -EIO;
diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index f2261ab54701..18663d4edae5 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -20,21 +20,40 @@
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 
 struct pwm_beeper {
 	struct input_dev *input;
 	struct pwm_device *pwm;
+	struct work_struct work;
 	unsigned long period;
 };
 
 #define HZ_TO_NANOSECONDS(x) (1000000000UL/(x))
 
+static void __pwm_beeper_set(struct pwm_beeper *beeper)
+{
+	unsigned long period = beeper->period;
+
+	if (period) {
+		pwm_config(beeper->pwm, period / 2, period);
+		pwm_enable(beeper->pwm);
+	} else
+		pwm_disable(beeper->pwm);
+}
+
+static void pwm_beeper_work(struct work_struct *work)
+{
+	struct pwm_beeper *beeper =
+		container_of(work, struct pwm_beeper, work);
+
+	__pwm_beeper_set(beeper);
+}
+
 static int pwm_beeper_event(struct input_dev *input,
 			    unsigned int type, unsigned int code, int value)
 {
-	int ret = 0;
 	struct pwm_beeper *beeper = input_get_drvdata(input);
-	unsigned long period;
 
 	if (type != EV_SND || value < 0)
 		return -EINVAL;
@@ -49,22 +68,31 @@ static int pwm_beeper_event(struct input_dev *input,
 		return -EINVAL;
 	}
 
-	if (value == 0) {
-		pwm_disable(beeper->pwm);
-	} else {
-		period = HZ_TO_NANOSECONDS(value);
-		ret = pwm_config(beeper->pwm, period / 2, period);
-		if (ret)
-			return ret;
-		ret = pwm_enable(beeper->pwm);
-		if (ret)
-			return ret;
-		beeper->period = period;
-	}
+	if (value == 0)
+		beeper->period = 0;
+	else
+		beeper->period = HZ_TO_NANOSECONDS(value);
+
+	schedule_work(&beeper->work);
 
 	return 0;
 }
 
+static void pwm_beeper_stop(struct pwm_beeper *beeper)
+{
+	cancel_work_sync(&beeper->work);
+
+	if (beeper->period)
+		pwm_disable(beeper->pwm);
+}
+
+static void pwm_beeper_close(struct input_dev *input)
+{
+	struct pwm_beeper *beeper = input_get_drvdata(input);
+
+	pwm_beeper_stop(beeper);
+}
+
 static int pwm_beeper_probe(struct platform_device *pdev)
 {
 	unsigned long pwm_id = (unsigned long)dev_get_platdata(&pdev->dev);
@@ -87,6 +115,8 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 		goto err_free;
 	}
 
+	INIT_WORK(&beeper->work, pwm_beeper_work);
+
 	beeper->input = input_allocate_device();
 	if (!beeper->input) {
 		dev_err(&pdev->dev, "Failed to allocate input device\n");
@@ -106,6 +136,7 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 	beeper->input->sndbit[0] = BIT(SND_TONE) | BIT(SND_BELL);
 
 	beeper->input->event = pwm_beeper_event;
+	beeper->input->close = pwm_beeper_close;
 
 	input_set_drvdata(beeper->input, beeper);
 
@@ -135,7 +166,6 @@ static int pwm_beeper_remove(struct platform_device *pdev)
 
 	input_unregister_device(beeper->input);
 
-	pwm_disable(beeper->pwm);
 	pwm_free(beeper->pwm);
 
 	kfree(beeper);
@@ -147,8 +177,7 @@ static int __maybe_unused pwm_beeper_suspend(struct device *dev)
 {
 	struct pwm_beeper *beeper = dev_get_drvdata(dev);
 
-	if (beeper->period)
-		pwm_disable(beeper->pwm);
+	pwm_beeper_stop(beeper);
 
 	return 0;
 }
@@ -157,10 +186,8 @@ static int __maybe_unused pwm_beeper_resume(struct device *dev)
 {
 	struct pwm_beeper *beeper = dev_get_drvdata(dev);
 
-	if (beeper->period) {
-		pwm_config(beeper->pwm, beeper->period / 2, beeper->period);
-		pwm_enable(beeper->pwm);
-	}
+	if (beeper->period)
+		__pwm_beeper_set(beeper);
 
 	return 0;
 }
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 5adbcedcb81c..2bb4c8633d3b 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -893,9 +893,15 @@ static long uinput_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 
 #ifdef CONFIG_COMPAT
+
+#define UI_SET_PHYS_COMPAT	_IOW(UINPUT_IOCTL_BASE, 108, compat_uptr_t)
+
 static long uinput_compat_ioctl(struct file *file,
 				unsigned int cmd, unsigned long arg)
 {
+	if (cmd == UI_SET_PHYS_COMPAT)
+		cmd = UI_SET_PHYS;
+
 	return uinput_ioctl_handler(file, cmd, arg, compat_ptr(arg));
 }
 #endif
diff --git a/drivers/input/misc/yealink.c b/drivers/input/misc/yealink.c
index 79c964c075f1..6e7ff9561d92 100644
--- a/drivers/input/misc/yealink.c
+++ b/drivers/input/misc/yealink.c
@@ -875,6 +875,10 @@ static int usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	int ret, pipe, i;
 
 	interface = intf->cur_altsetting;
+
+	if (interface->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &interface->endpoint[0].desc;
 	if (!usb_endpoint_is_int_in(endpoint))
 		return -ENODEV;
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 2f589857a039..681dce15fbc8 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -4,7 +4,8 @@
  * Copyright (c) 2013 ELAN Microelectronics Corp.
  *
  * Author: 林政維 (Duson Lin) <dusonlin@emc.com.tw>
- * Version: 1.6.0
+ * Author: KT Liao <kt.liao@emc.com.tw>
+ * Version: 1.6.2
  *
  * Based on cyapa driver:
  * copyright (c) 2011-2012 Cypress Semiconductor, Inc.
@@ -40,7 +41,7 @@
 #include "elan_i2c.h"
 
 #define DRIVER_NAME		"elan_i2c"
-#define ELAN_DRIVER_VERSION	"1.6.1"
+#define ELAN_DRIVER_VERSION	"1.6.2"
 #define ELAN_VENDOR_ID		0x04f3
 #define ETP_MAX_PRESSURE	255
 #define ETP_FWIDTH_REDUCE	90
@@ -199,9 +200,43 @@ static int elan_sleep(struct elan_tp_data *data)
 	return error;
 }
 
+static int elan_query_product(struct elan_tp_data *data)
+{
+	int error;
+
+	error = data->ops->get_product_id(data->client, &data->product_id);
+	if (error)
+		return error;
+
+	error = data->ops->get_sm_version(data->client, &data->ic_type,
+					  &data->sm_version);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+static int elan_check_ASUS_special_fw(struct elan_tp_data *data)
+{
+	if (data->ic_type == 0x0E) {
+		switch (data->product_id) {
+		case 0x05 ... 0x07:
+		case 0x09:
+		case 0x13:
+			return true;
+		}
+	} else if (data->ic_type == 0x08 && data->product_id == 0x26) {
+		/* ASUS EeeBook X205TA */
+		return true;
+	}
+
+	return false;
+}
+
 static int __elan_initialize(struct elan_tp_data *data)
 {
 	struct i2c_client *client = data->client;
+	bool woken_up = false;
 	int error;
 
 	error = data->ops->initialize(client);
@@ -210,6 +245,27 @@ static int __elan_initialize(struct elan_tp_data *data)
 		return error;
 	}
 
+	error = elan_query_product(data);
+	if (error)
+		return error;
+
+	/*
+	 * Some ASUS devices were shipped with firmware that requires
+	 * touchpads to be woken up first, before attempting to switch
+	 * them into absolute reporting mode.
+	 */
+	if (elan_check_ASUS_special_fw(data)) {
+		error = data->ops->sleep_control(client, false);
+		if (error) {
+			dev_err(&client->dev,
+				"failed to wake device up: %d\n", error);
+			return error;
+		}
+
+		msleep(200);
+		woken_up = true;
+	}
+
 	data->mode |= ETP_ENABLE_ABS;
 	error = data->ops->set_mode(client, data->mode);
 	if (error) {
@@ -218,11 +274,13 @@ static int __elan_initialize(struct elan_tp_data *data)
 		return error;
 	}
 
-	error = data->ops->sleep_control(client, false);
-	if (error) {
-		dev_err(&client->dev,
-			"failed to wake device up: %d\n", error);
-		return error;
+	if (!woken_up) {
+		error = data->ops->sleep_control(client, false);
+		if (error) {
+			dev_err(&client->dev,
+				"failed to wake device up: %d\n", error);
+			return error;
+		}
 	}
 
 	return 0;
@@ -248,10 +306,6 @@ static int elan_query_device_info(struct elan_tp_data *data)
 {
 	int error;
 
-	error = data->ops->get_product_id(data->client, &data->product_id);
-	if (error)
-		return error;
-
 	error = data->ops->get_version(data->client, false, &data->fw_version);
 	if (error)
 		return error;
@@ -261,11 +315,6 @@ static int elan_query_device_info(struct elan_tp_data *data)
 	if (error)
 		return error;
 
-	error = data->ops->get_sm_version(data->client, &data->ic_type,
-					  &data->sm_version);
-	if (error)
-		return error;
-
 	error = data->ops->get_version(data->client, true, &data->iap_version);
 	if (error)
 		return error;
@@ -1185,6 +1234,12 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN0000", 0 },
 	{ "ELAN0100", 0 },
 	{ "ELAN0600", 0 },
+	{ "ELAN0602", 0 },
+	{ "ELAN0605", 0 },
+	{ "ELAN0608", 0 },
+	{ "ELAN0605", 0 },
+	{ "ELAN0609", 0 },
+	{ "ELAN060B", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 78f93cf68840..6f4dc0fd2ca3 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1122,7 +1122,10 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E546   0x470f00        50, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E547   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
+ * Fujitsu LIFEBOOK E557   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu T725            0x470f01        05, 12, 09      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
@@ -1163,6 +1166,13 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H730"),
 		},
 	},
+	{
+		/* Fujitsu H760 also has a middle button */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"),
+		},
+	},
 #endif
 	{ }
 };
@@ -1507,10 +1517,10 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 		},
 	},
 	{
-		/* Fujitsu LIFEBOOK E554  does not work with crc_enabled == 0 */
+		/* Fujitsu H760 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"),
 		},
 	},
 	{
@@ -1521,6 +1531,41 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E546  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E554  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E556 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E556"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
@@ -1568,13 +1613,7 @@ static int elantech_set_properties(struct elantech_data *etd)
 		case 5:
 			etd->hw_version = 3;
 			break;
-		case 6:
-		case 7:
-		case 8:
-		case 9:
-		case 10:
-		case 13:
-		case 14:
+		case 6 ... 14:
 			etd->hw_version = 4;
 			break;
 		default:
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 6025eb430c0a..a41d8328c064 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -862,8 +862,9 @@ static void synaptics_report_ext_buttons(struct psmouse *psmouse,
 	if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap))
 		return;
 
-	/* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */
-	if (SYN_ID_FULL(priv->identity) == 0x801 &&
+	/* Bug in FW 8.1 & 8.2, buttons are reported only when ExtBit is 1 */
+	if ((SYN_ID_FULL(priv->identity) == 0x801 ||
+	     SYN_ID_FULL(priv->identity) == 0x802) &&
 	    !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02))
 		return;
 
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index 354d47ecd66a..7e2dc5e56632 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -265,7 +265,8 @@ static int trackpoint_start_protocol(struct psmouse *psmouse, unsigned char *fir
 	if (ps2_command(&psmouse->ps2dev, param, MAKE_PS2_CMD(0, 2, TP_READ_ID)))
 		return -1;
 
-	if (param[0] != TP_MAGIC_IDENT)
+	/* add new TP ID. */
+	if (!(param[0] & TP_MAGIC_IDENT))
 		return -1;
 
 	if (firmware_id)
@@ -380,8 +381,8 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties)
 		return 0;
 
 	if (trackpoint_read(&psmouse->ps2dev, TP_EXT_BTN, &button_info)) {
-		psmouse_warn(psmouse, "failed to get extended button data\n");
-		button_info = 0;
+		psmouse_warn(psmouse, "failed to get extended button data, assuming 3 buttons\n");
+		button_info = 0x33;
 	}
 
 	psmouse->private = kzalloc(sizeof(struct trackpoint_data), GFP_KERNEL);
diff --git a/drivers/input/mouse/trackpoint.h b/drivers/input/mouse/trackpoint.h
index 5617ed3a7d7a..88055755f82e 100644
--- a/drivers/input/mouse/trackpoint.h
+++ b/drivers/input/mouse/trackpoint.h
@@ -21,8 +21,9 @@
 #define TP_COMMAND		0xE2	/* Commands start with this */
 
 #define TP_READ_ID		0xE1	/* Sent for device identification */
-#define TP_MAGIC_IDENT		0x01	/* Sent after a TP_READ_ID followed */
+#define TP_MAGIC_IDENT		0x03	/* Sent after a TP_READ_ID followed */
 					/* by the firmware ID */
+					/* Firmware ID includes 0x1, 0x2, 0x3 */
 
 
 /*
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index a3f0f5a47490..0f586780ceb4 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		return -ENXIO;
 	}
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	/* Check if the device is present */
 	response = ~VMMOUSE_PROTO_MAGIC;
 	VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2);
-	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) {
-		release_region(VMMOUSE_PROTO_PORT, 4);
+	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU)
 		return -ENXIO;
-	}
 
 	if (set_properties) {
 		psmouse->vendor = VMMOUSE_VENDOR;
@@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties)
 		psmouse->model = version;
 	}
 
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return 0;
 }
 
@@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse)
 	psmouse_reset(psmouse);
 	input_unregister_device(priv->abs_dev);
 	kfree(priv);
-	release_region(VMMOUSE_PROTO_PORT, 4);
 }
 
 /**
@@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse)
 	struct input_dev *rel_dev = psmouse->dev, *abs_dev;
 	int error;
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	psmouse_reset(psmouse);
 	error = vmmouse_enable(psmouse);
 	if (error)
-		goto release_region;
+		return error;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	abs_dev = input_allocate_device();
@@ -502,8 +487,5 @@ init_fail:
 	kfree(priv);
 	psmouse->private = NULL;
 
-release_region:
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return error;
 }
diff --git a/drivers/input/serio/i8042-io.h b/drivers/input/serio/i8042-io.h
index a5eed2ade53d..34da81c006b6 100644
--- a/drivers/input/serio/i8042-io.h
+++ b/drivers/input/serio/i8042-io.h
@@ -81,7 +81,7 @@ static inline int i8042_platform_init(void)
 		return -EBUSY;
 #endif
 
-	i8042_reset = 1;
+	i8042_reset = I8042_RESET_ALWAYS;
 	return 0;
 }
 
diff --git a/drivers/input/serio/i8042-ip22io.h b/drivers/input/serio/i8042-ip22io.h
index ee1ad27d6ed0..08a1c10a1448 100644
--- a/drivers/input/serio/i8042-ip22io.h
+++ b/drivers/input/serio/i8042-ip22io.h
@@ -61,7 +61,7 @@ static inline int i8042_platform_init(void)
 		return -EBUSY;
 #endif
 
-	i8042_reset = 1;
+	i8042_reset = I8042_RESET_ALWAYS;
 
 	return 0;
 }
diff --git a/drivers/input/serio/i8042-ppcio.h b/drivers/input/serio/i8042-ppcio.h
index f708c75d16f1..1aabea43329e 100644
--- a/drivers/input/serio/i8042-ppcio.h
+++ b/drivers/input/serio/i8042-ppcio.h
@@ -44,7 +44,7 @@ static inline void i8042_write_command(int val)
 
 static inline int i8042_platform_init(void)
 {
-	i8042_reset = 1;
+	i8042_reset = I8042_RESET_ALWAYS;
 	return 0;
 }
 
diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index afcd1c1a05b2..6231d63860ee 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -130,7 +130,7 @@ static int __init i8042_platform_init(void)
 		}
 	}
 
-	i8042_reset = 1;
+	i8042_reset = I8042_RESET_ALWAYS;
 
 	return 0;
 }
diff --git a/drivers/input/serio/i8042-unicore32io.h b/drivers/input/serio/i8042-unicore32io.h
index 73f5cc124a36..455747552f85 100644
--- a/drivers/input/serio/i8042-unicore32io.h
+++ b/drivers/input/serio/i8042-unicore32io.h
@@ -61,7 +61,7 @@ static inline int i8042_platform_init(void)
 	if (!request_mem_region(I8042_REGION_START, I8042_REGION_SIZE, "i8042"))
 		return -EBUSY;
 
-	i8042_reset = 1;
+	i8042_reset = I8042_RESET_ALWAYS;
 	return 0;
 }
 
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 68f5f4a0f1e7..5be14ad29d46 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -120,6 +120,13 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 		},
 	},
 	{
+		/* Dell Embedded Box PC 3000 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"),
+		},
+	},
+	{
 		/* OQO Model 01 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "OQO"),
@@ -211,6 +218,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
+		},
+	},
 	{ }
 };
 
@@ -510,6 +523,90 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 	{ }
 };
 
+/*
+ * On some Asus laptops, just running self tests cause problems.
+ */
+static const struct dmi_system_id i8042_dmi_noselftest_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "A455LD"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "K401LB"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "K501LB"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "K501LX"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "R409L"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "V502LX"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X302LA"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X450LD"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X455LAB"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X455LDB"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X455LF"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Z450LA"),
+		},
+	},
+	{ }
+};
 static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 	{
 		/* MSI Wind U-100 */
@@ -588,6 +685,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "20046"),
 		},
 	},
+	{
+		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
+		},
+	},
 	{ }
 };
 
@@ -684,6 +788,13 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
 		},
 	},
+	{
+		/* Fujitsu UH554 laptop */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"),
+		},
+	},
 	{ }
 };
 
@@ -793,6 +904,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
 		},
 	},
+	{
+		/* Schenker XMG C504 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "XMG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C504"),
+		},
+	},
 	{ }
 };
 
@@ -1072,12 +1190,18 @@ static int __init i8042_platform_init(void)
 		return retval;
 
 #if defined(__ia64__)
-        i8042_reset = true;
+        i8042_reset = I8042_RESET_ALWAYS;
 #endif
 
 #ifdef CONFIG_X86
-	if (dmi_check_system(i8042_dmi_reset_table))
-		i8042_reset = true;
+	/* Honor module parameter when value is not default */
+	if (i8042_reset == I8042_RESET_DEFAULT) {
+		if (dmi_check_system(i8042_dmi_reset_table))
+			i8042_reset = I8042_RESET_ALWAYS;
+
+		if (dmi_check_system(i8042_dmi_noselftest_table))
+			i8042_reset = I8042_RESET_NEVER;
+	}
 
 	if (dmi_check_system(i8042_dmi_noloop_table))
 		i8042_noloop = true;
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 454195709a82..c84c685056b9 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -48,9 +48,39 @@ static bool i8042_unlock;
 module_param_named(unlock, i8042_unlock, bool, 0);
 MODULE_PARM_DESC(unlock, "Ignore keyboard lock.");
 
-static bool i8042_reset;
-module_param_named(reset, i8042_reset, bool, 0);
-MODULE_PARM_DESC(reset, "Reset controller during init and cleanup.");
+enum i8042_controller_reset_mode {
+	I8042_RESET_NEVER,
+	I8042_RESET_ALWAYS,
+	I8042_RESET_ON_S2RAM,
+#define I8042_RESET_DEFAULT	I8042_RESET_ON_S2RAM
+};
+static enum i8042_controller_reset_mode i8042_reset = I8042_RESET_DEFAULT;
+static int i8042_set_reset(const char *val, const struct kernel_param *kp)
+{
+	enum i8042_controller_reset_mode *arg = kp->arg;
+	int error;
+	bool reset;
+
+	if (val) {
+		error = kstrtobool(val, &reset);
+		if (error)
+			return error;
+	} else {
+		reset = true;
+	}
+
+	*arg = reset ? I8042_RESET_ALWAYS : I8042_RESET_NEVER;
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_reset_param = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = i8042_set_reset,
+};
+#define param_check_reset_param(name, p)	\
+	__param_check(name, p, enum i8042_controller_reset_mode)
+module_param_named(reset, i8042_reset, reset_param, 0);
+MODULE_PARM_DESC(reset, "Reset controller on resume, cleanup or both");
 
 static bool i8042_direct;
 module_param_named(direct, i8042_direct, bool, 0);
@@ -404,8 +434,10 @@ static int i8042_start(struct serio *serio)
 {
 	struct i8042_port *port = serio->port_data;
 
+	spin_lock_irq(&i8042_lock);
 	port->exists = true;
-	mb();
+	spin_unlock_irq(&i8042_lock);
+
 	return 0;
 }
 
@@ -418,16 +450,20 @@ static void i8042_stop(struct serio *serio)
 {
 	struct i8042_port *port = serio->port_data;
 
+	spin_lock_irq(&i8042_lock);
 	port->exists = false;
+	port->serio = NULL;
+	spin_unlock_irq(&i8042_lock);
 
 	/*
+	 * We need to make sure that interrupt handler finishes using
+	 * our serio port before we return from this function.
 	 * We synchronize with both AUX and KBD IRQs because there is
 	 * a (very unlikely) chance that AUX IRQ is raised for KBD port
 	 * and vice versa.
 	 */
 	synchronize_irq(I8042_AUX_IRQ);
 	synchronize_irq(I8042_KBD_IRQ);
-	port->serio = NULL;
 }
 
 /*
@@ -544,7 +580,7 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id)
 
 	spin_unlock_irqrestore(&i8042_lock, flags);
 
-	if (likely(port->exists && !filtered))
+	if (likely(serio && !filtered))
 		serio_interrupt(serio, data, dfl);
 
  out:
@@ -1019,7 +1055,7 @@ static int i8042_controller_init(void)
  * Reset the controller and reset CRT to the original value set by BIOS.
  */
 
-static void i8042_controller_reset(bool force_reset)
+static void i8042_controller_reset(bool s2r_wants_reset)
 {
 	i8042_flush();
 
@@ -1044,8 +1080,10 @@ static void i8042_controller_reset(bool force_reset)
  * Reset the controller if requested.
  */
 
-	if (i8042_reset || force_reset)
+	if (i8042_reset == I8042_RESET_ALWAYS ||
+	    (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) {
 		i8042_controller_selftest();
+	}
 
 /*
  * Restore the original control register setting.
@@ -1110,7 +1148,7 @@ static void i8042_dritek_enable(void)
  * before suspending.
  */
 
-static int i8042_controller_resume(bool force_reset)
+static int i8042_controller_resume(bool s2r_wants_reset)
 {
 	int error;
 
@@ -1118,7 +1156,8 @@ static int i8042_controller_resume(bool force_reset)
 	if (error)
 		return error;
 
-	if (i8042_reset || force_reset) {
+	if (i8042_reset == I8042_RESET_ALWAYS ||
+	    (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) {
 		error = i8042_controller_selftest();
 		if (error)
 			return error;
@@ -1195,7 +1234,7 @@ static int i8042_pm_resume_noirq(struct device *dev)
 
 static int i8042_pm_resume(struct device *dev)
 {
-	bool force_reset;
+	bool want_reset;
 	int i;
 
 	for (i = 0; i < I8042_NUM_PORTS; i++) {
@@ -1218,9 +1257,9 @@ static int i8042_pm_resume(struct device *dev)
 	 * off control to the platform firmware, otherwise we can simply restore
 	 * the mode.
 	 */
-	force_reset = pm_resume_via_firmware();
+	want_reset = pm_resume_via_firmware();
 
-	return i8042_controller_resume(force_reset);
+	return i8042_controller_resume(want_reset);
 }
 
 static int i8042_pm_thaw(struct device *dev)
@@ -1277,6 +1316,7 @@ static int __init i8042_create_kbd_port(void)
 	serio->start		= i8042_start;
 	serio->stop		= i8042_stop;
 	serio->close		= i8042_port_close;
+	serio->ps2_cmd_mutex	= &i8042_mutex;
 	serio->port_data	= port;
 	serio->dev.parent	= &i8042_platform_device->dev;
 	strlcpy(serio->name, "i8042 KBD port", sizeof(serio->name));
@@ -1304,6 +1344,7 @@ static int __init i8042_create_aux_port(int idx)
 	serio->write		= i8042_aux_write;
 	serio->start		= i8042_start;
 	serio->stop		= i8042_stop;
+	serio->ps2_cmd_mutex	= &i8042_mutex;
 	serio->port_data	= port;
 	serio->dev.parent	= &i8042_platform_device->dev;
 	if (idx < 0) {
@@ -1373,21 +1414,6 @@ static void i8042_unregister_ports(void)
 	}
 }
 
-/*
- * Checks whether port belongs to i8042 controller.
- */
-bool i8042_check_port_owner(const struct serio *port)
-{
-	int i;
-
-	for (i = 0; i < I8042_NUM_PORTS; i++)
-		if (i8042_ports[i].serio == port)
-			return true;
-
-	return false;
-}
-EXPORT_SYMBOL(i8042_check_port_owner);
-
 static void i8042_free_irqs(void)
 {
 	if (i8042_aux_irq_registered)
@@ -1495,7 +1521,7 @@ static int __init i8042_probe(struct platform_device *dev)
 
 	i8042_platform_device = dev;
 
-	if (i8042_reset) {
+	if (i8042_reset == I8042_RESET_ALWAYS) {
 		error = i8042_controller_selftest();
 		if (error)
 			return error;
diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c
index 316f2c897101..83e9c663aa67 100644
--- a/drivers/input/serio/libps2.c
+++ b/drivers/input/serio/libps2.c
@@ -56,19 +56,17 @@ EXPORT_SYMBOL(ps2_sendbyte);
 
 void ps2_begin_command(struct ps2dev *ps2dev)
 {
-	mutex_lock(&ps2dev->cmd_mutex);
+	struct mutex *m = ps2dev->serio->ps2_cmd_mutex ?: &ps2dev->cmd_mutex;
 
-	if (i8042_check_port_owner(ps2dev->serio))
-		i8042_lock_chip();
+	mutex_lock(m);
 }
 EXPORT_SYMBOL(ps2_begin_command);
 
 void ps2_end_command(struct ps2dev *ps2dev)
 {
-	if (i8042_check_port_owner(ps2dev->serio))
-		i8042_unlock_chip();
+	struct mutex *m = ps2dev->serio->ps2_cmd_mutex ?: &ps2dev->cmd_mutex;
 
-	mutex_unlock(&ps2dev->cmd_mutex);
+	mutex_unlock(m);
 }
 EXPORT_SYMBOL(ps2_end_command);
 
diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c
index 3a7f3a4a4396..7c18249d6c8e 100644
--- a/drivers/input/tablet/gtco.c
+++ b/drivers/input/tablet/gtco.c
@@ -858,6 +858,14 @@ static int gtco_probe(struct usb_interface *usbinterface,
 		goto err_free_buf;
 	}
 
+	/* Sanity check that a device has an endpoint */
+	if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) {
+		dev_err(&usbinterface->dev,
+			"Invalid number of endpoints\n");
+		error = -EINVAL;
+		goto err_free_urb;
+	}
+
 	/*
 	 * The endpoint is always altsetting 0, we know this since we know
 	 * this device only has one interrupt endpoint
@@ -879,7 +887,7 @@ static int gtco_probe(struct usb_interface *usbinterface,
 	 * HID report descriptor
 	 */
 	if (usb_get_extra_descriptor(usbinterface->cur_altsetting,
-				     HID_DEVICE_TYPE, &hid_desc) != 0){
+				     HID_DEVICE_TYPE, &hid_desc) != 0) {
 		dev_err(&usbinterface->dev,
 			"Can't retrieve exta USB descriptor to get hid report descriptor length\n");
 		error = -EIO;
diff --git a/drivers/input/tablet/hanwang.c b/drivers/input/tablet/hanwang.c
index cd852059b99e..df4bea96d7ed 100644
--- a/drivers/input/tablet/hanwang.c
+++ b/drivers/input/tablet/hanwang.c
@@ -340,6 +340,9 @@ static int hanwang_probe(struct usb_interface *intf, const struct usb_device_id
 	int error;
 	int i;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	hanwang = kzalloc(sizeof(struct hanwang), GFP_KERNEL);
 	input_dev = input_allocate_device();
 	if (!hanwang || !input_dev) {
diff --git a/drivers/input/tablet/kbtab.c b/drivers/input/tablet/kbtab.c
index d2ac7c2b5b82..2812f9236b7d 100644
--- a/drivers/input/tablet/kbtab.c
+++ b/drivers/input/tablet/kbtab.c
@@ -122,6 +122,9 @@ static int kbtab_probe(struct usb_interface *intf, const struct usb_device_id *i
 	struct input_dev *input_dev;
 	int error = -ENOMEM;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	kbtab = kzalloc(sizeof(struct kbtab), GFP_KERNEL);
 	input_dev = input_allocate_device();
 	if (!kbtab || !input_dev)
diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index ac09855fa435..486f8fe242da 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -905,9 +905,9 @@ static irqreturn_t elants_i2c_irq(int irq, void *_dev)
 
 		case QUEUE_HEADER_NORMAL:
 			report_count = ts->buf[FW_HDR_COUNT];
-			if (report_count > 3) {
+			if (report_count == 0 || report_count > 3) {
 				dev_err(&client->dev,
-					"too large report count: %*ph\n",
+					"bad report count: %*ph\n",
 					HEADER_SIZE, ts->buf);
 				break;
 			}
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index d214f22ed305..0146e2c74649 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -126,7 +126,7 @@ struct sur40_image_header {
 #define VIDEO_PACKET_SIZE  16384
 
 /* polling interval (ms) */
-#define POLL_INTERVAL 4
+#define POLL_INTERVAL 1
 
 /* maximum number of contacts FIXME: this is a guess? */
 #define MAX_CONTACTS 64
@@ -441,7 +441,7 @@ static void sur40_process_video(struct sur40_state *sur40)
 
 	/* return error if streaming was stopped in the meantime */
 	if (sur40->sequence == -1)
-		goto err_poll;
+		return;
 
 	/* mark as finished */
 	v4l2_get_timestamp(&new_buf->vb.timestamp);
@@ -500,6 +500,9 @@ static int sur40_probe(struct usb_interface *interface,
 	if (iface_desc->desc.bInterfaceClass != 0xFF)
 		return -ENODEV;
 
+	if (iface_desc->desc.bNumEndpoints < 5)
+		return -ENODEV;
+
 	/* Use endpoint #4 (0x86). */
 	endpoint = &iface_desc->endpoint[4].desc;
 	if (endpoint->bEndpointAddress != TOUCH_ENDPOINT)
@@ -730,6 +733,7 @@ static int sur40_start_streaming(struct vb2_queue *vq, unsigned int count)
 static void sur40_stop_streaming(struct vb2_queue *vq)
 {
 	struct sur40_state *sur40 = vb2_get_drv_priv(vq);
+	vb2_wait_for_all_buffers(vq);
 	sur40->sequence = -1;
 
 	/* Release all active buffers */
diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c
index 7295c198aa08..6fe55d598fac 100644
--- a/drivers/input/touchscreen/tsc2004.c
+++ b/drivers/input/touchscreen/tsc2004.c
@@ -22,6 +22,11 @@
 #include <linux/regmap.h>
 #include "tsc200x-core.h"
 
+static const struct input_id tsc2004_input_id = {
+	.bustype = BUS_I2C,
+	.product = 2004,
+};
+
 static int tsc2004_cmd(struct device *dev, u8 cmd)
 {
 	u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd;
@@ -42,7 +47,7 @@ static int tsc2004_probe(struct i2c_client *i2c,
 			 const struct i2c_device_id *id)
 
 {
-	return tsc200x_probe(&i2c->dev, i2c->irq, BUS_I2C,
+	return tsc200x_probe(&i2c->dev, i2c->irq, &tsc2004_input_id,
 			     devm_regmap_init_i2c(i2c, &tsc200x_regmap_config),
 			     tsc2004_cmd);
 }
diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c
index b9f593dfd2ef..f2c5f0e47f77 100644
--- a/drivers/input/touchscreen/tsc2005.c
+++ b/drivers/input/touchscreen/tsc2005.c
@@ -24,6 +24,11 @@
 #include <linux/regmap.h>
 #include "tsc200x-core.h"
 
+static const struct input_id tsc2005_input_id = {
+	.bustype = BUS_SPI,
+	.product = 2005,
+};
+
 static int tsc2005_cmd(struct device *dev, u8 cmd)
 {
 	u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd;
@@ -62,7 +67,7 @@ static int tsc2005_probe(struct spi_device *spi)
 	if (error)
 		return error;
 
-	return tsc200x_probe(&spi->dev, spi->irq, BUS_SPI,
+	return tsc200x_probe(&spi->dev, spi->irq, &tsc2005_input_id,
 			     devm_regmap_init_spi(spi, &tsc200x_regmap_config),
 			     tsc2005_cmd);
 }
diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c
index 15240c1ee850..dfa7f1c4f545 100644
--- a/drivers/input/touchscreen/tsc200x-core.c
+++ b/drivers/input/touchscreen/tsc200x-core.c
@@ -450,7 +450,7 @@ static void tsc200x_close(struct input_dev *input)
 	mutex_unlock(&ts->mutex);
 }
 
-int tsc200x_probe(struct device *dev, int irq, __u16 bustype,
+int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id,
 		  struct regmap *regmap,
 		  int (*tsc200x_cmd)(struct device *dev, u8 cmd))
 {
@@ -547,9 +547,18 @@ int tsc200x_probe(struct device *dev, int irq, __u16 bustype,
 	snprintf(ts->phys, sizeof(ts->phys),
 		 "%s/input-ts", dev_name(dev));
 
-	input_dev->name = "TSC200X touchscreen";
+	if (tsc_id->product == 2004) {
+		input_dev->name = "TSC200X touchscreen";
+	} else {
+		input_dev->name = devm_kasprintf(dev, GFP_KERNEL,
+						 "TSC%04d touchscreen",
+						 tsc_id->product);
+		if (!input_dev->name)
+			return -ENOMEM;
+	}
+
 	input_dev->phys = ts->phys;
-	input_dev->id.bustype = bustype;
+	input_dev->id = *tsc_id;
 	input_dev->dev.parent = dev;
 	input_dev->evbit[0] = BIT(EV_ABS) | BIT(EV_KEY);
 	input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h
index 7a482d102614..49a63a3c6840 100644
--- a/drivers/input/touchscreen/tsc200x-core.h
+++ b/drivers/input/touchscreen/tsc200x-core.h
@@ -70,7 +70,7 @@
 extern const struct regmap_config tsc200x_regmap_config;
 extern const struct dev_pm_ops tsc200x_pm_ops;
 
-int tsc200x_probe(struct device *dev, int irq, __u16 bustype,
+int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id,
 		  struct regmap *regmap,
 		  int (*tsc200x_cmd)(struct device *dev, u8 cmd));
 int tsc200x_remove(struct device *dev);
diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c
index 2792ca397dd0..3ed0ce1e4dcb 100644
--- a/drivers/input/touchscreen/wacom_w8001.c
+++ b/drivers/input/touchscreen/wacom_w8001.c
@@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar <jayakumar.lkml@gmail.com>");
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-#define W8001_MAX_LENGTH	11
+#define W8001_MAX_LENGTH	13
 #define W8001_LEAD_MASK		0x80
 #define W8001_LEAD_BYTE		0x80
 #define W8001_TAB_MASK		0x40
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 9bbadaaf6bc3..7b3845aa5983 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -370,8 +370,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
 			point.coord_x = point.coord_y = 0;
 		}
 
-		point.state = payload[9 * i + 5] & 0x03;
-		point.id = (payload[9 * i + 5] & 0xfc) >> 2;
+		point.state = payload[9 * i + 5] & 0x0f;
+		point.id = (payload[9 * i + 5] & 0xf0) >> 4;
 
 		/* determine touch major, minor and orientation */
 		point.area_major = max(payload[9 * i + 6],
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index fc836f523afa..a0ef57483ebb 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -91,6 +91,7 @@ struct iommu_dev_data {
 	struct list_head dev_data_list;	  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
 	u16 devid;			  /* PCI Device ID */
+	u16 alias;			  /* Alias Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	bool passthrough;		  /* Device is identity mapped */
 	struct {
@@ -125,6 +126,13 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom)
 	return container_of(dom, struct protection_domain, domain);
 }
 
+static inline u16 get_device_id(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return PCI_DEVID(pdev->bus->number, pdev->devfn);
+}
+
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -162,6 +170,68 @@ out_unlock:
 	return dev_data;
 }
 
+static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	*(u16 *)data = alias;
+	return 0;
+}
+
+static u16 get_alias(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	u16 devid, ivrs_alias, pci_alias;
+
+	devid = get_device_id(dev);
+	ivrs_alias = amd_iommu_alias_table[devid];
+	pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
+
+	if (ivrs_alias == pci_alias)
+		return ivrs_alias;
+
+	/*
+	 * DMA alias showdown
+	 *
+	 * The IVRS is fairly reliable in telling us about aliases, but it
+	 * can't know about every screwy device.  If we don't have an IVRS
+	 * reported alias, use the PCI reported alias.  In that case we may
+	 * still need to initialize the rlookup and dev_table entries if the
+	 * alias is to a non-existent device.
+	 */
+	if (ivrs_alias == devid) {
+		if (!amd_iommu_rlookup_table[pci_alias]) {
+			amd_iommu_rlookup_table[pci_alias] =
+				amd_iommu_rlookup_table[devid];
+			memcpy(amd_iommu_dev_table[pci_alias].data,
+			       amd_iommu_dev_table[devid].data,
+			       sizeof(amd_iommu_dev_table[pci_alias].data));
+		}
+
+		return pci_alias;
+	}
+
+	pr_info("AMD-Vi: Using IVRS reported alias %02x:%02x.%d "
+		"for device %s[%04x:%04x], kernel reported alias "
+		"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
+		PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device,
+		PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
+		PCI_FUNC(pci_alias));
+
+	/*
+	 * If we don't have a PCI DMA alias and the IVRS alias is on the same
+	 * bus, then the IVRS table may know about a quirk that we don't.
+	 */
+	if (pci_alias == devid &&
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
+		pdev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN;
+		pdev->dma_alias_devfn = ivrs_alias & 0xff;
+		pr_info("AMD-Vi: Added PCI DMA alias %02x.%d for %s\n",
+			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias),
+			dev_name(dev));
+	}
+
+	return ivrs_alias;
+}
+
 static struct iommu_dev_data *find_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -174,13 +244,6 @@ static struct iommu_dev_data *find_dev_data(u16 devid)
 	return dev_data;
 }
 
-static inline u16 get_device_id(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	return PCI_DEVID(pdev->bus->number, pdev->devfn);
-}
-
 static struct iommu_dev_data *get_dev_data(struct device *dev)
 {
 	return dev->archdata.iommu;
@@ -289,9 +352,11 @@ static void init_iommu_group(struct device *dev)
 	if (!domain)
 		goto out;
 
-	dma_domain = to_pdomain(domain)->priv;
+	if (to_pdomain(domain)->flags == PD_DMA_OPS_MASK) {
+		dma_domain = to_pdomain(domain)->priv;
+		init_unity_mappings_for_device(dev, dma_domain);
+	}
 
-	init_unity_mappings_for_device(dev, dma_domain);
 out:
 	iommu_group_put(group);
 }
@@ -308,6 +373,8 @@ static int iommu_init_device(struct device *dev)
 	if (!dev_data)
 		return -ENOMEM;
 
+	dev_data->alias = get_alias(dev);
+
 	if (pci_iommuv2_capable(pdev)) {
 		struct amd_iommu *iommu;
 
@@ -328,7 +395,7 @@ static void iommu_ignore_device(struct device *dev)
 	u16 devid, alias;
 
 	devid = get_device_id(dev);
-	alias = amd_iommu_alias_table[devid];
+	alias = get_alias(dev);
 
 	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
 	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
@@ -859,7 +926,7 @@ again:
 	next_tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE;
 	left      = (head - next_tail) % CMD_BUFFER_SIZE;
 
-	if (left <= 2) {
+	if (left <= 0x20) {
 		struct iommu_cmd sync_cmd;
 		volatile u64 sem = 0;
 		int ret;
@@ -1017,7 +1084,7 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 	int ret;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = amd_iommu_alias_table[dev_data->devid];
+	alias = dev_data->alias;
 
 	ret = iommu_flush_dte(iommu, dev_data->devid);
 	if (!ret && alias != dev_data->devid)
@@ -1766,6 +1833,9 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
 		kfree(dom->aperture[i]);
 	}
 
+	if (dom->domain.id)
+		domain_id_free(dom->domain.id);
+
 	kfree(dom);
 }
 
@@ -1891,7 +1961,7 @@ static void do_attach(struct iommu_dev_data *dev_data,
 	bool ats;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = amd_iommu_alias_table[dev_data->devid];
+	alias = dev_data->alias;
 	ats   = dev_data->ats.enabled;
 
 	/* Update data structures */
@@ -1925,7 +1995,7 @@ static void do_detach(struct iommu_dev_data *dev_data)
 		return;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
-	alias = amd_iommu_alias_table[dev_data->devid];
+	alias = dev_data->alias;
 
 	/* decrease reference counters */
 	dev_data->domain->dev_iommu[iommu->index] -= 1;
@@ -2257,8 +2327,15 @@ static void update_device_table(struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
 
-	list_for_each_entry(dev_data, &domain->dev_list, list)
+	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+
+		if (dev_data->devid == dev_data->alias)
+			continue;
+
+		/* There is an alias, update device table entry for it */
+		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled);
+	}
 }
 
 static void update_domain(struct protection_domain *domain)
@@ -2905,9 +2982,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
 	struct protection_domain *domain;
-
-	if (!dom)
-		return;
+	struct dma_ops_domain *dma_dom;
 
 	domain = to_pdomain(dom);
 
@@ -2916,13 +2991,24 @@ static void amd_iommu_domain_free(struct iommu_domain *dom)
 
 	BUG_ON(domain->dev_cnt != 0);
 
-	if (domain->mode != PAGE_MODE_NONE)
-		free_pagetable(domain);
+	if (!dom)
+		return;
 
-	if (domain->flags & PD_IOMMUV2_MASK)
-		free_gcr3_table(domain);
+	switch (dom->type) {
+	case IOMMU_DOMAIN_DMA:
+		dma_dom = domain->priv;
+		dma_ops_domain_free(dma_dom);
+		break;
+	default:
+		if (domain->mode != PAGE_MODE_NONE)
+			free_pagetable(domain);
 
-	protection_domain_free(domain);
+		if (domain->flags & PD_IOMMUV2_MASK)
+			free_gcr3_table(domain);
+
+		protection_domain_free(domain);
+		break;
+	}
 }
 
 static void amd_iommu_detach_device(struct iommu_domain *dom,
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index bf4959f4225b..94f1bf772ec9 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1363,13 +1363,23 @@ static int __init amd_iommu_init_pci(void)
 			break;
 	}
 
+	/*
+	 * Order is important here to make sure any unity map requirements are
+	 * fulfilled. The unity mappings are created and written to the device
+	 * table during the amd_iommu_init_api() call.
+	 *
+	 * After that we call init_device_table_dma() to make sure any
+	 * uninitialized DTE will block DMA, and in the end we flush the caches
+	 * of all IOMMUs to make sure the changes to the device table are
+	 * active.
+	 */
+	ret = amd_iommu_init_api();
+
 	init_device_table_dma();
 
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
 
-	ret = amd_iommu_init_api();
-
 	if (!ret)
 		print_iommu_info();
 
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 7caf2fa237f2..22160e481794 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -699,9 +699,9 @@ out_clear_state:
 
 out_unregister:
 	mmu_notifier_unregister(&pasid_state->mn, mm);
+	mmput(mm);
 
 out_free:
-	mmput(mm);
 	free_pasid_state(pasid_state);
 
 out:
@@ -809,8 +809,10 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 		goto out_free_domain;
 
 	group = iommu_group_get(&pdev->dev);
-	if (!group)
+	if (!group) {
+		ret = -EINVAL;
 		goto out_free_domain;
+	}
 
 	ret = iommu_attach_group(dev_state->domain, group);
 	if (ret != 0)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4e5118a4cd30..00df3832faab 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -870,7 +870,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
 	 * We may have concurrent producers, so we need to be careful
 	 * not to touch any of the shadow cmdq state.
 	 */
-	queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+	queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
 	dev_err(smmu->dev, "skipping command in error state:\n");
 	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
 		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
@@ -881,7 +881,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
 		return;
 	}
 
-	queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
 }
 
 static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
@@ -1025,6 +1025,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		case STRTAB_STE_0_CFG_S2_TRANS:
 			ste_live = true;
 			break;
+		case STRTAB_STE_0_CFG_ABORT:
+			if (disable_bypass)
+				break;
 		default:
 			BUG(); /* STE corruption */
 		}
@@ -1919,6 +1922,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.detach_dev		= arm_smmu_detach_dev,
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
+	.map_sg			= default_iommu_map_sg,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 72d6182666cb..347a3c17f73a 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -68,7 +68,8 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	if (!iovad)
 		return;
 
-	put_iova_domain(iovad);
+	if (iovad->granule)
+		put_iova_domain(iovad);
 	kfree(iovad);
 	domain->iova_cookie = NULL;
 }
@@ -403,7 +404,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 		unsigned int s_length = sg_dma_len(s);
 		unsigned int s_dma_len = s->length;
 
-		s->offset = s_offset;
+		s->offset += s_offset;
 		s->length = s_length;
 		sg_dma_address(s) = dma_addr + s_offset;
 		dma_addr += s_dma_len;
@@ -422,7 +423,7 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 
 	for_each_sg(sg, s, nents, i) {
 		if (sg_dma_address(s) != DMA_ERROR_CODE)
-			s->offset = sg_dma_address(s);
+			s->offset += sg_dma_address(s);
 		if (sg_dma_len(s))
 			s->length = sg_dma_len(s);
 		sg_dma_address(s) = DMA_ERROR_CODE;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 3821c4786662..e913a930ac80 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -326,7 +326,9 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 	struct pci_dev *pdev = to_pci_dev(data);
 	struct dmar_pci_notify_info *info;
 
-	/* Only care about add/remove events for physical functions */
+	/* Only care about add/remove events for physical functions.
+	 * For VFs we actually do the lookup based on the corresponding
+	 * PF in device_to_iommu() anyway. */
 	if (pdev->is_virtfn)
 		return NOTIFY_DONE;
 	if (action != BUS_NOTIFY_ADD_DEVICE &&
@@ -1858,10 +1860,11 @@ static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
 	/*
 	 * All PCI devices managed by this unit should have been destroyed.
 	 */
-	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
+	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt) {
 		for_each_active_dev_scope(dmaru->devices,
 					  dmaru->devices_cnt, i, dev)
 			return -EBUSY;
+	}
 
 	ret = dmar_ir_hotplug(dmaru, false);
 	if (ret == 0)
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 97c41b8ab5d9..29a31eb9ace3 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -647,6 +647,7 @@ static struct platform_driver exynos_sysmmu_driver __refdata = {
 		.name		= "exynos-sysmmu",
 		.of_match_table	= sysmmu_of_match,
 		.pm		= &sysmmu_pm_ops,
+		.suppress_bind_attrs = true,
 	}
 };
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a2e1b7f14df2..f9711aceef54 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -885,7 +885,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 		return NULL;
 
 	if (dev_is_pci(dev)) {
+		struct pci_dev *pf_pdev;
+
 		pdev = to_pci_dev(dev);
+		/* VFs aren't listed in scope tables; we need to look up
+		 * the PF instead to find the IOMMU. */
+		pf_pdev = pci_physfn(pdev);
+		dev = &pf_pdev->dev;
 		segment = pci_domain_nr(pdev->bus);
 	} else if (has_acpi_companion(dev))
 		dev = &ACPI_COMPANION(dev)->dev;
@@ -898,6 +904,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, tmp) {
 			if (tmp == dev) {
+				/* For a VF use its original BDF# not that of the PF
+				 * which we used for the IOMMU lookup. Strictly speaking
+				 * we could do this for all PCI devices; we only need to
+				 * get the BDF# from the scope table for ACPI matches. */
+				if (pdev && pdev->is_virtfn)
+					goto got_pdev;
+
 				*bus = drhd->devices[i].bus;
 				*devfn = drhd->devices[i].devfn;
 				goto out;
@@ -1124,7 +1137,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
 			goto next;
 
-		level_pfn = pfn & level_mask(level - 1);
+		level_pfn = pfn & level_mask(level);
 		level_pte = phys_to_virt(dma_pte_addr(pte));
 
 		if (level > 2)
@@ -1672,6 +1685,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 	if (!iommu->domains || !iommu->domain_ids)
 		return;
 
+again:
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
 		struct dmar_domain *domain;
@@ -1684,10 +1698,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 
 		domain = info->domain;
 
-		dmar_remove_one_dev_info(domain, info->dev);
+		__dmar_remove_one_dev_info(info);
 
-		if (!domain_type_is_vm_or_si(domain))
+		if (!domain_type_is_vm_or_si(domain)) {
+			/*
+			 * The domain_exit() function  can't be called under
+			 * device_domain_lock, as it takes this lock itself.
+			 * So release the lock here and re-run the loop
+			 * afterwards.
+			 */
+			spin_unlock_irqrestore(&device_domain_lock, flags);
 			domain_exit(domain);
+			goto again;
+		}
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
@@ -1970,6 +1993,28 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	if (context_present(context))
 		goto out_unlock;
 
+	/*
+	 * For kdump cases, old valid entries may be cached due to the
+	 * in-flight DMA and copied pgtable, but there is no unmapping
+	 * behaviour for them, thus we need an explicit cache flush for
+	 * the newly-mapped device. For kdump, at this point, the device
+	 * is supposed to finish reset at its driver probe stage, so no
+	 * in-flight DMA will exist, and we don't need to worry anymore
+	 * hereafter.
+	 */
+	if (context_copied(context)) {
+		u16 did_old = context_domain_id(context);
+
+		if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) {
+			iommu->flush.flush_context(iommu, did_old,
+						   (((u16)bus) << 8) | devfn,
+						   DMA_CCMD_MASK_NOBIT,
+						   DMA_CCMD_DEVICE_INVL);
+			iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
+						 DMA_TLB_DSI_FLUSH);
+		}
+	}
+
 	pgd = domain->pgd;
 
 	context_clear_entry(context);
@@ -2032,7 +2077,7 @@ out_unlock:
 	spin_unlock(&iommu->lock);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 struct domain_context_mapping_data {
@@ -3169,11 +3214,6 @@ static int __init init_dmars(void)
 			}
 		}
 
-		iommu_flush_write_buffer(iommu);
-		iommu_set_root_entry(iommu);
-		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
-		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
-
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
 #ifdef CONFIG_INTEL_IOMMU_SVM
@@ -3182,6 +3222,18 @@ static int __init init_dmars(void)
 #endif
 	}
 
+	/*
+	 * Now that qi is enabled on all iommus, set the root entry and flush
+	 * caches. This is required on some Intel X58 chipsets, otherwise the
+	 * flush_context function will loop forever and the boot hangs.
+	 */
+	for_each_active_iommu(iommu, drhd) {
+		iommu_flush_write_buffer(iommu);
+		iommu_set_root_entry(iommu);
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+	}
+
 	if (iommu_pass_through)
 		iommu_identity_mapping |= IDENTMAP_ALL;
 
@@ -3189,13 +3241,14 @@ static int __init init_dmars(void)
 	iommu_identity_mapping |= IDENTMAP_GFX;
 #endif
 
+	check_tylersburg_isoch();
+
 	if (iommu_identity_mapping) {
 		ret = si_domain_init(hw_pass_through);
 		if (ret)
 			goto free_iommu;
 	}
 
-	check_tylersburg_isoch();
 
 	/*
 	 * If we copied translations from a previous kernel in the kdump
@@ -4175,10 +4228,11 @@ int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 	if (!atsru)
 		return 0;
 
-	if (!atsru->include_all && atsru->devices && atsru->devices_cnt)
+	if (!atsru->include_all && atsru->devices && atsru->devices_cnt) {
 		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
 					  i, dev)
 			return -EBUSY;
+	}
 
 	return 0;
 }
@@ -4989,6 +5043,25 @@ static void intel_iommu_remove_device(struct device *dev)
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
+#define MAX_NR_PASID_BITS (20)
+static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu)
+{
+	/*
+	 * Convert ecap_pss to extend context entry pts encoding, also
+	 * respect the soft pasid_max value set by the iommu.
+	 * - number of PASID bits = ecap_pss + 1
+	 * - number of PASID table entries = 2^(pts + 5)
+	 * Therefore, pts = ecap_pss - 4
+	 * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15
+	 */
+	if (ecap_pss(iommu->ecap) < 5)
+		return 0;
+
+	/* pasid_max is encoded as actual number of entries not the bits */
+	return find_first_bit((unsigned long *)&iommu->pasid_max,
+			MAX_NR_PASID_BITS) - 5;
+}
+
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
 {
 	struct device_domain_info *info;
@@ -5021,7 +5094,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
 
 	if (!(ctx_lo & CONTEXT_PASIDE)) {
 		context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
-		context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap);
+		context[1].lo = (u64)virt_to_phys(iommu->pasid_table) |
+			intel_iommu_get_pts(iommu);
+
 		wmb();
 		/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
 		 * extended to permit requests-with-PASID if the PASIDE bit
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index d9939fa9b588..f929879ecae6 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 	struct page *pages;
 	int order;
 
-	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-	if (order < 0)
-		order = 0;
-
+	/* Start at 2 because it's defined as 2^(1+PSS) */
+	iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
+
+	/* Eventually I'm promised we will get a multi-level PASID table
+	 * and it won't have to be physically contiguous. Until then,
+	 * limit the size because 8MiB contiguous allocations can be hard
+	 * to come by. The limit of 0x20000, which is 1MiB for each of
+	 * the PASID and PASID-state tables, is somewhat arbitrary. */
+	if (iommu->pasid_max > 0x20000)
+		iommu->pasid_max = 0x20000;
+
+	order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!pages) {
 		pr_warn("IOMMU: %s: Failed to allocate PASID table\n",
@@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 	pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
 
 	if (ecap_dis(iommu->ecap)) {
+		/* Just making it explicit... */
+		BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));
 		pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (pages)
 			iommu->pasid_state_table = page_address(pages);
@@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 
 int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
 {
-	int order;
-
-	order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-	if (order < 0)
-		order = 0;
+	int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 
 	if (iommu->pasid_table) {
 		free_pages((unsigned long)iommu->pasid_table, order);
@@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		}
 		svm->iommu = iommu;
 
-		if (pasid_max > 2 << ecap_pss(iommu->ecap))
-			pasid_max = 2 << ecap_pss(iommu->ecap);
+		if (pasid_max > iommu->pasid_max)
+			pasid_max = iommu->pasid_max;
 
 		/* Do not use PASID 0 in caching mode (virtualised IOMMU) */
 		ret = idr_alloc(&iommu->pasid_idr, svm,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0e3b0092ec92..a070fa39521a 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -391,36 +391,30 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	device->dev = dev;
 
 	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
-	if (ret) {
-		kfree(device);
-		return ret;
-	}
+	if (ret)
+		goto err_free_device;
 
 	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
 rename:
 	if (!device->name) {
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_remove_link;
 	}
 
 	ret = sysfs_create_link_nowarn(group->devices_kobj,
 				       &dev->kobj, device->name);
 	if (ret) {
-		kfree(device->name);
 		if (ret == -EEXIST && i >= 0) {
 			/*
 			 * Account for the slim chance of collision
 			 * and append an instance to the name.
 			 */
+			kfree(device->name);
 			device->name = kasprintf(GFP_KERNEL, "%s.%d",
 						 kobject_name(&dev->kobj), i++);
 			goto rename;
 		}
-
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return ret;
+		goto err_free_name;
 	}
 
 	kobject_get(group->devices_kobj);
@@ -432,8 +426,10 @@ rename:
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain)
-		__iommu_attach_device(group->domain, dev);
+		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;
 
 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,
@@ -444,6 +440,21 @@ rename:
 	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
 
 	return 0;
+
+err_put_group:
+	mutex_lock(&group->mutex);
+	list_del(&device->list);
+	mutex_unlock(&group->mutex);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+err_free_name:
+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
 
@@ -848,7 +859,8 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	if (!group->default_domain) {
 		group->default_domain = __iommu_domain_alloc(dev->bus,
 							     IOMMU_DOMAIN_DMA);
-		group->domain = group->default_domain;
+		if (!group->domain)
+			group->domain = group->default_domain;
 	}
 
 	ret = iommu_group_add_device(group, dev);
diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c
index 37199b9b2cfa..831a195cb806 100644
--- a/drivers/irqchip/irq-atmel-aic-common.c
+++ b/drivers/irqchip/irq-atmel-aic-common.c
@@ -148,9 +148,9 @@ void __init aic_common_rtc_irq_fixup(struct device_node *root)
 	struct device_node *np;
 	void __iomem *regs;
 
-	np = of_find_compatible_node(root, NULL, "atmel,at91rm9200-rtc");
+	np = of_find_compatible_node(NULL, NULL, "atmel,at91rm9200-rtc");
 	if (!np)
-		np = of_find_compatible_node(root, NULL,
+		np = of_find_compatible_node(NULL, NULL,
 					     "atmel,at91sam9x5-rtc");
 
 	if (!np)
@@ -202,7 +202,6 @@ void __init aic_common_irq_fixup(const struct of_device_id *matches)
 		return;
 
 	match = of_match_node(matches, root);
-	of_node_put(root);
 
 	if (match) {
 		void (*fixup)(struct device_node *) = match->data;
diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index 8a0c7f288198..981c3959da59 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -176,6 +176,7 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 {
 	struct irq_domain_chip_generic *dgc = d->gc;
 	struct irq_chip_generic *gc;
+	unsigned long flags;
 	unsigned smr;
 	int idx;
 	int ret;
@@ -194,12 +195,12 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 
 	gc = dgc->gc[idx];
 
-	irq_gc_lock(gc);
+	irq_gc_lock_irqsave(gc, flags);
 	smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
 	ret = aic_common_set_priority(intspec[2], &smr);
 	if (!ret)
 		irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
-	irq_gc_unlock(gc);
+	irq_gc_unlock_irqrestore(gc, flags);
 
 	return ret;
 }
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 62bb840c613f..7dee71bde350 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -258,6 +258,7 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 				 unsigned int *out_type)
 {
 	struct irq_chip_generic *bgc = irq_get_domain_generic_chip(d, 0);
+	unsigned long flags;
 	unsigned smr;
 	int ret;
 
@@ -269,13 +270,13 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 	if (ret)
 		return ret;
 
-	irq_gc_lock(bgc);
+	irq_gc_lock_irqsave(bgc, flags);
 	irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
 	smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
 	ret = aic_common_set_priority(intspec[2], &smr);
 	if (!ret)
 		irq_reg_writel(bgc, intspec[2] | smr, AT91_AIC5_SMR);
-	irq_gc_unlock(bgc);
+	irq_gc_unlock_irqrestore(bgc, flags);
 
 	return ret;
 }
diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index 0fea985ef1dc..d7af88534971 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -216,6 +216,31 @@ static int bcm7038_l1_set_affinity(struct irq_data *d,
 	return 0;
 }
 
+static void bcm7038_l1_cpu_offline(struct irq_data *d)
+{
+	struct cpumask *mask = irq_data_get_affinity_mask(d);
+	int cpu = smp_processor_id();
+	cpumask_t new_affinity;
+
+	/* This CPU was not on the affinity mask */
+	if (!cpumask_test_cpu(cpu, mask))
+		return;
+
+	if (cpumask_weight(mask) > 1) {
+		/*
+		 * Multiple CPU affinity, remove this CPU from the affinity
+		 * mask
+		 */
+		cpumask_copy(&new_affinity, mask);
+		cpumask_clear_cpu(cpu, &new_affinity);
+	} else {
+		/* Only CPU, put on the lowest online CPU */
+		cpumask_clear(&new_affinity);
+		cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity);
+	}
+	irq_set_affinity_locked(d, &new_affinity, false);
+}
+
 static int __init bcm7038_l1_init_one(struct device_node *dn,
 				      unsigned int idx,
 				      struct bcm7038_l1_chip *intc)
@@ -267,6 +292,7 @@ static struct irq_chip bcm7038_l1_irq_chip = {
 	.irq_mask		= bcm7038_l1_mask,
 	.irq_unmask		= bcm7038_l1_unmask,
 	.irq_set_affinity	= bcm7038_l1_set_affinity,
+	.irq_cpu_offline	= bcm7038_l1_cpu_offline,
 };
 
 static int bcm7038_l1_map(struct irq_domain *d, unsigned int virq,
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index a159529f9d53..c5f1757ac61d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
 
@@ -71,6 +72,7 @@ struct its_node {
 	struct list_head	its_device_list;
 	u64			flags;
 	u32			ite_size;
+	int			numa_node;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -600,11 +602,23 @@ static void its_unmask_irq(struct irq_data *d)
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu;
+	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+		if (its_dev->its->numa_node >= 0) {
+			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+			if (!cpumask_intersects(mask_val, cpu_mask))
+				return -EINVAL;
+		}
+	}
+
+	cpu = cpumask_any_and(mask_val, cpu_mask);
+
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -1081,6 +1095,16 @@ static void its_cpu_init_collection(void)
 	list_for_each_entry(its, &its_nodes, entry) {
 		u64 target;
 
+		/* avoid cross node collections and its mapping */
+		if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+			struct device_node *cpu_node;
+
+			cpu_node = of_get_cpu_node(cpu, NULL);
+			if (its->numa_node != NUMA_NO_NODE &&
+				its->numa_node != of_node_to_nid(cpu_node))
+				continue;
+		}
+
 		/*
 		 * We now have to bind each collection to its target
 		 * redistributor.
@@ -1308,9 +1332,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	const struct cpumask *cpu_mask = cpu_online_mask;
+
+	/* get the cpu_mask of local node */
+	if (its_dev->its->numa_node >= 0)
+		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
 	/* Bind the LPI to the first possible CPU */
-	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
@@ -1400,6 +1429,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1409,6 +1445,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_22375,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+	{
+		.desc	= "ITS: Cavium erratum 23144",
+		.iidr	= 0xa100034c,	/* ThunderX pass 1.x */
+		.mask	= 0xffff0fff,
+		.init	= its_enable_quirk_cavium_23144,
+	},
+#endif
 	{
 	}
 };
@@ -1470,6 +1514,7 @@ static int its_probe(struct device_node *node, struct irq_domain *parent)
 	its->base = its_base;
 	its->phys_base = res.start;
 	its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+	its->numa_node = of_node_to_nid(node);
 
 	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
 	if (!its->cmd_base) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index d7be6ddc34f6..5a1490b046ac 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -142,7 +142,7 @@ static void gic_enable_redist(bool enable)
 			return;	/* No PM support in this redistributor */
 	}
 
-	while (count--) {
+	while (--count) {
 		val = readl_relaxed(rbase + GICR_WAKER);
 		if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
 			break;
@@ -361,6 +361,13 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 			if (static_key_true(&supports_deactivate))
 				gic_write_dir(irqnr);
 #ifdef CONFIG_SMP
+			/*
+			 * Unlike GICv2, we don't need an smp_rmb() here.
+			 * The control dependency from gic_read_iar to
+			 * the ISB in gic_write_eoir is enough to ensure
+			 * that any shared data read by handle_IPI will
+			 * be read after the ACK.
+			 */
 			handle_IPI(irqnr, regs);
 #else
 			WARN_ONCE(true, "Unexpected SGI received!\n");
@@ -380,6 +387,15 @@ static void __init gic_dist_init(void)
 	writel_relaxed(0, base + GICD_CTLR);
 	gic_dist_wait_for_rwp();
 
+	/*
+	 * Configure SPIs as non-secure Group-1. This will only matter
+	 * if the GIC only has a single security state. This will not
+	 * do the right thing if the kernel is running in secure mode,
+	 * but that's not the intended use case anyway.
+	 */
+	for (i = 32; i < gic_data.irq_nr; i += 32)
+		writel_relaxed(~0, base + GICD_IGROUPR + i / 8);
+
 	gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
 
 	/* Enable distributor with ARE, Group1 */
@@ -494,6 +510,9 @@ static void gic_cpu_init(void)
 
 	rbase = gic_data_rdist_sgi_base();
 
+	/* Configure SGIs/PPIs as non-secure Group-1 */
+	writel_relaxed(~0, rbase + GICR_IGROUPR0);
+
 	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
 
 	/* Give LPIs a spin */
@@ -525,7 +544,7 @@ static struct notifier_block gic_cpu_notifier = {
 static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
 				   unsigned long cluster_id)
 {
-	int cpu = *base_cpu;
+	int next_cpu, cpu = *base_cpu;
 	unsigned long mpidr = cpu_logical_map(cpu);
 	u16 tlist = 0;
 
@@ -539,9 +558,10 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
 
 		tlist |= 1 << (mpidr & 0xf);
 
-		cpu = cpumask_next(cpu, mask);
-		if (cpu >= nr_cpu_ids)
+		next_cpu = cpumask_next(cpu, mask);
+		if (next_cpu >= nr_cpu_ids)
 			goto out;
+		cpu = next_cpu;
 
 		mpidr = cpu_logical_map(cpu);
 
@@ -612,6 +632,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	int enabled;
 	u64 val;
 
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
+
 	if (gic_irq_in_rdist(d))
 		return -EINVAL;
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index abf2ffaed392..cebd8efe651a 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -347,6 +347,14 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 			if (static_key_true(&supports_deactivate))
 				writel_relaxed(irqstat, cpu_base + GIC_CPU_DEACTIVATE);
 #ifdef CONFIG_SMP
+			/*
+			 * Ensure any shared data written by the CPU sending
+			 * the IPI is read after we've read the ACK register
+			 * on the GIC.
+			 *
+			 * Pairs with the write barrier in gic_raise_softirq
+			 */
+			smp_rmb();
 			handle_IPI(irqnr, regs);
 #endif
 			continue;
diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c
index 15af9a9753e5..2d203b422129 100644
--- a/drivers/irqchip/irq-imx-gpcv2.c
+++ b/drivers/irqchip/irq-imx-gpcv2.c
@@ -230,6 +230,8 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
+	raw_spin_lock_init(&cd->rlock);
+
 	cd->gpc_base = of_iomap(node, 0);
 	if (!cd->gpc_base) {
 		pr_err("fsl-gpcv2: unable to map gpc registers\n");
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index deb89d63a728..e684be1bb7c0 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -19,9 +19,9 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
@@ -39,6 +39,7 @@ struct keystone_irq_device {
 	struct irq_domain	*irqd;
 	struct regmap		*devctrl_regs;
 	u32			devctrl_offset;
+	raw_spinlock_t		wa_lock;
 };
 
 static inline u32 keystone_irq_readl(struct keystone_irq_device *kirq)
@@ -83,17 +84,15 @@ static void keystone_irq_ack(struct irq_data *d)
 	/* nothing to do here */
 }
 
-static void keystone_irq_handler(struct irq_desc *desc)
+static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
-	struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
+	struct keystone_irq_device *kirq = keystone_irq;
+	unsigned long wa_lock_flags;
 	unsigned long pending;
 	int src, virq;
 
 	dev_dbg(kirq->dev, "start irq %d\n", irq);
 
-	chained_irq_enter(irq_desc_get_chip(desc), desc);
-
 	pending = keystone_irq_readl(kirq);
 	keystone_irq_writel(kirq, pending);
 
@@ -111,13 +110,15 @@ static void keystone_irq_handler(struct irq_desc *desc)
 			if (!virq)
 				dev_warn(kirq->dev, "sporious irq detected hwirq %d, virq %d\n",
 					 src, virq);
+			raw_spin_lock_irqsave(&kirq->wa_lock, wa_lock_flags);
 			generic_handle_irq(virq);
+			raw_spin_unlock_irqrestore(&kirq->wa_lock,
+						   wa_lock_flags);
 		}
 	}
 
-	chained_irq_exit(irq_desc_get_chip(desc), desc);
-
 	dev_dbg(kirq->dev, "end irq %d\n", irq);
+	return IRQ_HANDLED;
 }
 
 static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
@@ -182,9 +183,16 @@ static int keystone_irq_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	raw_spin_lock_init(&kirq->wa_lock);
+
 	platform_set_drvdata(pdev, kirq);
 
-	irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
+	ret = request_irq(kirq->irq, keystone_irq_handler,
+			  0, dev_name(dev), kirq);
+	if (ret) {
+		irq_domain_remove(kirq->irqd);
+		return ret;
+	}
 
 	/* clear all source bits */
 	keystone_irq_writel(kirq, ~0x0);
@@ -199,6 +207,8 @@ static int keystone_irq_remove(struct platform_device *pdev)
 	struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
 	int hwirq;
 
+	free_irq(kirq->irq, kirq);
+
 	for (hwirq = 0; hwirq < KEYSTONE_N_IRQ; hwirq++)
 		irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
 
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 9e17ef27a183..6f1dbd52ec91 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -915,8 +915,11 @@ static int __init gic_of_init(struct device_node *node,
 		gic_len = resource_size(&res);
 	}
 
-	if (mips_cm_present())
+	if (mips_cm_present()) {
 		write_gcr_gic_base(gic_base | CM_GCR_GIC_BASE_GICEN_MSK);
+		/* Ensure GIC region is enabled before trying to access it */
+		__sync();
+	}
 	gic_present = true;
 
 	__gic_init(gic_base, gic_len, cpu_vec, 0, node);
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index efe50845939d..05fa9f7af53c 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -131,12 +131,16 @@ static struct irq_chip mxs_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = icoll_mask_irq,
 	.irq_unmask = icoll_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 static struct irq_chip asm9260_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = asm9260_mask_irq,
 	.irq_unmask = asm9260_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs)
@@ -183,7 +187,7 @@ static void __iomem * __init icoll_init_iobase(struct device_node *np)
 	void __iomem *icoll_base;
 
 	icoll_base = of_io_request_and_map(np, 0, np->name);
-	if (!icoll_base)
+	if (IS_ERR(icoll_base))
 		panic("%s: unable to map resource", np->full_name);
 	return icoll_base;
 }
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 4ef178078e5b..1254e98f6b57 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -154,9 +154,9 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
 
 	gc = irq_get_domain_generic_chip(domain, 0);
 	gc->reg_base = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!gc->reg_base) {
+	if (IS_ERR(gc->reg_base)) {
 		pr_err("unable to map resource\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(gc->reg_base);
 		goto fail_irqd_remove;
 	}
 
diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c
index bb3ac5fe5846..72a391e01011 100644
--- a/drivers/irqchip/irq-xtensa-mx.c
+++ b/drivers/irqchip/irq-xtensa-mx.c
@@ -142,7 +142,7 @@ static struct irq_chip xtensa_mx_irq_chip = {
 int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent)
 {
 	struct irq_domain *root_domain =
-		irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+		irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0,
 				&xtensa_mx_irq_domain_ops,
 				&xtensa_mx_irq_chip);
 	irq_set_default_host(root_domain);
diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c
index 472ae1770964..f728755fa292 100644
--- a/drivers/irqchip/irq-xtensa-pic.c
+++ b/drivers/irqchip/irq-xtensa-pic.c
@@ -89,7 +89,7 @@ static struct irq_chip xtensa_irq_chip = {
 int __init xtensa_pic_init_legacy(struct device_node *interrupt_parent)
 {
 	struct irq_domain *root_domain =
-		irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+		irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0,
 				&xtensa_irq_domain_ops, &xtensa_irq_chip);
 	irq_set_default_host(root_domain);
 	return 0;
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index aecec6d32463..7f1c625b08ec 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -2317,6 +2317,9 @@ static int gigaset_probe(struct usb_interface *interface,
 		return -ENODEV;
 	}
 
+	if (hostif->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	dev_info(&udev->dev,
 		 "%s: Device matched (Vendor: 0x%x, Product: 0x%x)\n",
 		 __func__, le16_to_cpu(udev->descriptor.idVendor),
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 2a506fe0c8a4..74bf1a17ae7c 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -762,8 +762,10 @@ static int __init ser_gigaset_init(void)
 	driver = gigaset_initdriver(GIGASET_MINOR, GIGASET_MINORS,
 				    GIGASET_MODULENAME, GIGASET_DEVNAME,
 				    &ops, THIS_MODULE);
-	if (!driver)
+	if (!driver) {
+		rc = -ENOMEM;
 		goto error;
+	}
 
 	rc = tty_register_ldisc(N_GIGASET_M101, &gigaset_ldisc);
 	if (rc != 0) {
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index d7c286656a25..7b4ddf0a39ec 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -11304,7 +11304,8 @@ static void mixer_notify_update(PLCI *plci, byte others)
 				((CAPI_MSG *) msg)->header.ncci = 0;
 				((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT;
 				((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3;
-				PUT_WORD(&(((CAPI_MSG *) msg)->info.facility_req.structs[1]), LI_REQ_SILENT_UPDATE);
+				((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff;
+				((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8;
 				((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0;
 				w = api_put(notify_plci->appl, (CAPI_MSG *) msg);
 				if (w != _QUEUE_FULL)
diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c
index 9b856e1890d1..e4c43a17b333 100644
--- a/drivers/isdn/i4l/isdn_common.c
+++ b/drivers/isdn/i4l/isdn_common.c
@@ -1379,6 +1379,7 @@ isdn_ioctl(struct file *file, uint cmd, ulong arg)
 			if (arg) {
 				if (copy_from_user(bname, argp, sizeof(bname) - 1))
 					return -EFAULT;
+				bname[sizeof(bname)-1] = 0;
 			} else
 				return -EINVAL;
 			ret = mutex_lock_interruptible(&dev->mtx);
diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c
index aa5dd5668528..dbad5c431bcb 100644
--- a/drivers/isdn/i4l/isdn_net.c
+++ b/drivers/isdn/i4l/isdn_net.c
@@ -2611,10 +2611,9 @@ isdn_net_newslave(char *parm)
 	char newname[10];
 
 	if (p) {
-		/* Slave-Name MUST not be empty */
-		if (!strlen(p + 1))
+		/* Slave-Name MUST not be empty or overflow 'newname' */
+		if (strscpy(newname, p + 1, sizeof(newname)) <= 0)
 			return NULL;
-		strcpy(newname, p + 1);
 		*p = 0;
 		/* Master must already exist */
 		if (!(n = isdn_net_findif(parm)))
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 9c1e8adaf4fc..bf3fbd00a091 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -2364,7 +2364,7 @@ static struct ippp_ccp_reset_state *isdn_ppp_ccp_reset_alloc_state(struct ippp_s
 		       id);
 		return NULL;
 	} else {
-		rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_KERNEL);
+		rs = kzalloc(sizeof(struct ippp_ccp_reset_state), GFP_ATOMIC);
 		if (!rs)
 			return NULL;
 		rs->state = CCPResetIdle;
diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c
index feca07be85f5..1eb9fb33db38 100644
--- a/drivers/leds/leds-ktd2692.c
+++ b/drivers/leds/leds-ktd2692.c
@@ -296,15 +296,15 @@ static int ktd2692_parse_dt(struct ktd2692_context *led, struct device *dev,
 		return -ENXIO;
 
 	led->ctrl_gpio = devm_gpiod_get(dev, "ctrl", GPIOD_ASIS);
-	if (IS_ERR(led->ctrl_gpio)) {
-		ret = PTR_ERR(led->ctrl_gpio);
+	ret = PTR_ERR_OR_ZERO(led->ctrl_gpio);
+	if (ret) {
 		dev_err(dev, "cannot get ctrl-gpios %d\n", ret);
 		return ret;
 	}
 
 	led->aux_gpio = devm_gpiod_get(dev, "aux", GPIOD_ASIS);
-	if (IS_ERR(led->aux_gpio)) {
-		ret = PTR_ERR(led->aux_gpio);
+	ret = PTR_ERR_OR_ZERO(led->aux_gpio);
+	if (ret) {
 		dev_err(dev, "cannot get aux-gpios %d\n", ret);
 		return ret;
 	}
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index a54b339951a3..2a96ff6923f0 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -89,6 +89,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 
 		list_move_tail(&blk->list, &lun->bb_list);
 		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_free_blocks--;
 	}
 
 	return 0;
@@ -345,7 +346,7 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	if (!dev->ops->submit_io)
-		return 0;
+		return -ENODEV;
 
 	/* Convert address space */
 	gennvm_generic_to_addr_mode(dev, rqd);
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 134e4faba482..596347f345db 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -287,6 +287,10 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
 	}
 
 	page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
+	if (!page) {
+		bio_put(bio);
+		return -ENOMEM;
+	}
 
 	while ((slot = find_first_zero_bit(rblk->invalid_pages,
 					    nr_pgs_per_blk)) < nr_pgs_per_blk) {
@@ -427,7 +431,7 @@ static void rrpc_lun_gc(struct work_struct *work)
 	if (nr_blocks_need < rrpc->nr_luns)
 		nr_blocks_need = rrpc->nr_luns;
 
-	spin_lock(&lun->lock);
+	spin_lock(&rlun->lock);
 	while (nr_blocks_need > lun->nr_free_blocks &&
 					!list_empty(&rlun->prio_list)) {
 		struct rrpc_block *rblock = block_prio_find_max(rlun);
@@ -436,16 +440,16 @@ static void rrpc_lun_gc(struct work_struct *work)
 		if (!rblock->nr_invalid_pages)
 			break;
 
+		gcb = mempool_alloc(rrpc->gcb_pool, GFP_ATOMIC);
+		if (!gcb)
+			break;
+
 		list_del_init(&rblock->prio);
 
 		BUG_ON(!block_is_full(rrpc, rblock));
 
 		pr_debug("rrpc: selected block '%lu' for GC\n", block->id);
 
-		gcb = mempool_alloc(rrpc->gcb_pool, GFP_ATOMIC);
-		if (!gcb)
-			break;
-
 		gcb->rrpc = rrpc;
 		gcb->rblk = rblock;
 		INIT_WORK(&gcb->ws_gc, rrpc_block_gc);
@@ -454,7 +458,7 @@ static void rrpc_lun_gc(struct work_struct *work)
 
 		nr_blocks_need--;
 	}
-	spin_unlock(&lun->lock);
+	spin_unlock(&rlun->lock);
 
 	/* TODO: Hint that request queue can be started again */
 }
@@ -650,11 +654,12 @@ static int rrpc_end_io(struct nvm_rq *rqd, int error)
 	if (bio_data_dir(rqd->bio) == WRITE)
 		rrpc_end_io_write(rrpc, rrqd, laddr, npages);
 
+	bio_put(rqd->bio);
+
 	if (rrqd->flags & NVM_IOTYPE_GC)
 		return 0;
 
 	rrpc_unlock_rq(rrpc, rqd);
-	bio_put(rqd->bio);
 
 	if (npages > 1)
 		nvm_dev_dma_free(rrpc->dev, rqd->ppa_list, rqd->dma_ppa_list);
@@ -841,6 +846,13 @@ static int rrpc_submit_io(struct rrpc *rrpc, struct bio *bio,
 	err = nvm_submit_io(rrpc->dev, rqd);
 	if (err) {
 		pr_err("rrpc: I/O submission failed: %d\n", err);
+		bio_put(bio);
+		if (!(flags & NVM_IOTYPE_GC)) {
+			rrpc_unlock_rq(rrpc, rqd);
+			if (rqd->nr_pages > 1)
+				nvm_dev_dma_free(rrpc->dev,
+			rqd->ppa_list, rqd->dma_ppa_list);
+		}
 		return NVM_IO_ERR;
 	}
 
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index 6a4811f85705..9cf826df89b1 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -104,11 +104,14 @@ static void tx_tick(struct mbox_chan *chan, int r)
 	/* Submit next message */
 	msg_submit(chan);
 
+	if (!mssg)
+		return;
+
 	/* Notify the client */
-	if (mssg && chan->cl->tx_done)
+	if (chan->cl->tx_done)
 		chan->cl->tx_done(chan->cl, mssg, r);
 
-	if (chan->cl->tx_block)
+	if (r != -ETIME && chan->cl->tx_block)
 		complete(&chan->tx_complete);
 }
 
@@ -261,7 +264,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 
 	msg_submit(chan);
 
-	if (chan->cl->tx_block && chan->active_req) {
+	if (chan->cl->tx_block) {
 		unsigned long wait;
 		int ret;
 
@@ -272,8 +275,8 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 
 		ret = wait_for_completion_timeout(&chan->tx_complete, wait);
 		if (ret == 0) {
-			t = -EIO;
-			tx_tick(chan, -EIO);
+			t = -ETIME;
+			tx_tick(chan, t);
 		}
 	}
 
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index 004926955263..b0155b05cddb 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -57,7 +57,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus,
 	mdev->id = GDD_DEV(reg1);
 	mdev->rev = GDD_REV(reg1);
 	mdev->var = GDD_VAR(reg1);
-	mdev->bar = GDD_BAR(reg1);
+	mdev->bar = GDD_BAR(reg2);
 	mdev->group = GDD_GRP(reg2);
 	mdev->inst = GDD_INS(reg2);
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 7913fdcfc849..108249f52fa9 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -357,6 +357,7 @@ config DM_LOG_USERSPACE
 config DM_RAID
        tristate "RAID 1/4/5/6/10 target"
        depends on BLK_DEV_DM
+       select MD_RAID0
        select MD_RAID1
        select MD_RAID10
        select MD_RAID456
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 6b420a55c745..c3ea03c9a1a8 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -425,7 +425,7 @@ struct cache {
 	 * until a gc finishes - otherwise we could pointlessly burn a ton of
 	 * cpu
 	 */
-	unsigned		invalidate_needs_gc:1;
+	unsigned		invalidate_needs_gc;
 
 	bool			discard; /* Get rid of? */
 
@@ -593,8 +593,8 @@ struct cache_set {
 
 	/* Counts how many sectors bio_insert has added to the cache */
 	atomic_t		sectors_to_gc;
+	wait_queue_head_t	gc_wait;
 
-	wait_queue_head_t	moving_gc_wait;
 	struct keybuf		moving_gc_keys;
 	/* Number of moving GC bios in flight */
 	struct semaphore	moving_in_flight;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 22b9e34ceb75..5b815e64c1c9 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1762,33 +1762,34 @@ static void bch_btree_gc(struct cache_set *c)
 	bch_moving_gc(c);
 }
 
-static int bch_gc_thread(void *arg)
+static bool gc_should_run(struct cache_set *c)
 {
-	struct cache_set *c = arg;
 	struct cache *ca;
 	unsigned i;
 
-	while (1) {
-again:
-		bch_btree_gc(c);
+	for_each_cache(ca, c, i)
+		if (ca->invalidate_needs_gc)
+			return true;
 
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (kthread_should_stop())
-			break;
+	if (atomic_read(&c->sectors_to_gc) < 0)
+		return true;
 
-		mutex_lock(&c->bucket_lock);
+	return false;
+}
 
-		for_each_cache(ca, c, i)
-			if (ca->invalidate_needs_gc) {
-				mutex_unlock(&c->bucket_lock);
-				set_current_state(TASK_RUNNING);
-				goto again;
-			}
+static int bch_gc_thread(void *arg)
+{
+	struct cache_set *c = arg;
 
-		mutex_unlock(&c->bucket_lock);
+	while (1) {
+		wait_event_interruptible(c->gc_wait,
+			   kthread_should_stop() || gc_should_run(c));
 
-		try_to_freeze();
-		schedule();
+		if (kthread_should_stop())
+			break;
+
+		set_gc_sectors(c);
+		bch_btree_gc(c);
 	}
 
 	return 0;
@@ -1796,11 +1797,10 @@ again:
 
 int bch_gc_thread_start(struct cache_set *c)
 {
-	c->gc_thread = kthread_create(bch_gc_thread, c, "bcache_gc");
+	c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc");
 	if (IS_ERR(c->gc_thread))
 		return PTR_ERR(c->gc_thread);
 
-	set_task_state(c->gc_thread, TASK_INTERRUPTIBLE);
 	return 0;
 }
 
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index 5c391fa01bed..9b80417cd547 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -260,8 +260,7 @@ void bch_initial_mark_key(struct cache_set *, int, struct bkey *);
 
 static inline void wake_up_gc(struct cache_set *c)
 {
-	if (c->gc_thread)
-		wake_up_process(c->gc_thread);
+	wake_up(&c->gc_wait);
 }
 
 #define MAP_DONE	0
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 25fa8445bb24..2410df1c2a05 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -196,10 +196,8 @@ static void bch_data_insert_start(struct closure *cl)
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
-	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
-		set_gc_sectors(op->c);
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
 		wake_up_gc(op->c);
-	}
 
 	if (op->bypass)
 		return bch_data_invalidate(cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 8d0ead98eb6e..7b5880b8874c 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1015,8 +1015,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	 */
 	atomic_set(&dc->count, 1);
 
-	if (bch_cached_dev_writeback_start(dc))
+	/* Block writeback thread, but spawn it */
+	down_write(&dc->writeback_lock);
+	if (bch_cached_dev_writeback_start(dc)) {
+		up_write(&dc->writeback_lock);
 		return -ENOMEM;
+	}
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
 		bch_sectors_dirty_init(dc);
@@ -1028,6 +1032,9 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
 
+	/* Allow the writeback thread to proceed */
+	up_write(&dc->writeback_lock);
+
 	pr_info("Caching %s as %s on set %pU",
 		bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
 		dc->disk.c->sb.set_uuid);
@@ -1366,6 +1373,9 @@ static void cache_set_flush(struct closure *cl)
 	struct btree *b;
 	unsigned i;
 
+	if (!c)
+		closure_return(cl);
+
 	bch_cache_accounting_destroy(&c->accounting);
 
 	kobject_put(&c->internal);
@@ -1479,6 +1489,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
 	init_waitqueue_head(&c->bucket_wait);
+	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
 
 	spin_lock_init(&c->btree_gc_time.lock);
@@ -1537,6 +1548,7 @@ static void run_cache_set(struct cache_set *c)
 
 	for_each_cache(ca, c, i)
 		c->nbuckets += ca->sb.nbuckets;
+	set_gc_sectors(c);
 
 	if (CACHE_SYNC(&c->sb)) {
 		LIST_HEAD(journal);
@@ -1808,7 +1820,7 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
 	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
-	    !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
@@ -1828,11 +1840,12 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 	return 0;
 }
 
-static void register_cache(struct cache_sb *sb, struct page *sb_page,
+static int register_cache(struct cache_sb *sb, struct page *sb_page,
 				struct block_device *bdev, struct cache *ca)
 {
 	char name[BDEVNAME_SIZE];
-	const char *err = "cannot allocate memory";
+	const char *err = NULL;
+	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
 	ca->bdev = bdev;
@@ -1847,27 +1860,35 @@ static void register_cache(struct cache_sb *sb, struct page *sb_page,
 	if (blk_queue_discard(bdev_get_queue(ca->bdev)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
-	if (cache_alloc(sb, ca) != 0)
+	ret = cache_alloc(sb, ca);
+	if (ret != 0)
 		goto err;
 
-	err = "error creating kobject";
-	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache"))
-		goto err;
+	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
+		err = "error calling kobject_add";
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	mutex_lock(&bch_register_lock);
 	err = register_cache_set(ca);
 	mutex_unlock(&bch_register_lock);
 
-	if (err)
-		goto err;
+	if (err) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	pr_info("registered cache device %s", bdevname(bdev, name));
+
 out:
 	kobject_put(&ca->kobj);
-	return;
+
 err:
-	pr_notice("error opening %s: %s", bdevname(bdev, name), err);
-	goto out;
+	if (err)
+		pr_notice("error opening %s: %s", bdevname(bdev, name), err);
+
+	return ret;
 }
 
 /* Global interfaces/init */
@@ -1965,7 +1986,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		if (!ca)
 			goto err_close;
 
-		register_cache(sb, sb_page, bdev, ca);
+		if (register_cache(sb, sb_page, bdev, ca) != 0)
+			goto err_close;
 	}
 out:
 	if (sb_page)
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 2dd33085b331..cdceefd0e57d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -222,7 +222,7 @@ static DEFINE_SPINLOCK(param_spinlock);
  * Buffers are freed after this timeout
  */
 static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
-static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
+static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
 static unsigned long dm_bufio_allocated_kmem_cache;
@@ -914,10 +914,11 @@ static void __get_memory_limit(struct dm_bufio_client *c,
 {
 	unsigned long buffers;
 
-	if (ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch) {
-		mutex_lock(&dm_bufio_clients_lock);
-		__cache_size_refresh();
-		mutex_unlock(&dm_bufio_clients_lock);
+	if (unlikely(ACCESS_ONCE(dm_bufio_cache_size) != dm_bufio_cache_size_latch)) {
+		if (mutex_trylock(&dm_bufio_clients_lock)) {
+			__cache_size_refresh();
+			mutex_unlock(&dm_bufio_clients_lock);
+		}
 	}
 
 	buffers = dm_bufio_cache_size_per_client >>
@@ -1513,10 +1514,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp)
 	return true;
 }
 
-static unsigned get_retain_buffers(struct dm_bufio_client *c)
+static unsigned long get_retain_buffers(struct dm_bufio_client *c)
 {
-        unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
-        return retain_bytes / c->block_size;
+        unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
+        return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT);
 }
 
 static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
@@ -1526,7 +1527,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 	struct dm_buffer *b, *tmp;
 	unsigned long freed = 0;
 	unsigned long count = nr_to_scan;
-	unsigned retain_target = get_retain_buffers(c);
+	unsigned long retain_target = get_retain_buffers(c);
 
 	for (l = 0; l < LIST_SIZE; l++) {
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
@@ -1752,11 +1753,19 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz)
 static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
 {
 	struct dm_buffer *b, *tmp;
-	unsigned retain_target = get_retain_buffers(c);
-	unsigned count;
+	unsigned long retain_target = get_retain_buffers(c);
+	unsigned long count;
+	LIST_HEAD(write_list);
 
 	dm_bufio_lock(c);
 
+	__check_watermark(c, &write_list);
+	if (unlikely(!list_empty(&write_list))) {
+		dm_bufio_unlock(c);
+		__flush_write_list(&write_list);
+		dm_bufio_lock(c);
+	}
+
 	count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY];
 	list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_CLEAN], lru_list) {
 		if (count <= retain_target)
@@ -1781,6 +1790,8 @@ static void cleanup_old_buffers(void)
 
 	mutex_lock(&dm_bufio_clients_lock);
 
+	__cache_size_refresh();
+
 	list_for_each_entry(c, &dm_bufio_all_clients, client_list)
 		__evict_old_buffers(c, max_age_hz);
 
@@ -1904,7 +1915,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
 module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
 
-module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR);
+module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");
 
 module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index f6543f3a970f..d3c55d7754af 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -867,18 +867,55 @@ static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd,
 	return 0;
 }
 
-#define WRITE_LOCK(cmd) \
-	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
-		return -EINVAL; \
-	down_write(&cmd->root_lock)
+static bool cmd_write_lock(struct dm_cache_metadata *cmd)
+{
+	down_write(&cmd->root_lock);
+	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) {
+		up_write(&cmd->root_lock);
+		return false;
+	}
+	return true;
+}
 
-#define WRITE_LOCK_VOID(cmd) \
-	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
-		return; \
-	down_write(&cmd->root_lock)
+#define WRITE_LOCK(cmd)				\
+	do {					\
+		if (!cmd_write_lock((cmd)))	\
+			return -EINVAL;		\
+	} while(0)
+
+#define WRITE_LOCK_VOID(cmd)			\
+	do {					\
+		if (!cmd_write_lock((cmd)))	\
+			return;			\
+	} while(0)
 
 #define WRITE_UNLOCK(cmd) \
-	up_write(&cmd->root_lock)
+	up_write(&(cmd)->root_lock)
+
+static bool cmd_read_lock(struct dm_cache_metadata *cmd)
+{
+	down_read(&cmd->root_lock);
+	if (cmd->fail_io) {
+		up_read(&cmd->root_lock);
+		return false;
+	}
+	return true;
+}
+
+#define READ_LOCK(cmd)				\
+	do {					\
+		if (!cmd_read_lock((cmd)))	\
+			return -EINVAL;		\
+	} while(0)
+
+#define READ_LOCK_VOID(cmd)			\
+	do {					\
+		if (!cmd_read_lock((cmd)))	\
+			return;			\
+	} while(0)
+
+#define READ_UNLOCK(cmd) \
+	up_read(&(cmd)->root_lock)
 
 int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
 {
@@ -1015,22 +1052,20 @@ int dm_cache_load_discards(struct dm_cache_metadata *cmd,
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = __load_discards(cmd, fn, context);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
 
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd)
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result)
 {
-	dm_cblock_t r;
+	READ_LOCK(cmd);
+	*result = cmd->cache_blocks;
+	READ_UNLOCK(cmd);
 
-	down_read(&cmd->root_lock);
-	r = cmd->cache_blocks;
-	up_read(&cmd->root_lock);
-
-	return r;
+	return 0;
 }
 
 static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
@@ -1188,9 +1223,9 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = __load_mappings(cmd, policy, fn, context);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1215,18 +1250,18 @@ static int __dump_mappings(struct dm_cache_metadata *cmd)
 
 void dm_cache_dump(struct dm_cache_metadata *cmd)
 {
-	down_read(&cmd->root_lock);
+	READ_LOCK_VOID(cmd);
 	__dump_mappings(cmd);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 }
 
 int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = cmd->changed;
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1276,9 +1311,9 @@ int dm_cache_set_dirty(struct dm_cache_metadata *cmd,
 void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
 				 struct dm_cache_statistics *stats)
 {
-	down_read(&cmd->root_lock);
+	READ_LOCK_VOID(cmd);
 	*stats = cmd->stats;
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 }
 
 void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
@@ -1291,17 +1326,19 @@ void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
 
 int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown)
 {
-	int r;
+	int r = -EINVAL;
 	flags_mutator mutator = (clean_shutdown ? set_clean_shutdown :
 				 clear_clean_shutdown);
 
 	WRITE_LOCK(cmd);
+	if (cmd->fail_io)
+		goto out;
+
 	r = __commit_transaction(cmd, mutator);
 	if (r)
 		goto out;
 
 	r = __begin_transaction(cmd);
-
 out:
 	WRITE_UNLOCK(cmd);
 	return r;
@@ -1312,9 +1349,10 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
 {
 	int r = -EINVAL;
 
-	down_read(&cmd->root_lock);
-	r = dm_sm_get_nr_free(cmd->metadata_sm, result);
-	up_read(&cmd->root_lock);
+	READ_LOCK(cmd);
+	if (!cmd->fail_io)
+		r = dm_sm_get_nr_free(cmd->metadata_sm, result);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1324,9 +1362,10 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
 {
 	int r = -EINVAL;
 
-	down_read(&cmd->root_lock);
-	r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
-	up_read(&cmd->root_lock);
+	READ_LOCK(cmd);
+	if (!cmd->fail_io)
+		r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1417,7 +1456,13 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
 
 int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result)
 {
-	return blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+	int r;
+
+	READ_LOCK(cmd);
+	r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+	READ_UNLOCK(cmd);
+
+	return r;
 }
 
 void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd)
@@ -1440,10 +1485,7 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
 	struct dm_block *sblock;
 	struct cache_disk_superblock *disk_super;
 
-	/*
-	 * We ignore fail_io for this function.
-	 */
-	down_write(&cmd->root_lock);
+	WRITE_LOCK(cmd);
 	set_bit(NEEDS_CHECK, &cmd->flags);
 
 	r = superblock_lock(cmd, &sblock);
@@ -1458,19 +1500,17 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
 	dm_bm_unlock(sblock);
 
 out:
-	up_write(&cmd->root_lock);
+	WRITE_UNLOCK(cmd);
 	return r;
 }
 
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd)
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result)
 {
-	bool needs_check;
+	READ_LOCK(cmd);
+	*result = !!test_bit(NEEDS_CHECK, &cmd->flags);
+	READ_UNLOCK(cmd);
 
-	down_read(&cmd->root_lock);
-	needs_check = !!test_bit(NEEDS_CHECK, &cmd->flags);
-	up_read(&cmd->root_lock);
-
-	return needs_check;
+	return 0;
 }
 
 int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index 2ffee21f318d..8528744195e5 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -66,7 +66,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
  * origin blocks to map to.
  */
 int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size);
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd);
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result);
 
 int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
 				   sector_t discard_block_size,
@@ -137,7 +137,7 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
  */
 int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result);
 
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd);
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result);
 int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd);
 void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd);
 void dm_cache_metadata_set_read_write(struct dm_cache_metadata *cmd);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 2fd4c8296144..b59615ddf6ba 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -251,7 +251,7 @@ struct cache {
 	/*
 	 * Fields for converting from sectors to blocks.
 	 */
-	uint32_t sectors_per_block;
+	sector_t sectors_per_block;
 	int sectors_per_block_shift;
 
 	spinlock_t lock;
@@ -987,9 +987,14 @@ static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mod
 
 static void set_cache_mode(struct cache *cache, enum cache_metadata_mode new_mode)
 {
-	bool needs_check = dm_cache_metadata_needs_check(cache->cmd);
+	bool needs_check;
 	enum cache_metadata_mode old_mode = get_cache_mode(cache);
 
+	if (dm_cache_metadata_needs_check(cache->cmd, &needs_check)) {
+		DMERR("unable to read needs_check flag, setting failure mode");
+		new_mode = CM_FAIL;
+	}
+
 	if (new_mode == CM_WRITE && needs_check) {
 		DMERR("%s: unable to switch cache to write mode until repaired.",
 		      cache_device_name(cache));
@@ -3513,6 +3518,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 	char buf[BDEVNAME_SIZE];
 	struct cache *cache = ti->private;
 	dm_cblock_t residency;
+	bool needs_check;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -3541,11 +3547,11 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
 		residency = policy_residency(cache->policy);
 
-		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
+		DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ",
 		       (unsigned)DM_CACHE_METADATA_BLOCK_SIZE,
 		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
 		       (unsigned long long)nr_blocks_metadata,
-		       cache->sectors_per_block,
+		       (unsigned long long)cache->sectors_per_block,
 		       (unsigned long long) from_cblock(residency),
 		       (unsigned long long) from_cblock(cache->cache_size),
 		       (unsigned) atomic_read(&cache->stats.read_hit),
@@ -3586,7 +3592,9 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("rw ");
 
-		if (dm_cache_metadata_needs_check(cache->cmd))
+		r = dm_cache_metadata_needs_check(cache->cmd, &needs_check);
+
+		if (r || needs_check)
 			DMEMIT("needs_check ");
 		else
 			DMEMIT("- ");
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 3147c8d09ea8..de628883ee3d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -112,8 +112,7 @@ struct iv_tcw_private {
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
-	     DM_CRYPT_EXIT_THREAD};
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
 
 /*
  * The fields in here must be read only after initialization.
@@ -1204,18 +1203,20 @@ continue_locked:
 		if (!RB_EMPTY_ROOT(&cc->write_tree))
 			goto pop_from_list;
 
-		if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) {
-			spin_unlock_irq(&cc->write_thread_wait.lock);
-			break;
-		}
-
-		__set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 		__add_wait_queue(&cc->write_thread_wait, &wait);
 
 		spin_unlock_irq(&cc->write_thread_wait.lock);
 
+		if (unlikely(kthread_should_stop())) {
+			set_task_state(current, TASK_RUNNING);
+			remove_wait_queue(&cc->write_thread_wait, &wait);
+			break;
+		}
+
 		schedule();
 
+		set_task_state(current, TASK_RUNNING);
 		spin_lock_irq(&cc->write_thread_wait.lock);
 		__remove_wait_queue(&cc->write_thread_wait, &wait);
 		goto continue_locked;
@@ -1499,12 +1500,15 @@ static int crypt_set_key(struct crypt_config *cc, char *key)
 	if (!cc->key_size && strcmp(key, "-"))
 		goto out;
 
+	/* clear the flag since following operations may invalidate previously valid key */
+	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+
 	if (cc->key_size && crypt_decode_key(cc->key, key, cc->key_size) < 0)
 		goto out;
 
-	set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
-
 	r = crypt_setkey_allcpus(cc);
+	if (!r)
+		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
 out:
 	/* Hex key string not needed after here, so wipe it. */
@@ -1530,13 +1534,8 @@ static void crypt_dtr(struct dm_target *ti)
 	if (!cc)
 		return;
 
-	if (cc->write_thread) {
-		spin_lock_irq(&cc->write_thread_wait.lock);
-		set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags);
-		wake_up_locked(&cc->write_thread_wait);
-		spin_unlock_irq(&cc->write_thread_wait.lock);
+	if (cc->write_thread)
 		kthread_stop(cc->write_thread);
-	}
 
 	if (cc->io_queue)
 		destroy_workqueue(cc->io_queue);
@@ -1920,6 +1919,13 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 
+	/*
+	 * Check if bio is too large, split as needed.
+	 */
+	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+	    bio_data_dir(bio) == WRITE)
+		dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+
 	io = dm_per_bio_data(bio, cc->per_bio_data_size);
 	crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
 	io->ctx.req = (struct ablkcipher_request *)(io + 1);
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 665bf3285618..32e76c5ee741 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -961,15 +961,15 @@ static int metadata_commit(struct era_metadata *md)
 		}
 	}
 
-	r = save_sm_root(md);
+	r = dm_tm_pre_commit(md->tm);
 	if (r) {
-		DMERR("%s: save_sm_root failed", __func__);
+		DMERR("%s: pre commit failed", __func__);
 		return r;
 	}
 
-	r = dm_tm_pre_commit(md->tm);
+	r = save_sm_root(md);
 	if (r) {
-		DMERR("%s: pre commit failed", __func__);
+		DMERR("%s: save_sm_root failed", __func__);
 		return r;
 	}
 
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 09e2afcafd2d..78f403b45ab3 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -200,11 +200,13 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	if (!(fc->up_interval + fc->down_interval)) {
 		ti->error = "Total (up + down) interval is zero";
+		r = -EINVAL;
 		goto bad;
 	}
 
 	if (fc->up_interval + fc->down_interval < fc->up_interval) {
 		ti->error = "Interval overflow";
+		r = -EINVAL;
 		goto bad;
 	}
 
@@ -289,10 +291,14 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		pb->bio_submitted = true;
 
 		/*
-		 * Map reads as normal.
+		 * Error reads if neither corrupt_bio_byte or drop_writes are set.
+		 * Otherwise, flakey_end_io() will decide if the reads should be modified.
 		 */
-		if (bio_data_dir(bio) == READ)
+		if (bio_data_dir(bio) == READ) {
+			if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags))
+				return -EIO;
 			goto map_bio;
+		}
 
 		/*
 		 * Drop writes?
@@ -328,14 +334,22 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	/*
-	 * Corrupt successful READs while in down state.
-	 * If flags were specified, only corrupt those that match.
-	 */
-	if (fc->corrupt_bio_byte && !error && pb->bio_submitted &&
-	    (bio_data_dir(bio) == READ) && (fc->corrupt_bio_rw == READ) &&
-	    all_corrupt_bio_flags_match(bio, fc))
-		corrupt_bio_data(bio, fc);
+	if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
+		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
+		    all_corrupt_bio_flags_match(bio, fc)) {
+			/*
+			 * Corrupt successful matching READs while in down state.
+			 */
+			corrupt_bio_data(bio, fc);
+
+		} else if (!test_bit(DROP_WRITES, &fc->flags)) {
+			/*
+			 * Error read during the down_interval if drop_writes
+			 * wasn't configured.
+			 */
+			return -EIO;
+		}
+	}
 
 	return error;
 }
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 80a439543259..e503279c34fc 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1843,7 +1843,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
 	if (r)
 		goto out;
 
-	param->data_size = sizeof(*param);
+	param->data_size = offsetof(struct dm_ioctl, data);
 	r = fn(param, input_param_size);
 
 	if (unlikely(param->flags & DM_BUFFER_FULL_FLAG) &&
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 624589d51c2c..c8b513ee117c 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -258,12 +258,12 @@ static int log_one_block(struct log_writes_c *lc,
 		goto out;
 	sector++;
 
-	bio = bio_alloc(GFP_KERNEL, block->vec_cnt);
+	atomic_inc(&lc->io_blocks);
+	bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES));
 	if (!bio) {
 		DMERR("Couldn't alloc log bio");
 		goto error;
 	}
-	atomic_inc(&lc->io_blocks);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = lc->logdev->bdev;
@@ -280,7 +280,7 @@ static int log_one_block(struct log_writes_c *lc,
 		if (ret != block->vecs[i].bv_len) {
 			atomic_inc(&lc->io_blocks);
 			submit_bio(WRITE, bio);
-			bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i);
+			bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES));
 			if (!bio) {
 				DMERR("Couldn't alloc log bio");
 				goto error;
@@ -456,9 +456,9 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	ret = -EINVAL;
 	lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write");
-	if (!lc->log_kthread) {
+	if (IS_ERR(lc->log_kthread)) {
+		ret = PTR_ERR(lc->log_kthread);
 		ti->error = "Couldn't alloc kthread";
 		dm_put_device(ti, lc->dev);
 		dm_put_device(ti, lc->logdev);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index cfa29f574c2a..5b2ef966012b 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1220,10 +1220,10 @@ static void activate_path(struct work_struct *work)
 {
 	struct pgpath *pgpath =
 		container_of(work, struct pgpath, activate_path.work);
+	struct request_queue *q = bdev_get_queue(pgpath->path.dev->bdev);
 
-	if (pgpath->is_active)
-		scsi_dh_activate(bdev_get_queue(pgpath->path.dev->bdev),
-				 pg_init_done, pgpath);
+	if (pgpath->is_active && !blk_queue_dying(q))
+		scsi_dh_activate(q, pg_init_done, pgpath);
 	else
 		pg_init_done(pgpath, SCSI_DH_DEV_OFFLINED);
 }
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f2a363a89629..115bd3846c3f 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1288,6 +1288,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
+			bio->bi_error = 0;
 
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 61f184ad081c..e108deebbaaa 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1106,6 +1106,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int i;
 	int r = -EINVAL;
 	char *origin_path, *cow_path;
+	dev_t origin_dev, cow_dev;
 	unsigned args_used, num_flush_bios = 1;
 	fmode_t origin_mode = FMODE_READ;
 
@@ -1136,11 +1137,19 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Cannot get origin device";
 		goto bad_origin;
 	}
+	origin_dev = s->origin->bdev->bd_dev;
 
 	cow_path = argv[0];
 	argv++;
 	argc--;
 
+	cow_dev = dm_get_dev_t(cow_path);
+	if (cow_dev && cow_dev == origin_dev) {
+		ti->error = "COW device cannot be the same as origin device";
+		r = -EINVAL;
+		goto bad_cow;
+	}
+
 	r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow);
 	if (r) {
 		ti->error = "Cannot get COW device";
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8289804ccd99..d5ea9f28ae70 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -175,6 +175,7 @@ static void dm_stat_free(struct rcu_head *head)
 	int cpu;
 	struct dm_stat *s = container_of(head, struct dm_stat, rcu_head);
 
+	kfree(s->histogram_boundaries);
 	kfree(s->program_id);
 	kfree(s->aux_data);
 	for_each_possible_cpu(cpu) {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 061152a43730..cb5d0daf53bb 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -365,6 +365,26 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 }
 
 /*
+ * Convert the path to a device
+ */
+dev_t dm_get_dev_t(const char *path)
+{
+	dev_t uninitialized_var(dev);
+	struct block_device *bdev;
+
+	bdev = lookup_bdev(path);
+	if (IS_ERR(bdev))
+		dev = name_to_dev_t(path);
+	else {
+		dev = bdev->bd_dev;
+		bdput(bdev);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(dm_get_dev_t);
+
+/*
  * Add a device to the list, or just increment the usage count if
  * it's already present.
  */
@@ -372,23 +392,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		  struct dm_dev **result)
 {
 	int r;
-	dev_t uninitialized_var(dev);
+	dev_t dev;
 	struct dm_dev_internal *dd;
 	struct dm_table *t = ti->table;
-	struct block_device *bdev;
 
 	BUG_ON(!t);
 
-	/* convert the path to a device */
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev)) {
-		dev = name_to_dev_t(path);
-		if (!dev)
-			return -ENODEV;
-	} else {
-		dev = bdev->bd_dev;
-		bdput(bdev);
-	}
+	dev = dm_get_dev_t(path);
+	if (!dev)
+		return -ENODEV;
 
 	dd = find_device(&t->devices, dev);
 	if (!dd) {
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index c219a053c7f6..3b67afda430b 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -485,11 +485,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
-	r = save_sm_roots(pmd);
+	r = dm_tm_pre_commit(pmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(pmd->tm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 
@@ -1943,5 +1943,8 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
 
 void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd)
 {
-	dm_tm_issue_prefetches(pmd->tm);
+	down_read(&pmd->root_lock);
+	if (!pmd->fail_io)
+		dm_tm_issue_prefetches(pmd->tm);
+	up_read(&pmd->root_lock);
 }
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dd834927bc66..320eb3c4bb6b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1109,12 +1109,8 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	 * back into ->request_fn() could deadlock attempting to grab the
 	 * queue lock again.
 	 */
-	if (run_queue) {
-		if (md->queue->mq_ops)
-			blk_mq_run_hw_queues(md->queue, true);
-		else
-			blk_run_queue_async(md->queue);
-	}
+	if (!md->queue->mq_ops && run_queue)
+		blk_run_queue_async(md->queue);
 
 	/*
 	 * dm_put() must be at the end of this function. See the comment above
@@ -1214,9 +1210,9 @@ static void dm_requeue_original_request(struct mapped_device *md,
 {
 	int rw = rq_data_dir(rq);
 
+	rq_end_stats(md, rq);
 	dm_unprep_request(rq);
 
-	rq_end_stats(md, rq);
 	if (!rq->q->mq_ops)
 		old_requeue_request(rq);
 	else {
@@ -1336,7 +1332,10 @@ static void dm_complete_request(struct request *rq, int error)
 	struct dm_rq_target_io *tio = tio_from_request(rq);
 
 	tio->error = error;
-	blk_complete_request(rq);
+	if (!rq->q->mq_ops)
+		blk_complete_request(rq);
+	else
+		blk_mq_complete_request(rq, error);
 }
 
 /*
@@ -1468,11 +1467,65 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
+/*
+ * Flush current->bio_list when the target map method blocks.
+ * This fixes deadlocks in snapshot and possibly in other targets.
+ */
+struct dm_offload {
+	struct blk_plug plug;
+	struct blk_plug_cb cb;
+};
+
+static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
+	struct bio_list list;
+	struct bio *bio;
+	int i;
+
+	INIT_LIST_HEAD(&o->cb.list);
+
+	if (unlikely(!current->bio_list))
+		return;
+
+	for (i = 0; i < 2; i++) {
+		list = current->bio_list[i];
+		bio_list_init(&current->bio_list[i]);
+
+		while ((bio = bio_list_pop(&list))) {
+			struct bio_set *bs = bio->bi_pool;
+			if (unlikely(!bs) || bs == fs_bio_set) {
+				bio_list_add(&current->bio_list[i], bio);
+				continue;
+			}
+
+			spin_lock(&bs->rescue_lock);
+			bio_list_add(&bs->rescue_list, bio);
+			queue_work(bs->rescue_workqueue, &bs->rescue_work);
+			spin_unlock(&bs->rescue_lock);
+		}
+	}
+}
+
+static void dm_offload_start(struct dm_offload *o)
+{
+	blk_start_plug(&o->plug);
+	o->cb.callback = flush_current_bio_list;
+	list_add(&o->cb.list, &current->plug->cb_list);
+}
+
+static void dm_offload_end(struct dm_offload *o)
+{
+	list_del(&o->cb.list);
+	blk_finish_plug(&o->plug);
+}
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
 	sector_t sector;
 	struct mapped_device *md;
+	struct dm_offload o;
 	struct bio *clone = &tio->clone;
 	struct dm_target *ti = tio->ti;
 
@@ -1485,7 +1538,11 @@ static void __map_bio(struct dm_target_io *tio)
 	 */
 	atomic_inc(&tio->io->io_count);
 	sector = clone->bi_iter.bi_sector;
+
+	dm_offload_start(&o);
 	r = ti->type->map(ti, clone);
+	dm_offload_end(&o);
+
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
 
@@ -2261,8 +2318,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->bs)
 		bioset_free(md->bs);
 
-	cleanup_srcu_struct(&md->io_barrier);
-
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;
@@ -2274,6 +2329,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->queue)
 		blk_cleanup_queue(md->queue);
 
+	cleanup_srcu_struct(&md->io_barrier);
+
 	if (md->bdev) {
 		bdput(md->bdev);
 		md->bdev = NULL;
@@ -2870,6 +2927,7 @@ EXPORT_SYMBOL_GPL(dm_device_name);
 
 static void __dm_destroy(struct mapped_device *md, bool wait)
 {
+	struct request_queue *q = dm_get_md_queue(md);
 	struct dm_table *map;
 	int srcu_idx;
 
@@ -2880,6 +2938,10 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
 
+	spin_lock_irq(q->queue_lock);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
+	spin_unlock_irq(q->queue_lock);
+
 	if (dm_request_based(md) && md->kworker_task)
 		flush_kthread_worker(&md->kworker);
 
@@ -3079,7 +3141,8 @@ static void unlock_fs(struct mapped_device *md)
  * Caller must hold md->suspend_lock
  */
 static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
-			unsigned suspend_flags, int interruptible)
+			unsigned suspend_flags, int interruptible,
+			int dmf_suspended_flag)
 {
 	bool do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG;
 	bool noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG;
@@ -3146,6 +3209,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 	 * to finish.
 	 */
 	r = dm_wait_for_completion(md, interruptible);
+	if (!r)
+		set_bit(dmf_suspended_flag, &md->flags);
 
 	if (noflush)
 		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
@@ -3207,12 +3272,10 @@ retry:
 
 	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 
-	r = __dm_suspend(md, map, suspend_flags, TASK_INTERRUPTIBLE);
+	r = __dm_suspend(md, map, suspend_flags, TASK_INTERRUPTIBLE, DMF_SUSPENDED);
 	if (r)
 		goto out_unlock;
 
-	set_bit(DMF_SUSPENDED, &md->flags);
-
 	dm_table_postsuspend_targets(map);
 
 out_unlock:
@@ -3245,10 +3308,11 @@ static int __dm_resume(struct mapped_device *md, struct dm_table *map)
 
 int dm_resume(struct mapped_device *md)
 {
-	int r = -EINVAL;
+	int r;
 	struct dm_table *map = NULL;
 
 retry:
+	r = -EINVAL;
 	mutex_lock_nested(&md->suspend_lock, SINGLE_DEPTH_NESTING);
 
 	if (!dm_suspended_md(md))
@@ -3272,8 +3336,6 @@ retry:
 		goto out;
 
 	clear_bit(DMF_SUSPENDED, &md->flags);
-
-	r = 0;
 out:
 	mutex_unlock(&md->suspend_lock);
 
@@ -3306,9 +3368,8 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 	 * would require changing .presuspend to return an error -- avoid this
 	 * until there is a need for more elaborate variants of internal suspend.
 	 */
-	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE);
-
-	set_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
+	(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
+			    DMF_SUSPENDED_INTERNALLY);
 
 	dm_table_postsuspend_targets(map);
 }
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b7fe7e9fc777..6ba3227e29b2 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -52,18 +52,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
+/*
+ * In linear_congested() conf->raid_disks is used as a copy of
+ * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
+ * and conf->disks[] are created in linear_conf(), they are always
+ * consitent with each other, but mddev->raid_disks does not.
+ */
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	conf = mddev->private;
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < conf->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
 
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -143,6 +151,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	return conf;
 
 out:
@@ -195,15 +216,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
 	mddev_suspend(mddev);
-	oldconf = mddev->private;
+	oldconf = rcu_dereference(mddev->private);
 	mddev->raid_disks++;
-	mddev->private = newconf;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree(oldconf);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 
diff --git a/drivers/md/linear.h b/drivers/md/linear.h
index b685ddd7d7f7..8d392e6098b3 100644
--- a/drivers/md/linear.h
+++ b/drivers/md/linear.h
@@ -10,6 +10,7 @@ struct linear_conf
 {
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
+	int			raid_disks; /* a copy of mddev->raid_disks */
 	struct dev_info		disks[0];
 };
 #endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b1e1f6b95782..0a856cb181e9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -293,6 +293,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	 * go away inside make_request
 	 */
 	sectors = bio_sectors(bio);
+	/* bio could be mergeable after passing to underlayer */
+	bio->bi_rw &= ~REQ_NOMERGE;
 	mddev->pers->make_request(mddev, bio);
 
 	cpu = part_stat_lock();
@@ -1864,7 +1866,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	}
 	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
-	sb->super_offset = rdev->sb_start;
+	sb->super_offset = cpu_to_le64(rdev->sb_start);
 	sb->sb_csum = calc_sb_1_csum(sb);
 	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
 		       rdev->sb_page);
@@ -2271,7 +2273,7 @@ static bool does_sb_need_changing(struct mddev *mddev)
 	/* Check if any mddev parameters have changed */
 	if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
 	    (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
-	    (mddev->layout != le64_to_cpu(sb->layout)) ||
+	    (mddev->layout != le32_to_cpu(sb->layout)) ||
 	    (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
 	    (mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
 		return true;
@@ -6769,7 +6771,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		/* need to ensure recovery thread has run */
 		wait_event_interruptible_timeout(mddev->sb_wait,
 						 !test_bit(MD_RECOVERY_NEEDED,
-							   &mddev->flags),
+							   &mddev->recovery),
 						 msecs_to_jiffies(5000));
 	if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) {
 		/* Need to flush page cache, and ensure no-one else opens
@@ -7570,16 +7572,12 @@ EXPORT_SYMBOL(unregister_md_cluster_operations);
 
 int md_setup_cluster(struct mddev *mddev, int nodes)
 {
-	int err;
-
-	err = request_module("md-cluster");
-	if (err) {
-		pr_err("md-cluster module not found.\n");
-		return -ENOENT;
-	}
-
+	if (!md_cluster_ops)
+		request_module("md-cluster");
 	spin_lock(&pers_lock);
+	/* ensure module won't be unloaded */
 	if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
+		pr_err("can't find md-cluster module or get it's reference.\n");
 		spin_unlock(&pers_lock);
 		return -ENOENT;
 	}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 0a72ab6e6c20..dd483bb2e111 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -129,7 +129,9 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	}
 	multipath = conf->multipaths + mp_bh->path;
 
-	mp_bh->bio = *bio;
+	bio_init(&mp_bh->bio);
+	__bio_clone_fast(&mp_bh->bio, bio);
+
 	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
 	mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index b1ced58eb5e1..a1a68209bd36 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -887,8 +887,12 @@ static int find_key(struct ro_spine *s, dm_block_t block, bool find_highest,
 		else
 			*result_key = le64_to_cpu(ro_node(s)->keys[0]);
 
-		if (next_block || flags & INTERNAL_NODE)
-			block = value64(ro_node(s), i);
+		if (next_block || flags & INTERNAL_NODE) {
+			if (find_highest)
+				block = value64(ro_node(s), i);
+			else
+				block = value64(ro_node(s), 0);
+		}
 
 	} while (flags & INTERNAL_NODE);
 
diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c
index ebb280a14325..32adf6b4a9c7 100644
--- a/drivers/md/persistent-data/dm-space-map-disk.c
+++ b/drivers/md/persistent-data/dm-space-map-disk.c
@@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b)
 
 static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b)
 {
+	int r;
+	uint32_t old_count;
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	return sm_ll_dec(&smd->ll, b, &ev);
+	r = sm_ll_dec(&smd->ll, b, &ev);
+	if (!r && (ev == SM_FREE)) {
+		/*
+		 * It's only free if it's also free in the last
+		 * transaction.
+		 */
+		r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+		if (!r && !old_count)
+			smd->nr_allocated_this_transaction--;
+	}
+
+	return r;
 }
 
 static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 7e44005595c1..20557e2c60c6 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -775,17 +775,15 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
 
 	r = sm_ll_new_metadata(&smm->ll, tm);
+	if (!r) {
+		if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+			nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
+		r = sm_ll_extend(&smm->ll, nr_blocks);
+	}
+	memcpy(&smm->sm, &ops, sizeof(smm->sm));
 	if (r)
 		return r;
 
-	if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
-		nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
-	r = sm_ll_extend(&smm->ll, nr_blocks);
-	if (r)
-		return r;
-
-	memcpy(&smm->sm, &ops, sizeof(smm->sm));
-
 	/*
 	 * Now we need to update the newly created data structures with the
 	 * allocated blocks that they were built from.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c4b913409226..f24a9e14021d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -570,7 +570,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 			if (best_dist_disk < 0) {
 				if (is_badblock(rdev, this_sector, sectors,
 						&first_bad, &bad_sectors)) {
-					if (first_bad < this_sector)
+					if (first_bad <= this_sector)
 						/* Cannot use this */
 						continue;
 					best_good_sectors = first_bad - this_sector;
@@ -877,7 +877,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 				     ((conf->start_next_window <
 				       conf->next_resync + RESYNC_SECTORS) &&
 				      current->bio_list &&
-				      !bio_list_empty(current->bio_list))),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1])))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
@@ -1087,7 +1088,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 		 */
 		DEFINE_WAIT(w);
 		for (;;) {
-			flush_signals(current);
+			sigset_t full, old;
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_INTERRUPTIBLE);
 			if (bio_end_sector(bio) <= mddev->suspend_lo ||
@@ -1096,7 +1097,10 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 			     !md_cluster_ops->area_resyncing(mddev, WRITE,
 				     bio->bi_iter.bi_sector, bio_end_sector(bio))))
 				break;
+			sigfillset(&full);
+			sigprocmask(SIG_BLOCK, &full, &old);
 			schedule();
+			sigprocmask(SIG_SETMASK, &old, NULL);
 		}
 		finish_wait(&conf->wait_barrier, &w);
 	}
@@ -2274,6 +2278,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 	if (fail) {
 		spin_lock_irq(&conf->device_lock);
 		list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+		conf->nr_queued++;
 		spin_unlock_irq(&conf->device_lock);
 		md_wakeup_thread(conf->mddev->thread);
 	} else {
@@ -2391,8 +2396,10 @@ static void raid1d(struct md_thread *thread)
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
-			list_add(&tmp, &conf->bio_end_io_list);
-			list_del_init(&conf->bio_end_io_list);
+			while (!list_empty(&conf->bio_end_io_list)) {
+				list_move(conf->bio_end_io_list.prev, &tmp);
+				conf->nr_queued--;
+			}
 		}
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		while (!list_empty(&tmp)) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ce959b4ae4df..e5ee4e9e0ea5 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -946,7 +946,8 @@ static void wait_barrier(struct r10conf *conf)
 				    !conf->barrier ||
 				    (conf->nr_pending &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
@@ -1072,6 +1073,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	int max_sectors;
 	int sectors;
 
+	md_write_start(mddev, bio);
+
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
@@ -1455,8 +1458,6 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 		return;
 	}
 
-	md_write_start(mddev, bio);
-
 	do {
 
 		/*
@@ -1477,7 +1478,25 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
 		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
 	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
@@ -2664,6 +2683,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 		if (fail) {
 			spin_lock_irq(&conf->device_lock);
 			list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+			conf->nr_queued++;
 			spin_unlock_irq(&conf->device_lock);
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
@@ -2691,8 +2711,10 @@ static void raid10d(struct md_thread *thread)
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
-			list_add(&tmp, &conf->bio_end_io_list);
-			list_del_init(&conf->bio_end_io_list);
+			while (!list_empty(&conf->bio_end_io_list)) {
+				list_move(conf->bio_end_io_list.prev, &tmp);
+				conf->nr_queued--;
+			}
 		}
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		while (!list_empty(&tmp)) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 704ef7fcfbf8..8f60520c8392 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -340,8 +340,7 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 					 int hash)
 {
 	int size;
-	unsigned long do_wakeup = 0;
-	int i = 0;
+	bool do_wakeup = false;
 	unsigned long flags;
 
 	if (hash == NR_STRIPE_HASH_LOCKS) {
@@ -362,19 +361,15 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 			    !list_empty(list))
 				atomic_dec(&conf->empty_inactive_list_nr);
 			list_splice_tail_init(list, conf->inactive_list + hash);
-			do_wakeup |= 1 << hash;
+			do_wakeup = true;
 			spin_unlock_irqrestore(conf->hash_locks + hash, flags);
 		}
 		size--;
 		hash--;
 	}
 
-	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
-		if (do_wakeup & (1 << i))
-			wake_up(&conf->wait_for_stripe[i]);
-	}
-
 	if (do_wakeup) {
+		wake_up(&conf->wait_for_stripe);
 		if (atomic_read(&conf->active_stripes) == 0)
 			wake_up(&conf->wait_for_quiescent);
 		if (conf->retry_read_aligned)
@@ -687,15 +682,14 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 			if (!sh) {
 				set_bit(R5_INACTIVE_BLOCKED,
 					&conf->cache_state);
-				wait_event_exclusive_cmd(
-					conf->wait_for_stripe[hash],
+				wait_event_lock_irq(
+					conf->wait_for_stripe,
 					!list_empty(conf->inactive_list + hash) &&
 					(atomic_read(&conf->active_stripes)
 					 < (conf->max_nr_stripes * 3 / 4)
 					 || !test_bit(R5_INACTIVE_BLOCKED,
 						      &conf->cache_state)),
-					spin_unlock_irq(conf->hash_locks + hash),
-					spin_lock_irq(conf->hash_locks + hash));
+					*(conf->hash_locks + hash));
 				clear_bit(R5_INACTIVE_BLOCKED,
 					  &conf->cache_state);
 			} else {
@@ -720,9 +714,6 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 		}
 	} while (sh == NULL);
 
-	if (!list_empty(conf->inactive_list + hash))
-		wake_up(&conf->wait_for_stripe[hash]);
-
 	spin_unlock_irq(conf->hash_locks + hash);
 	return sh;
 }
@@ -2091,6 +2082,14 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	unsigned long cpu;
 	int err = 0;
 
+	/*
+	 * Never shrink. And mddev_suspend() could deadlock if this is called
+	 * from raid5d. In that case, scribble_disks and scribble_sectors
+	 * should equal to new_disks and new_sectors
+	 */
+	if (conf->scribble_disks >= new_disks &&
+	    conf->scribble_sectors >= new_sectors)
+		return 0;
 	mddev_suspend(conf->mddev);
 	get_online_cpus();
 	for_each_present_cpu(cpu) {
@@ -2112,6 +2111,10 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	}
 	put_online_cpus();
 	mddev_resume(conf->mddev);
+	if (!err) {
+		conf->scribble_disks = new_disks;
+		conf->scribble_sectors = new_sectors;
+	}
 	return err;
 }
 
@@ -2192,7 +2195,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	cnt = 0;
 	list_for_each_entry(nsh, &newstripes, lru) {
 		lock_device_hash_lock(conf, hash);
-		wait_event_exclusive_cmd(conf->wait_for_stripe[hash],
+		wait_event_cmd(conf->wait_for_stripe,
 				    !list_empty(conf->inactive_list + hash),
 				    unlock_device_hash_lock(conf, hash),
 				    lock_device_hash_lock(conf, hash));
@@ -2229,6 +2232,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		err = -ENOMEM;
 
 	mutex_unlock(&conf->cache_size_mutex);
+
+	conf->slab_cache = sc;
+	conf->active_name = 1-conf->active_name;
+
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -2246,8 +2253,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	}
 	/* critical section pass, GFP_NOIO no longer needed */
 
-	conf->slab_cache = sc;
-	conf->active_name = 1-conf->active_name;
 	if (!err)
 		conf->pool_size = newsize;
 	return err;
@@ -4238,7 +4243,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 		WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
 					  (1 << STRIPE_SYNCING) |
 					  (1 << STRIPE_REPLACED) |
-					  (1 << STRIPE_PREREAD_ACTIVE) |
 					  (1 << STRIPE_DELAYED) |
 					  (1 << STRIPE_BIT_DELAY) |
 					  (1 << STRIPE_FULL_WRITE) |
@@ -4253,6 +4257,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					      (1 << STRIPE_REPLACED)));
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+					    (1 << STRIPE_PREREAD_ACTIVE) |
 					    (1 << STRIPE_DEGRADED)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
@@ -5274,12 +5279,15 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				 * userspace, we want an interruptible
 				 * wait.
 				 */
-				flush_signals(current);
 				prepare_to_wait(&conf->wait_for_overlap,
 						&w, TASK_INTERRUPTIBLE);
 				if (logical_sector >= mddev->suspend_lo &&
 				    logical_sector < mddev->suspend_hi) {
+					sigset_t full, old;
+					sigfillset(&full);
+					sigprocmask(SIG_BLOCK, &full, &old);
 					schedule();
+					sigprocmask(SIG_SETMASK, &old, NULL);
 					do_prepare = true;
 				}
 				goto retry;
@@ -5813,6 +5821,8 @@ static void raid5_do_work(struct work_struct *work)
 	pr_debug("%d stripes handled\n", handled);
 
 	spin_unlock_irq(&conf->device_lock);
+
+	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 
 	pr_debug("--- raid5worker inactive\n");
@@ -6414,6 +6424,12 @@ static int raid5_alloc_percpu(struct r5conf *conf)
 	}
 	put_online_cpus();
 
+	if (!err) {
+		conf->scribble_disks = max(conf->raid_disks,
+			conf->previous_raid_disks);
+		conf->scribble_sectors = max(conf->chunk_sectors,
+			conf->prev_chunk_sectors);
+	}
 	return err;
 }
 
@@ -6504,9 +6520,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	seqcount_init(&conf->gen_lock);
 	mutex_init(&conf->cache_size_mutex);
 	init_waitqueue_head(&conf->wait_for_quiescent);
-	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
-		init_waitqueue_head(&conf->wait_for_stripe[i]);
-	}
+	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
 	INIT_LIST_HEAD(&conf->hold_list);
@@ -6973,6 +6987,15 @@ static int run(struct mddev *mddev)
 			stripe = (stripe | (stripe-1)) + 1;
 		mddev->queue->limits.discard_alignment = stripe;
 		mddev->queue->limits.discard_granularity = stripe;
+
+		/*
+		 * We use 16-bit counter of active stripes in bi_phys_segments
+		 * (minus one for over-loaded initialization)
+		 */
+		blk_queue_max_hw_sectors(mddev->queue, 0xfffe * STRIPE_SECTORS);
+		blk_queue_max_discard_sectors(mddev->queue,
+					      0xfffe * STRIPE_SECTORS);
+
 		/*
 		 * unaligned part of discard request will be ignored, so can't
 		 * guarantee discard_zeroes_data
@@ -7015,8 +7038,8 @@ static int run(struct mddev *mddev)
 		}
 
 		if (discard_supported &&
-		   mddev->queue->limits.max_discard_sectors >= stripe &&
-		   mddev->queue->limits.discard_granularity >= stripe)
+		    mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
+		    mddev->queue->limits.discard_granularity >= stripe)
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
 						mddev->queue);
 		else
@@ -7510,12 +7533,10 @@ static void end_reshape(struct r5conf *conf)
 {
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		struct md_rdev *rdev;
 
 		spin_lock_irq(&conf->device_lock);
 		conf->previous_raid_disks = conf->raid_disks;
-		rdev_for_each(rdev, conf->mddev)
-			rdev->data_offset = rdev->new_data_offset;
+		md_finish_reshape(conf->mddev);
 		smp_wmb();
 		conf->reshape_progress = MaxSector;
 		conf->mddev->reshape_position = MaxSector;
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index a415e1cd39b8..517d4b68a1be 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -510,6 +510,8 @@ struct r5conf {
 					      * conversions
 					      */
 	} __percpu *percpu;
+	int scribble_disks;
+	int scribble_sectors;
 #ifdef CONFIG_HOTPLUG_CPU
 	struct notifier_block	cpu_notify;
 #endif
@@ -522,7 +524,7 @@ struct r5conf {
 	atomic_t		empty_inactive_list_nr;
 	struct llist_head	released_stripes;
 	wait_queue_head_t	wait_for_quiescent;
-	wait_queue_head_t	wait_for_stripe[NR_STRIPE_HASH_LOCKS];
+	wait_queue_head_t	wait_for_stripe;
 	wait_queue_head_t	wait_for_overlap;
 	unsigned long		cache_state;
 #define R5_INACTIVE_BLOCKED	1	/* release of inactive stripes blocked,
diff --git a/drivers/media/dvb-core/dvb_ringbuffer.c b/drivers/media/dvb-core/dvb_ringbuffer.c
index 1100e98a7b1d..7df7fb3738a0 100644
--- a/drivers/media/dvb-core/dvb_ringbuffer.c
+++ b/drivers/media/dvb-core/dvb_ringbuffer.c
@@ -55,7 +55,13 @@ void dvb_ringbuffer_init(struct dvb_ringbuffer *rbuf, void *data, size_t len)
 
 int dvb_ringbuffer_empty(struct dvb_ringbuffer *rbuf)
 {
-	return (rbuf->pread==rbuf->pwrite);
+	/* smp_load_acquire() to load write pointer on reader side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_write(),
+	 * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset()
+	 *
+	 * for memory barriers also see Documentation/circular-buffers.txt
+	 */
+	return (rbuf->pread == smp_load_acquire(&rbuf->pwrite));
 }
 
 
@@ -64,7 +70,12 @@ ssize_t dvb_ringbuffer_free(struct dvb_ringbuffer *rbuf)
 {
 	ssize_t free;
 
-	free = rbuf->pread - rbuf->pwrite;
+	/* ACCESS_ONCE() to load read pointer on writer side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_read(),
+	 * dvb_ringbuffer_read_user(), dvb_ringbuffer_flush(),
+	 * or dvb_ringbuffer_reset()
+	 */
+	free = ACCESS_ONCE(rbuf->pread) - rbuf->pwrite;
 	if (free <= 0)
 		free += rbuf->size;
 	return free-1;
@@ -76,7 +87,11 @@ ssize_t dvb_ringbuffer_avail(struct dvb_ringbuffer *rbuf)
 {
 	ssize_t avail;
 
-	avail = rbuf->pwrite - rbuf->pread;
+	/* smp_load_acquire() to load write pointer on reader side
+	 * this pairs with smp_store_release() in dvb_ringbuffer_write(),
+	 * dvb_ringbuffer_write_user(), or dvb_ringbuffer_reset()
+	 */
+	avail = smp_load_acquire(&rbuf->pwrite) - rbuf->pread;
 	if (avail < 0)
 		avail += rbuf->size;
 	return avail;
@@ -86,14 +101,25 @@ ssize_t dvb_ringbuffer_avail(struct dvb_ringbuffer *rbuf)
 
 void dvb_ringbuffer_flush(struct dvb_ringbuffer *rbuf)
 {
-	rbuf->pread = rbuf->pwrite;
+	/* dvb_ringbuffer_flush() counts as read operation
+	 * smp_load_acquire() to load write pointer
+	 * smp_store_release() to update read pointer, this ensures that the
+	 * correct pointer is visible for subsequent dvb_ringbuffer_free()
+	 * calls on other cpu cores
+	 */
+	smp_store_release(&rbuf->pread, smp_load_acquire(&rbuf->pwrite));
 	rbuf->error = 0;
 }
 EXPORT_SYMBOL(dvb_ringbuffer_flush);
 
 void dvb_ringbuffer_reset(struct dvb_ringbuffer *rbuf)
 {
-	rbuf->pread = rbuf->pwrite = 0;
+	/* dvb_ringbuffer_reset() counts as read and write operation
+	 * smp_store_release() to update read pointer
+	 */
+	smp_store_release(&rbuf->pread, 0);
+	/* smp_store_release() to update write pointer */
+	smp_store_release(&rbuf->pwrite, 0);
 	rbuf->error = 0;
 }
 
@@ -119,12 +145,17 @@ ssize_t dvb_ringbuffer_read_user(struct dvb_ringbuffer *rbuf, u8 __user *buf, si
 			return -EFAULT;
 		buf += split;
 		todo -= split;
-		rbuf->pread = 0;
+		/* smp_store_release() for read pointer update to ensure
+		 * that buf is not overwritten until read is complete,
+		 * this pairs with ACCESS_ONCE() in dvb_ringbuffer_free()
+		 */
+		smp_store_release(&rbuf->pread, 0);
 	}
 	if (copy_to_user(buf, rbuf->data+rbuf->pread, todo))
 		return -EFAULT;
 
-	rbuf->pread = (rbuf->pread + todo) % rbuf->size;
+	/* smp_store_release() to update read pointer, see above */
+	smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size);
 
 	return len;
 }
@@ -139,11 +170,16 @@ void dvb_ringbuffer_read(struct dvb_ringbuffer *rbuf, u8 *buf, size_t len)
 		memcpy(buf, rbuf->data+rbuf->pread, split);
 		buf += split;
 		todo -= split;
-		rbuf->pread = 0;
+		/* smp_store_release() for read pointer update to ensure
+		 * that buf is not overwritten until read is complete,
+		 * this pairs with ACCESS_ONCE() in dvb_ringbuffer_free()
+		 */
+		smp_store_release(&rbuf->pread, 0);
 	}
 	memcpy(buf, rbuf->data+rbuf->pread, todo);
 
-	rbuf->pread = (rbuf->pread + todo) % rbuf->size;
+	/* smp_store_release() to update read pointer, see above */
+	smp_store_release(&rbuf->pread, (rbuf->pread + todo) % rbuf->size);
 }
 
 
@@ -158,10 +194,16 @@ ssize_t dvb_ringbuffer_write(struct dvb_ringbuffer *rbuf, const u8 *buf, size_t
 		memcpy(rbuf->data+rbuf->pwrite, buf, split);
 		buf += split;
 		todo -= split;
-		rbuf->pwrite = 0;
+		/* smp_store_release() for write pointer update to ensure that
+		 * written data is visible on other cpu cores before the pointer
+		 * update, this pairs with smp_load_acquire() in
+		 * dvb_ringbuffer_empty() or dvb_ringbuffer_avail()
+		 */
+		smp_store_release(&rbuf->pwrite, 0);
 	}
 	memcpy(rbuf->data+rbuf->pwrite, buf, todo);
-	rbuf->pwrite = (rbuf->pwrite + todo) % rbuf->size;
+	/* smp_store_release() for write pointer update, see above */
+	smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size);
 
 	return len;
 }
@@ -181,12 +223,18 @@ ssize_t dvb_ringbuffer_write_user(struct dvb_ringbuffer *rbuf,
 			return len - todo;
 		buf += split;
 		todo -= split;
-		rbuf->pwrite = 0;
+		/* smp_store_release() for write pointer update to ensure that
+		 * written data is visible on other cpu cores before the pointer
+		 * update, this pairs with smp_load_acquire() in
+		 * dvb_ringbuffer_empty() or dvb_ringbuffer_avail()
+		 */
+		smp_store_release(&rbuf->pwrite, 0);
 	}
 	status = copy_from_user(rbuf->data+rbuf->pwrite, buf, todo);
 	if (status)
 		return len - todo;
-	rbuf->pwrite = (rbuf->pwrite + todo) % rbuf->size;
+	/* smp_store_release() for write pointer update, see above */
+	smp_store_release(&rbuf->pwrite, (rbuf->pwrite + todo) % rbuf->size);
 
 	return len;
 }
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 292c9479bb75..310e4b8beae8 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -264,7 +264,7 @@ config DVB_MB86A16
 config DVB_TDA10071
 	tristate "NXP TDA10071"
 	depends on DVB_CORE && I2C
-	select REGMAP
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y when you want to support this frontend.
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index fdffb2f0ded8..107853b0fddd 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -2678,7 +2678,9 @@ static struct  dvb_frontend_ops cxd2841er_dvbt_t2_ops = {
 			FE_CAN_MUTE_TS |
 			FE_CAN_2G_MODULATION,
 		.frequency_min = 42000000,
-		.frequency_max = 1002000000
+		.frequency_max = 1002000000,
+		.symbol_rate_min = 870000,
+		.symbol_rate_max = 11700000
 	},
 	.init = cxd2841er_init_tc,
 	.sleep = cxd2841er_sleep_tc,
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index cfc005ee11d8..7fc72de2434c 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -71,25 +71,27 @@ static struct regdata mb86a20s_init1[] = {
 };
 
 static struct regdata mb86a20s_init2[] = {
-	{ 0x28, 0x22 }, { 0x29, 0x00 }, { 0x2a, 0x1f }, { 0x2b, 0xf0 },
+	{ 0x50, 0xd1 }, { 0x51, 0x22 },
+	{ 0x39, 0x01 },
+	{ 0x71, 0x00 },
 	{ 0x3b, 0x21 },
-	{ 0x3c, 0x38 },
+	{ 0x3c, 0x3a },
 	{ 0x01, 0x0d },
-	{ 0x04, 0x08 }, { 0x05, 0x03 },
+	{ 0x04, 0x08 }, { 0x05, 0x05 },
 	{ 0x04, 0x0e }, { 0x05, 0x00 },
-	{ 0x04, 0x0f }, { 0x05, 0x37 },
-	{ 0x04, 0x0b }, { 0x05, 0x78 },
+	{ 0x04, 0x0f }, { 0x05, 0x14 },
+	{ 0x04, 0x0b }, { 0x05, 0x8c },
 	{ 0x04, 0x00 }, { 0x05, 0x00 },
-	{ 0x04, 0x01 }, { 0x05, 0x1e },
-	{ 0x04, 0x02 }, { 0x05, 0x07 },
-	{ 0x04, 0x03 }, { 0x05, 0xd0 },
+	{ 0x04, 0x01 }, { 0x05, 0x07 },
+	{ 0x04, 0x02 }, { 0x05, 0x0f },
+	{ 0x04, 0x03 }, { 0x05, 0xa0 },
 	{ 0x04, 0x09 }, { 0x05, 0x00 },
 	{ 0x04, 0x0a }, { 0x05, 0xff },
-	{ 0x04, 0x27 }, { 0x05, 0x00 },
+	{ 0x04, 0x27 }, { 0x05, 0x64 },
 	{ 0x04, 0x28 }, { 0x05, 0x00 },
-	{ 0x04, 0x1e }, { 0x05, 0x00 },
-	{ 0x04, 0x29 }, { 0x05, 0x64 },
-	{ 0x04, 0x32 }, { 0x05, 0x02 },
+	{ 0x04, 0x1e }, { 0x05, 0xff },
+	{ 0x04, 0x29 }, { 0x05, 0x0a },
+	{ 0x04, 0x32 }, { 0x05, 0x0a },
 	{ 0x04, 0x14 }, { 0x05, 0x02 },
 	{ 0x04, 0x04 }, { 0x05, 0x00 },
 	{ 0x04, 0x05 }, { 0x05, 0x22 },
@@ -97,8 +99,6 @@ static struct regdata mb86a20s_init2[] = {
 	{ 0x04, 0x07 }, { 0x05, 0xd8 },
 	{ 0x04, 0x12 }, { 0x05, 0x00 },
 	{ 0x04, 0x13 }, { 0x05, 0xff },
-	{ 0x04, 0x15 }, { 0x05, 0x4e },
-	{ 0x04, 0x16 }, { 0x05, 0x20 },
 
 	/*
 	 * On this demod, when the bit count reaches the count below,
@@ -152,42 +152,36 @@ static struct regdata mb86a20s_init2[] = {
 	{ 0x50, 0x51 }, { 0x51, 0x04 },		/* MER symbol 4 */
 	{ 0x45, 0x04 },				/* CN symbol 4 */
 	{ 0x48, 0x04 },				/* CN manual mode */
-
+	{ 0x50, 0xd5 }, { 0x51, 0x01 },
 	{ 0x50, 0xd6 }, { 0x51, 0x1f },
 	{ 0x50, 0xd2 }, { 0x51, 0x03 },
-	{ 0x50, 0xd7 }, { 0x51, 0xbf },
-	{ 0x28, 0x74 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0xff },
-	{ 0x28, 0x46 }, { 0x29, 0x00 }, { 0x2a, 0x1a }, { 0x2b, 0x0c },
-
-	{ 0x04, 0x40 }, { 0x05, 0x00 },
-	{ 0x28, 0x00 }, { 0x2b, 0x08 },
-	{ 0x28, 0x05 }, { 0x2b, 0x00 },
+	{ 0x50, 0xd7 }, { 0x51, 0x3f },
 	{ 0x1c, 0x01 },
-	{ 0x28, 0x06 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x1f },
-	{ 0x28, 0x07 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x18 },
-	{ 0x28, 0x08 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x12 },
-	{ 0x28, 0x09 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x30 },
-	{ 0x28, 0x0a }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x37 },
-	{ 0x28, 0x0b }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x02 },
-	{ 0x28, 0x0c }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x09 },
-	{ 0x28, 0x0d }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x06 },
-	{ 0x28, 0x0e }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x7b },
-	{ 0x28, 0x0f }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x76 },
-	{ 0x28, 0x10 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x7d },
-	{ 0x28, 0x11 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x08 },
-	{ 0x28, 0x12 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x0b },
-	{ 0x28, 0x13 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x00 },
-	{ 0x28, 0x14 }, { 0x29, 0x00 }, { 0x2a, 0x01 }, { 0x2b, 0xf2 },
-	{ 0x28, 0x15 }, { 0x29, 0x00 }, { 0x2a, 0x01 }, { 0x2b, 0xf3 },
-	{ 0x28, 0x16 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x05 },
-	{ 0x28, 0x17 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x16 },
-	{ 0x28, 0x18 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x0f },
-	{ 0x28, 0x19 }, { 0x29, 0x00 }, { 0x2a, 0x07 }, { 0x2b, 0xef },
-	{ 0x28, 0x1a }, { 0x29, 0x00 }, { 0x2a, 0x07 }, { 0x2b, 0xd8 },
-	{ 0x28, 0x1b }, { 0x29, 0x00 }, { 0x2a, 0x07 }, { 0x2b, 0xf1 },
-	{ 0x28, 0x1c }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x3d },
-	{ 0x28, 0x1d }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x94 },
-	{ 0x28, 0x1e }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0xba },
+	{ 0x28, 0x06 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x03 },
+	{ 0x28, 0x07 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x0d },
+	{ 0x28, 0x08 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x02 },
+	{ 0x28, 0x09 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x01 },
+	{ 0x28, 0x0a }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x21 },
+	{ 0x28, 0x0b }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x29 },
+	{ 0x28, 0x0c }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x16 },
+	{ 0x28, 0x0d }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x31 },
+	{ 0x28, 0x0e }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x0e },
+	{ 0x28, 0x0f }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x4e },
+	{ 0x28, 0x10 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x46 },
+	{ 0x28, 0x11 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x0f },
+	{ 0x28, 0x12 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x56 },
+	{ 0x28, 0x13 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x35 },
+	{ 0x28, 0x14 }, { 0x29, 0x00 }, { 0x2a, 0x01 }, { 0x2b, 0xbe },
+	{ 0x28, 0x15 }, { 0x29, 0x00 }, { 0x2a, 0x01 }, { 0x2b, 0x84 },
+	{ 0x28, 0x16 }, { 0x29, 0x00 }, { 0x2a, 0x03 }, { 0x2b, 0xee },
+	{ 0x28, 0x17 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x98 },
+	{ 0x28, 0x18 }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x9f },
+	{ 0x28, 0x19 }, { 0x29, 0x00 }, { 0x2a, 0x07 }, { 0x2b, 0xb2 },
+	{ 0x28, 0x1a }, { 0x29, 0x00 }, { 0x2a, 0x06 }, { 0x2b, 0xc2 },
+	{ 0x28, 0x1b }, { 0x29, 0x00 }, { 0x2a, 0x07 }, { 0x2b, 0x4a },
+	{ 0x28, 0x1c }, { 0x29, 0x00 }, { 0x2a, 0x01 }, { 0x2b, 0xbc },
+	{ 0x28, 0x1d }, { 0x29, 0x00 }, { 0x2a, 0x04 }, { 0x2b, 0xba },
+	{ 0x28, 0x1e }, { 0x29, 0x00 }, { 0x2a, 0x06 }, { 0x2b, 0x14 },
 	{ 0x50, 0x1e }, { 0x51, 0x5d },
 	{ 0x50, 0x22 }, { 0x51, 0x00 },
 	{ 0x50, 0x23 }, { 0x51, 0xc8 },
@@ -196,9 +190,7 @@ static struct regdata mb86a20s_init2[] = {
 	{ 0x50, 0x26 }, { 0x51, 0x00 },
 	{ 0x50, 0x27 }, { 0x51, 0xc3 },
 	{ 0x50, 0x39 }, { 0x51, 0x02 },
-	{ 0xec, 0x0f },
-	{ 0xeb, 0x1f },
-	{ 0x28, 0x6a }, { 0x29, 0x00 }, { 0x2a, 0x00 }, { 0x2b, 0x00 },
+	{ 0x50, 0xd5 }, { 0x51, 0x01 },
 	{ 0xd0, 0x00 },
 };
 
@@ -317,7 +309,11 @@ static int mb86a20s_read_status(struct dvb_frontend *fe, enum fe_status *status)
 	if (val >= 7)
 		*status |= FE_HAS_SYNC;
 
-	if (val >= 8)				/* Maybe 9? */
+	/*
+	 * Actually, on state S8, it starts receiving TS, but the TS
+	 * output is only on normal state after the transition to S9.
+	 */
+	if (val >= 9)
 		*status |= FE_HAS_LOCK;
 
 	dev_dbg(&state->i2c->dev, "%s: Status = 0x%02x (state = %d)\n",
@@ -2067,6 +2063,11 @@ static void mb86a20s_release(struct dvb_frontend *fe)
 	kfree(state);
 }
 
+static int mb86a20s_get_frontend_algo(struct dvb_frontend *fe)
+{
+        return DVBFE_ALGO_HW;
+}
+
 static struct dvb_frontend_ops mb86a20s_ops;
 
 struct dvb_frontend *mb86a20s_attach(const struct mb86a20s_config *config,
@@ -2140,6 +2141,7 @@ static struct dvb_frontend_ops mb86a20s_ops = {
 	.read_status = mb86a20s_read_status_and_stats,
 	.read_signal_strength = mb86a20s_read_signal_strength_from_cache,
 	.tune = mb86a20s_tune,
+	.get_frontend_algo = mb86a20s_get_frontend_algo,
 };
 
 MODULE_DESCRIPTION("DVB Frontend module for Fujitsu mb86A20s hardware");
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 521bbf1b29bc..670240c0ece8 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -607,6 +607,7 @@ config VIDEO_S5K6A3
 config VIDEO_S5K4ECGX
         tristate "Samsung S5K4ECGX sensor support"
         depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	select CRC32
         ---help---
           This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M
           camera sensor with an embedded SoC image signal processor.
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index e4900df1140b..c24839cfcc35 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -1161,12 +1161,23 @@ static void adv7511_dbg_dump_edid(int lvl, int debug, struct v4l2_subdev *sd, in
 	}
 }
 
+static void adv7511_notify_no_edid(struct v4l2_subdev *sd)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+	struct adv7511_edid_detect ed;
+
+	/* We failed to read the EDID, so send an event for this. */
+	ed.present = false;
+	ed.segment = adv7511_rd(sd, 0xc4);
+	v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
+	v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x0);
+}
+
 static void adv7511_edid_handler(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct adv7511_state *state = container_of(dwork, struct adv7511_state, edid_handler);
 	struct v4l2_subdev *sd = &state->sd;
-	struct adv7511_edid_detect ed;
 
 	v4l2_dbg(1, debug, sd, "%s:\n", __func__);
 
@@ -1191,9 +1202,7 @@ static void adv7511_edid_handler(struct work_struct *work)
 	}
 
 	/* We failed to read the EDID, so send an event for this. */
-	ed.present = false;
-	ed.segment = adv7511_rd(sd, 0xc4);
-	v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
+	adv7511_notify_no_edid(sd);
 	v4l2_dbg(1, debug, sd, "%s: no edid found\n", __func__);
 }
 
@@ -1264,7 +1273,6 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd)
 	/* update read only ctrls */
 	v4l2_ctrl_s_ctrl(state->hotplug_ctrl, adv7511_have_hotplug(sd) ? 0x1 : 0x0);
 	v4l2_ctrl_s_ctrl(state->rx_sense_ctrl, adv7511_have_rx_sense(sd) ? 0x1 : 0x0);
-	v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0);
 
 	if ((status & MASK_ADV7511_HPD_DETECT) && ((status & MASK_ADV7511_MSEN_DETECT) || state->edid.segments)) {
 		v4l2_dbg(1, debug, sd, "%s: hotplug and (rx-sense or edid)\n", __func__);
@@ -1294,6 +1302,7 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd)
 		}
 		adv7511_s_power(sd, false);
 		memset(&state->edid, 0, sizeof(struct adv7511_state_edid));
+		adv7511_notify_no_edid(sd);
 	}
 }
 
@@ -1370,6 +1379,7 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 		}
 		/* one more segment read ok */
 		state->edid.segments = segment + 1;
+		v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x1);
 		if (((state->edid.data[0x7e] >> 1) + 1) > state->edid.segments) {
 			/* Request next EDID segment */
 			v4l2_dbg(1, debug, sd, "%s: request segment %d\n", __func__, state->edid.segments);
@@ -1389,7 +1399,6 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 		ed.present = true;
 		ed.segment = 0;
 		state->edid_detect_counter++;
-		v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0);
 		v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
 		return ed.present;
 	}
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
index 8001cde1db1e..503135a4f47a 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-ctrls.c
@@ -211,7 +211,7 @@ static int s5c73m3_3a_lock(struct s5c73m3 *state, struct v4l2_ctrl *ctrl)
 	}
 
 	if ((ctrl->val ^ ctrl->cur.val) & V4L2_LOCK_FOCUS)
-		ret = s5c73m3_af_run(state, ~af_lock);
+		ret = s5c73m3_af_run(state, !af_lock);
 
 	return ret;
 }
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 15a4ebc2844d..51dbef2f9a48 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -2334,6 +2334,19 @@ static int bttv_g_fmt_vid_overlay(struct file *file, void *priv,
 	return 0;
 }
 
+static void bttv_get_width_mask_vid_cap(const struct bttv_format *fmt,
+					unsigned int *width_mask,
+					unsigned int *width_bias)
+{
+	if (fmt->flags & FORMAT_FLAGS_PLANAR) {
+		*width_mask = ~15; /* width must be a multiple of 16 pixels */
+		*width_bias = 8;   /* nearest */
+	} else {
+		*width_mask = ~3; /* width must be a multiple of 4 pixels */
+		*width_bias = 2;  /* nearest */
+	}
+}
+
 static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 						struct v4l2_format *f)
 {
@@ -2343,6 +2356,7 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 	enum v4l2_field field;
 	__s32 width, height;
 	__s32 height2;
+	unsigned int width_mask, width_bias;
 	int rc;
 
 	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
@@ -2375,9 +2389,9 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 	width = f->fmt.pix.width;
 	height = f->fmt.pix.height;
 
+	bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias);
 	rc = limit_scaled_size_lock(fh, &width, &height, field,
-			       /* width_mask: 4 pixels */ ~3,
-			       /* width_bias: nearest */ 2,
+			       width_mask, width_bias,
 			       /* adjust_size */ 1,
 			       /* adjust_crop */ 0);
 	if (0 != rc)
@@ -2410,6 +2424,7 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	struct bttv_fh *fh = priv;
 	struct bttv *btv = fh->btv;
 	__s32 width, height;
+	unsigned int width_mask, width_bias;
 	enum v4l2_field field;
 
 	retval = bttv_switch_type(fh, f->type);
@@ -2424,9 +2439,10 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	height = f->fmt.pix.height;
 	field = f->fmt.pix.field;
 
+	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+	bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias);
 	retval = limit_scaled_size_lock(fh, &width, &height, f->fmt.pix.field,
-			       /* width_mask: 4 pixels */ ~3,
-			       /* width_bias: nearest */ 2,
+			       width_mask, width_bias,
 			       /* adjust_size */ 1,
 			       /* adjust_crop */ 1);
 	if (0 != retval)
@@ -2434,8 +2450,6 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 
 	f->fmt.pix.field = field;
 
-	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
-
 	/* update our state informations */
 	fh->fmt              = fmt;
 	fh->cap.field        = f->fmt.pix.field;
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index c4307ad8594c..e543cbbf2ec4 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -2168,11 +2168,12 @@ static int dvb_register(struct cx23885_tsport *port)
 		}
 		port->i2c_client_tuner = client_tuner;
 		break;
-	case CX23885_BOARD_HAUPPAUGE_HVR5525:
-		switch (port->nr) {
+	case CX23885_BOARD_HAUPPAUGE_HVR5525: {
 		struct m88rs6000t_config m88rs6000t_config;
 		struct a8293_platform_data a8293_pdata = {};
 
+		switch (port->nr) {
+
 		/* port b - satellite */
 		case 1:
 			/* attach frontend */
@@ -2267,6 +2268,7 @@ static int dvb_register(struct cx23885_tsport *port)
 			break;
 		}
 		break;
+	}
 	default:
 		printk(KERN_INFO "%s: The frontend of your DVB/ATSC card "
 			" isn't supported yet\n",
diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c
index 8f2556ec3971..61611d1682d1 100644
--- a/drivers/media/pci/cx88/cx88-cards.c
+++ b/drivers/media/pci/cx88/cx88-cards.c
@@ -3691,7 +3691,14 @@ struct cx88_core *cx88_core_create(struct pci_dev *pci, int nr)
 	core->nr = nr;
 	sprintf(core->name, "cx88[%d]", core->nr);
 
-	core->tvnorm = V4L2_STD_NTSC_M;
+	/*
+	 * Note: Setting initial standard here would cause first call to
+	 * cx88_set_tvnorm() to return without programming any registers.  Leave
+	 * it blank for at this point and it will get set later in
+	 * cx8800_initdev()
+	 */
+	core->tvnorm  = 0;
+
 	core->width   = 320;
 	core->height  = 240;
 	core->field   = V4L2_FIELD_INTERLACED;
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index aef9acf351f6..abbf5b05b6f5 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -1429,7 +1429,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 
 	/* initial device configuration */
 	mutex_lock(&core->lock);
-	cx88_set_tvnorm(core, core->tvnorm);
+	cx88_set_tvnorm(core, V4L2_STD_NTSC_M);
 	v4l2_ctrl_handler_setup(&core->video_hdl);
 	v4l2_ctrl_handler_setup(&core->audio_hdl);
 	cx88_video_mux(core, 0);
diff --git a/drivers/media/pci/dm1105/Kconfig b/drivers/media/pci/dm1105/Kconfig
index 173daf0c0847..14fa7e40f2a6 100644
--- a/drivers/media/pci/dm1105/Kconfig
+++ b/drivers/media/pci/dm1105/Kconfig
@@ -1,6 +1,6 @@
 config DVB_DM1105
 	tristate "SDMC DM1105 based PCI cards"
-	depends on DVB_CORE && PCI && I2C
+	depends on DVB_CORE && PCI && I2C && I2C_ALGOBIT
 	select DVB_PLL if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_STV0299 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_STV0288 if MEDIA_SUBDRV_AUTOSELECT
diff --git a/drivers/media/pci/saa7134/saa7134-i2c.c b/drivers/media/pci/saa7134/saa7134-i2c.c
index 8ef6399d794f..bc957528f69f 100644
--- a/drivers/media/pci/saa7134/saa7134-i2c.c
+++ b/drivers/media/pci/saa7134/saa7134-i2c.c
@@ -355,12 +355,43 @@ static struct i2c_client saa7134_client_template = {
 
 /* ----------------------------------------------------------- */
 
+/* On Medion 7134 reading EEPROM needs DVB-T demod i2c gate open */
+static void saa7134_i2c_eeprom_md7134_gate(struct saa7134_dev *dev)
+{
+	u8 subaddr = 0x7, dmdregval;
+	u8 data[2];
+	int ret;
+	struct i2c_msg i2cgatemsg_r[] = { {.addr = 0x08, .flags = 0,
+					   .buf = &subaddr, .len = 1},
+					  {.addr = 0x08,
+					   .flags = I2C_M_RD,
+					   .buf = &dmdregval, .len = 1}
+					};
+	struct i2c_msg i2cgatemsg_w[] = { {.addr = 0x08, .flags = 0,
+					   .buf = data, .len = 2} };
+
+	ret = i2c_transfer(&dev->i2c_adap, i2cgatemsg_r, 2);
+	if ((ret == 2) && (dmdregval & 0x2)) {
+		pr_debug("%s: DVB-T demod i2c gate was left closed\n",
+			 dev->name);
+
+		data[0] = subaddr;
+		data[1] = (dmdregval & ~0x2);
+		if (i2c_transfer(&dev->i2c_adap, i2cgatemsg_w, 1) != 1)
+			pr_err("%s: EEPROM i2c gate open failure\n",
+			  dev->name);
+	}
+}
+
 static int
 saa7134_i2c_eeprom(struct saa7134_dev *dev, unsigned char *eedata, int len)
 {
 	unsigned char buf;
 	int i,err;
 
+	if (dev->board == SAA7134_BOARD_MD7134)
+		saa7134_i2c_eeprom_md7134_gate(dev);
+
 	dev->i2c_client.addr = 0xa0 >> 1;
 	buf = 0;
 	if (1 != (err = i2c_master_send(&dev->i2c_client,&buf,1))) {
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index 518086c7aed5..15e56c07b217 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -1219,10 +1219,13 @@ static int saa7134_g_fmt_vid_cap(struct file *file, void *priv,
 	f->fmt.pix.height       = dev->height;
 	f->fmt.pix.field        = dev->field;
 	f->fmt.pix.pixelformat  = dev->fmt->fourcc;
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * dev->fmt->depth) >> 3;
+	if (dev->fmt->planar)
+		f->fmt.pix.bytesperline = f->fmt.pix.width;
+	else
+		f->fmt.pix.bytesperline =
+			(f->fmt.pix.width * dev->fmt->depth) / 8;
 	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
+		(f->fmt.pix.height * f->fmt.pix.width * dev->fmt->depth) / 8;
 	f->fmt.pix.colorspace   = V4L2_COLORSPACE_SMPTE170M;
 	return 0;
 }
@@ -1298,10 +1301,13 @@ static int saa7134_try_fmt_vid_cap(struct file *file, void *priv,
 	if (f->fmt.pix.height > maxh)
 		f->fmt.pix.height = maxh;
 	f->fmt.pix.width &= ~0x03;
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * fmt->depth) >> 3;
+	if (fmt->planar)
+		f->fmt.pix.bytesperline = f->fmt.pix.width;
+	else
+		f->fmt.pix.bytesperline =
+			(f->fmt.pix.width * fmt->depth) / 8;
 	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
+		(f->fmt.pix.height * f->fmt.pix.width * fmt->depth) / 8;
 	f->fmt.pix.colorspace   = V4L2_COLORSPACE_SMPTE170M;
 
 	return 0;
diff --git a/drivers/media/pci/saa7164/saa7164-bus.c b/drivers/media/pci/saa7164/saa7164-bus.c
index a18fe5d47238..b4857cd7069e 100644
--- a/drivers/media/pci/saa7164/saa7164-bus.c
+++ b/drivers/media/pci/saa7164/saa7164-bus.c
@@ -393,11 +393,11 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 	msg_tmp.size = le16_to_cpu((__force __le16)msg_tmp.size);
 	msg_tmp.command = le32_to_cpu((__force __le32)msg_tmp.command);
 	msg_tmp.controlselector = le16_to_cpu((__force __le16)msg_tmp.controlselector);
+	memcpy(msg, &msg_tmp, sizeof(*msg));
 
 	/* No need to update the read positions, because this was a peek */
 	/* If the caller specifically want to peek, return */
 	if (peekonly) {
-		memcpy(msg, &msg_tmp, sizeof(*msg));
 		goto peekout;
 	}
 
@@ -442,21 +442,15 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 		space_rem = bus->m_dwSizeGetRing - curr_grp;
 
 		if (space_rem < sizeof(*msg)) {
-			/* msg wraps around the ring */
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, space_rem);
-			memcpy_fromio((u8 *)msg + space_rem, bus->m_pdwGetRing,
-				sizeof(*msg) - space_rem);
 			if (buf)
 				memcpy_fromio(buf, bus->m_pdwGetRing + sizeof(*msg) -
 					space_rem, buf_size);
 
 		} else if (space_rem == sizeof(*msg)) {
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 			if (buf)
 				memcpy_fromio(buf, bus->m_pdwGetRing, buf_size);
 		} else {
 			/* Additional data wraps around the ring */
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 			if (buf) {
 				memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp +
 					sizeof(*msg), space_rem - sizeof(*msg));
@@ -469,15 +463,10 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 
 	} else {
 		/* No wrapping */
-		memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 		if (buf)
 			memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp + sizeof(*msg),
 				buf_size);
 	}
-	/* Convert from little endian to CPU */
-	msg->size = le16_to_cpu((__force __le16)msg->size);
-	msg->command = le32_to_cpu((__force __le32)msg->command);
-	msg->controlselector = le16_to_cpu((__force __le16)msg->controlselector);
 
 	/* Update the read positions, adjusting the ring */
 	saa7164_writel(bus->m_dwGetReadPos, new_grp);
diff --git a/drivers/media/pci/solo6x10/solo6x10.h b/drivers/media/pci/solo6x10/solo6x10.h
index 4ab6586c0467..f53e59e9c0ea 100644
--- a/drivers/media/pci/solo6x10/solo6x10.h
+++ b/drivers/media/pci/solo6x10/solo6x10.h
@@ -286,7 +286,10 @@ static inline u32 solo_reg_read(struct solo_dev *solo_dev, int reg)
 static inline void solo_reg_write(struct solo_dev *solo_dev, int reg,
 				  u32 data)
 {
+	u16 val;
+
 	writel(data, solo_dev->reg_base + reg);
+	pci_read_config_word(solo_dev->pdev, PCI_STATUS, &val);
 }
 
 static inline void solo_irq_on(struct solo_dev *dev, u32 mask)
diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c
index f0480d687f17..572bc043b62d 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.c
+++ b/drivers/media/platform/am437x/am437x-vpfe.c
@@ -1576,7 +1576,7 @@ static int vpfe_s_fmt(struct file *file, void *priv,
 		return -EBUSY;
 	}
 
-	ret = vpfe_try_fmt(file, priv, &format);
+	ret = __vpfe_get_format(vpfe, &format, &bpp);
 	if (ret)
 		return ret;
 
@@ -1706,7 +1706,7 @@ static int vpfe_get_app_input_index(struct vpfe_device *vpfe,
 		sdinfo = &cfg->sub_devs[i];
 		client = v4l2_get_subdevdata(sdinfo->sd);
 		if (client->addr == curr_client->addr &&
-		    client->adapter->nr == client->adapter->nr) {
+		    client->adapter->nr == curr_client->adapter->nr) {
 			if (vpfe->current_input >= 1)
 				return -1;
 			*app_input_index = j + vpfe->current_input;
diff --git a/drivers/media/platform/blackfin/ppi.c b/drivers/media/platform/blackfin/ppi.c
index cff63e511e6d..b8f3d9fa66e9 100644
--- a/drivers/media/platform/blackfin/ppi.c
+++ b/drivers/media/platform/blackfin/ppi.c
@@ -214,6 +214,8 @@ static int ppi_set_params(struct ppi_if *ppi, struct ppi_params *params)
 	if (params->dlen > 24 || params->dlen <= 0)
 		return -EINVAL;
 	pctrl = devm_pinctrl_get(ppi->dev);
+	if (IS_ERR(pctrl))
+		return PTR_ERR(pctrl);
 	pstate = pinctrl_lookup_state(pctrl,
 				      pin_state[(params->dlen + 7) / 8 - 1]);
 	if (pinctrl_select_state(pctrl, pstate))
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 654e964f84a2..d76511c1c1e3 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1342,7 +1342,7 @@ static void coda_finish_encode(struct coda_ctx *ctx)
 
 	/* Calculate bytesused field */
 	if (dst_buf->sequence == 0) {
-		vb2_set_plane_payload(&dst_buf->vb2_buf, 0,
+		vb2_set_plane_payload(&dst_buf->vb2_buf, 0, wr_ptr - start_ptr +
 					ctx->vpu_header_size[0] +
 					ctx->vpu_header_size[1] +
 					ctx->vpu_header_size[2]);
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 15516a6e3a39..323aad3c89de 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -2119,14 +2119,12 @@ static int coda_probe(struct platform_device *pdev)
 
 	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
 
-	if (of_id) {
+	if (of_id)
 		dev->devtype = of_id->data;
-	} else if (pdev_id) {
+	else if (pdev_id)
 		dev->devtype = &coda_devdata[pdev_id->driver_data];
-	} else {
-		ret = -EINVAL;
-		goto err_v4l2_register;
-	}
+	else
+		return -EINVAL;
 
 	spin_lock_init(&dev->irqlock);
 	INIT_LIST_HEAD(&dev->instances);
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index 7767e072d623..1f656a3a84b9 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -1709,27 +1709,9 @@ static long vpfe_param_handler(struct file *file, void *priv,
 
 	switch (cmd) {
 	case VPFE_CMD_S_CCDC_RAW_PARAMS:
+		ret = -EINVAL;
 		v4l2_warn(&vpfe_dev->v4l2_dev,
-			  "VPFE_CMD_S_CCDC_RAW_PARAMS: experimental ioctl\n");
-		if (ccdc_dev->hw_ops.set_params) {
-			ret = ccdc_dev->hw_ops.set_params(param);
-			if (ret) {
-				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-					"Error setting parameters in CCDC\n");
-				goto unlock_out;
-			}
-			ret = vpfe_get_ccdc_image_format(vpfe_dev,
-							 &vpfe_dev->fmt);
-			if (ret < 0) {
-				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-					"Invalid image format at CCDC\n");
-				goto unlock_out;
-			}
-		} else {
-			ret = -EINVAL;
-			v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-				"VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n");
-		}
+			"VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n");
 		break;
 	default:
 		ret = -ENOTTY;
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index 4a608cbe0fdb..9c6fc09b88e0 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -1098,10 +1098,10 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result,
 			       struct s5p_jpeg_ctx *ctx)
 {
 	int c, components = 0, notfound, n_dht = 0, n_dqt = 0;
-	unsigned int height, width, word, subsampling = 0, sos = 0, sof = 0,
-		     sof_len = 0;
-	unsigned int dht[S5P_JPEG_MAX_MARKER], dht_len[S5P_JPEG_MAX_MARKER],
-		     dqt[S5P_JPEG_MAX_MARKER], dqt_len[S5P_JPEG_MAX_MARKER];
+	unsigned int height = 0, width = 0, word, subsampling = 0;
+	unsigned int sos = 0, sof = 0, sof_len = 0;
+	unsigned int dht[S5P_JPEG_MAX_MARKER], dht_len[S5P_JPEG_MAX_MARKER];
+	unsigned int dqt[S5P_JPEG_MAX_MARKER], dqt_len[S5P_JPEG_MAX_MARKER];
 	long length;
 	struct s5p_jpeg_buffer jpeg_buffer;
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index 3ffe2ecfd5ef..7727789dbda1 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -173,6 +173,7 @@ static void s5p_mfc_watchdog_worker(struct work_struct *work)
 		}
 		s5p_mfc_clock_on();
 		ret = s5p_mfc_init_hw(dev);
+		s5p_mfc_clock_off();
 		if (ret)
 			mfc_err("Failed to reinit FW\n");
 	}
@@ -1029,6 +1030,11 @@ static int match_child(struct device *dev, void *data)
 	return !strcmp(dev_name(dev), (char *)data);
 }
 
+static void s5p_mfc_memdev_release(struct device *dev)
+{
+	dma_release_declared_memory(dev);
+}
+
 static void *mfc_get_drv_data(struct platform_device *pdev);
 
 static int s5p_mfc_alloc_memdevs(struct s5p_mfc_dev *dev)
@@ -1041,6 +1047,9 @@ static int s5p_mfc_alloc_memdevs(struct s5p_mfc_dev *dev)
 		mfc_err("Not enough memory\n");
 		return -ENOMEM;
 	}
+
+	dev_set_name(dev->mem_dev_l, "%s", "s5p-mfc-l");
+	dev->mem_dev_l->release = s5p_mfc_memdev_release;
 	device_initialize(dev->mem_dev_l);
 	of_property_read_u32_array(dev->plat_dev->dev.of_node,
 			"samsung,mfc-l", mem_info, 2);
@@ -1058,6 +1067,9 @@ static int s5p_mfc_alloc_memdevs(struct s5p_mfc_dev *dev)
 		mfc_err("Not enough memory\n");
 		return -ENOMEM;
 	}
+
+	dev_set_name(dev->mem_dev_r, "%s", "s5p-mfc-r");
+	dev->mem_dev_r->release = s5p_mfc_memdev_release;
 	device_initialize(dev->mem_dev_r);
 	of_property_read_u32_array(dev->plat_dev->dev.of_node,
 			"samsung,mfc-r", mem_info, 2);
diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index 6310acab60e7..d41ae950d1a1 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -154,6 +154,7 @@ static int sru_s_stream(struct v4l2_subdev *subdev, int enable)
 	mutex_lock(sru->ctrls.lock);
 	ctrl0 |= vsp1_sru_read(sru, VI6_SRU_CTRL0)
 	       & (VI6_SRU_CTRL0_PARAM0_MASK | VI6_SRU_CTRL0_PARAM1_MASK);
+	vsp1_sru_write(sru, VI6_SRU_CTRL0, ctrl0);
 	mutex_unlock(sru->ctrls.lock);
 
 	vsp1_sru_write(sru, VI6_SRU_CTRL1, VI6_SRU_CTRL1_PARAM5);
diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c
index 65f80b8b9f7a..eb9e7feb9b13 100644
--- a/drivers/media/rc/imon.c
+++ b/drivers/media/rc/imon.c
@@ -1629,7 +1629,7 @@ static void imon_incoming_packet(struct imon_context *ictx,
 	if (kc == KEY_KEYBOARD && !ictx->release_code) {
 		ictx->last_keycode = kc;
 		if (!nomouse) {
-			ictx->pad_mouse = ~(ictx->pad_mouse) & 0x1;
+			ictx->pad_mouse = !ictx->pad_mouse;
 			dev_dbg(dev, "toggling to %s mode\n",
 				ictx->pad_mouse ? "mouse" : "keyboard");
 			spin_unlock_irqrestore(&ictx->kc_lock, flags);
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index a32659fcd266..efc21b1da211 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -254,7 +254,7 @@ static long ir_lirc_ioctl(struct file *filep, unsigned int cmd,
 		return 0;
 
 	case LIRC_GET_REC_RESOLUTION:
-		val = dev->rx_resolution;
+		val = dev->rx_resolution / 1000;
 		break;
 
 	case LIRC_SET_WIDEBAND_RECEIVER:
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 84fa6e9b59a1..67314c034cdb 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -29,7 +29,7 @@
 #define RC5_BIT_START		(1 * RC5_UNIT)
 #define RC5_BIT_END		(1 * RC5_UNIT)
 #define RC5X_SPACE		(4 * RC5_UNIT)
-#define RC5_TRAILER		(10 * RC5_UNIT) /* In reality, approx 100 */
+#define RC5_TRAILER		(6 * RC5_UNIT) /* In reality, approx 100 */
 
 enum rc5_state {
 	STATE_INACTIVE,
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 0f301903aa6f..63165d324fff 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -263,6 +263,8 @@ static void ite_set_carrier_params(struct ite_dev *dev)
 
 			if (allowance > ITE_RXDCR_MAX)
 				allowance = ITE_RXDCR_MAX;
+
+			use_demodulator = true;
 		}
 	}
 
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 2cdb740cde48..f838d9c7ed12 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1321,8 +1321,8 @@ static int mceusb_dev_probe(struct usb_interface *intf,
 			}
 		}
 	}
-	if (ep_in == NULL) {
-		dev_dbg(&intf->dev, "inbound and/or endpoint not found");
+	if (!ep_in || !ep_out) {
+		dev_dbg(&intf->dev, "required endpoints not found\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 4e941f00b600..8d96a22647b3 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -281,6 +281,14 @@ static void free_firmware(struct xc2028_data *priv)
 	int i;
 	tuner_dbg("%s called\n", __func__);
 
+	/* free allocated f/w string */
+	if (priv->fname != firmware_name)
+		kfree(priv->fname);
+	priv->fname = NULL;
+
+	priv->state = XC2028_NO_FIRMWARE;
+	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
+
 	if (!priv->firm)
 		return;
 
@@ -291,9 +299,6 @@ static void free_firmware(struct xc2028_data *priv)
 
 	priv->firm = NULL;
 	priv->firm_size = 0;
-	priv->state = XC2028_NO_FIRMWARE;
-
-	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
 }
 
 static int load_all_firmwares(struct dvb_frontend *fe,
@@ -884,9 +889,8 @@ read_not_reliable:
 	return 0;
 
 fail:
-	priv->state = XC2028_NO_FIRMWARE;
+	free_firmware(priv);
 
-	memset(&priv->cur_fw, 0, sizeof(priv->cur_fw));
 	if (retry_count < 8) {
 		msleep(50);
 		retry_count++;
@@ -1332,11 +1336,8 @@ static int xc2028_dvb_release(struct dvb_frontend *fe)
 	mutex_lock(&xc2028_list_mutex);
 
 	/* only perform final cleanup if this is the last instance */
-	if (hybrid_tuner_report_instance_count(priv) == 1) {
+	if (hybrid_tuner_report_instance_count(priv) == 1)
 		free_firmware(priv);
-		kfree(priv->ctrl.fname);
-		priv->ctrl.fname = NULL;
-	}
 
 	if (priv)
 		hybrid_tuner_release_state(priv);
@@ -1399,16 +1400,8 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 	/*
 	 * Copy the config data.
-	 * For the firmware name, keep a local copy of the string,
-	 * in order to avoid troubles during device release.
 	 */
-	kfree(priv->ctrl.fname);
 	memcpy(&priv->ctrl, p, sizeof(priv->ctrl));
-	if (p->fname) {
-		priv->ctrl.fname = kstrdup(p->fname, GFP_KERNEL);
-		if (priv->ctrl.fname == NULL)
-			rc = -ENOMEM;
-	}
 
 	/*
 	 * If firmware name changed, frees firmware. As free_firmware will
@@ -1423,10 +1416,15 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 	if (priv->state == XC2028_NO_FIRMWARE) {
 		if (!firmware_name[0])
-			priv->fname = priv->ctrl.fname;
+			priv->fname = kstrdup(p->fname, GFP_KERNEL);
 		else
 			priv->fname = firmware_name;
 
+		if (!priv->fname) {
+			rc = -ENOMEM;
+			goto unlock;
+		}
+
 		rc = request_firmware_nowait(THIS_MODULE, 1,
 					     priv->fname,
 					     priv->i2c_props.adap->dev.parent,
@@ -1439,6 +1437,7 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 		} else
 			priv->state = XC2028_WAITING_FIRMWARE;
 	}
+unlock:
 	mutex_unlock(&priv->lock);
 
 	return rc;
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index 565a59310747..34b35ebd60ac 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -1073,7 +1073,7 @@ static int airspy_probe(struct usb_interface *intf,
 	if (ret) {
 		dev_err(s->dev, "Failed to register as video device (%d)\n",
 				ret);
-		goto err_unregister_v4l2_dev;
+		goto err_free_controls;
 	}
 	dev_info(s->dev, "Registered as %s\n",
 			video_device_node_name(&s->vdev));
@@ -1082,7 +1082,6 @@ static int airspy_probe(struct usb_interface *intf,
 
 err_free_controls:
 	v4l2_ctrl_handler_free(&s->hdl);
-err_unregister_v4l2_dev:
 	v4l2_device_unregister(&s->v4l2_dev);
 err_free_mem:
 	kfree(s);
diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c
index 0934024fb89d..d91ded795c93 100644
--- a/drivers/media/usb/au0828/au0828-core.c
+++ b/drivers/media/usb/au0828/au0828-core.c
@@ -159,7 +159,7 @@ static void au0828_usb_disconnect(struct usb_interface *interface)
 	   Set the status so poll routines can check and avoid
 	   access after disconnect.
 	*/
-	dev->dev_state = DEV_DISCONNECTED;
+	set_bit(DEV_DISCONNECTED, &dev->dev_state);
 
 	au0828_rc_unregister(dev);
 	/* Digital TV */
diff --git a/drivers/media/usb/au0828/au0828-input.c b/drivers/media/usb/au0828/au0828-input.c
index b0f067971979..3d6687f0407d 100644
--- a/drivers/media/usb/au0828/au0828-input.c
+++ b/drivers/media/usb/au0828/au0828-input.c
@@ -130,7 +130,7 @@ static int au0828_get_key_au8522(struct au0828_rc *ir)
 	bool first = true;
 
 	/* do nothing if device is disconnected */
-	if (ir->dev->dev_state == DEV_DISCONNECTED)
+	if (test_bit(DEV_DISCONNECTED, &ir->dev->dev_state))
 		return 0;
 
 	/* Check IR int */
@@ -260,7 +260,7 @@ static void au0828_rc_stop(struct rc_dev *rc)
 	cancel_delayed_work_sync(&ir->work);
 
 	/* do nothing if device is disconnected */
-	if (ir->dev->dev_state != DEV_DISCONNECTED) {
+	if (!test_bit(DEV_DISCONNECTED, &ir->dev->dev_state)) {
 		/* Disable IR */
 		au8522_rc_clear(ir, 0xe0, 1 << 4);
 	}
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 45c622e234f7..7b2fe1b56039 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -104,14 +104,13 @@ static inline void print_err_status(struct au0828_dev *dev,
 
 static int check_dev(struct au0828_dev *dev)
 {
-	if (dev->dev_state & DEV_DISCONNECTED) {
+	if (test_bit(DEV_DISCONNECTED, &dev->dev_state)) {
 		pr_info("v4l2 ioctl: device not present\n");
 		return -ENODEV;
 	}
 
-	if (dev->dev_state & DEV_MISCONFIGURED) {
-		pr_info("v4l2 ioctl: device is misconfigured; "
-		       "close and open it again\n");
+	if (test_bit(DEV_MISCONFIGURED, &dev->dev_state)) {
+		pr_info("v4l2 ioctl: device is misconfigured; close and open it again\n");
 		return -EIO;
 	}
 	return 0;
@@ -519,8 +518,8 @@ static inline int au0828_isoc_copy(struct au0828_dev *dev, struct urb *urb)
 	if (!dev)
 		return 0;
 
-	if ((dev->dev_state & DEV_DISCONNECTED) ||
-	    (dev->dev_state & DEV_MISCONFIGURED))
+	if (test_bit(DEV_DISCONNECTED, &dev->dev_state) ||
+	    test_bit(DEV_MISCONFIGURED, &dev->dev_state))
 		return 0;
 
 	if (urb->status < 0) {
@@ -766,10 +765,10 @@ static int au0828_stream_interrupt(struct au0828_dev *dev)
 	int ret = 0;
 
 	dev->stream_state = STREAM_INTERRUPT;
-	if (dev->dev_state == DEV_DISCONNECTED)
+	if (test_bit(DEV_DISCONNECTED, &dev->dev_state))
 		return -ENODEV;
 	else if (ret) {
-		dev->dev_state = DEV_MISCONFIGURED;
+		set_bit(DEV_MISCONFIGURED, &dev->dev_state);
 		dprintk(1, "%s device is misconfigured!\n", __func__);
 		return ret;
 	}
@@ -958,7 +957,7 @@ static int au0828_v4l2_open(struct file *filp)
 	int ret;
 
 	dprintk(1,
-		"%s called std_set %d dev_state %d stream users %d users %d\n",
+		"%s called std_set %d dev_state %ld stream users %d users %d\n",
 		__func__, dev->std_set_in_tuner_core, dev->dev_state,
 		dev->streaming_users, dev->users);
 
@@ -977,7 +976,7 @@ static int au0828_v4l2_open(struct file *filp)
 		au0828_analog_stream_enable(dev);
 		au0828_analog_stream_reset(dev);
 		dev->stream_state = STREAM_OFF;
-		dev->dev_state |= DEV_INITIALIZED;
+		set_bit(DEV_INITIALIZED, &dev->dev_state);
 	}
 	dev->users++;
 	mutex_unlock(&dev->lock);
@@ -991,7 +990,7 @@ static int au0828_v4l2_close(struct file *filp)
 	struct video_device *vdev = video_devdata(filp);
 
 	dprintk(1,
-		"%s called std_set %d dev_state %d stream users %d users %d\n",
+		"%s called std_set %d dev_state %ld stream users %d users %d\n",
 		__func__, dev->std_set_in_tuner_core, dev->dev_state,
 		dev->streaming_users, dev->users);
 
@@ -1007,7 +1006,7 @@ static int au0828_v4l2_close(struct file *filp)
 		del_timer_sync(&dev->vbi_timeout);
 	}
 
-	if (dev->dev_state == DEV_DISCONNECTED)
+	if (test_bit(DEV_DISCONNECTED, &dev->dev_state))
 		goto end;
 
 	if (dev->users == 1) {
@@ -1036,7 +1035,7 @@ static void au0828_init_tuner(struct au0828_dev *dev)
 		.type = V4L2_TUNER_ANALOG_TV,
 	};
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	if (dev->std_set_in_tuner_core)
@@ -1108,7 +1107,7 @@ static int vidioc_querycap(struct file *file, void  *priv,
 	struct video_device *vdev = video_devdata(file);
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	strlcpy(cap->driver, "au0828", sizeof(cap->driver));
@@ -1151,7 +1150,7 @@ static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	f->fmt.pix.width = dev->width;
@@ -1170,7 +1169,7 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	return au0828_set_format(dev, VIDIOC_TRY_FMT, f);
@@ -1182,7 +1181,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 	struct au0828_dev *dev = video_drvdata(file);
 	int rc;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	rc = check_dev(dev);
@@ -1204,7 +1203,7 @@ static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id norm)
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	if (norm == dev->std)
@@ -1236,7 +1235,7 @@ static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *norm)
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	*norm = dev->std;
@@ -1259,7 +1258,7 @@ static int vidioc_enum_input(struct file *file, void *priv,
 		[AU0828_VMUX_DEBUG] = "tv debug"
 	};
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	tmp = input->index;
@@ -1289,7 +1288,7 @@ static int vidioc_g_input(struct file *file, void *priv, unsigned int *i)
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	*i = dev->ctrl_input;
@@ -1300,7 +1299,7 @@ static void au0828_s_input(struct au0828_dev *dev, int index)
 {
 	int i;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	switch (AUVI_INPUT(index).type) {
@@ -1385,7 +1384,7 @@ static int vidioc_g_audio(struct file *file, void *priv, struct v4l2_audio *a)
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	a->index = dev->ctrl_ainput;
@@ -1405,7 +1404,7 @@ static int vidioc_s_audio(struct file *file, void *priv, const struct v4l2_audio
 	if (a->index != dev->ctrl_ainput)
 		return -EINVAL;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 	return 0;
 }
@@ -1417,7 +1416,7 @@ static int vidioc_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 	if (t->index != 0)
 		return -EINVAL;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	strcpy(t->name, "Auvitek tuner");
@@ -1437,7 +1436,7 @@ static int vidioc_s_tuner(struct file *file, void *priv,
 	if (t->index != 0)
 		return -EINVAL;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	au0828_init_tuner(dev);
@@ -1459,7 +1458,7 @@ static int vidioc_g_frequency(struct file *file, void *priv,
 
 	if (freq->tuner != 0)
 		return -EINVAL;
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 	freq->frequency = dev->ctrl_freq;
 	return 0;
@@ -1474,7 +1473,7 @@ static int vidioc_s_frequency(struct file *file, void *priv,
 	if (freq->tuner != 0)
 		return -EINVAL;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	au0828_init_tuner(dev);
@@ -1500,7 +1499,7 @@ static int vidioc_g_fmt_vbi_cap(struct file *file, void *priv,
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	format->fmt.vbi.samples_per_line = dev->vbi_width;
@@ -1526,7 +1525,7 @@ static int vidioc_cropcap(struct file *file, void *priv,
 	if (cc->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	cc->bounds.left = 0;
@@ -1548,7 +1547,7 @@ static int vidioc_g_register(struct file *file, void *priv,
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	reg->val = au0828_read(dev, reg->reg);
@@ -1561,7 +1560,7 @@ static int vidioc_s_register(struct file *file, void *priv,
 {
 	struct au0828_dev *dev = video_drvdata(file);
 
-	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
+	dprintk(1, "%s called std_set %d dev_state %ld\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
 	return au0828_writereg(dev, reg->reg, reg->val);
diff --git a/drivers/media/usb/au0828/au0828.h b/drivers/media/usb/au0828/au0828.h
index 60b59391ea2a..d1b6405a05a4 100644
--- a/drivers/media/usb/au0828/au0828.h
+++ b/drivers/media/usb/au0828/au0828.h
@@ -21,6 +21,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitops.h>
 #include <linux/usb.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
@@ -122,9 +123,9 @@ enum au0828_stream_state {
 
 /* device state */
 enum au0828_dev_state {
-	DEV_INITIALIZED = 0x01,
-	DEV_DISCONNECTED = 0x02,
-	DEV_MISCONFIGURED = 0x04
+	DEV_INITIALIZED = 0,
+	DEV_DISCONNECTED = 1,
+	DEV_MISCONFIGURED = 2
 };
 
 struct au0828_dev;
@@ -248,7 +249,7 @@ struct au0828_dev {
 	int input_type;
 	int std_set_in_tuner_core;
 	unsigned int ctrl_input;
-	enum au0828_dev_state dev_state;
+	long unsigned int dev_state; /* defined at enum au0828_dev_state */;
 	enum au0828_stream_state stream_state;
 	wait_queue_head_t open;
 
diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index de4ae5eb4830..10d8a08e36e6 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -671,10 +671,8 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 
 	spin_lock_init(&adev->slock);
 	err = snd_pcm_new(card, "Cx231xx Audio", 0, 0, 1, &pcm);
-	if (err < 0) {
-		snd_card_free(card);
-		return err;
-	}
+	if (err < 0)
+		goto err_free_card;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE,
 			&snd_cx231xx_pcm_capture);
@@ -688,10 +686,9 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 	INIT_WORK(&dev->wq_trigger, audio_trigger);
 
 	err = snd_card_register(card);
-	if (err < 0) {
-		snd_card_free(card);
-		return err;
-	}
+	if (err < 0)
+		goto err_free_card;
+
 	adev->sndcard = card;
 	adev->udev = dev->udev;
 
@@ -701,6 +698,11 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 					    hs_config_info[0].interface_info.
 					    audio_index + 1];
 
+	if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) {
+		err = -ENODEV;
+		goto err_free_card;
+	}
+
 	adev->end_point_addr =
 	    uif->altsetting[0].endpoint[isoc_pipe].desc.
 			bEndpointAddress;
@@ -710,13 +712,20 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 		"audio EndPoint Addr 0x%x, Alternate settings: %i\n",
 		adev->end_point_addr, adev->num_alt);
 	adev->alt_max_pkt_size = kmalloc(32 * adev->num_alt, GFP_KERNEL);
-
-	if (adev->alt_max_pkt_size == NULL)
-		return -ENOMEM;
+	if (!adev->alt_max_pkt_size) {
+		err = -ENOMEM;
+		goto err_free_card;
+	}
 
 	for (i = 0; i < adev->num_alt; i++) {
-		u16 tmp =
-		    le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.
+		u16 tmp;
+
+		if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) {
+			err = -ENODEV;
+			goto err_free_pkt_size;
+		}
+
+		tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.
 				wMaxPacketSize);
 		adev->alt_max_pkt_size[i] =
 		    (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1);
@@ -726,6 +735,13 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 	}
 
 	return 0;
+
+err_free_pkt_size:
+	kfree(adev->alt_max_pkt_size);
+err_free_card:
+	snd_card_free(card);
+
+	return err;
 }
 
 static int cx231xx_audio_fini(struct cx231xx *dev)
diff --git a/drivers/media/usb/cx231xx/cx231xx-avcore.c b/drivers/media/usb/cx231xx/cx231xx-avcore.c
index 491913778bcc..2f52d66b4dae 100644
--- a/drivers/media/usb/cx231xx/cx231xx-avcore.c
+++ b/drivers/media/usb/cx231xx/cx231xx-avcore.c
@@ -1264,7 +1264,10 @@ int cx231xx_set_agc_analog_digital_mux_select(struct cx231xx *dev,
 				   dev->board.agc_analog_digital_select_gpio,
 				   analog_or_digital);
 
-	return status;
+	if (status < 0)
+		return status;
+
+	return 0;
 }
 
 int cx231xx_enable_i2c_port_3(struct cx231xx *dev, bool is_port_3)
diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c
index 4a117a58c39a..2c5f76d588ac 100644
--- a/drivers/media/usb/cx231xx/cx231xx-cards.c
+++ b/drivers/media/usb/cx231xx/cx231xx-cards.c
@@ -486,7 +486,7 @@ struct cx231xx_board cx231xx_boards[] = {
 		.output_mode = OUT_MODE_VIP11,
 		.demod_xfer_mode = 0,
 		.ctl_pin_status_mask = 0xFFFFFFC4,
-		.agc_analog_digital_select_gpio = 0x00,	/* According with PV cxPolaris.inf file */
+		.agc_analog_digital_select_gpio = 0x1c,
 		.tuner_sif_gpio = -1,
 		.tuner_scl_gpio = -1,
 		.tuner_sda_gpio = -1,
@@ -1447,6 +1447,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 
 	uif = udev->actconfig->interface[idx];
 
+	if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1)
+		return -ENODEV;
+
 	dev->video_mode.end_point_addr = uif->altsetting[0].endpoint[isoc_pipe].desc.bEndpointAddress;
 	dev->video_mode.num_alt = uif->num_altsetting;
 
@@ -1460,7 +1463,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 		return -ENOMEM;
 
 	for (i = 0; i < dev->video_mode.num_alt; i++) {
-		u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.wMaxPacketSize);
+		u16 tmp;
+
+		if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1)
+			return -ENODEV;
+
+		tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].desc.wMaxPacketSize);
 		dev->video_mode.alt_max_pkt_size[i] = (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1);
 		dev_dbg(dev->dev,
 			"Alternate setting %i, max size= %i\n", i,
@@ -1477,6 +1485,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 	}
 	uif = udev->actconfig->interface[idx];
 
+	if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1)
+		return -ENODEV;
+
 	dev->vbi_mode.end_point_addr =
 	    uif->altsetting[0].endpoint[isoc_pipe].desc.
 			bEndpointAddress;
@@ -1493,8 +1504,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 		return -ENOMEM;
 
 	for (i = 0; i < dev->vbi_mode.num_alt; i++) {
-		u16 tmp =
-		    le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].
+		u16 tmp;
+
+		if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1)
+			return -ENODEV;
+
+		tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].
 				desc.wMaxPacketSize);
 		dev->vbi_mode.alt_max_pkt_size[i] =
 		    (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1);
@@ -1514,6 +1529,9 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 	}
 	uif = udev->actconfig->interface[idx];
 
+	if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1)
+		return -ENODEV;
+
 	dev->sliced_cc_mode.end_point_addr =
 	    uif->altsetting[0].endpoint[isoc_pipe].desc.
 			bEndpointAddress;
@@ -1528,7 +1546,12 @@ static int cx231xx_init_v4l2(struct cx231xx *dev,
 		return -ENOMEM;
 
 	for (i = 0; i < dev->sliced_cc_mode.num_alt; i++) {
-		u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].
+		u16 tmp;
+
+		if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1)
+			return -ENODEV;
+
+		tmp = le16_to_cpu(uif->altsetting[i].endpoint[isoc_pipe].
 				desc.wMaxPacketSize);
 		dev->sliced_cc_mode.alt_max_pkt_size[i] =
 		    (tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1);
@@ -1693,6 +1716,11 @@ static int cx231xx_usb_probe(struct usb_interface *interface,
 		}
 		uif = udev->actconfig->interface[idx];
 
+		if (uif->altsetting[0].desc.bNumEndpoints < isoc_pipe + 1) {
+			retval = -ENODEV;
+			goto err_video_alt;
+		}
+
 		dev->ts1_mode.end_point_addr =
 		    uif->altsetting[0].endpoint[isoc_pipe].
 				desc.bEndpointAddress;
@@ -1710,7 +1738,14 @@ static int cx231xx_usb_probe(struct usb_interface *interface,
 		}
 
 		for (i = 0; i < dev->ts1_mode.num_alt; i++) {
-			u16 tmp = le16_to_cpu(uif->altsetting[i].
+			u16 tmp;
+
+			if (uif->altsetting[i].desc.bNumEndpoints < isoc_pipe + 1) {
+				retval = -ENODEV;
+				goto err_video_alt;
+			}
+
+			tmp = le16_to_cpu(uif->altsetting[i].
 						endpoint[isoc_pipe].desc.
 						wMaxPacketSize);
 			dev->ts1_mode.alt_max_pkt_size[i] =
diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c
index a2fd49b6be83..19b0293312a0 100644
--- a/drivers/media/usb/cx231xx/cx231xx-core.c
+++ b/drivers/media/usb/cx231xx/cx231xx-core.c
@@ -712,6 +712,7 @@ int cx231xx_set_mode(struct cx231xx *dev, enum cx231xx_mode set_mode)
 			break;
 		case CX231XX_BOARD_CNXT_RDE_253S:
 		case CX231XX_BOARD_CNXT_RDU_253S:
+		case CX231XX_BOARD_PV_PLAYTV_USB_HYBRID:
 			errCode = cx231xx_set_agc_analog_digital_mux_select(dev, 1);
 			break;
 		case CX231XX_BOARD_HAUPPAUGE_EXETER:
@@ -738,7 +739,7 @@ int cx231xx_set_mode(struct cx231xx *dev, enum cx231xx_mode set_mode)
 		case CX231XX_BOARD_PV_PLAYTV_USB_HYBRID:
 		case CX231XX_BOARD_HAUPPAUGE_USB2_FM_PAL:
 		case CX231XX_BOARD_HAUPPAUGE_USB2_FM_NTSC:
-		errCode = cx231xx_set_agc_analog_digital_mux_select(dev, 0);
+			errCode = cx231xx_set_agc_analog_digital_mux_select(dev, 0);
 			break;
 		default:
 			break;
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
index f5df9eaba04f..9757f35cd5f5 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -1010,8 +1010,8 @@ EXPORT_SYMBOL(dvb_usbv2_probe);
 void dvb_usbv2_disconnect(struct usb_interface *intf)
 {
 	struct dvb_usb_device *d = usb_get_intfdata(intf);
-	const char *name = d->name;
-	struct device dev = d->udev->dev;
+	const char *devname = kstrdup(dev_name(&d->udev->dev), GFP_KERNEL);
+	const char *drvname = d->name;
 
 	dev_dbg(&d->udev->dev, "%s: bInterfaceNumber=%d\n", __func__,
 			intf->cur_altsetting->desc.bInterfaceNumber);
@@ -1021,8 +1021,9 @@ void dvb_usbv2_disconnect(struct usb_interface *intf)
 
 	dvb_usbv2_exit(d);
 
-	dev_info(&dev, "%s: '%s' successfully deinitialized and disconnected\n",
-			KBUILD_MODNAME, name);
+	pr_info("%s: '%s:%s' successfully deinitialized and disconnected\n",
+		KBUILD_MODNAME, drvname, devname);
+	kfree(devname);
 }
 EXPORT_SYMBOL(dvb_usbv2_disconnect);
 
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index 0d248ce02a9b..d1b4b729e814 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -677,7 +677,7 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 	struct dvb_usb_device *d = purb->context;
 	struct dib0700_rc_response *poll_reply;
 	enum rc_type protocol;
-	u32 uninitialized_var(keycode);
+	u32 keycode;
 	u8 toggle;
 
 	deb_info("%s()\n", __func__);
@@ -719,7 +719,8 @@ static void dib0700_rc_urb_completion(struct urb *purb)
 		    poll_reply->nec.data       == 0x00 &&
 		    poll_reply->nec.not_data   == 0xff) {
 			poll_reply->data_state = 2;
-			break;
+			rc_repeat(d->rc_dev);
+			goto resubmit;
 		}
 
 		if ((poll_reply->nec.data ^ poll_reply->nec.not_data) != 0xff) {
@@ -782,6 +783,9 @@ int dib0700_rc_setup(struct dvb_usb_device *d, struct usb_interface *intf)
 
 	/* Starting in firmware 1.20, the RC info is provided on a bulk pipe */
 
+	if (intf->altsetting[0].desc.bNumEndpoints < rc_ep + 1)
+		return -ENODEV;
+
 	purb = usb_alloc_urb(0, GFP_KERNEL);
 	if (purb == NULL) {
 		err("rc usb alloc urb failed");
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
index 733a7ff7b207..caad3b5c01ad 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
@@ -35,42 +35,51 @@ static int usb_cypress_writemem(struct usb_device *udev,u16 addr,u8 *data, u8 le
 
 int usb_cypress_load_firmware(struct usb_device *udev, const struct firmware *fw, int type)
 {
-	struct hexline hx;
-	u8 reset;
-	int ret,pos=0;
+	struct hexline *hx;
+	u8 *buf;
+	int ret, pos = 0;
+	u16 cpu_cs_register = cypress[type].cpu_cs_register;
+
+	buf = kmalloc(sizeof(*hx), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	hx = (struct hexline *)buf;
 
 	/* stop the CPU */
-	reset = 1;
-	if ((ret = usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1)) != 1)
+	buf[0] = 1;
+	if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1)
 		err("could not stop the USB controller CPU.");
 
-	while ((ret = dvb_usb_get_hexline(fw,&hx,&pos)) > 0) {
-		deb_fw("writing to address 0x%04x (buffer: 0x%02x %02x)\n",hx.addr,hx.len,hx.chk);
-		ret = usb_cypress_writemem(udev,hx.addr,hx.data,hx.len);
+	while ((ret = dvb_usb_get_hexline(fw, hx, &pos)) > 0) {
+		deb_fw("writing to address 0x%04x (buffer: 0x%02x %02x)\n", hx->addr, hx->len, hx->chk);
+		ret = usb_cypress_writemem(udev, hx->addr, hx->data, hx->len);
 
-		if (ret != hx.len) {
+		if (ret != hx->len) {
 			err("error while transferring firmware "
 				"(transferred size: %d, block size: %d)",
-				ret,hx.len);
+				ret, hx->len);
 			ret = -EINVAL;
 			break;
 		}
 	}
 	if (ret < 0) {
 		err("firmware download failed at %d with %d",pos,ret);
+		kfree(buf);
 		return ret;
 	}
 
 	if (ret == 0) {
 		/* restart the CPU */
-		reset = 0;
-		if (ret || usb_cypress_writemem(udev,cypress[type].cpu_cs_register,&reset,1) != 1) {
+		buf[0] = 0;
+		if (usb_cypress_writemem(udev, cpu_cs_register, buf, 1) != 1) {
 			err("could not restart the USB controller CPU.");
 			ret = -EINVAL;
 		}
 	} else
 		ret = -EIO;
 
+	kfree(buf);
+
 	return ret;
 }
 EXPORT_SYMBOL(usb_cypress_load_firmware);
diff --git a/drivers/media/usb/dvb-usb/ttusb2.c b/drivers/media/usb/dvb-usb/ttusb2.c
index f10717311e05..dd93c2c8fea9 100644
--- a/drivers/media/usb/dvb-usb/ttusb2.c
+++ b/drivers/media/usb/dvb-usb/ttusb2.c
@@ -78,6 +78,9 @@ static int ttusb2_msg(struct dvb_usb_device *d, u8 cmd,
 	u8 *s, *r = NULL;
 	int ret = 0;
 
+	if (4 + rlen > 64)
+		return -EIO;
+
 	s = kzalloc(wlen+4, GFP_KERNEL);
 	if (!s)
 		return -ENOMEM;
@@ -381,6 +384,22 @@ static int ttusb2_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num
 		write_read = i+1 < num && (msg[i+1].flags & I2C_M_RD);
 		read = msg[i].flags & I2C_M_RD;
 
+		if (3 + msg[i].len > sizeof(obuf)) {
+			err("i2c wr len=%d too high", msg[i].len);
+			break;
+		}
+		if (write_read) {
+			if (3 + msg[i+1].len > sizeof(ibuf)) {
+				err("i2c rd len=%d too high", msg[i+1].len);
+				break;
+			}
+		} else if (read) {
+			if (3 + msg[i].len > sizeof(ibuf)) {
+				err("i2c rd len=%d too high", msg[i].len);
+				break;
+			}
+		}
+
 		obuf[0] = (msg[i].addr << 1) | (write_read | read);
 		if (read)
 			obuf[1] = 0;
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index a19b5c8b56ff..1a9e1e556706 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -507,9 +507,8 @@ static int em28xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 	if (dev->disconnected)
 		return -ENODEV;
 
-	rc = rt_mutex_trylock(&dev->i2c_bus_lock);
-	if (rc < 0)
-		return rc;
+	if (!rt_mutex_trylock(&dev->i2c_bus_lock))
+		return -EAGAIN;
 
 	/* Switch I2C bus if needed */
 	if (bus != dev->cur_i2c_bus &&
diff --git a/drivers/media/usb/gspca/cpia1.c b/drivers/media/usb/gspca/cpia1.c
index f23df4a9d8c5..52b88e9e656b 100644
--- a/drivers/media/usb/gspca/cpia1.c
+++ b/drivers/media/usb/gspca/cpia1.c
@@ -1624,7 +1624,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 static void sd_stopN(struct gspca_dev *gspca_dev)
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 
 	command_pause(gspca_dev);
 
diff --git a/drivers/media/usb/gspca/konica.c b/drivers/media/usb/gspca/konica.c
index 39c96bb4c985..0f6d57fbf91b 100644
--- a/drivers/media/usb/gspca/konica.c
+++ b/drivers/media/usb/gspca/konica.c
@@ -188,6 +188,9 @@ static int sd_start(struct gspca_dev *gspca_dev)
 		return -EIO;
 	}
 
+	if (alt->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
 
 	n = gspca_dev->cam.cam_mode[gspca_dev->curr_mode].priv;
@@ -243,7 +246,7 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 static void sd_stopN(struct gspca_dev *gspca_dev)
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 
 	konica_stream_off(gspca_dev);
 #if IS_ENABLED(CONFIG_INPUT)
diff --git a/drivers/media/usb/gspca/t613.c b/drivers/media/usb/gspca/t613.c
index e2cc4e5a0ccb..bb52fc1fe598 100644
--- a/drivers/media/usb/gspca/t613.c
+++ b/drivers/media/usb/gspca/t613.c
@@ -837,7 +837,7 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev,
 			u8 *data,			/* isoc packet */
 			int len)			/* iso packet length */
 {
-	struct sd *sd = (struct sd *) gspca_dev;
+	struct sd *sd __maybe_unused = (struct sd *) gspca_dev;
 	int pkt_type;
 
 	if (data[0] == 0x5a) {
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
index e1907cd0c3b7..7613d1fee104 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
@@ -123,15 +123,10 @@ int pvr2_eeprom_analyze(struct pvr2_hdw *hdw)
 	memset(&tvdata,0,sizeof(tvdata));
 
 	eeprom = pvr2_eeprom_fetch(hdw);
-	if (!eeprom) return -EINVAL;
-
-	{
-		struct i2c_client fake_client;
-		/* Newer version expects a useless client interface */
-		fake_client.addr = hdw->eeprom_addr;
-		fake_client.adapter = &hdw->i2c_adap;
-		tveeprom_hauppauge_analog(&fake_client,&tvdata,eeprom);
-	}
+	if (!eeprom)
+		return -EINVAL;
+
+	tveeprom_hauppauge_analog(NULL, &tvdata, eeprom);
 
 	trace_eeprom("eeprom assumed v4l tveeprom module");
 	trace_eeprom("eeprom direct call results:");
diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c
index b79c36fd8cd2..58f23bcfe94e 100644
--- a/drivers/media/usb/pwc/pwc-if.c
+++ b/drivers/media/usb/pwc/pwc-if.c
@@ -91,6 +91,7 @@ static const struct usb_device_id pwc_device_table [] = {
 	{ USB_DEVICE(0x0471, 0x0312) },
 	{ USB_DEVICE(0x0471, 0x0313) }, /* the 'new' 720K */
 	{ USB_DEVICE(0x0471, 0x0329) }, /* Philips SPC 900NC PC Camera */
+	{ USB_DEVICE(0x0471, 0x032C) }, /* Philips SPC 880NC PC Camera */
 	{ USB_DEVICE(0x069A, 0x0001) }, /* Askey */
 	{ USB_DEVICE(0x046D, 0x08B0) }, /* Logitech QuickCam Pro 3000 */
 	{ USB_DEVICE(0x046D, 0x08B1) }, /* Logitech QuickCam Notebook Pro */
@@ -811,6 +812,11 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id
 			name = "Philips SPC 900NC webcam";
 			type_id = 740;
 			break;
+		case 0x032C:
+			PWC_INFO("Philips SPC 880NC USB webcam detected.\n");
+			name = "Philips SPC 880NC webcam";
+			type_id = 740;
+			break;
 		default:
 			return -ENODEV;
 			break;
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index c945e4c2fbd4..ec30a004f319 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -200,22 +200,30 @@ static int smsusb_start_streaming(struct smsusb_device_t *dev)
 static int smsusb_sendrequest(void *context, void *buffer, size_t size)
 {
 	struct smsusb_device_t *dev = (struct smsusb_device_t *) context;
-	struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer;
-	int dummy;
+	struct sms_msg_hdr *phdr;
+	int dummy, ret;
 
 	if (dev->state != SMSUSB_ACTIVE) {
 		pr_debug("Device not active yet\n");
 		return -ENOENT;
 	}
 
+	phdr = kmalloc(size, GFP_KERNEL);
+	if (!phdr)
+		return -ENOMEM;
+	memcpy(phdr, buffer, size);
+
 	pr_debug("sending %s(%d) size: %d\n",
 		  smscore_translate_msg(phdr->msg_type), phdr->msg_type,
 		  phdr->msg_length);
 
 	smsendian_handle_tx_message((struct sms_msg_data *) phdr);
-	smsendian_handle_message_header((struct sms_msg_hdr *)buffer);
-	return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
-			    buffer, size, &dummy, 1000);
+	smsendian_handle_message_header((struct sms_msg_hdr *)phdr);
+	ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
+			    phdr, size, &dummy, 1000);
+
+	kfree(phdr);
+	return ret;
 }
 
 static char *smsusb1_fw_lkup[] = {
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 78c12d22dfbb..5dab02432e82 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -278,6 +278,9 @@ static void snd_usbtv_trigger(struct work_struct *work)
 {
 	struct usbtv *chip = container_of(work, struct usbtv, snd_trigger);
 
+	if (!chip->snd)
+		return;
+
 	if (atomic_read(&chip->snd_stream))
 		usbtv_audio_start(chip);
 	else
@@ -378,6 +381,8 @@ err:
 
 void usbtv_audio_free(struct usbtv *usbtv)
 {
+	cancel_work_sync(&usbtv->snd_trigger);
+
 	if (usbtv->snd && usbtv->udev) {
 		snd_card_free(usbtv->snd);
 		usbtv->snd = NULL;
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index b693206f66dd..91d709efef7a 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -1463,9 +1463,23 @@ static int usbvision_probe(struct usb_interface *intf,
 
 	if (usbvision_device_data[model].interface >= 0)
 		interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0];
-	else
+	else if (ifnum < dev->actconfig->desc.bNumInterfaces)
 		interface = &dev->actconfig->interface[ifnum]->altsetting[0];
+	else {
+		dev_err(&intf->dev, "interface %d is invalid, max is %d\n",
+		    ifnum, dev->actconfig->desc.bNumInterfaces - 1);
+		ret = -ENODEV;
+		goto err_usb;
+	}
+
+	if (interface->desc.bNumEndpoints < 2) {
+		dev_err(&intf->dev, "interface %d has %d endpoints, but must"
+		    " have minimum 2\n", ifnum, interface->desc.bNumEndpoints);
+		ret = -ENODEV;
+		goto err_usb;
+	}
 	endpoint = &interface->endpoint[1].desc;
+
 	if (!usb_endpoint_xfer_isoc(endpoint)) {
 		dev_err(&intf->dev, "%s: interface %d. has non-ISO endpoint!\n",
 		    __func__, ifnum);
@@ -1509,7 +1523,14 @@ static int usbvision_probe(struct usb_interface *intf,
 	}
 
 	for (i = 0; i < usbvision->num_alt; i++) {
-		u16 tmp = le16_to_cpu(uif->altsetting[i].endpoint[1].desc.
+		u16 tmp;
+
+		if (uif->altsetting[i].desc.bNumEndpoints < 2) {
+			ret = -ENODEV;
+			goto err_pkt;
+		}
+
+		tmp = le16_to_cpu(uif->altsetting[i].endpoint[1].desc.
 				      wMaxPacketSize);
 		usbvision->alt_max_pkt_size[i] =
 			(tmp & 0x07ff) * (((tmp & 0x1800) >> 11) + 1);
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index d11fd6ac2df0..885f689ac870 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -148,6 +148,26 @@ static struct uvc_format_desc uvc_fmts[] = {
 		.guid		= UVC_GUID_FORMAT_H264,
 		.fcc		= V4L2_PIX_FMT_H264,
 	},
+	{
+		.name		= "Greyscale 8 L/R (Y8I)",
+		.guid		= UVC_GUID_FORMAT_Y8I,
+		.fcc		= V4L2_PIX_FMT_Y8I,
+	},
+	{
+		.name		= "Greyscale 12 L/R (Y12I)",
+		.guid		= UVC_GUID_FORMAT_Y12I,
+		.fcc		= V4L2_PIX_FMT_Y12I,
+	},
+	{
+		.name		= "Depth data 16-bit (Z16)",
+		.guid		= UVC_GUID_FORMAT_Z16,
+		.fcc		= V4L2_PIX_FMT_Z16,
+	},
+	{
+		.name		= "Bayer 10-bit (SRGGB10P)",
+		.guid		= UVC_GUID_FORMAT_RW10,
+		.fcc		= V4L2_PIX_FMT_SRGGB10P,
+	},
 };
 
 /* ------------------------------------------------------------------------
@@ -1575,6 +1595,114 @@ static const char *uvc_print_chain(struct uvc_video_chain *chain)
 	return buffer;
 }
 
+static struct uvc_video_chain *uvc_alloc_chain(struct uvc_device *dev)
+{
+	struct uvc_video_chain *chain;
+
+	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+	if (chain == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&chain->entities);
+	mutex_init(&chain->ctrl_mutex);
+	chain->dev = dev;
+	v4l2_prio_init(&chain->prio);
+
+	return chain;
+}
+
+/*
+ * Fallback heuristic for devices that don't connect units and terminals in a
+ * valid chain.
+ *
+ * Some devices have invalid baSourceID references, causing uvc_scan_chain()
+ * to fail, but if we just take the entities we can find and put them together
+ * in the most sensible chain we can think of, turns out they do work anyway.
+ * Note: This heuristic assumes there is a single chain.
+ *
+ * At the time of writing, devices known to have such a broken chain are
+ *  - Acer Integrated Camera (5986:055a)
+ *  - Realtek rtl157a7 (0bda:57a7)
+ */
+static int uvc_scan_fallback(struct uvc_device *dev)
+{
+	struct uvc_video_chain *chain;
+	struct uvc_entity *iterm = NULL;
+	struct uvc_entity *oterm = NULL;
+	struct uvc_entity *entity;
+	struct uvc_entity *prev;
+
+	/*
+	 * Start by locating the input and output terminals. We only support
+	 * devices with exactly one of each for now.
+	 */
+	list_for_each_entry(entity, &dev->entities, list) {
+		if (UVC_ENTITY_IS_ITERM(entity)) {
+			if (iterm)
+				return -EINVAL;
+			iterm = entity;
+		}
+
+		if (UVC_ENTITY_IS_OTERM(entity)) {
+			if (oterm)
+				return -EINVAL;
+			oterm = entity;
+		}
+	}
+
+	if (iterm == NULL || oterm == NULL)
+		return -EINVAL;
+
+	/* Allocate the chain and fill it. */
+	chain = uvc_alloc_chain(dev);
+	if (chain == NULL)
+		return -ENOMEM;
+
+	if (uvc_scan_chain_entity(chain, oterm) < 0)
+		goto error;
+
+	prev = oterm;
+
+	/*
+	 * Add all Processing and Extension Units with two pads. The order
+	 * doesn't matter much, use reverse list traversal to connect units in
+	 * UVC descriptor order as we build the chain from output to input. This
+	 * leads to units appearing in the order meant by the manufacturer for
+	 * the cameras known to require this heuristic.
+	 */
+	list_for_each_entry_reverse(entity, &dev->entities, list) {
+		if (entity->type != UVC_VC_PROCESSING_UNIT &&
+		    entity->type != UVC_VC_EXTENSION_UNIT)
+			continue;
+
+		if (entity->num_pads != 2)
+			continue;
+
+		if (uvc_scan_chain_entity(chain, entity) < 0)
+			goto error;
+
+		prev->baSourceID[0] = entity->id;
+		prev = entity;
+	}
+
+	if (uvc_scan_chain_entity(chain, iterm) < 0)
+		goto error;
+
+	prev->baSourceID[0] = iterm->id;
+
+	list_add_tail(&chain->list, &dev->chains);
+
+	uvc_trace(UVC_TRACE_PROBE,
+		  "Found a video chain by fallback heuristic (%s).\n",
+		  uvc_print_chain(chain));
+
+	return 0;
+
+error:
+	kfree(chain);
+	return -EINVAL;
+}
+
 /*
  * Scan the device for video chains and register video devices.
  *
@@ -1597,15 +1725,10 @@ static int uvc_scan_device(struct uvc_device *dev)
 		if (term->chain.next || term->chain.prev)
 			continue;
 
-		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+		chain = uvc_alloc_chain(dev);
 		if (chain == NULL)
 			return -ENOMEM;
 
-		INIT_LIST_HEAD(&chain->entities);
-		mutex_init(&chain->ctrl_mutex);
-		chain->dev = dev;
-		v4l2_prio_init(&chain->prio);
-
 		term->flags |= UVC_ENTITY_FLAG_DEFAULT;
 
 		if (uvc_scan_chain(chain, term) < 0) {
@@ -1619,6 +1742,9 @@ static int uvc_scan_device(struct uvc_device *dev)
 		list_add_tail(&chain->list, &dev->chains);
 	}
 
+	if (list_empty(&dev->chains))
+		uvc_scan_fallback(dev);
+
 	if (list_empty(&dev->chains)) {
 		uvc_printk(KERN_INFO, "No valid video chain found.\n");
 		return -1;
diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c
index cfb868a48b5f..ff6feff21e94 100644
--- a/drivers/media/usb/uvc/uvc_queue.c
+++ b/drivers/media/usb/uvc/uvc_queue.c
@@ -416,7 +416,7 @@ struct uvc_buffer *uvc_queue_next_buffer(struct uvc_video_queue *queue,
 		nextbuf = NULL;
 	spin_unlock_irqrestore(&queue->irqlock, flags);
 
-	buf->state = buf->error ? VB2_BUF_STATE_ERROR : UVC_BUF_STATE_DONE;
+	buf->state = buf->error ? UVC_BUF_STATE_ERROR : UVC_BUF_STATE_DONE;
 	vb2_set_plane_payload(&buf->buf.vb2_buf, 0, buf->bytesused);
 	vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE);
 
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index 2764f43607c1..0e7d16fe84d4 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -1388,47 +1388,44 @@ static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
 static long uvc_v4l2_compat_ioctl32(struct file *file,
 		     unsigned int cmd, unsigned long arg)
 {
+	struct uvc_fh *handle = file->private_data;
 	union {
 		struct uvc_xu_control_mapping xmap;
 		struct uvc_xu_control_query xqry;
 	} karg;
 	void __user *up = compat_ptr(arg);
-	mm_segment_t old_fs;
 	long ret;
 
 	switch (cmd) {
 	case UVCIOC_CTRL_MAP32:
-		cmd = UVCIOC_CTRL_MAP;
 		ret = uvc_v4l2_get_xu_mapping(&karg.xmap, up);
+		if (ret)
+			return ret;
+		ret = uvc_ioctl_ctrl_map(handle->chain, &karg.xmap);
+		if (ret)
+			return ret;
+		ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
+		if (ret)
+			return ret;
+
 		break;
 
 	case UVCIOC_CTRL_QUERY32:
-		cmd = UVCIOC_CTRL_QUERY;
 		ret = uvc_v4l2_get_xu_query(&karg.xqry, up);
+		if (ret)
+			return ret;
+		ret = uvc_xu_ctrl_query(handle->chain, &karg.xqry);
+		if (ret)
+			return ret;
+		ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
+		if (ret)
+			return ret;
 		break;
 
 	default:
 		return -ENOIOCTLCMD;
 	}
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = video_ioctl2(file, cmd, (unsigned long)&karg);
-	set_fs(old_fs);
-
-	if (ret < 0)
-		return ret;
-
-	switch (cmd) {
-	case UVCIOC_CTRL_MAP:
-		ret = uvc_v4l2_put_xu_mapping(&karg.xmap, up);
-		break;
-
-	case UVCIOC_CTRL_QUERY:
-		ret = uvc_v4l2_put_xu_query(&karg.xqry, up);
-		break;
-	}
-
 	return ret;
 }
 #endif
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index f0f2391e1b43..7e4d3eea371b 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -119,6 +119,18 @@
 #define UVC_GUID_FORMAT_H264 \
 	{ 'H',  '2',  '6',  '4', 0x00, 0x00, 0x10, 0x00, \
 	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y8I \
+	{ 'Y',  '8',  'I',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y12I \
+	{ 'Y',  '1',  '2',  'I', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Z16 \
+	{ 'Z',  '1',  '6',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_RW10 \
+	{ 'R',  'W',  '1',  '0', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
 
 /* ------------------------------------------------------------------------
  * Driver specific constants.
diff --git a/drivers/media/usb/zr364xx/zr364xx.c b/drivers/media/usb/zr364xx/zr364xx.c
index 7433ba5c4bad..fd6a3b36208e 100644
--- a/drivers/media/usb/zr364xx/zr364xx.c
+++ b/drivers/media/usb/zr364xx/zr364xx.c
@@ -604,6 +604,14 @@ static int zr364xx_read_video_callback(struct zr364xx_camera *cam,
 	ptr = pdest = frm->lpvbits;
 
 	if (frm->ulState == ZR364XX_READ_IDLE) {
+		if (purb->actual_length < 128) {
+			/* header incomplete */
+			dev_info(&cam->udev->dev,
+				 "%s: buffer (%d bytes) too small to hold jpeg header. Discarding.\n",
+				 __func__, purb->actual_length);
+			return -EINVAL;
+		}
+
 		frm->ulState = ZR364XX_READ_FRAME;
 		frm->cur_size = 0;
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 327e83ac2469..109f687d1cbd 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -280,7 +280,8 @@ static int put_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user
 static int put_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
 	if (!access_ok(VERIFY_WRITE, up, sizeof(struct v4l2_create_buffers32)) ||
-	    copy_to_user(up, kp, offsetof(struct v4l2_create_buffers32, format)))
+	    copy_to_user(up, kp, offsetof(struct v4l2_create_buffers32, format)) ||
+	    copy_to_user(up->reserved, kp->reserved, sizeof(kp->reserved)))
 		return -EFAULT;
 	return __put_v4l2_format32(&kp->format, &up->format);
 }
@@ -415,7 +416,8 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		get_user(kp->index, &up->index) ||
 		get_user(kp->type, &up->type) ||
 		get_user(kp->flags, &up->flags) ||
-		get_user(kp->memory, &up->memory))
+		get_user(kp->memory, &up->memory) ||
+		get_user(kp->length, &up->length))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_OUTPUT(kp->type))
@@ -427,9 +429,6 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
-		if (get_user(kp->length, &up->length))
-			return -EFAULT;
-
 		num_planes = kp->length;
 		if (num_planes == 0) {
 			kp->m.planes = NULL;
@@ -462,16 +461,14 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
-			if (get_user(kp->length, &up->length) ||
-				get_user(kp->m.offset, &up->m.offset))
+			if (get_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_USERPTR:
 			{
 			compat_long_t tmp;
 
-			if (get_user(kp->length, &up->length) ||
-			    get_user(tmp, &up->m.userptr))
+			if (get_user(tmp, &up->m.userptr))
 				return -EFAULT;
 
 			kp->m.userptr = (unsigned long)compat_ptr(tmp);
@@ -513,7 +510,8 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		copy_to_user(&up->timecode, &kp->timecode, sizeof(struct v4l2_timecode)) ||
 		put_user(kp->sequence, &up->sequence) ||
 		put_user(kp->reserved2, &up->reserved2) ||
-		put_user(kp->reserved, &up->reserved))
+		put_user(kp->reserved, &up->reserved) ||
+		put_user(kp->length, &up->length))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
@@ -536,13 +534,11 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
-			if (put_user(kp->length, &up->length) ||
-				put_user(kp->m.offset, &up->m.offset))
+			if (put_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_USERPTR:
-			if (put_user(kp->length, &up->length) ||
-				put_user(kp->m.userptr, &up->m.userptr))
+			if (put_user(kp->m.userptr, &up->m.userptr))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_OVERLAY:
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 33bdd81065e8..3dc9ed2e0774 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -793,7 +793,7 @@ EXPORT_SYMBOL_GPL(vb2_core_create_bufs);
  */
 void *vb2_plane_vaddr(struct vb2_buffer *vb, unsigned int plane_no)
 {
-	if (plane_no > vb->num_planes || !vb->planes[plane_no].mem_priv)
+	if (plane_no >= vb->num_planes || !vb->planes[plane_no].mem_priv)
 		return NULL;
 
 	return call_ptr_memop(vb, vaddr, vb->planes[plane_no].mem_priv);
@@ -1502,10 +1502,10 @@ static int __vb2_wait_for_done_vb(struct vb2_queue *q, int nonblocking)
  * Will sleep if required for nonblocking == false.
  */
 static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb,
-				int nonblocking)
+			     void *pb, int nonblocking)
 {
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * Wait for at least one buffer to become available on the done_list.
@@ -1521,12 +1521,14 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb,
 	spin_lock_irqsave(&q->done_lock, flags);
 	*vb = list_first_entry(&q->done_list, struct vb2_buffer, done_entry);
 	/*
-	 * Only remove the buffer from done_list if v4l2_buffer can handle all
-	 * the planes.
-	 * Verifying planes is NOT necessary since it already has been checked
-	 * before the buffer is queued/prepared. So it can never fail.
+	 * Only remove the buffer from done_list if all planes can be
+	 * handled. Some cases such as V4L2 file I/O and DVB have pb
+	 * == NULL; skip the check then as there's nothing to verify.
 	 */
-	list_del(&(*vb)->done_entry);
+	if (pb)
+		ret = call_bufop(q, verify_planes_array, *vb, pb);
+	if (!ret)
+		list_del(&(*vb)->done_entry);
 	spin_unlock_irqrestore(&q->done_lock, flags);
 
 	return ret;
@@ -1604,7 +1606,7 @@ int vb2_core_dqbuf(struct vb2_queue *q, void *pb, bool nonblocking)
 	struct vb2_buffer *vb = NULL;
 	int ret;
 
-	ret = __vb2_get_done_vb(q, &vb, nonblocking);
+	ret = __vb2_get_done_vb(q, &vb, pb, nonblocking);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c
index dbec5923fcf0..3c3b517f1d1c 100644
--- a/drivers/media/v4l2-core/videobuf2-memops.c
+++ b/drivers/media/v4l2-core/videobuf2-memops.c
@@ -49,7 +49,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
 	vec = frame_vector_create(nr);
 	if (!vec)
 		return ERR_PTR(-ENOMEM);
-	ret = get_vaddr_frames(start, nr, write, 1, vec);
+	ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec);
 	if (ret < 0)
 		goto out_destroy;
 	/* We accept only complete set of PFNs */
diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c
index 502984c724ff..6c441be8f893 100644
--- a/drivers/media/v4l2-core/videobuf2-v4l2.c
+++ b/drivers/media/v4l2-core/videobuf2-v4l2.c
@@ -67,6 +67,11 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer
 	return 0;
 }
 
+static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb)
+{
+	return __verify_planes_array(vb, pb);
+}
+
 /**
  * __verify_length() - Verify that the bytesused value for each plane fits in
  * the plane length and that the data offset doesn't exceed the bytesused value.
@@ -432,6 +437,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb,
 }
 
 static const struct vb2_buf_ops v4l2_buf_ops = {
+	.verify_planes_array	= __verify_planes_array_core,
 	.fill_user_buffer	= __fill_v4l2_buffer,
 	.fill_vb2_buffer	= __fill_vb2_buffer,
 	.set_timestamp		= __set_timestamp,
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 6515dfc2b805..55cba89dbdb8 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -394,7 +394,7 @@ static void gpmc_cs_bool_timings(int cs, const struct gpmc_bool_timings *p)
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
 			   GPMC_CONFIG4_OEEXTRADELAY, p->oe_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG4,
-			   GPMC_CONFIG4_OEEXTRADELAY, p->we_extra_delay);
+			   GPMC_CONFIG4_WEEXTRADELAY, p->we_extra_delay);
 	gpmc_cs_modify_reg(cs, GPMC_CS_CONFIG6,
 			   GPMC_CONFIG6_CYCLE2CYCLESAMECSEN,
 			   p->cycle2cyclesamecsen);
diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index 1105db2355d2..83bfb1659abe 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -524,6 +524,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
 	int rc;
 
 	if (!host->req) {
+		pm_runtime_get_sync(ms_dev(host));
 		do {
 			rc = memstick_next_req(msh, &host->req);
 			dev_dbg(ms_dev(host), "next req %d\n", rc);
@@ -544,6 +545,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
 						host->req->error);
 			}
 		} while (!rc);
+		pm_runtime_put(ms_dev(host));
 	}
 
 }
@@ -570,6 +572,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
 	dev_dbg(ms_dev(host), "%s: param = %d, value = %d\n",
 			__func__, param, value);
 
+	pm_runtime_get_sync(ms_dev(host));
 	mutex_lock(&ucr->dev_mutex);
 
 	err = rtsx_usb_card_exclusive_check(ucr, RTSX_USB_MS_CARD);
@@ -635,6 +638,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
 	}
 out:
 	mutex_unlock(&ucr->dev_mutex);
+	pm_runtime_put(ms_dev(host));
 
 	/* power-on delay */
 	if (param == MEMSTICK_POWER && value == MEMSTICK_POWER_ON)
@@ -681,6 +685,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
 	int err;
 
 	for (;;) {
+		pm_runtime_get_sync(ms_dev(host));
 		mutex_lock(&ucr->dev_mutex);
 
 		/* Check pending MS card changes */
@@ -703,6 +708,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
 		}
 
 poll_again:
+		pm_runtime_put(ms_dev(host));
 		if (host->eject)
 			break;
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 4d92df6ef9fe..7398262a2fab 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1460,6 +1460,7 @@ config MFD_WM8350
 config MFD_WM8350_I2C
 	bool "Wolfson Microelectronics WM8350 with I2C"
 	select MFD_WM8350
+	select REGMAP_I2C
 	depends on I2C=y
 	help
 	  The WM8350 is an integrated audio and power management
diff --git a/drivers/mfd/atmel-hlcdc.c b/drivers/mfd/atmel-hlcdc.c
index 06c205868573..c216c3a55793 100644
--- a/drivers/mfd/atmel-hlcdc.c
+++ b/drivers/mfd/atmel-hlcdc.c
@@ -50,8 +50,9 @@ static int regmap_atmel_hlcdc_reg_write(void *context, unsigned int reg,
 	if (reg <= ATMEL_HLCDC_DIS) {
 		u32 status;
 
-		readl_poll_timeout(hregmap->regs + ATMEL_HLCDC_SR, status,
-				   !(status & ATMEL_HLCDC_SIP), 1, 100);
+		readl_poll_timeout_atomic(hregmap->regs + ATMEL_HLCDC_SR,
+					  status, !(status & ATMEL_HLCDC_SIP),
+					  1, 100);
 	}
 
 	writel(val, hregmap->regs + reg);
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 6255513f54c7..fe89e5e337d5 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -33,6 +33,7 @@
 #define LPSS_DEV_SIZE		0x200
 #define LPSS_PRIV_OFFSET	0x200
 #define LPSS_PRIV_SIZE		0x100
+#define LPSS_PRIV_REG_COUNT	(LPSS_PRIV_SIZE / 4)
 #define LPSS_IDMA64_OFFSET	0x800
 #define LPSS_IDMA64_SIZE	0x800
 
@@ -75,6 +76,7 @@ struct intel_lpss {
 	const struct mfd_cell *cell;
 	struct device *dev;
 	void __iomem *priv;
+	u32 priv_ctx[LPSS_PRIV_REG_COUNT];
 	int devid;
 	u32 caps;
 	u32 active_ltr;
@@ -445,6 +447,7 @@ int intel_lpss_probe(struct device *dev,
 err_remove_ltr:
 	intel_lpss_debugfs_remove(lpss);
 	intel_lpss_ltr_hide(lpss);
+	intel_lpss_unregister_clock(lpss);
 
 err_clk_register:
 	ida_simple_remove(&intel_lpss_devid_ida, lpss->devid);
@@ -484,6 +487,13 @@ EXPORT_SYMBOL_GPL(intel_lpss_prepare);
 
 int intel_lpss_suspend(struct device *dev)
 {
+	struct intel_lpss *lpss = dev_get_drvdata(dev);
+	unsigned int i;
+
+	/* Save device context */
+	for (i = 0; i < LPSS_PRIV_REG_COUNT; i++)
+		lpss->priv_ctx[i] = readl(lpss->priv + i * 4);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(intel_lpss_suspend);
@@ -491,8 +501,13 @@ EXPORT_SYMBOL_GPL(intel_lpss_suspend);
 int intel_lpss_resume(struct device *dev)
 {
 	struct intel_lpss *lpss = dev_get_drvdata(dev);
+	unsigned int i;
 
-	intel_lpss_init_dev(lpss);
+	intel_lpss_deassert_reset(lpss);
+
+	/* Restore device context */
+	for (i = 0; i < LPSS_PRIV_REG_COUNT; i++)
+		writel(lpss->priv_ctx[i], lpss->priv + i * 4);
 
 	return 0;
 }
diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
index d9e15cf7c6c8..12d6ebb4ae5d 100644
--- a/drivers/mfd/intel_soc_pmic_core.c
+++ b/drivers/mfd/intel_soc_pmic_core.c
@@ -35,6 +35,7 @@ static struct gpiod_lookup_table panel_gpio_table = {
 	.table = {
 		/* Panel EN/DISABLE */
 		GPIO_LOOKUP("gpio_crystalcove", 94, "panel", GPIO_ACTIVE_HIGH),
+		{ },
 	},
 };
 
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 60b60dc63ddd..022c9374ce8b 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -354,6 +354,8 @@ int mfd_clone_cell(const char *cell, const char **clones, size_t n_clones)
 					clones[i]);
 	}
 
+	put_device(dev);
+
 	return 0;
 }
 EXPORT_SYMBOL(mfd_clone_cell);
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index b7b3e8ee64f2..fe51e9709210 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -269,6 +269,8 @@ static int usbtll_omap_probe(struct platform_device *pdev)
 
 		if (IS_ERR(tll->ch_clk[i]))
 			dev_dbg(dev, "can't get clock : %s\n", clkname);
+		else
+			clk_prepare(tll->ch_clk[i]);
 	}
 
 	pm_runtime_put_sync(dev);
@@ -301,9 +303,12 @@ static int usbtll_omap_remove(struct platform_device *pdev)
 	tll_dev = NULL;
 	spin_unlock(&tll_lock);
 
-	for (i = 0; i < tll->nch; i++)
-		if (!IS_ERR(tll->ch_clk[i]))
+	for (i = 0; i < tll->nch; i++) {
+		if (!IS_ERR(tll->ch_clk[i])) {
+			clk_unprepare(tll->ch_clk[i]);
 			clk_put(tll->ch_clk[i]);
+		}
+	}
 
 	pm_runtime_disable(&pdev->dev);
 	return 0;
@@ -370,8 +375,8 @@ int omap_tll_init(struct usbhs_omap_platform_data *pdata)
 				 * and use SDR Mode
 				 */
 				reg &= ~(OMAP_TLL_CHANNEL_CONF_UTMIAUTOIDLE
-					| OMAP_TLL_CHANNEL_CONF_ULPINOBITSTUFF
 					| OMAP_TLL_CHANNEL_CONF_ULPIDDRMODE);
+				reg |= OMAP_TLL_CHANNEL_CONF_ULPINOBITSTUFF;
 			} else if (pdata->port_mode[i] ==
 					OMAP_EHCI_PORT_MODE_HSIC) {
 				/*
@@ -420,7 +425,7 @@ int omap_tll_enable(struct usbhs_omap_platform_data *pdata)
 			if (IS_ERR(tll->ch_clk[i]))
 				continue;
 
-			r = clk_prepare_enable(tll->ch_clk[i]);
+			r = clk_enable(tll->ch_clk[i]);
 			if (r) {
 				dev_err(tll_dev,
 				 "Error enabling ch %d clock: %d\n", i, r);
@@ -448,7 +453,7 @@ int omap_tll_disable(struct usbhs_omap_platform_data *pdata)
 	for (i = 0; i < tll->nch; i++) {
 		if (omap_usb_mode_needs_tll(pdata->port_mode[i])) {
 			if (!IS_ERR(tll->ch_clk[i]))
-				clk_disable_unprepare(tll->ch_clk[i]);
+				clk_disable(tll->ch_clk[i]);
 		}
 	}
 
diff --git a/drivers/mfd/qcom_rpm.c b/drivers/mfd/qcom_rpm.c
index 207a3bd68559..a867cc91657e 100644
--- a/drivers/mfd/qcom_rpm.c
+++ b/drivers/mfd/qcom_rpm.c
@@ -34,7 +34,13 @@ struct qcom_rpm_resource {
 struct qcom_rpm_data {
 	u32 version;
 	const struct qcom_rpm_resource *resource_table;
-	unsigned n_resources;
+	unsigned int n_resources;
+	unsigned int req_ctx_off;
+	unsigned int req_sel_off;
+	unsigned int ack_ctx_off;
+	unsigned int ack_sel_off;
+	unsigned int req_sel_size;
+	unsigned int ack_sel_size;
 };
 
 struct qcom_rpm {
@@ -61,11 +67,7 @@ struct qcom_rpm {
 
 #define RPM_REQUEST_TIMEOUT	(5 * HZ)
 
-#define RPM_REQUEST_CONTEXT	3
-#define RPM_REQ_SELECT		11
-#define RPM_ACK_CONTEXT		15
-#define RPM_ACK_SELECTOR	23
-#define RPM_SELECT_SIZE		7
+#define RPM_MAX_SEL_SIZE	7
 
 #define RPM_NOTIFICATION	BIT(30)
 #define RPM_REJECTED		BIT(31)
@@ -157,6 +159,12 @@ static const struct qcom_rpm_data apq8064_template = {
 	.version = 3,
 	.resource_table = apq8064_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(apq8064_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource msm8660_rpm_resource_table[] = {
@@ -240,6 +248,12 @@ static const struct qcom_rpm_data msm8660_template = {
 	.version = 2,
 	.resource_table = msm8660_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(msm8660_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 19,
+	.ack_sel_off = 27,
+	.req_sel_size = 7,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource msm8960_rpm_resource_table[] = {
@@ -322,6 +336,12 @@ static const struct qcom_rpm_data msm8960_template = {
 	.version = 3,
 	.resource_table = msm8960_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(msm8960_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource ipq806x_rpm_resource_table[] = {
@@ -362,6 +382,12 @@ static const struct qcom_rpm_data ipq806x_template = {
 	.version = 3,
 	.resource_table = ipq806x_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(ipq806x_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct of_device_id qcom_rpm_of_match[] = {
@@ -380,7 +406,7 @@ int qcom_rpm_write(struct qcom_rpm *rpm,
 {
 	const struct qcom_rpm_resource *res;
 	const struct qcom_rpm_data *data = rpm->data;
-	u32 sel_mask[RPM_SELECT_SIZE] = { 0 };
+	u32 sel_mask[RPM_MAX_SEL_SIZE] = { 0 };
 	int left;
 	int ret = 0;
 	int i;
@@ -398,12 +424,12 @@ int qcom_rpm_write(struct qcom_rpm *rpm,
 		writel_relaxed(buf[i], RPM_REQ_REG(rpm, res->target_id + i));
 
 	bitmap_set((unsigned long *)sel_mask, res->select_id, 1);
-	for (i = 0; i < ARRAY_SIZE(sel_mask); i++) {
+	for (i = 0; i < rpm->data->req_sel_size; i++) {
 		writel_relaxed(sel_mask[i],
-			       RPM_CTRL_REG(rpm, RPM_REQ_SELECT + i));
+			       RPM_CTRL_REG(rpm, rpm->data->req_sel_off + i));
 	}
 
-	writel_relaxed(BIT(state), RPM_CTRL_REG(rpm, RPM_REQUEST_CONTEXT));
+	writel_relaxed(BIT(state), RPM_CTRL_REG(rpm, rpm->data->req_ctx_off));
 
 	reinit_completion(&rpm->ack);
 	regmap_write(rpm->ipc_regmap, rpm->ipc_offset, BIT(rpm->ipc_bit));
@@ -426,10 +452,11 @@ static irqreturn_t qcom_rpm_ack_interrupt(int irq, void *dev)
 	u32 ack;
 	int i;
 
-	ack = readl_relaxed(RPM_CTRL_REG(rpm, RPM_ACK_CONTEXT));
-	for (i = 0; i < RPM_SELECT_SIZE; i++)
-		writel_relaxed(0, RPM_CTRL_REG(rpm, RPM_ACK_SELECTOR + i));
-	writel(0, RPM_CTRL_REG(rpm, RPM_ACK_CONTEXT));
+	ack = readl_relaxed(RPM_CTRL_REG(rpm, rpm->data->ack_ctx_off));
+	for (i = 0; i < rpm->data->ack_sel_size; i++)
+		writel_relaxed(0,
+			RPM_CTRL_REG(rpm, rpm->data->ack_sel_off + i));
+	writel(0, RPM_CTRL_REG(rpm, rpm->data->ack_ctx_off));
 
 	if (ack & RPM_NOTIFICATION) {
 		dev_warn(rpm->dev, "ignoring notification!\n");
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
index dbd907d7170e..691dab791f7a 100644
--- a/drivers/mfd/rtsx_usb.c
+++ b/drivers/mfd/rtsx_usb.c
@@ -46,9 +46,6 @@ static void rtsx_usb_sg_timed_out(unsigned long data)
 
 	dev_dbg(&ucr->pusb_intf->dev, "%s: sg transfer timed out", __func__);
 	usb_sg_cancel(&ucr->current_sg);
-
-	/* we know the cancellation is caused by time-out */
-	ucr->current_sg.status = -ETIMEDOUT;
 }
 
 static int rtsx_usb_bulk_transfer_sglist(struct rtsx_ucr *ucr,
@@ -67,12 +64,15 @@ static int rtsx_usb_bulk_transfer_sglist(struct rtsx_ucr *ucr,
 	ucr->sg_timer.expires = jiffies + msecs_to_jiffies(timeout);
 	add_timer(&ucr->sg_timer);
 	usb_sg_wait(&ucr->current_sg);
-	del_timer_sync(&ucr->sg_timer);
+	if (!del_timer_sync(&ucr->sg_timer))
+		ret = -ETIMEDOUT;
+	else
+		ret = ucr->current_sg.status;
 
 	if (act_len)
 		*act_len = ucr->current_sg.bytes;
 
-	return ucr->current_sg.status;
+	return ret;
 }
 
 int rtsx_usb_transfer_data(struct rtsx_ucr *ucr, unsigned int pipe,
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 22892c701c63..4bf7d50b1bc7 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -439,7 +439,7 @@ config ARM_CHARLCD
 	  still useful.
 
 config BMP085
-	bool
+	tristate
 	depends on SYSFS
 
 config BMP085_I2C
diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c
index 15e88078ba1e..f1a0b99f5a9a 100644
--- a/drivers/misc/ad525x_dpot.c
+++ b/drivers/misc/ad525x_dpot.c
@@ -216,7 +216,7 @@ static s32 dpot_read_i2c(struct dpot_data *dpot, u8 reg)
 			 */
 			value = swab16(value);
 
-			if (dpot->uid == DPOT_UID(AD5271_ID))
+			if (dpot->uid == DPOT_UID(AD5274_ID))
 				value = value >> 2;
 		return value;
 	default:
diff --git a/drivers/misc/c2port/c2port-duramar2150.c b/drivers/misc/c2port/c2port-duramar2150.c
index 5484301d57d9..3dc61ea7dc64 100644
--- a/drivers/misc/c2port/c2port-duramar2150.c
+++ b/drivers/misc/c2port/c2port-duramar2150.c
@@ -129,8 +129,8 @@ static int __init duramar2150_c2port_init(void)
 
 	duramar2150_c2port_dev = c2port_device_register("uc",
 					&duramar2150_c2port_ops, NULL);
-	if (!duramar2150_c2port_dev) {
-		ret = -ENODEV;
+	if (IS_ERR(duramar2150_c2port_dev)) {
+		ret = PTR_ERR(duramar2150_c2port_dev);
 		goto free_region;
 	}
 
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 6982f603fadc..ab6f392d3504 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,4 @@
-ccflags-y := -Werror -Wno-unused-const-variable
+ccflags-y := -Werror $(call cc-disable-warning, unused-const-variable)
 
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 103baf0e0c5b..ea3eeb7011e1 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -25,7 +25,6 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 
 	afu = cxl_pci_to_afu(dev);
 
-	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx)) {
 		rc = PTR_ERR(ctx);
@@ -61,7 +60,6 @@ err_mapping:
 err_ctx:
 	kfree(ctx);
 err_dev:
-	put_device(&afu->dev);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
@@ -87,8 +85,6 @@ int cxl_release_context(struct cxl_context *ctx)
 	if (ctx->status >= STARTED)
 		return -EBUSY;
 
-	put_device(&ctx->afu->dev);
-
 	cxl_context_free(ctx);
 
 	return 0;
@@ -176,7 +172,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 
 	if (task) {
 		ctx->pid = get_task_pid(task, PIDTYPE_PID);
-		get_pid(ctx->pid);
+		ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
 		kernel = false;
 	}
 
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 2faa1270d085..262b88eac414 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -42,7 +42,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	spin_lock_init(&ctx->sste_lock);
 	ctx->afu = afu;
 	ctx->master = master;
-	ctx->pid = NULL; /* Set in start work ioctl */
+	ctx->pid = ctx->glpid = NULL; /* Set in start work ioctl */
 	mutex_init(&ctx->mapping_lock);
 	ctx->mapping = mapping;
 
@@ -97,6 +97,12 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	ctx->pe = i;
 	ctx->elem = &ctx->afu->spa[i];
 	ctx->pe_inserted = false;
+
+	/*
+	 * take a ref on the afu so that it stays alive at-least till
+	 * this context is reclaimed inside reclaim_ctx.
+	 */
+	cxl_afu_get(afu);
 	return 0;
 }
 
@@ -211,7 +217,11 @@ int __detach_context(struct cxl_context *ctx)
 	WARN_ON(cxl_detach_process(ctx) &&
 		cxl_adapter_link_ok(ctx->afu->adapter));
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
+
+	/* release the reference to the group leader and mm handling pid */
 	put_pid(ctx->pid);
+	put_pid(ctx->glpid);
+
 	cxl_ctx_put();
 	return 0;
 }
@@ -278,6 +288,9 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	if (ctx->irq_bitmap)
 		kfree(ctx->irq_bitmap);
 
+	/* Drop ref to the afu device taken during cxl_context_init */
+	cxl_afu_put(ctx->afu);
+
 	kfree(ctx);
 }
 
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 0cfb9c129f27..a521bc72cec2 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -403,6 +403,18 @@ struct cxl_afu {
 	bool enabled;
 };
 
+/* AFU refcount management */
+static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu)
+{
+
+	return (get_device(&afu->dev) == NULL) ? NULL : afu;
+}
+
+static inline void  cxl_afu_put(struct cxl_afu *afu)
+{
+	put_device(&afu->dev);
+}
+
 
 struct cxl_irq_name {
 	struct list_head list;
@@ -433,6 +445,9 @@ struct cxl_context {
 	unsigned int sst_size, sst_lru;
 
 	wait_queue_head_t wq;
+	/* pid of the group leader associated with the pid */
+	struct pid *glpid;
+	/* use mm context associated with this pid for ds faults */
 	struct pid *pid;
 	spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */
 	/* Only used in PR mode */
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 25a5418c55cb..81c3f75b7330 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -166,13 +166,92 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 	cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
 }
 
+/*
+ * Returns the mm_struct corresponding to the context ctx via ctx->pid
+ * In case the task has exited we use the task group leader accessible
+ * via ctx->glpid to find the next task in the thread group that has a
+ * valid  mm_struct associated with it. If a task with valid mm_struct
+ * is found the ctx->pid is updated to use the task struct for subsequent
+ * translations. In case no valid mm_struct is found in the task group to
+ * service the fault a NULL is returned.
+ */
+static struct mm_struct *get_mem_context(struct cxl_context *ctx)
+{
+	struct task_struct *task = NULL;
+	struct mm_struct *mm = NULL;
+	struct pid *old_pid = ctx->pid;
+
+	if (old_pid == NULL) {
+		pr_warn("%s: Invalid context for pe=%d\n",
+			 __func__, ctx->pe);
+		return NULL;
+	}
+
+	task = get_pid_task(old_pid, PIDTYPE_PID);
+
+	/*
+	 * pid_alive may look racy but this saves us from costly
+	 * get_task_mm when the task is a zombie. In worst case
+	 * we may think a task is alive, which is about to die
+	 * but get_task_mm will return NULL.
+	 */
+	if (task != NULL && pid_alive(task))
+		mm = get_task_mm(task);
+
+	/* release the task struct that was taken earlier */
+	if (task)
+		put_task_struct(task);
+	else
+		pr_devel("%s: Context owning pid=%i for pe=%i dead\n",
+			__func__, pid_nr(old_pid), ctx->pe);
+
+	/*
+	 * If we couldn't find the mm context then use the group
+	 * leader to iterate over the task group and find a task
+	 * that gives us mm_struct.
+	 */
+	if (unlikely(mm == NULL && ctx->glpid != NULL)) {
+
+		rcu_read_lock();
+		task = pid_task(ctx->glpid, PIDTYPE_PID);
+		if (task)
+			do {
+				mm = get_task_mm(task);
+				if (mm) {
+					ctx->pid = get_task_pid(task,
+								PIDTYPE_PID);
+					break;
+				}
+				task = next_thread(task);
+			} while (task && !thread_group_leader(task));
+		rcu_read_unlock();
+
+		/* check if we switched pid */
+		if (ctx->pid != old_pid) {
+			if (mm)
+				pr_devel("%s:pe=%i switch pid %i->%i\n",
+					 __func__, ctx->pe, pid_nr(old_pid),
+					 pid_nr(ctx->pid));
+			else
+				pr_devel("%s:Cannot find mm for pid=%i\n",
+					 __func__, pid_nr(old_pid));
+
+			/* drop the reference to older pid */
+			put_pid(old_pid);
+		}
+	}
+
+	return mm;
+}
+
+
+
 void cxl_handle_fault(struct work_struct *fault_work)
 {
 	struct cxl_context *ctx =
 		container_of(fault_work, struct cxl_context, fault_work);
 	u64 dsisr = ctx->dsisr;
 	u64 dar = ctx->dar;
-	struct task_struct *task = NULL;
 	struct mm_struct *mm = NULL;
 
 	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
@@ -195,17 +274,17 @@ void cxl_handle_fault(struct work_struct *fault_work)
 		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
 
 	if (!ctx->kernel) {
-		if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-			pr_devel("cxl_handle_fault unable to get task %i\n",
-				 pid_nr(ctx->pid));
+
+		mm = get_mem_context(ctx);
+		/* indicates all the thread in task group have exited */
+		if (mm == NULL) {
+			pr_devel("%s: unable to get mm for pe=%d pid=%i\n",
+				 __func__, ctx->pe, pid_nr(ctx->pid));
 			cxl_ack_ae(ctx);
 			return;
-		}
-		if (!(mm = get_task_mm(task))) {
-			pr_devel("cxl_handle_fault unable to get mm %i\n",
-				 pid_nr(ctx->pid));
-			cxl_ack_ae(ctx);
-			goto out;
+		} else {
+			pr_devel("Handling page fault for pe=%d pid=%i\n",
+				 ctx->pe, pid_nr(ctx->pid));
 		}
 	}
 
@@ -218,33 +297,22 @@ void cxl_handle_fault(struct work_struct *fault_work)
 
 	if (mm)
 		mmput(mm);
-out:
-	if (task)
-		put_task_struct(task);
 }
 
 static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
 {
-	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_one unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_one unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		put_task_struct(task);
 		return;
 	}
 
-	rc = cxl_fault_segment(ctx, mm, ea);
+	cxl_fault_segment(ctx, mm, ea);
 
 	mmput(mm);
-	put_task_struct(task);
 }
 
 static u64 next_segment(u64 ea, u64 vsid)
@@ -263,18 +331,13 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	struct copro_slb slb;
 	struct vm_area_struct *vma;
 	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_vma unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_vm unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		goto out1;
+		return;
 	}
 
 	down_read(&mm->mmap_sem);
@@ -295,8 +358,6 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	up_read(&mm->mmap_sem);
 
 	mmput(mm);
-out1:
-	put_task_struct(task);
 }
 
 void cxl_prefault(struct cxl_context *ctx, u64 wed)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 7ccd2998be92..10a02934bfc0 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -67,7 +67,13 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 		spin_unlock(&adapter->afu_list_lock);
 		goto err_put_adapter;
 	}
-	get_device(&afu->dev);
+
+	/*
+	 * taking a ref to the afu so that it doesn't go away
+	 * for rest of the function. This ref is released before
+	 * we return.
+	 */
+	cxl_afu_get(afu);
 	spin_unlock(&adapter->afu_list_lock);
 
 	if (!afu->current_mode)
@@ -90,13 +96,12 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 	file->private_data = ctx;
 	cxl_ctx_get();
 
-	/* Our ref on the AFU will now hold the adapter */
-	put_device(&adapter->dev);
-
-	return 0;
+	/* indicate success */
+	rc = 0;
 
 err_put_afu:
-	put_device(&afu->dev);
+	/* release the ref taken earlier */
+	cxl_afu_put(afu);
 err_put_adapter:
 	put_device(&adapter->dev);
 	return rc;
@@ -131,8 +136,6 @@ int afu_release(struct inode *inode, struct file *file)
 		mutex_unlock(&ctx->mapping_lock);
 	}
 
-	put_device(&ctx->afu->dev);
-
 	/*
 	 * At this this point all bottom halfs have finished and we should be
 	 * getting no more IRQs from the hardware for this context.  Once it's
@@ -155,11 +158,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 
 	/* Do this outside the status_mutex to avoid a circular dependency with
 	 * the locking in cxl_mmap_fault() */
-	if (copy_from_user(&work, uwork,
-			   sizeof(struct cxl_ioctl_start_work))) {
-		rc = -EFAULT;
-		goto out;
-	}
+	if (copy_from_user(&work, uwork, sizeof(work)))
+		return -EFAULT;
 
 	mutex_lock(&ctx->status_mutex);
 	if (ctx->status != OPENED) {
@@ -198,8 +198,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	 * where a process (master, some daemon, etc) has opened the chardev on
 	 * behalf of another process, so the AFU's mm gets bound to the process
 	 * that performs this ioctl and not the process that opened the file.
+	 * Also we grab the PID of the group leader so that if the task that
+	 * has performed the attach operation exits the mm context of the
+	 * process is still accessible.
 	 */
-	ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID));
+	ctx->pid = get_task_pid(current, PIDTYPE_PID);
+	ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
 
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index 09a406058c46..efbb6945eb18 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -288,7 +288,6 @@ unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
 void cxl_unmap_irq(unsigned int virq, void *cookie)
 {
 	free_irq(virq, cookie);
-	irq_dispose_mapping(virq);
 }
 
 static int cxl_register_one_irq(struct cxl *adapter,
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index be2c8e248e2e..0c6c17a1c59e 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -138,6 +138,7 @@ static const struct pci_device_id cxl_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0601), },
 	{ PCI_DEVICE_CLASS(0x120000, ~0), },
 
 	{ }
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 65fed7146e9b..cc91f7b3d90c 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -375,6 +375,7 @@ int enclosure_add_device(struct enclosure_device *edev, int component,
 			 struct device *dev)
 {
 	struct enclosure_component *cdev;
+	int err;
 
 	if (!edev || component >= edev->components)
 		return -EINVAL;
@@ -384,12 +385,17 @@ int enclosure_add_device(struct enclosure_device *edev, int component,
 	if (cdev->dev == dev)
 		return -EEXIST;
 
-	if (cdev->dev)
+	if (cdev->dev) {
 		enclosure_remove_links(cdev);
-
-	put_device(cdev->dev);
+		put_device(cdev->dev);
+	}
 	cdev->dev = get_device(dev);
-	return enclosure_add_links(cdev);
+	err = enclosure_add_links(cdev);
+	if (err) {
+		put_device(cdev->dev);
+		cdev->dev = NULL;
+	}
+	return err;
 }
 EXPORT_SYMBOL_GPL(enclosure_add_device);
 
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 222367cc8c81..524660510599 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -352,17 +352,27 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
 		if (copy_from_user(sgl->lpage, user_addr + user_size -
 				   sgl->lpage_size, sgl->lpage_size)) {
 			rc = -EFAULT;
-			goto err_out1;
+			goto err_out2;
 		}
 	}
 	return 0;
 
+ err_out2:
+	__genwqe_free_consistent(cd, PAGE_SIZE, sgl->lpage,
+				 sgl->lpage_dma_addr);
+	sgl->lpage = NULL;
+	sgl->lpage_dma_addr = 0;
  err_out1:
 	__genwqe_free_consistent(cd, PAGE_SIZE, sgl->fpage,
 				 sgl->fpage_dma_addr);
+	sgl->fpage = NULL;
+	sgl->fpage_dma_addr = 0;
  err_out:
 	__genwqe_free_consistent(cd, sgl->sgl_size, sgl->sgl,
 				 sgl->sgl_dma_addr);
+	sgl->sgl = NULL;
+	sgl->sgl_dma_addr = 0;
+	sgl->sgl_size = 0;
 	return -ENOMEM;
 }
 
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index cd0403f09267..e79c0371ee6f 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -417,8 +417,10 @@ int mei_amthif_irq_read_msg(struct mei_cl *cl,
 
 	dev = cl->dev;
 
-	if (dev->iamthif_state != MEI_IAMTHIF_READING)
+	if (dev->iamthif_state != MEI_IAMTHIF_READING) {
+		mei_irq_discard_msg(dev, mei_hdr);
 		return 0;
+	}
 
 	ret = mei_cl_irq_read_msg(cl, mei_hdr, cmpl_list);
 	if (ret)
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 020de5919c21..bdc7fcd80eca 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -151,7 +151,7 @@ static int mei_nfc_if_version(struct mei_cl *cl,
 
 	ret = 0;
 	bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length);
-	if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) {
+	if (bytes_recv < if_version_length) {
 		dev_err(bus->dev, "Could not read IF version\n");
 		ret = -EIO;
 		goto err;
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 0b05aa938799..be74a25708b2 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -53,6 +53,11 @@ ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length,
 	bus = cl->dev;
 
 	mutex_lock(&bus->device_lock);
+	if (bus->dev_state != MEI_DEV_ENABLED) {
+		rets = -ENODEV;
+		goto out;
+	}
+
 	if (!mei_cl_is_connected(cl)) {
 		rets = -ENODEV;
 		goto out;
@@ -109,6 +114,10 @@ ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length)
 	bus = cl->dev;
 
 	mutex_lock(&bus->device_lock);
+	if (bus->dev_state != MEI_DEV_ENABLED) {
+		rets = -ENODEV;
+		goto out;
+	}
 
 	cb = mei_cl_read_cb(cl, NULL);
 	if (cb)
@@ -135,7 +144,7 @@ ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length)
 		mutex_lock(&bus->device_lock);
 
 		if (!mei_cl_is_connected(cl)) {
-			rets = -EBUSY;
+			rets = -ENODEV;
 			goto out;
 		}
 	}
@@ -213,17 +222,23 @@ EXPORT_SYMBOL_GPL(mei_cldev_recv);
 static void mei_cl_bus_event_work(struct work_struct *work)
 {
 	struct mei_cl_device *cldev;
+	struct mei_device *bus;
 
 	cldev = container_of(work, struct mei_cl_device, event_work);
 
+	bus = cldev->bus;
+
 	if (cldev->event_cb)
 		cldev->event_cb(cldev, cldev->events, cldev->event_context);
 
 	cldev->events = 0;
 
 	/* Prepare for the next read */
-	if (cldev->events_mask & BIT(MEI_CL_EVENT_RX))
+	if (cldev->events_mask & BIT(MEI_CL_EVENT_RX)) {
+		mutex_lock(&bus->device_lock);
 		mei_cl_read_start(cldev->cl, 0, NULL);
+		mutex_unlock(&bus->device_lock);
+	}
 }
 
 /**
@@ -287,6 +302,7 @@ int mei_cldev_register_event_cb(struct mei_cl_device *cldev,
 				unsigned long events_mask,
 				mei_cldev_event_cb_t event_cb, void *context)
 {
+	struct mei_device *bus = cldev->bus;
 	int ret;
 
 	if (cldev->event_cb)
@@ -299,15 +315,17 @@ int mei_cldev_register_event_cb(struct mei_cl_device *cldev,
 	INIT_WORK(&cldev->event_work, mei_cl_bus_event_work);
 
 	if (cldev->events_mask & BIT(MEI_CL_EVENT_RX)) {
+		mutex_lock(&bus->device_lock);
 		ret = mei_cl_read_start(cldev->cl, 0, NULL);
+		mutex_unlock(&bus->device_lock);
 		if (ret && ret != -EBUSY)
 			return ret;
 	}
 
 	if (cldev->events_mask & BIT(MEI_CL_EVENT_NOTIF)) {
-		mutex_lock(&cldev->cl->dev->device_lock);
+		mutex_lock(&bus->device_lock);
 		ret = mei_cl_notify_request(cldev->cl, NULL, event_cb ? 1 : 0);
-		mutex_unlock(&cldev->cl->dev->device_lock);
+		mutex_unlock(&bus->device_lock);
 		if (ret)
 			return ret;
 	}
@@ -381,7 +399,7 @@ bool mei_cldev_enabled(struct mei_cl_device *cldev)
 EXPORT_SYMBOL_GPL(mei_cldev_enabled);
 
 /**
- * mei_cldev_enable_device - enable me client device
+ * mei_cldev_enable - enable me client device
  *     create connection with me client
  *
  * @cldev: me client device
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index a6c87c713193..2ff39fbc70d1 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -698,7 +698,7 @@ void mei_host_client_init(struct work_struct *work)
 
 	pm_runtime_mark_last_busy(dev->dev);
 	dev_dbg(dev->dev, "rpm: autosuspend\n");
-	pm_runtime_autosuspend(dev->dev);
+	pm_request_autosuspend(dev->dev);
 }
 
 /**
@@ -1735,6 +1735,10 @@ void mei_cl_complete(struct mei_cl *cl, struct mei_cl_cb *cb)
 			wake_up(&cl->wait);
 
 		break;
+	case MEI_FOP_DISCONNECT_RSP:
+		mei_io_cb_free(cb);
+		mei_cl_set_disconnected(cl);
+		break;
 	default:
 		BUG_ON(0);
 	}
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index e7b7aad0999b..fd8a9f057ea6 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -873,8 +873,7 @@ static int mei_hbm_fw_disconnect_req(struct mei_device *dev,
 		cb = mei_io_cb_init(cl, MEI_FOP_DISCONNECT_RSP, NULL);
 		if (!cb)
 			return -ENOMEM;
-		cl_dbg(dev, cl, "add disconnect response as first\n");
-		list_add(&cb->list, &dev->ctrl_wr_list.list);
+		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
 	return 0;
 }
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index a8a68acd3267..d2774197fe58 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -121,6 +121,15 @@
 #define MEI_DEV_ID_SPT_2      0x9D3B  /* Sunrise Point 2 */
 #define MEI_DEV_ID_SPT_H      0xA13A  /* Sunrise Point H */
 #define MEI_DEV_ID_SPT_H_2    0xA13B  /* Sunrise Point H 2 */
+
+#define MEI_DEV_ID_KBP        0xA2BA  /* Kaby Point */
+#define MEI_DEV_ID_KBP_2      0xA2BB  /* Kaby Point 2 */
+
+#define MEI_DEV_ID_LBG        0xA1BA  /* Lewisburg (SPT) */
+
+#define MEI_DEV_ID_BXT_M      0x1A9A  /* Broxton M */
+#define MEI_DEV_ID_APL_I      0x5A9A  /* Apollo Lake I */
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 25b1997a62cb..36333750c512 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -1258,8 +1258,14 @@ static bool mei_me_fw_type_nm(struct pci_dev *pdev)
 static bool mei_me_fw_type_sps(struct pci_dev *pdev)
 {
 	u32 reg;
-	/* Read ME FW Status check for SPS Firmware */
-	pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+	unsigned int devfn;
+
+	/*
+	 * Read ME FW Status register to check for SPS Firmware
+	 * The SPS FW is only signaled in pci function 0
+	 */
+	devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0);
+	pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_1, &reg);
 	/* if bits [19:16] = 15, running SPS Firmware */
 	return (reg & 0xf0000) == 0xf0000;
 }
diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c
index bae680c648ff..396d75d9fb11 100644
--- a/drivers/misc/mei/hw-txe.c
+++ b/drivers/misc/mei/hw-txe.c
@@ -972,11 +972,13 @@ static bool mei_txe_check_and_ack_intrs(struct mei_device *dev, bool do_ack)
 	hisr = mei_txe_br_reg_read(hw, HISR_REG);
 
 	aliveness = mei_txe_aliveness_get(dev);
-	if (hhisr & IPC_HHIER_SEC && aliveness)
+	if (hhisr & IPC_HHIER_SEC && aliveness) {
 		ipc_isr = mei_txe_sec_reg_read_silent(hw,
 				SEC_IPC_HOST_INT_STATUS_REG);
-	else
+	} else {
 		ipc_isr = 0;
+		hhisr &= ~IPC_HHIER_SEC;
+	}
 
 	generated = generated ||
 		(hisr & HISR_INT_STS_MSK) ||
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index 64b568a0268d..d1df797c7568 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -76,7 +76,6 @@ static inline int mei_cl_hbm_equal(struct mei_cl *cl,
  * @dev: mei device
  * @hdr: message header
  */
-static inline
 void mei_irq_discard_msg(struct mei_device *dev, struct mei_msg_hdr *hdr)
 {
 	/*
@@ -184,10 +183,7 @@ static int mei_cl_irq_disconnect_rsp(struct mei_cl *cl, struct mei_cl_cb *cb,
 		return -EMSGSIZE;
 
 	ret = mei_hbm_cl_disconnect_rsp(dev, cl);
-	mei_cl_set_disconnected(cl);
-	mei_io_cb_free(cb);
-	mei_me_cl_put(cl->me_cl);
-	cl->me_cl = NULL;
+	list_move_tail(&cb->list, &cmpl_list->list);
 
 	return ret;
 }
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 80f9afcb1382..4ef189a7a2fb 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -207,7 +207,7 @@ static ssize_t mei_read(struct file *file, char __user *ubuf,
 
 		mutex_lock(&dev->device_lock);
 		if (!mei_cl_is_connected(cl)) {
-			rets = -EBUSY;
+			rets = -ENODEV;
 			goto out;
 		}
 	}
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 4250555d5e72..1b06e2fd6858 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -782,6 +782,8 @@ bool mei_hbuf_acquire(struct mei_device *dev);
 
 bool mei_write_is_idle(struct mei_device *dev);
 
+void mei_irq_discard_msg(struct mei_device *dev, struct mei_msg_hdr *hdr);
+
 #if IS_ENABLED(CONFIG_DEBUG_FS)
 int mei_dbgfs_register(struct mei_device *dev, const char *name);
 void mei_dbgfs_deregister(struct mei_device *dev);
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 27678d8154e0..adab5bbb642a 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -84,8 +84,15 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT, mei_me_pch8_cfg)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, mei_me_pch8_cfg)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_cfg)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_cfg)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_sps_cfg)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_sps_cfg)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_LBG, mei_me_pch8_cfg)},
+
+	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP, mei_me_pch8_cfg)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_KBP_2, mei_me_pch8_cfg)},
+
+	{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, mei_me_pch8_cfg)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, mei_me_pch8_cfg)},
 
 	/* required last entry */
 	{0, }
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index 8310b4dbff06..6a451bd65bf3 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -1511,7 +1511,7 @@ off_t scif_register_pinned_pages(scif_epd_t epd,
 	if ((map_flags & SCIF_MAP_FIXED) &&
 	    ((ALIGN(offset, PAGE_SIZE) != offset) ||
 	    (offset < 0) ||
-	    (offset + (off_t)len < offset)))
+	    (len > LONG_MAX - offset)))
 		return -EINVAL;
 
 	might_sleep();
@@ -1614,7 +1614,7 @@ off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
 	if ((map_flags & SCIF_MAP_FIXED) &&
 	    ((ALIGN(offset, PAGE_SIZE) != offset) ||
 	    (offset < 0) ||
-	    (offset + (off_t)len < offset)))
+	    (len > LONG_MAX - offset)))
 		return -EINVAL;
 
 	/* Unsupported protection requested */
@@ -1732,7 +1732,8 @@ scif_unregister(scif_epd_t epd, off_t offset, size_t len)
 
 	/* Offset is not page aligned or offset+len wraps around */
 	if ((ALIGN(offset, PAGE_SIZE) != offset) ||
-	    (offset + (off_t)len < offset))
+	    (offset < 0) ||
+	    (len > LONG_MAX - offset))
 		return -EINVAL;
 
 	err = scif_verify_epd(ep);
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index d8486168415a..f2b733275a0a 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -596,6 +596,14 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 	struct mmc_card *card;
 	int err = 0, ioc_err = 0;
 
+	/*
+	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
+	 * whole block device, not on a partition.  This prevents overspray
+	 * between sibling partitions.
+	 */
+	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+		return -EPERM;
+
 	idata = mmc_blk_ioctl_copy_from_user(ic_ptr);
 	if (IS_ERR(idata))
 		return PTR_ERR(idata);
@@ -638,6 +646,14 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
 	int i, err = 0, ioc_err = 0;
 	__u64 num_of_cmds;
 
+	/*
+	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
+	 * whole block device, not on a partition.  This prevents overspray
+	 * between sibling partitions.
+	 */
+	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+		return -EPERM;
+
 	if (copy_from_user(&num_of_cmds, &user->num_of_cmds,
 			   sizeof(num_of_cmds)))
 		return -EFAULT;
@@ -693,14 +709,6 @@ cmd_err:
 static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
-	/*
-	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
-	 * whole block device, not on a partition.  This prevents overspray
-	 * between sibling partitions.
-	 */
-	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
-		return -EPERM;
-
 	switch (cmd) {
 	case MMC_IOC_CMD:
 		return mmc_blk_ioctl_cmd(bdev,
@@ -1747,7 +1755,7 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
 	struct mmc_blk_data *md = mq->data;
 	struct mmc_packed *packed = mqrq->packed;
 	bool do_rel_wr, do_data_tag;
-	u32 *packed_cmd_hdr;
+	__le32 *packed_cmd_hdr;
 	u8 hdr_blocks;
 	u8 i = 1;
 
@@ -1759,8 +1767,8 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
 
 	packed_cmd_hdr = packed->cmd_hdr;
 	memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr));
-	packed_cmd_hdr[0] = (packed->nr_entries << 16) |
-		(PACKED_CMD_WR << 8) | PACKED_CMD_VER;
+	packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) |
+		(PACKED_CMD_WR << 8) | PACKED_CMD_VER);
 	hdr_blocks = mmc_large_sector(card) ? 8 : 1;
 
 	/*
@@ -1774,14 +1782,14 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
 			((brq->data.blocks * brq->data.blksz) >=
 			 card->ext_csd.data_tag_unit_size);
 		/* Argument of CMD23 */
-		packed_cmd_hdr[(i * 2)] =
+		packed_cmd_hdr[(i * 2)] = cpu_to_le32(
 			(do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) |
 			(do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) |
-			blk_rq_sectors(prq);
+			blk_rq_sectors(prq));
 		/* Argument of CMD18 or CMD25 */
-		packed_cmd_hdr[((i * 2)) + 1] =
+		packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32(
 			mmc_card_blockaddr(card) ?
-			blk_rq_pos(prq) : blk_rq_pos(prq) << 9;
+			blk_rq_pos(prq) : blk_rq_pos(prq) << 9);
 		packed->blocks += blk_rq_sectors(prq);
 		i++;
 	}
@@ -2271,7 +2279,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	set_capacity(md->disk, size);
 
 	if (mmc_host_cmd23(card->host)) {
-		if (mmc_card_mmc(card) ||
+		if ((mmc_card_mmc(card) &&
+		     card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
 		    (mmc_card_sd(card) &&
 		     card->scr.cmds & SD_SCR_CMD23_SUPPORT))
 			md->flags |= MMC_BLK_CMD23;
@@ -2506,11 +2515,12 @@ static const struct mmc_fixup blk_fixups[] =
 		  MMC_QUIRK_BLK_NO_CMD23),
 
 	/*
-	 * Some Micron MMC cards needs longer data read timeout than
-	 * indicated in CSD.
+	 * Some MMC cards need longer data read timeout than indicated in CSD.
 	 */
 	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc,
 		  MMC_QUIRK_LONG_READ_TIME),
+	MMC_FIXUP("008GE0", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_LONG_READ_TIME),
 
 	/*
 	 * On these Samsung MoviNAND parts, performing secure erase or
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 7fc9174d4619..9a11aaa6e985 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -791,7 +791,7 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 	struct mmc_async_req *cur_areq = &test_areq[0].areq;
 	struct mmc_async_req *other_areq = &test_areq[1].areq;
 	int i;
-	int ret;
+	int ret = RESULT_OK;
 
 	test_areq[0].test = test;
 	test_areq[1].test = test;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 36cddab57d77..cf30b3712cb2 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -25,7 +25,7 @@ enum mmc_packed_type {
 
 struct mmc_packed {
 	struct list_head	list;
-	u32			cmd_hdr[1024];
+	__le32			cmd_hdr[1024];
 	unsigned int		blocks;
 	u8			nr_entries;
 	u8			retries;
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 5ae89e48fd85..5f7d10ba498a 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -874,11 +874,11 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
 	/*
 	 * Some cards require longer data read timeout than indicated in CSD.
 	 * Address this by setting the read timeout to a "reasonably high"
-	 * value. For the cards tested, 300ms has proven enough. If necessary,
+	 * value. For the cards tested, 600ms has proven enough. If necessary,
 	 * this value can be increased if other problematic cards require this.
 	 */
 	if (mmc_card_long_read_time(card) && data->flags & MMC_DATA_READ) {
-		data->timeout_ns = 300000000;
+		data->timeout_ns = 600000000;
 		data->timeout_clks = 0;
 	}
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 3d5087b03999..79a0c26e1419 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -333,6 +333,9 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 	}
 }
 
+/* Minimum partition switch timeout in milliseconds */
+#define MMC_MIN_PART_SWITCH_TIME	300
+
 /*
  * Decode extended CSD.
  */
@@ -397,6 +400,10 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 
 		/* EXT_CSD value is in units of 10ms, but we store in ms */
 		card->ext_csd.part_time = 10 * ext_csd[EXT_CSD_PART_SWITCH_TIME];
+		/* Some eMMC set the value too low so set a minimum */
+		if (card->ext_csd.part_time &&
+		    card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
+			card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
 
 		/* Sleep / awake timeout in 100ns units */
 		if (sa_shift > 0 && sa_shift <= 0x17)
@@ -1574,10 +1581,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_select_hs400(card);
 		if (err)
 			goto free_card;
-	} else if (mmc_card_hs(card)) {
+	} else {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
-		if (!IS_ERR_VALUE(err)) {
+		if (!IS_ERR_VALUE(err) && mmc_card_hs(card)) {
 			err = mmc_select_hs_ddr(card);
 			if (err)
 				goto free_card;
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 1dee533634c9..2e6d2fff1096 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -97,6 +97,7 @@ config MMC_RICOH_MMC
 config MMC_SDHCI_ACPI
 	tristate "SDHCI support for ACPI enumerated SDHCI controllers"
 	depends on MMC_SDHCI && ACPI
+	select IOSF_MBI if X86
 	help
 	  This selects support for ACPI enumerated SDHCI controllers,
 	  identified by ACPI Compatibility ID PNP0D40 or specific
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index 7e1d13b68b06..7dcfb1d5034f 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -59,12 +59,13 @@ int dw_mci_pltfm_register(struct platform_device *pdev,
 	host->pdata = pdev->dev.platform_data;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	/* Get registers' physical base address */
-	host->phy_regs = (void *)(regs->start);
 	host->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
 
+	/* Get registers' physical base address */
+	host->phy_regs = regs->start;
+
 	platform_set_drvdata(pdev, host);
 	return dw_mci_probe(host);
 }
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 7a6cedbe48a8..fb204ee6ff89 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -699,7 +699,7 @@ static int dw_mci_edmac_start_dma(struct dw_mci *host,
 	int ret = 0;
 
 	/* Set external dma config: burst size, burst width */
-	cfg.dst_addr = (dma_addr_t)(host->phy_regs + fifo_offset);
+	cfg.dst_addr = host->phy_regs + fifo_offset;
 	cfg.src_addr = cfg.dst_addr;
 	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 1c1b45ef3faf..aad3243a48fc 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1436,6 +1436,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 					     host->pdata->cd_debounce);
 		if (status != 0)
 			goto fail_add_host;
+
+		/* The platform has a CD GPIO signal that may support
+		 * interrupts, so let mmc_gpiod_request_cd_irq() decide
+		 * if polling is needed or not.
+		 */
+		mmc->caps &= ~MMC_CAP_NEEDS_POLL;
 		mmc_gpiod_request_cd_irq(mmc);
 	}
 
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index d839147e591d..c8b8ac66ff7e 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -309,6 +309,9 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	cmd0 = BF_SSP(cmd->opcode, CMD0_CMD);
 	cmd1 = cmd->arg;
 
+	if (cmd->opcode == MMC_STOP_TRANSMISSION)
+		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
+
 	if (host->sdio_irq_en) {
 		ctrl0 |= BM_SSP_CTRL0_SDIO_IRQ_CHECK;
 		cmd0 |= BM_SSP_CMD0_CONT_CLKING_EN | BM_SSP_CMD0_SLOW_CLKING_EN;
@@ -417,8 +420,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 		       ssp->base + HW_SSP_BLOCK_SIZE);
 	}
 
-	if ((cmd->opcode == MMC_STOP_TRANSMISSION) ||
-	    (cmd->opcode == SD_IO_RW_EXTENDED))
+	if (cmd->opcode == SD_IO_RW_EXTENDED)
 		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
 
 	cmd1 = cmd->arg;
@@ -661,13 +663,13 @@ static int mxs_mmc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mmc);
 
+	spin_lock_init(&host->lock);
+
 	ret = devm_request_irq(&pdev->dev, irq_err, mxs_mmc_irq_handler, 0,
 			       dev_name(&pdev->dev), host);
 	if (ret)
 		goto out_free_dma;
 
-	spin_lock_init(&host->lock);
-
 	ret = mmc_add_host(mmc);
 	if (ret)
 		goto out_free_dma;
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 28a057fae0a1..72bbb12fb938 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -798,14 +798,16 @@ static int pxamci_probe(struct platform_device *pdev)
 		gpio_direction_output(gpio_power,
 				      host->pdata->gpio_power_invert);
 	}
-	if (gpio_is_valid(gpio_ro))
+	if (gpio_is_valid(gpio_ro)) {
 		ret = mmc_gpio_request_ro(mmc, gpio_ro);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
-		goto out;
-	} else {
-		mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
-			0 : MMC_CAP2_RO_ACTIVE_HIGH;
+		if (ret) {
+			dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n",
+				gpio_ro);
+			goto out;
+		} else {
+			mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
+				0 : MMC_CAP2_RO_ACTIVE_HIGH;
+		}
 	}
 
 	if (gpio_is_valid(gpio_cd))
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 6c71fc9f76c7..da9f71b8deb0 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1138,11 +1138,6 @@ static void sdmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	dev_dbg(sdmmc_dev(host), "%s\n", __func__);
 	mutex_lock(&ucr->dev_mutex);
 
-	if (rtsx_usb_card_exclusive_check(ucr, RTSX_USB_SD_CARD)) {
-		mutex_unlock(&ucr->dev_mutex);
-		return;
-	}
-
 	sd_set_power_mode(host, ios->power_mode);
 	sd_set_bus_width(host, ios->bus_width);
 	sd_set_timing(host, ios->timing, &host->ddr_mode);
@@ -1314,6 +1309,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
 		container_of(work, struct rtsx_usb_sdmmc, led_work);
 	struct rtsx_ucr *ucr = host->ucr;
 
+	pm_runtime_get_sync(sdmmc_dev(host));
 	mutex_lock(&ucr->dev_mutex);
 
 	if (host->led.brightness == LED_OFF)
@@ -1322,6 +1318,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
 		rtsx_usb_turn_on_led(ucr);
 
 	mutex_unlock(&ucr->dev_mutex);
+	pm_runtime_put(sdmmc_dev(host));
 }
 #endif
 
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index a5cda926d38e..5a05bf400ca8 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -41,6 +41,11 @@
 #include <linux/mmc/pm.h>
 #include <linux/mmc/slot-gpio.h>
 
+#ifdef CONFIG_X86
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+#endif
+
 #include "sdhci.h"
 
 enum {
@@ -146,6 +151,75 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 	.ops = &sdhci_acpi_ops_int,
 };
 
+#ifdef CONFIG_X86
+
+static bool sdhci_acpi_byt(void)
+{
+	static const struct x86_cpu_id byt[] = {
+		{ X86_VENDOR_INTEL, 6, 0x37 },
+		{}
+	};
+
+	return x86_match_cpu(byt);
+}
+
+#define BYT_IOSF_SCCEP			0x63
+#define BYT_IOSF_OCP_NETCTRL0		0x1078
+#define BYT_IOSF_OCP_TIMEOUT_BASE	GENMASK(10, 8)
+
+static void sdhci_acpi_byt_setting(struct device *dev)
+{
+	u32 val = 0;
+
+	if (!sdhci_acpi_byt())
+		return;
+
+	if (iosf_mbi_read(BYT_IOSF_SCCEP, 0x06, BYT_IOSF_OCP_NETCTRL0,
+			  &val)) {
+		dev_err(dev, "%s read error\n", __func__);
+		return;
+	}
+
+	if (!(val & BYT_IOSF_OCP_TIMEOUT_BASE))
+		return;
+
+	val &= ~BYT_IOSF_OCP_TIMEOUT_BASE;
+
+	if (iosf_mbi_write(BYT_IOSF_SCCEP, 0x07, BYT_IOSF_OCP_NETCTRL0,
+			   val)) {
+		dev_err(dev, "%s write error\n", __func__);
+		return;
+	}
+
+	dev_dbg(dev, "%s completed\n", __func__);
+}
+
+static bool sdhci_acpi_byt_defer(struct device *dev)
+{
+	if (!sdhci_acpi_byt())
+		return false;
+
+	if (!iosf_mbi_available())
+		return true;
+
+	sdhci_acpi_byt_setting(dev);
+
+	return false;
+}
+
+#else
+
+static inline void sdhci_acpi_byt_setting(struct device *dev)
+{
+}
+
+static inline bool sdhci_acpi_byt_defer(struct device *dev)
+{
+	return false;
+}
+
+#endif
+
 static int bxt_get_cd(struct mmc_host *mmc)
 {
 	int gpio_cd = mmc_gpio_get_cd(mmc);
@@ -233,7 +307,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.chip    = &sdhci_acpi_chip_int,
 	.caps    = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 		   MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
-		   MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+		   MMC_CAP_WAIT_WHILE_BUSY,
 	.caps2   = MMC_CAP2_HC_ERASE_SZ,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
@@ -248,7 +322,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
 		   SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_HOST_OFF_CARD_ON,
 	.caps    = MMC_CAP_NONREMOVABLE | MMC_CAP_POWER_OFF_CARD |
-		   MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+		   MMC_CAP_WAIT_WHILE_BUSY,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.pm_caps = MMC_PM_KEEP_POWER,
 	.probe_slot	= sdhci_acpi_sdio_probe_slot,
@@ -260,7 +334,7 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
 		   SDHCI_QUIRK2_STOP_WITH_TC,
-	.caps    = MMC_CAP_BUS_WIDTH_TEST | MMC_CAP_WAIT_WHILE_BUSY,
+	.caps    = MMC_CAP_WAIT_WHILE_BUSY,
 	.probe_slot	= sdhci_acpi_sd_probe_slot,
 };
 
@@ -337,6 +411,9 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	if (acpi_bus_get_status(device) || !device->status.present)
 		return -ENODEV;
 
+	if (sdhci_acpi_byt_defer(dev))
+		return -EPROBE_DEFER;
+
 	hid = acpi_device_hid(device);
 	uid = device->pnp.unique_id;
 
@@ -460,6 +537,8 @@ static int sdhci_acpi_resume(struct device *dev)
 {
 	struct sdhci_acpi_host *c = dev_get_drvdata(dev);
 
+	sdhci_acpi_byt_setting(&c->pdev->dev);
+
 	return sdhci_resume_host(c->host);
 }
 
@@ -483,6 +562,8 @@ static int sdhci_acpi_runtime_resume(struct device *dev)
 {
 	struct sdhci_acpi_host *c = dev_get_drvdata(dev);
 
+	sdhci_acpi_byt_setting(&c->pdev->dev);
+
 	return sdhci_runtime_resume_host(c->host);
 }
 
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 1f1582f6cccb..8d838779fd1b 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -804,6 +804,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host,
 
 	switch (uhs) {
 	case MMC_TIMING_UHS_SDR50:
+	case MMC_TIMING_UHS_DDR50:
 		pinctrl = imx_data->pins_100mhz;
 		break;
 	case MMC_TIMING_UHS_SDR104:
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 3b423b0ad8e7..f280744578e4 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -156,7 +156,8 @@ static const struct sdhci_ops sdhci_iproc_ops = {
 };
 
 static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = {
-	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
+	.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+		  SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
 	.quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
 	.ops = &sdhci_iproc_ops,
 };
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 45ee07d3a761..5ebe6eb6b89e 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -361,7 +361,6 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 				 MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
-				 MMC_CAP_BUS_WIDTH_TEST |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	slot->host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
 	slot->hw_reset = sdhci_pci_int_hw_reset;
@@ -377,19 +376,18 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE |
-				 MMC_CAP_BUS_WIDTH_TEST |
 				 MMC_CAP_WAIT_WHILE_BUSY;
 	return 0;
 }
 
 static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 {
-	slot->host->mmc->caps |= MMC_CAP_BUS_WIDTH_TEST |
-				 MMC_CAP_WAIT_WHILE_BUSY;
+	slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
+	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXTM_SD ||
 	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD)
 		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
 
@@ -1173,6 +1171,30 @@ static const struct pci_device_id pci_ids[] = {
 
 	{
 		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXTM_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXTM_SDIO,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXTM_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sd,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
 		.device		= PCI_DEVICE_ID_INTEL_APL_EMMC,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index d1a0b4db60db..89e7151684a1 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -28,6 +28,9 @@
 #define PCI_DEVICE_ID_INTEL_BXT_SD	0x0aca
 #define PCI_DEVICE_ID_INTEL_BXT_EMMC	0x0acc
 #define PCI_DEVICE_ID_INTEL_BXT_SDIO	0x0ad0
+#define PCI_DEVICE_ID_INTEL_BXTM_SD	0x1aca
+#define PCI_DEVICE_ID_INTEL_BXTM_EMMC	0x1acc
+#define PCI_DEVICE_ID_INTEL_BXTM_SDIO	0x1ad0
 #define PCI_DEVICE_ID_INTEL_APL_SD	0x5aca
 #define PCI_DEVICE_ID_INTEL_APL_EMMC	0x5acc
 #define PCI_DEVICE_ID_INTEL_APL_SDIO	0x5ad0
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 8814eb6b83bf..62d37d2ac557 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -492,7 +492,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		host->align_buffer, host->align_buffer_sz, direction);
 	if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr))
 		goto fail;
-	BUG_ON(host->align_addr & host->align_mask);
+	BUG_ON(host->align_addr & SDHCI_ADMA2_MASK);
 
 	host->sg_count = sdhci_pre_dma_transfer(host, data);
 	if (host->sg_count < 0)
@@ -514,8 +514,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		 * the (up to three) bytes that screw up the
 		 * alignment.
 		 */
-		offset = (host->align_sz - (addr & host->align_mask)) &
-			 host->align_mask;
+		offset = (SDHCI_ADMA2_ALIGN - (addr & SDHCI_ADMA2_MASK)) &
+			 SDHCI_ADMA2_MASK;
 		if (offset) {
 			if (data->flags & MMC_DATA_WRITE) {
 				buffer = sdhci_kmap_atomic(sg, &flags);
@@ -529,8 +529,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 
 			BUG_ON(offset > 65536);
 
-			align += host->align_sz;
-			align_addr += host->align_sz;
+			align += SDHCI_ADMA2_ALIGN;
+			align_addr += SDHCI_ADMA2_ALIGN;
 
 			desc += host->desc_sz;
 
@@ -611,7 +611,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 	/* Do a quick scan of the SG list for any unaligned mappings */
 	has_unaligned = false;
 	for_each_sg(data->sg, sg, host->sg_count, i)
-		if (sg_dma_address(sg) & host->align_mask) {
+		if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
 			has_unaligned = true;
 			break;
 		}
@@ -623,15 +623,15 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		align = host->align_buffer;
 
 		for_each_sg(data->sg, sg, host->sg_count, i) {
-			if (sg_dma_address(sg) & host->align_mask) {
-				size = host->align_sz -
-				       (sg_dma_address(sg) & host->align_mask);
+			if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
+				size = SDHCI_ADMA2_ALIGN -
+				       (sg_dma_address(sg) & SDHCI_ADMA2_MASK);
 
 				buffer = sdhci_kmap_atomic(sg, &flags);
 				memcpy(buffer, align, size);
 				sdhci_kunmap_atomic(buffer, &flags);
 
-				align += host->align_sz;
+				align += SDHCI_ADMA2_ALIGN;
 			}
 		}
 	}
@@ -666,9 +666,20 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 	if (!data)
 		target_timeout = cmd->busy_timeout * 1000;
 	else {
-		target_timeout = data->timeout_ns / 1000;
-		if (host->clock)
-			target_timeout += data->timeout_clks / host->clock;
+		target_timeout = DIV_ROUND_UP(data->timeout_ns, 1000);
+		if (host->clock && data->timeout_clks) {
+			unsigned long long val;
+
+			/*
+			 * data->timeout_clks is in units of clock cycles.
+			 * host->clock is in Hz.  target_timeout is in us.
+			 * Hence, us = 1000000 * cycles / Hz.  Round up.
+			 */
+			val = 1000000ULL * data->timeout_clks;
+			if (do_div(val, host->clock))
+				target_timeout++;
+			target_timeout += val;
+		}
 	}
 
 	/*
@@ -1263,7 +1274,9 @@ clock_set:
 			return;
 		}
 		timeout--;
-		mdelay(1);
+		spin_unlock_irq(&host->lock);
+		usleep_range(900, 1100);
+		spin_lock_irq(&host->lock);
 	}
 
 	clk |= SDHCI_CLOCK_CARD_EN;
@@ -1304,7 +1317,9 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
 			pwr = SDHCI_POWER_330;
 			break;
 		default:
-			BUG();
+			WARN(1, "%s: Invalid vdd %#x\n",
+			     mmc_hostname(host->mmc), vdd);
+			break;
 		}
 	}
 
@@ -2027,7 +2042,27 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 			ctrl &= ~SDHCI_CTRL_EXEC_TUNING;
 			sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 
+			sdhci_do_reset(host, SDHCI_RESET_CMD);
+			sdhci_do_reset(host, SDHCI_RESET_DATA);
+
 			err = -EIO;
+
+			if (cmd.opcode != MMC_SEND_TUNING_BLOCK_HS200)
+				goto out;
+
+			sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+			sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+
+			spin_unlock_irqrestore(&host->lock, flags);
+
+			memset(&cmd, 0, sizeof(cmd));
+			cmd.opcode = MMC_STOP_TRANSMISSION;
+			cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+			cmd.busy_timeout = 50;
+			mmc_wait_for_cmd(mmc, &cmd, 0);
+
+			spin_lock_irqsave(&host->lock, flags);
+
 			goto out;
 		}
 
@@ -2596,7 +2631,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 			pr_err("%s: Card is consuming too much power!\n",
 				mmc_hostname(host->mmc));
 
-		if (intmask & SDHCI_INT_CARD_INT) {
+		if ((intmask & SDHCI_INT_CARD_INT) &&
+		    (host->ier & SDHCI_INT_CARD_INT)) {
 			sdhci_enable_sdio_irq_nolock(host, false);
 			host->thread_isr |= SDHCI_INT_CARD_INT;
 			result = IRQ_WAKE_THREAD;
@@ -2972,24 +3008,17 @@ int sdhci_add_host(struct sdhci_host *host)
 		if (host->flags & SDHCI_USE_64_BIT_DMA) {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_64_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_64_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_64_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_64_ALIGN;
-			host->align_mask = SDHCI_ADMA2_64_ALIGN - 1;
 		} else {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_32_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_32_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_32_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_32_ALIGN;
-			host->align_mask = SDHCI_ADMA2_32_ALIGN - 1;
 		}
 		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
 						      host->adma_table_sz,
 						      &host->adma_addr,
 						      GFP_KERNEL);
+		host->align_buffer_sz = SDHCI_MAX_SEGS * SDHCI_ADMA2_ALIGN;
 		host->align_buffer = kmalloc(host->align_buffer_sz, GFP_KERNEL);
 		if (!host->adma_table || !host->align_buffer) {
 			if (host->adma_table)
@@ -3003,7 +3032,7 @@ int sdhci_add_host(struct sdhci_host *host)
 			host->flags &= ~SDHCI_USE_ADMA;
 			host->adma_table = NULL;
 			host->align_buffer = NULL;
-		} else if (host->adma_addr & host->align_mask) {
+		} else if (host->adma_addr & (SDHCI_ADMA2_DESC_ALIGN - 1)) {
 			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
@@ -3095,14 +3124,14 @@ int sdhci_add_host(struct sdhci_host *host)
 		if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT)
 			host->timeout_clk *= 1000;
 
+		if (override_timeout_clk)
+			host->timeout_clk = override_timeout_clk;
+
 		mmc->max_busy_timeout = host->ops->get_max_timeout_count ?
 			host->ops->get_max_timeout_count(host) : 1 << 27;
 		mmc->max_busy_timeout /= host->timeout_clk;
 	}
 
-	if (override_timeout_clk)
-		host->timeout_clk = override_timeout_clk;
-
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
 	mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 9c331ac5ad6b..0115e9907bf8 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -272,22 +272,27 @@
 /* ADMA2 32-bit DMA descriptor size */
 #define SDHCI_ADMA2_32_DESC_SZ	8
 
-/* ADMA2 32-bit DMA alignment */
-#define SDHCI_ADMA2_32_ALIGN	4
-
 /* ADMA2 32-bit descriptor */
 struct sdhci_adma2_32_desc {
 	__le16	cmd;
 	__le16	len;
 	__le32	addr;
-}  __packed __aligned(SDHCI_ADMA2_32_ALIGN);
+}  __packed __aligned(4);
+
+/* ADMA2 data alignment */
+#define SDHCI_ADMA2_ALIGN	4
+#define SDHCI_ADMA2_MASK	(SDHCI_ADMA2_ALIGN - 1)
+
+/*
+ * ADMA2 descriptor alignment.  Some controllers (e.g. Intel) require 8 byte
+ * alignment for the descriptor table even in 32-bit DMA mode.  Memory
+ * allocation is at least 8 byte aligned anyway, so just stipulate 8 always.
+ */
+#define SDHCI_ADMA2_DESC_ALIGN	8
 
 /* ADMA2 64-bit DMA descriptor size */
 #define SDHCI_ADMA2_64_DESC_SZ	12
 
-/* ADMA2 64-bit DMA alignment */
-#define SDHCI_ADMA2_64_ALIGN	8
-
 /*
  * ADMA2 64-bit descriptor. Note 12-byte descriptor can't always be 8-byte
  * aligned.
@@ -483,8 +488,6 @@ struct sdhci_host {
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
 
 	unsigned int desc_sz;	/* ADMA descriptor size */
-	unsigned int align_sz;	/* ADMA alignment */
-	unsigned int align_mask;	/* ADMA alignment mask */
 
 	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index ad9ffea7d659..6234eab38ff3 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -397,38 +397,26 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 }
 
 static struct dma_chan *
-sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
-			 struct sh_mmcif_plat_data *pdata,
-			 enum dma_transfer_direction direction)
+sh_mmcif_request_dma_pdata(struct sh_mmcif_host *host, uintptr_t slave_id)
 {
-	struct dma_slave_config cfg = { 0, };
-	struct dma_chan *chan;
-	void *slave_data = NULL;
-	struct resource *res;
-	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cap_mask_t mask;
-	int ret;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
+	if (slave_id <= 0)
+		return NULL;
 
-	if (pdata)
-		slave_data = direction == DMA_MEM_TO_DEV ?
-			(void *)pdata->slave_id_tx :
-			(void *)pdata->slave_id_rx;
-
-	chan = dma_request_slave_channel_compat(mask, shdma_chan_filter,
-				slave_data, dev,
-				direction == DMA_MEM_TO_DEV ? "tx" : "rx");
-
-	dev_dbg(dev, "%s: %s: got channel %p\n", __func__,
-		direction == DMA_MEM_TO_DEV ? "TX" : "RX", chan);
+	return dma_request_channel(mask, shdma_chan_filter, (void *)slave_id);
+}
 
-	if (!chan)
-		return NULL;
+static int sh_mmcif_dma_slave_config(struct sh_mmcif_host *host,
+				     struct dma_chan *chan,
+				     enum dma_transfer_direction direction)
+{
+	struct resource *res;
+	struct dma_slave_config cfg = { 0, };
 
 	res = platform_get_resource(host->pd, IORESOURCE_MEM, 0);
-
 	cfg.direction = direction;
 
 	if (direction == DMA_DEV_TO_MEM) {
@@ -439,38 +427,42 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	}
 
-	ret = dmaengine_slave_config(chan, &cfg);
-	if (ret < 0) {
-		dma_release_channel(chan);
-		return NULL;
-	}
-
-	return chan;
+	return dmaengine_slave_config(chan, &cfg);
 }
 
-static void sh_mmcif_request_dma(struct sh_mmcif_host *host,
-				 struct sh_mmcif_plat_data *pdata)
+static void sh_mmcif_request_dma(struct sh_mmcif_host *host)
 {
 	struct device *dev = sh_mmcif_host_to_dev(host);
 	host->dma_active = false;
 
-	if (pdata) {
-		if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0)
-			return;
-	} else if (!dev->of_node) {
-		return;
+	/* We can only either use DMA for both Tx and Rx or not use it at all */
+	if (IS_ENABLED(CONFIG_SUPERH) && dev->platform_data) {
+		struct sh_mmcif_plat_data *pdata = dev->platform_data;
+
+		host->chan_tx = sh_mmcif_request_dma_pdata(host,
+							pdata->slave_id_tx);
+		host->chan_rx = sh_mmcif_request_dma_pdata(host,
+							pdata->slave_id_rx);
+	} else {
+		host->chan_tx = dma_request_slave_channel(dev, "tx");
+		host->chan_rx = dma_request_slave_channel(dev, "rx");
 	}
+	dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx,
+		host->chan_rx);
 
-	/* We can only either use DMA for both Tx and Rx or not use it at all */
-	host->chan_tx = sh_mmcif_request_dma_one(host, pdata, DMA_MEM_TO_DEV);
-	if (!host->chan_tx)
-		return;
+	if (!host->chan_tx || !host->chan_rx ||
+	    sh_mmcif_dma_slave_config(host, host->chan_tx, DMA_MEM_TO_DEV) ||
+	    sh_mmcif_dma_slave_config(host, host->chan_rx, DMA_DEV_TO_MEM))
+		goto error;
 
-	host->chan_rx = sh_mmcif_request_dma_one(host, pdata, DMA_DEV_TO_MEM);
-	if (!host->chan_rx) {
+	return;
+
+error:
+	if (host->chan_tx)
 		dma_release_channel(host->chan_tx);
-		host->chan_tx = NULL;
-	}
+	if (host->chan_rx)
+		dma_release_channel(host->chan_rx);
+	host->chan_tx = host->chan_rx = NULL;
 }
 
 static void sh_mmcif_release_dma(struct sh_mmcif_host *host)
@@ -1102,7 +1094,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->power_mode == MMC_POWER_UP) {
 		if (!host->card_present) {
 			/* See if we also get DMA */
-			sh_mmcif_request_dma(host, dev->platform_data);
+			sh_mmcif_request_dma(host);
 			host->card_present = true;
 		}
 		sh_mmcif_set_power(host, ios);
diff --git a/drivers/mmc/host/ushc.c b/drivers/mmc/host/ushc.c
index d2c386f09d69..1d843357422e 100644
--- a/drivers/mmc/host/ushc.c
+++ b/drivers/mmc/host/ushc.c
@@ -426,6 +426,9 @@ static int ushc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct ushc_data *ushc;
 	int ret;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	mmc = mmc_alloc_host(sizeof(struct ushc_data), &intf->dev);
 	if (mmc == NULL)
 		return -ENOMEM;
diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c
index c0720c1ee4c9..9190057535e6 100644
--- a/drivers/mtd/bcm47xxpart.c
+++ b/drivers/mtd/bcm47xxpart.c
@@ -66,11 +66,13 @@ static const char *bcm47xxpart_trx_data_part_name(struct mtd_info *master,
 {
 	uint32_t buf;
 	size_t bytes_read;
+	int err;
 
-	if (mtd_read(master, offset, sizeof(buf), &bytes_read,
-		     (uint8_t *)&buf) < 0) {
-		pr_err("mtd_read error while parsing (offset: 0x%X)!\n",
-			offset);
+	err  = mtd_read(master, offset, sizeof(buf), &bytes_read,
+			(uint8_t *)&buf);
+	if (err && !mtd_is_bitflip(err)) {
+		pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
+			offset, err);
 		goto out_default;
 	}
 
@@ -95,6 +97,7 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 	int trx_part = -1;
 	int last_trx_part = -1;
 	int possible_nvram_sizes[] = { 0x8000, 0xF000, 0x10000, };
+	int err;
 
 	/*
 	 * Some really old flashes (like AT45DB*) had smaller erasesize-s, but
@@ -118,8 +121,8 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 	/* Parse block by block looking for magics */
 	for (offset = 0; offset <= master->size - blocksize;
 	     offset += blocksize) {
-		/* Nothing more in higher memory */
-		if (offset >= 0x2000000)
+		/* Nothing more in higher memory on BCM47XX (MIPS) */
+		if (config_enabled(CONFIG_BCM47XX) && offset >= 0x2000000)
 			break;
 
 		if (curr_part >= BCM47XXPART_MAX_PARTS) {
@@ -128,10 +131,11 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 		}
 
 		/* Read beginning of the block */
-		if (mtd_read(master, offset, BCM47XXPART_BYTES_TO_READ,
-			     &bytes_read, (uint8_t *)buf) < 0) {
-			pr_err("mtd_read error while parsing (offset: 0x%X)!\n",
-			       offset);
+		err = mtd_read(master, offset, BCM47XXPART_BYTES_TO_READ,
+			       &bytes_read, (uint8_t *)buf);
+		if (err && !mtd_is_bitflip(err)) {
+			pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
+			       offset, err);
 			continue;
 		}
 
@@ -225,12 +229,10 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 
 			last_trx_part = curr_part - 1;
 
-			/*
-			 * We have whole TRX scanned, skip to the next part. Use
-			 * roundown (not roundup), as the loop will increase
-			 * offset in next step.
-			 */
-			offset = rounddown(offset + trx->length, blocksize);
+			/* Jump to the end of TRX */
+			offset = roundup(offset + trx->length, blocksize);
+			/* Next loop iteration will increase the offset */
+			offset -= blocksize;
 			continue;
 		}
 
@@ -254,10 +256,11 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 		}
 
 		/* Read middle of the block */
-		if (mtd_read(master, offset + 0x8000, 0x4,
-			     &bytes_read, (uint8_t *)buf) < 0) {
-			pr_err("mtd_read error while parsing (offset: 0x%X)!\n",
-			       offset);
+		err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read,
+			       (uint8_t *)buf);
+		if (err && !mtd_is_bitflip(err)) {
+			pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
+			       offset, err);
 			continue;
 		}
 
@@ -277,10 +280,11 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 		}
 
 		offset = master->size - possible_nvram_sizes[i];
-		if (mtd_read(master, offset, 0x4, &bytes_read,
-			     (uint8_t *)buf) < 0) {
-			pr_err("mtd_read error while reading at offset 0x%X!\n",
-			       offset);
+		err = mtd_read(master, offset, 0x4, &bytes_read,
+			       (uint8_t *)buf);
+		if (err && !mtd_is_bitflip(err)) {
+			pr_err("mtd_read error while reading (offset 0x%X): %d\n",
+			       offset, err);
 			continue;
 		}
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index 54479c481a7a..8a25adced79f 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -111,6 +111,7 @@ config MTD_MAP_BANK_WIDTH_16
 
 config MTD_MAP_BANK_WIDTH_32
 	bool "Support 256-bit buswidth" if MTD_CFI_GEOMETRY
+	select MTD_COMPLEX_MAPPINGS if HAS_IOMEM
 	default n
 	help
 	  If you wish to support CFI devices on a physical bus which is
diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c
index 744ca5cacc9b..2051f28ddac6 100644
--- a/drivers/mtd/maps/pmcmsp-flash.c
+++ b/drivers/mtd/maps/pmcmsp-flash.c
@@ -75,15 +75,15 @@ static int __init init_msp_flash(void)
 
 	printk(KERN_NOTICE "Found %d PMC flash devices\n", fcnt);
 
-	msp_flash = kmalloc(fcnt * sizeof(struct map_info *), GFP_KERNEL);
+	msp_flash = kcalloc(fcnt, sizeof(*msp_flash), GFP_KERNEL);
 	if (!msp_flash)
 		return -ENOMEM;
 
-	msp_parts = kmalloc(fcnt * sizeof(struct mtd_partition *), GFP_KERNEL);
+	msp_parts = kcalloc(fcnt, sizeof(*msp_parts), GFP_KERNEL);
 	if (!msp_parts)
 		goto free_msp_flash;
 
-	msp_maps = kcalloc(fcnt, sizeof(struct mtd_info), GFP_KERNEL);
+	msp_maps = kcalloc(fcnt, sizeof(*msp_maps), GFP_KERNEL);
 	if (!msp_maps)
 		goto free_msp_parts;
 
@@ -139,15 +139,13 @@ static int __init init_msp_flash(void)
 		}
 
 		msp_maps[i].bankwidth = 1;
-		msp_maps[i].name = kmalloc(7, GFP_KERNEL);
+		msp_maps[i].name = kstrndup(flash_name, 7, GFP_KERNEL);
 		if (!msp_maps[i].name) {
 			iounmap(msp_maps[i].virt);
 			kfree(msp_parts[i]);
 			goto cleanup_loop;
 		}
 
-		msp_maps[i].name = strncpy(msp_maps[i].name, flash_name, 7);
-
 		for (j = 0; j < pcnt; j++) {
 			part_name[5] = '0' + i;
 			part_name[7] = '0' + j;
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index 142fc3d79463..784c6e1a0391 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -230,8 +230,10 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev,
 
 		info->mtd = mtd_concat_create(cdev, info->num_subdev,
 					      plat->name);
-		if (info->mtd == NULL)
+		if (info->mtd == NULL) {
 			ret = -ENXIO;
+			goto err;
+		}
 	}
 	info->mtd->dev.parent = &pdev->dev;
 
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 289664089cf3..8f49f8aeff1a 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -527,7 +527,7 @@ config MTD_NAND_FSMC
 	  Flexible Static Memory Controller (FSMC)
 
 config MTD_NAND_XWAY
-	tristate "Support for NAND on Lantiq XWAY SoC"
+	bool "Support for NAND on Lantiq XWAY SoC"
 	depends on LANTIQ && SOC_TYPE_XWAY
 	select MTD_NAND_PLATFORM
 	help
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c
index 12c6190c6e33..4a07ba1195b5 100644
--- a/drivers/mtd/nand/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/brcmnand/brcmnand.c
@@ -309,6 +309,36 @@ static const u16 brcmnand_regs_v60[] = {
 	[BRCMNAND_FC_BASE]		= 0x400,
 };
 
+/* BRCMNAND v7.1 */
+static const u16 brcmnand_regs_v71[] = {
+	[BRCMNAND_CMD_START]		=  0x04,
+	[BRCMNAND_CMD_EXT_ADDRESS]	=  0x08,
+	[BRCMNAND_CMD_ADDRESS]		=  0x0c,
+	[BRCMNAND_INTFC_STATUS]		=  0x14,
+	[BRCMNAND_CS_SELECT]		=  0x18,
+	[BRCMNAND_CS_XOR]		=  0x1c,
+	[BRCMNAND_LL_OP]		=  0x20,
+	[BRCMNAND_CS0_BASE]		=  0x50,
+	[BRCMNAND_CS1_BASE]		=     0,
+	[BRCMNAND_CORR_THRESHOLD]	=  0xdc,
+	[BRCMNAND_CORR_THRESHOLD_EXT]	=  0xe0,
+	[BRCMNAND_UNCORR_COUNT]		=  0xfc,
+	[BRCMNAND_CORR_COUNT]		= 0x100,
+	[BRCMNAND_CORR_EXT_ADDR]	= 0x10c,
+	[BRCMNAND_CORR_ADDR]		= 0x110,
+	[BRCMNAND_UNCORR_EXT_ADDR]	= 0x114,
+	[BRCMNAND_UNCORR_ADDR]		= 0x118,
+	[BRCMNAND_SEMAPHORE]		= 0x150,
+	[BRCMNAND_ID]			= 0x194,
+	[BRCMNAND_ID_EXT]		= 0x198,
+	[BRCMNAND_LL_RDATA]		= 0x19c,
+	[BRCMNAND_OOB_READ_BASE]	= 0x200,
+	[BRCMNAND_OOB_READ_10_BASE]	=     0,
+	[BRCMNAND_OOB_WRITE_BASE]	= 0x280,
+	[BRCMNAND_OOB_WRITE_10_BASE]	=     0,
+	[BRCMNAND_FC_BASE]		= 0x400,
+};
+
 enum brcmnand_cs_reg {
 	BRCMNAND_CS_CFG_EXT = 0,
 	BRCMNAND_CS_CFG,
@@ -404,7 +434,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
 	}
 
 	/* Register offsets */
-	if (ctrl->nand_version >= 0x0600)
+	if (ctrl->nand_version >= 0x0701)
+		ctrl->reg_offsets = brcmnand_regs_v71;
+	else if (ctrl->nand_version >= 0x0600)
 		ctrl->reg_offsets = brcmnand_regs_v60;
 	else if (ctrl->nand_version >= 0x0500)
 		ctrl->reg_offsets = brcmnand_regs_v50;
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index c72313d66cf6..bc054a5ed7f8 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -241,6 +241,9 @@ static void nand_davinci_hwctl_4bit(struct mtd_info *mtd, int mode)
 	unsigned long flags;
 	u32 val;
 
+	/* Reset ECC hardware */
+	davinci_nand_readl(info, NAND_4BIT_ECC1_OFFSET);
+
 	spin_lock_irqsave(&davinci_nand_lock, flags);
 
 	/* Start 4-bit ECC calculation for read/write */
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 3ff583f165cd..54ab48827258 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2586,7 +2586,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 		int cached = writelen > bytes && page != blockmask;
 		uint8_t *wbuf = buf;
 		int use_bufpoi;
-		int part_pagewr = (column || writelen < (mtd->writesize - 1));
+		int part_pagewr = (column || writelen < mtd->writesize);
 
 		if (part_pagewr)
 			use_bufpoi = 1;
@@ -3979,7 +3979,6 @@ static int nand_dt_init(struct mtd_info *mtd, struct nand_chip *chip,
  * This is the first phase of the normal nand_scan() function. It reads the
  * flash ID and sets up MTD fields accordingly.
  *
- * The mtd->owner field must be set to the module of the caller.
  */
 int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 		    struct nand_flash_dev *table)
@@ -4403,19 +4402,12 @@ EXPORT_SYMBOL(nand_scan_tail);
  *
  * This fills out all the uninitialized function pointers with the defaults.
  * The flash ID is read and the mtd/chip structures are filled with the
- * appropriate values. The mtd->owner field must be set to the module of the
- * caller.
+ * appropriate values.
  */
 int nand_scan(struct mtd_info *mtd, int maxchips)
 {
 	int ret;
 
-	/* Many callers got this wrong, so check for it for a while... */
-	if (!mtd->owner && caller_is_module()) {
-		pr_crit("%s called with NULL mtd->owner!\n", __func__);
-		BUG();
-	}
-
 	ret = nand_scan_ident(mtd, maxchips, NULL);
 	if (!ret)
 		ret = nand_scan_tail(mtd);
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index 43b3392ffee7..652d01832873 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -2599,6 +2599,7 @@ static int onenand_default_block_markbad(struct mtd_info *mtd, loff_t ofs)
  */
 static int onenand_block_markbad(struct mtd_info *mtd, loff_t ofs)
 {
+	struct onenand_chip *this = mtd->priv;
 	int ret;
 
 	ret = onenand_block_isbad(mtd, ofs);
@@ -2610,7 +2611,7 @@ static int onenand_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	}
 
 	onenand_get_device(mtd, FL_WRITING);
-	ret = mtd_block_markbad(mtd, ofs);
+	ret = this->block_markbad(mtd, ofs);
 	onenand_release_device(mtd);
 	return ret;
 }
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 32477c4eb421..64d6f053c2a5 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -1057,6 +1057,13 @@ static int spansion_quad_enable(struct spi_nor *nor)
 		return -EINVAL;
 	}
 
+	ret = spi_nor_wait_till_ready(nor);
+	if (ret) {
+		dev_err(nor->dev,
+			"timeout while writing configuration register\n");
+		return ret;
+	}
+
 	/* read back and check it */
 	ret = read_cr(nor);
 	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
@@ -1067,45 +1074,6 @@ static int spansion_quad_enable(struct spi_nor *nor)
 	return 0;
 }
 
-static int micron_quad_enable(struct spi_nor *nor)
-{
-	int ret;
-	u8 val;
-
-	ret = nor->read_reg(nor, SPINOR_OP_RD_EVCR, &val, 1);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading EVCR\n", ret);
-		return ret;
-	}
-
-	write_enable(nor);
-
-	/* set EVCR, enable quad I/O */
-	nor->cmd_buf[0] = val & ~EVCR_QUAD_EN_MICRON;
-	ret = nor->write_reg(nor, SPINOR_OP_WD_EVCR, nor->cmd_buf, 1);
-	if (ret < 0) {
-		dev_err(nor->dev, "error while writing EVCR register\n");
-		return ret;
-	}
-
-	ret = spi_nor_wait_till_ready(nor);
-	if (ret)
-		return ret;
-
-	/* read EVCR and check it */
-	ret = nor->read_reg(nor, SPINOR_OP_RD_EVCR, &val, 1);
-	if (ret < 0) {
-		dev_err(nor->dev, "error %d reading EVCR\n", ret);
-		return ret;
-	}
-	if (val & EVCR_QUAD_EN_MICRON) {
-		dev_err(nor->dev, "Micron EVCR Quad bit not clear\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info)
 {
 	int status;
@@ -1119,12 +1087,7 @@ static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info)
 		}
 		return status;
 	case SNOR_MFR_MICRON:
-		status = micron_quad_enable(nor);
-		if (status) {
-			dev_err(nor->dev, "Micron quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
+		return 0;
 	default:
 		status = spansion_quad_enable(nor);
 		if (status) {
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 22fd19c0c5d3..27de0463226e 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -869,7 +869,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 	for (i = 0; i < UBI_MAX_DEVICES; i++) {
 		ubi = ubi_devices[i];
 		if (ubi && mtd->index == ubi->mtd->index) {
-			ubi_err(ubi, "mtd%d is already attached to ubi%d",
+			pr_err("ubi: mtd%d is already attached to ubi%d",
 				mtd->index, i);
 			return -EEXIST;
 		}
@@ -884,7 +884,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 	 * no sense to attach emulated MTD devices, so we prohibit this.
 	 */
 	if (mtd->type == MTD_UBIVOLUME) {
-		ubi_err(ubi, "refuse attaching mtd%d - it is already emulated on top of UBI",
+		pr_err("ubi: refuse attaching mtd%d - it is already emulated on top of UBI",
 			mtd->index);
 		return -EINVAL;
 	}
@@ -895,7 +895,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 			if (!ubi_devices[ubi_num])
 				break;
 		if (ubi_num == UBI_MAX_DEVICES) {
-			ubi_err(ubi, "only %d UBI devices may be created",
+			pr_err("ubi: only %d UBI devices may be created",
 				UBI_MAX_DEVICES);
 			return -ENFILE;
 		}
@@ -905,7 +905,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 
 		/* Make sure ubi_num is not busy */
 		if (ubi_devices[ubi_num]) {
-			ubi_err(ubi, "already exists");
+			pr_err("ubi: ubi%i already exists", ubi_num);
 			return -EEXIST;
 		}
 	}
@@ -987,6 +987,9 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 			goto out_detach;
 	}
 
+	/* Make device "available" before it becomes accessible via sysfs */
+	ubi_devices[ubi_num] = ubi;
+
 	err = uif_init(ubi, &ref);
 	if (err)
 		goto out_detach;
@@ -1031,7 +1034,6 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 	wake_up_process(ubi->bgt_thread);
 	spin_unlock(&ubi->wl_lock);
 
-	ubi_devices[ubi_num] = ubi;
 	ubi_notify_all(ubi, UBI_VOLUME_ADDED, NULL);
 	return ubi_num;
 
@@ -1042,6 +1044,7 @@ out_uif:
 	ubi_assert(ref);
 	uif_close(ubi);
 out_detach:
+	ubi_devices[ubi_num] = NULL;
 	ubi_wl_close(ubi);
 	ubi_free_internal_volumes(ubi);
 	vfree(ubi->vtbl);
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 5b9834cf2820..4dd0391d2942 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -426,8 +426,25 @@ retry:
 						 pnum, vol_id, lnum);
 					err = -EBADMSG;
 				} else {
-					err = -EINVAL;
-					ubi_ro_mode(ubi);
+					/*
+					 * Ending up here in the non-Fastmap case
+					 * is a clear bug as the VID header had to
+					 * be present at scan time to have it referenced.
+					 * With fastmap the story is more complicated.
+					 * Fastmap has the mapping info without the need
+					 * of a full scan. So the LEB could have been
+					 * unmapped, Fastmap cannot know this and keeps
+					 * the LEB referenced.
+					 * This is valid and works as the layer above UBI
+					 * has to do bookkeeping about used/referenced
+					 * LEBs in any case.
+					 */
+					if (ubi->fast_attach) {
+						err = -EBADMSG;
+					} else {
+						err = -EINVAL;
+						ubi_ro_mode(ubi);
+					}
 				}
 			}
 			goto out_free;
@@ -558,6 +575,7 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
 	int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
 	struct ubi_volume *vol = ubi->volumes[idx];
 	struct ubi_vid_hdr *vid_hdr;
+	uint32_t crc;
 
 	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
 	if (!vid_hdr)
@@ -582,14 +600,8 @@ retry:
 		goto out_put;
 	}
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
-	if (err) {
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
 
-	data_size = offset + len;
 	mutex_lock(&ubi->buf_mutex);
 	memset(ubi->peb_buf + offset, 0xFF, len);
 
@@ -604,6 +616,19 @@ retry:
 
 	memcpy(ubi->peb_buf + offset, buf, len);
 
+	data_size = offset + len;
+	crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size);
+	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+	vid_hdr->copy_flag = 1;
+	vid_hdr->data_size = cpu_to_be32(data_size);
+	vid_hdr->data_crc = cpu_to_be32(crc);
+	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
+	if (err) {
+		mutex_unlock(&ubi->buf_mutex);
+		up_read(&ubi->fm_eba_sem);
+		goto write_error;
+	}
+
 	err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
 	if (err) {
 		mutex_unlock(&ubi->buf_mutex);
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 263b439e21a8..bba7dd1b5ebf 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -513,10 +513,11 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			unsigned long long ec = be64_to_cpu(ech->ec);
 			unmap_peb(ai, pnum);
 			dbg_bld("Adding PEB to free: %i", pnum);
+
 			if (err == UBI_IO_FF_BITFLIPS)
-				add_aeb(ai, free, pnum, ec, 1);
-			else
-				add_aeb(ai, free, pnum, ec, 0);
+				scrub = 1;
+
+			add_aeb(ai, free, pnum, ec, scrub);
 			continue;
 		} else if (err == 0 || err == UBI_IO_BITFLIPS) {
 			dbg_bld("Found non empty PEB:%i in pool", pnum);
@@ -748,11 +749,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 			     fmvhdr->vol_type,
 			     be32_to_cpu(fmvhdr->last_eb_bytes));
 
-		if (!av)
-			goto fail_bad;
-		if (PTR_ERR(av) == -EINVAL) {
-			ubi_err(ubi, "volume (ID %i) already exists",
-				fmvhdr->vol_id);
+		if (IS_ERR(av)) {
+			if (PTR_ERR(av) == -EEXIST)
+				ubi_err(ubi, "volume (ID %i) already exists",
+					fmvhdr->vol_id);
+
 			goto fail_bad;
 		}
 
@@ -1058,6 +1059,7 @@ int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai,
 	ubi_msg(ubi, "fastmap WL pool size: %d",
 		ubi->fm_wl_pool.max_size);
 	ubi->fm_disabled = 0;
+	ubi->fast_attach = 1;
 
 	ubi_free_vid_hdr(ubi, vh);
 	kfree(ech);
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 2974b67f6c6c..de1ea2e4c37d 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -462,6 +462,7 @@ struct ubi_debug_info {
  * @fm_eba_sem: allows ubi_update_fastmap() to block EBA table changes
  * @fm_work: fastmap work queue
  * @fm_work_scheduled: non-zero if fastmap work was scheduled
+ * @fast_attach: non-zero if UBI was attached by fastmap
  *
  * @used: RB-tree of used physical eraseblocks
  * @erroneous: RB-tree of erroneous used physical eraseblocks
@@ -570,6 +571,7 @@ struct ubi_device {
 	size_t fm_size;
 	struct work_struct fm_work;
 	int fm_work_scheduled;
+	int fast_attach;
 
 	/* Wear-leveling sub-system's stuff */
 	struct rb_root used;
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index 0134ba32a057..39712560b4c1 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 			return err;
 	}
 
-	if (bytes == 0) {
-		err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
-		if (err)
-			return err;
+	err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
+	if (err)
+		return err;
 
+	if (bytes == 0) {
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c
index 1ae17bb9b889..3ea4c022cbb9 100644
--- a/drivers/mtd/ubi/vmt.c
+++ b/drivers/mtd/ubi/vmt.c
@@ -488,13 +488,6 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		spin_unlock(&ubi->volumes_lock);
 	}
 
-	/* Change volume table record */
-	vtbl_rec = ubi->vtbl[vol_id];
-	vtbl_rec.reserved_pebs = cpu_to_be32(reserved_pebs);
-	err = ubi_change_vtbl_record(ubi, vol_id, &vtbl_rec);
-	if (err)
-		goto out_acc;
-
 	if (pebs < 0) {
 		for (i = 0; i < -pebs; i++) {
 			err = ubi_eba_unmap_leb(ubi, vol, reserved_pebs + i);
@@ -512,6 +505,24 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs)
 		spin_unlock(&ubi->volumes_lock);
 	}
 
+	/*
+	 * When we shrink a volume we have to flush all pending (erase) work.
+	 * Otherwise it can happen that upon next attach UBI finds a LEB with
+	 * lnum > highest_lnum and refuses to attach.
+	 */
+	if (pebs < 0) {
+		err = ubi_wl_flush(ubi, vol_id, UBI_ALL);
+		if (err)
+			goto out_acc;
+	}
+
+	/* Change volume table record */
+	vtbl_rec = ubi->vtbl[vol_id];
+	vtbl_rec.reserved_pebs = cpu_to_be32(reserved_pebs);
+	err = ubi_change_vtbl_record(ubi, vol_id, &vtbl_rec);
+	if (err)
+		goto out_acc;
+
 	vol->reserved_pebs = reserved_pebs;
 	if (vol->vol_type == UBI_DYNAMIC_VOLUME) {
 		vol->used_ebs = reserved_pebs;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 56065632a5b8..75286588b823 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -643,7 +643,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 				int shutdown)
 {
 	int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
-	int vol_id = -1, lnum = -1;
+	int erase = 0, keep = 0, vol_id = -1, lnum = -1;
 #ifdef CONFIG_MTD_UBI_FASTMAP
 	int anchor = wrk->anchor;
 #endif
@@ -777,6 +777,16 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			       e1->pnum);
 			scrubbing = 1;
 			goto out_not_moved;
+		} else if (ubi->fast_attach && err == UBI_IO_BAD_HDR_EBADMSG) {
+			/*
+			 * While a full scan would detect interrupted erasures
+			 * at attach time we can face them here when attached from
+			 * Fastmap.
+			 */
+			dbg_wl("PEB %d has ECC errors, maybe from an interrupted erasure",
+			       e1->pnum);
+			erase = 1;
+			goto out_not_moved;
 		}
 
 		ubi_err(ubi, "error %d while reading VID header from PEB %d",
@@ -810,6 +820,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			 * Target PEB had bit-flips or write error - torture it.
 			 */
 			torture = 1;
+			keep = 1;
 			goto out_not_moved;
 		}
 
@@ -895,7 +906,7 @@ out_not_moved:
 		ubi->erroneous_peb_count += 1;
 	} else if (scrubbing)
 		wl_tree_add(e1, &ubi->scrub);
-	else
+	else if (keep)
 		wl_tree_add(e1, &ubi->used);
 	ubi_assert(!ubi->move_to_put);
 	ubi->move_from = ubi->move_to = NULL;
@@ -907,6 +918,12 @@ out_not_moved:
 	if (err)
 		goto out_ro;
 
+	if (erase) {
+		err = do_sync_erase(ubi, e1, vol_id, lnum, 1);
+		if (err)
+			goto out_ro;
+	}
+
 	mutex_unlock(&ubi->move_mutex);
 	return 0;
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 28bbca0af238..5dca77e0ffed 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1317,9 +1317,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			    slave_dev->name);
 	}
 
-	/* already enslaved */
-	if (slave_dev->flags & IFF_SLAVE) {
-		netdev_dbg(bond_dev, "Error: Device was already enslaved\n");
+	/* already in-use? */
+	if (netdev_is_rx_handler_busy(slave_dev)) {
+		netdev_err(bond_dev,
+			   "Error: Device is in use and cannot be enslaved\n");
 		return -EBUSY;
 	}
 
@@ -3260,6 +3261,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3268,43 +3293,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4118,6 +4123,7 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
+	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index db760e84119f..b8df0f5e8c25 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 	if (err < 0)
 		return err;
 
-	return register_netdevice(bond_dev);
+	err = register_netdevice(bond_dev);
+
+	netif_carrier_off(bond_dev);
+
+	return err;
 }
 
 static size_t bond_get_size(const struct net_device *bond_dev)
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 8b3275d7792a..8f5e93cb7975 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -712,9 +712,10 @@ static int at91_poll_rx(struct net_device *dev, int quota)
 
 	/* upper group completed, look again in lower */
 	if (priv->rx_next > get_mb_rx_low_last(priv) &&
-	    quota > 0 && mb > get_mb_rx_last(priv)) {
+	    mb > get_mb_rx_last(priv)) {
 		priv->rx_next = get_mb_rx_first(priv);
-		goto again;
+		if (quota > 0)
+			goto again;
 	}
 
 	return received;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index f91b094288da..e3dccd3200d5 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
 
-	for (i = 0; i < frame->can_dlc; i += 2) {
-		priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2,
-				frame->data[i] | (frame->data[i + 1] << 8));
+	if (priv->type == BOSCH_D_CAN) {
+		u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
+
+		for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+			data = (u32)frame->data[i];
+			data |= (u32)frame->data[i + 1] << 8;
+			data |= (u32)frame->data[i + 2] << 16;
+			data |= (u32)frame->data[i + 3] << 24;
+			priv->write_reg32(priv, dreg, data);
+		}
+	} else {
+		for (i = 0; i < frame->can_dlc; i += 2) {
+			priv->write_reg(priv,
+					C_CAN_IFACE(DATA1_REG, iface) + i / 2,
+					frame->data[i] |
+					(frame->data[i + 1] << 8));
+		}
 	}
 }
 
@@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 	} else {
 		int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
-		for (i = 0; i < frame->can_dlc; i += 2, dreg ++) {
-			data = priv->read_reg(priv, dreg);
-			frame->data[i] = data;
-			frame->data[i + 1] = data >> 8;
+		if (priv->type == BOSCH_D_CAN) {
+			for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+				data = priv->read_reg32(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+				frame->data[i + 2] = data >> 16;
+				frame->data[i + 3] = data >> 24;
+			}
+		} else {
+			for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+				data = priv->read_reg(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+			}
 		}
 	}
 
diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c
index 7be393c96b1a..cf7c18947189 100644
--- a/drivers/net/can/c_can/c_can_pci.c
+++ b/drivers/net/can/c_can/c_can_pci.c
@@ -161,6 +161,7 @@ static int c_can_pci_probe(struct pci_dev *pdev,
 
 	dev->irq = pdev->irq;
 	priv->base = addr;
+	priv->device = &pdev->dev;
 
 	if (!c_can_pci_data->freq) {
 		dev_err(&pdev->dev, "no clock frequency defined\n");
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 141c2a42d7ed..eab132778e67 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
+#include <linux/workqueue.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/skb.h>
@@ -471,9 +472,8 @@ EXPORT_SYMBOL_GPL(can_free_echo_skb);
 /*
  * CAN device restart for bus-off recovery
  */
-static void can_restart(unsigned long data)
+static void can_restart(struct net_device *dev)
 {
-	struct net_device *dev = (struct net_device *)data;
 	struct can_priv *priv = netdev_priv(dev);
 	struct net_device_stats *stats = &dev->stats;
 	struct sk_buff *skb;
@@ -513,6 +513,14 @@ restart:
 		netdev_err(dev, "Error %d during restart", err);
 }
 
+static void can_restart_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct can_priv *priv = container_of(dwork, struct can_priv, restart_work);
+
+	can_restart(priv->dev);
+}
+
 int can_restart_now(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
@@ -526,8 +534,8 @@ int can_restart_now(struct net_device *dev)
 	if (priv->state != CAN_STATE_BUS_OFF)
 		return -EBUSY;
 
-	/* Runs as soon as possible in the timer context */
-	mod_timer(&priv->restart_timer, jiffies);
+	cancel_delayed_work_sync(&priv->restart_work);
+	can_restart(dev);
 
 	return 0;
 }
@@ -548,8 +556,8 @@ void can_bus_off(struct net_device *dev)
 	netif_carrier_off(dev);
 
 	if (priv->restart_ms)
-		mod_timer(&priv->restart_timer,
-			  jiffies + (priv->restart_ms * HZ) / 1000);
+		schedule_delayed_work(&priv->restart_work,
+				      msecs_to_jiffies(priv->restart_ms));
 }
 EXPORT_SYMBOL_GPL(can_bus_off);
 
@@ -658,6 +666,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 		return NULL;
 
 	priv = netdev_priv(dev);
+	priv->dev = dev;
 
 	if (echo_skb_max) {
 		priv->echo_skb_max = echo_skb_max;
@@ -667,7 +676,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 
 	priv->state = CAN_STATE_STOPPED;
 
-	init_timer(&priv->restart_timer);
+	INIT_DELAYED_WORK(&priv->restart_work, can_restart_work);
 
 	return dev;
 }
@@ -696,11 +705,17 @@ int can_change_mtu(struct net_device *dev, int new_mtu)
 	/* allow change of MTU according to the CANFD ability of the device */
 	switch (new_mtu) {
 	case CAN_MTU:
+		/* 'CANFD-only' controllers can not switch to CAN_MTU */
+		if (priv->ctrlmode_static & CAN_CTRLMODE_FD)
+			return -EINVAL;
+
 		priv->ctrlmode &= ~CAN_CTRLMODE_FD;
 		break;
 
 	case CANFD_MTU:
-		if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD))
+		/* check for potential CANFD ability */
+		if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) &&
+		    !(priv->ctrlmode_static & CAN_CTRLMODE_FD))
 			return -EINVAL;
 
 		priv->ctrlmode |= CAN_CTRLMODE_FD;
@@ -742,8 +757,6 @@ int open_candev(struct net_device *dev)
 	if (!netif_carrier_ok(dev))
 		netif_carrier_on(dev);
 
-	setup_timer(&priv->restart_timer, can_restart, (unsigned long)dev);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(open_candev);
@@ -758,7 +771,7 @@ void close_candev(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
 
-	del_timer_sync(&priv->restart_timer);
+	cancel_delayed_work_sync(&priv->restart_work);
 	can_flush_echo_skb(dev);
 }
 EXPORT_SYMBOL_GPL(close_candev);
@@ -782,6 +795,38 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming_const) },
 };
 
+static int can_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	bool is_can_fd = false;
+
+	/* Make sure that valid CAN FD configurations always consist of
+	 * - nominal/arbitration bittiming
+	 * - data bittiming
+	 * - control mode with CAN_CTRLMODE_FD set
+	 */
+
+	if (!data)
+		return 0;
+
+	if (data[IFLA_CAN_CTRLMODE]) {
+		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
+
+		is_can_fd = cm->flags & cm->mask & CAN_CTRLMODE_FD;
+	}
+
+	if (is_can_fd) {
+		if (!data[IFLA_CAN_BITTIMING] || !data[IFLA_CAN_DATA_BITTIMING])
+			return -EOPNOTSUPP;
+	}
+
+	if (data[IFLA_CAN_DATA_BITTIMING]) {
+		if (!is_can_fd || !data[IFLA_CAN_BITTIMING])
+			return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int can_changelink(struct net_device *dev,
 			  struct nlattr *tb[], struct nlattr *data[])
 {
@@ -813,19 +858,31 @@ static int can_changelink(struct net_device *dev,
 
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm;
+		u32 ctrlstatic;
+		u32 maskedflags;
 
 		/* Do not allow changing controller mode while running */
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
 		cm = nla_data(data[IFLA_CAN_CTRLMODE]);
+		ctrlstatic = priv->ctrlmode_static;
+		maskedflags = cm->flags & cm->mask;
+
+		/* check whether provided bits are allowed to be passed */
+		if (cm->mask & ~(priv->ctrlmode_supported | ctrlstatic))
+			return -EOPNOTSUPP;
 
-		/* check whether changed bits are allowed to be modified */
-		if (cm->mask & ~priv->ctrlmode_supported)
+		/* do not check for static fd-non-iso if 'fd' is disabled */
+		if (!(maskedflags & CAN_CTRLMODE_FD))
+			ctrlstatic &= ~CAN_CTRLMODE_FD_NON_ISO;
+
+		/* make sure static options are provided by configuration */
+		if ((maskedflags & ctrlstatic) != ctrlstatic)
 			return -EOPNOTSUPP;
 
 		/* clear bits to be modified and copy the flag values */
 		priv->ctrlmode &= ~cm->mask;
-		priv->ctrlmode |= (cm->flags & cm->mask);
+		priv->ctrlmode |= maskedflags;
 
 		/* CAN_CTRLMODE_FD can only be set when driver supports FD */
 		if (priv->ctrlmode & CAN_CTRLMODE_FD)
@@ -961,13 +1018,20 @@ static int can_newlink(struct net *src_net, struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static void can_dellink(struct net_device *dev, struct list_head *head)
+{
+	return;
+}
+
 static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.kind		= "can",
 	.maxtype	= IFLA_CAN_MAX,
 	.policy		= can_policy,
 	.setup		= can_setup,
+	.validate	= can_validate,
 	.newlink	= can_newlink,
 	.changelink	= can_changelink,
+	.dellink	= can_dellink,
 	.get_size	= can_get_size,
 	.fill_info	= can_fill_info,
 	.get_xstats_size = can_get_xstats_size,
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 41c0fc9f3b14..16f7cadda5c3 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1268,11 +1268,10 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	err = flexcan_chip_disable(priv);
-	if (err)
-		return err;
-
 	if (netif_running(dev)) {
+		err = flexcan_chip_disable(priv);
+		if (err)
+			return err;
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
 	}
@@ -1285,13 +1284,17 @@ static int __maybe_unused flexcan_resume(struct device *device)
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
+	int err;
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);
+		err = flexcan_chip_enable(priv);
+		if (err)
+			return err;
 	}
-	return flexcan_chip_enable(priv);
+	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(flexcan_pm_ops, flexcan_suspend, flexcan_resume);
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 39cf911f7a1e..195f15edb32e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -955,7 +955,7 @@ static struct net_device *alloc_m_can_dev(void)
 	priv->can.do_get_berr_counter = m_can_get_berr_counter;
 
 	/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.1 */
-	priv->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO;
+	can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
 
 	/* CAN_CTRLMODE_FD_NON_ISO can not be changed with M_CAN IP v3.0.1 */
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 680d1ff07a55..6749b1829469 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -948,7 +948,12 @@ static int ti_hecc_probe(struct platform_device *pdev)
 	netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll,
 		HECC_DEF_NAPI_WEIGHT);
 
-	clk_enable(priv->clk);
+	err = clk_prepare_enable(priv->clk);
+	if (err) {
+		dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
+		goto probe_exit_clk;
+	}
+
 	err = register_candev(ndev);
 	if (err) {
 		dev_err(&pdev->dev, "register_candev() failed\n");
@@ -981,7 +986,7 @@ static int ti_hecc_remove(struct platform_device *pdev)
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
-	clk_disable(priv->clk);
+	clk_disable_unprepare(priv->clk);
 	clk_put(priv->clk);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iounmap(priv->base);
@@ -1006,7 +1011,7 @@ static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state)
 	hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
 	priv->can.state = CAN_STATE_SLEEPING;
 
-	clk_disable(priv->clk);
+	clk_disable_unprepare(priv->clk);
 
 	return 0;
 }
@@ -1015,8 +1020,11 @@ static int ti_hecc_resume(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct ti_hecc_priv *priv = netdev_priv(dev);
+	int err;
 
-	clk_enable(priv->clk);
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
 
 	hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index cbc99d5649af..ae5709354546 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -246,6 +246,8 @@ static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev)
 			     sizeof(*dm),
 			     1000);
 
+	kfree(dm);
+
 	return rc;
 }
 
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 5a2e341a6d1e..91be4575b524 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -872,23 +872,25 @@ lbl_free_candev:
 static void peak_usb_disconnect(struct usb_interface *intf)
 {
 	struct peak_usb_device *dev;
+	struct peak_usb_device *dev_prev_siblings;
 
 	/* unregister as many netdev devices as siblings */
-	for (dev = usb_get_intfdata(intf); dev; dev = dev->prev_siblings) {
+	for (dev = usb_get_intfdata(intf); dev; dev = dev_prev_siblings) {
 		struct net_device *netdev = dev->netdev;
 		char name[IFNAMSIZ];
 
+		dev_prev_siblings = dev->prev_siblings;
 		dev->state &= ~PCAN_USB_STATE_CONNECTED;
 		strncpy(name, netdev->name, IFNAMSIZ);
 
 		unregister_netdev(netdev);
-		free_candev(netdev);
 
 		kfree(dev->cmd_buf);
 		dev->next_siblings = NULL;
 		if (dev->adapter->dev_free)
 			dev->adapter->dev_free(dev);
 
+		free_candev(netdev);
 		dev_info(&intf->dev, "%s removed\n", name);
 	}
 
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index a731720f1d13..449b2a47f9a8 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -954,8 +954,8 @@ static int usb_8dev_probe(struct usb_interface *intf,
 	for (i = 0; i < MAX_TX_URBS; i++)
 		priv->tx_contexts[i].echo_index = MAX_TX_URBS;
 
-	priv->cmd_msg_buffer = kzalloc(sizeof(struct usb_8dev_cmd_msg),
-				      GFP_KERNEL);
+	priv->cmd_msg_buffer = devm_kzalloc(&intf->dev, sizeof(struct usb_8dev_cmd_msg),
+					    GFP_KERNEL);
 	if (!priv->cmd_msg_buffer)
 		goto cleanup_candev;
 
@@ -969,7 +969,7 @@ static int usb_8dev_probe(struct usb_interface *intf,
 	if (err) {
 		netdev_err(netdev,
 			"couldn't register CAN device: %d\n", err);
-		goto cleanup_cmd_msg_buffer;
+		goto cleanup_candev;
 	}
 
 	err = usb_8dev_cmd_version(priv, &version);
@@ -990,9 +990,6 @@ static int usb_8dev_probe(struct usb_interface *intf,
 cleanup_unregister_candev:
 	unregister_netdev(priv->netdev);
 
-cleanup_cmd_msg_buffer:
-	kfree(priv->cmd_msg_buffer);
-
 cleanup_candev:
 	free_candev(netdev);
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 6f946fedbb77..0864f05633a2 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1137,6 +1137,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct ethtool_eee *p = &priv->port_sts[port].eee;
 	u32 id_mode_dis = 0, port_mode;
 	const char *str = NULL;
 	u32 reg;
@@ -1211,6 +1212,9 @@ force_link:
 		reg |= DUPLX_MODE;
 
 	core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
+
+	if (!phydev->is_pseudo_fixed_link)
+		p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev);
 }
 
 static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 6bba1c98d764..c7994e372284 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -187,8 +187,8 @@ static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
 static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
 {									\
-	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 	priv->irq##which##_mask &= ~(mask);				\
+	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 }									\
 static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index ac7288240d55..f089fa954f42 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1153,6 +1153,12 @@ static void init_ring(struct net_device *dev)
 		if (skb == NULL)
 			break;
 		np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+		if (pci_dma_mapping_error(np->pci_dev,
+					  np->rx_info[i].mapping)) {
+			dev_kfree_skb(skb);
+			np->rx_info[i].skb = NULL;
+			break;
+		}
 		/* Grrr, we cannot offset to correctly align the IP header. */
 		np->rx_ring[i].rxaddr = cpu_to_dma(np->rx_info[i].mapping | RxDescValid);
 	}
@@ -1183,8 +1189,9 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	unsigned int entry;
+	unsigned int prev_tx;
 	u32 status;
-	int i;
+	int i, j;
 
 	/*
 	 * be cautious here, wrapping the queue has weird semantics
@@ -1202,6 +1209,7 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 	}
 #endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */
 
+	prev_tx = np->cur_tx;
 	entry = np->cur_tx % TX_RING_SIZE;
 	for (i = 0; i < skb_num_frags(skb); i++) {
 		int wrap_ring = 0;
@@ -1235,6 +1243,11 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 					       skb_frag_size(this_frag),
 					       PCI_DMA_TODEVICE);
 		}
+		if (pci_dma_mapping_error(np->pci_dev,
+					  np->tx_info[entry].mapping)) {
+			dev->stats.tx_dropped++;
+			goto err_out;
+		}
 
 		np->tx_ring[entry].addr = cpu_to_dma(np->tx_info[entry].mapping);
 		np->tx_ring[entry].status = cpu_to_le32(status);
@@ -1269,8 +1282,30 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 		netif_stop_queue(dev);
 
 	return NETDEV_TX_OK;
-}
 
+err_out:
+	entry = prev_tx % TX_RING_SIZE;
+	np->tx_info[entry].skb = NULL;
+	if (i > 0) {
+		pci_unmap_single(np->pci_dev,
+				 np->tx_info[entry].mapping,
+				 skb_first_frag_len(skb),
+				 PCI_DMA_TODEVICE);
+		np->tx_info[entry].mapping = 0;
+		entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE;
+		for (j = 1; j < i; j++) {
+			pci_unmap_single(np->pci_dev,
+					 np->tx_info[entry].mapping,
+					 skb_frag_size(
+						&skb_shinfo(skb)->frags[j-1]),
+					 PCI_DMA_TODEVICE);
+			entry++;
+		}
+	}
+	dev_kfree_skb_any(skb);
+	np->cur_tx = prev_tx;
+	return NETDEV_TX_OK;
+}
 
 /* The interrupt handler does all of the Rx thread work and cleans up
    after the Tx thread. */
@@ -1570,6 +1605,12 @@ static void refill_rx_ring(struct net_device *dev)
 				break;	/* Better luck next round. */
 			np->rx_info[entry].mapping =
 				pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+			if (pci_dma_mapping_error(np->pci_dev,
+						np->rx_info[entry].mapping)) {
+				dev_kfree_skb(skb);
+				np->rx_info[entry].skb = NULL;
+				break;
+			}
 			np->rx_ring[entry].rxaddr =
 				cpu_to_dma(np->rx_info[entry].mapping | RxDescValid);
 		}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index b6fa89102526..66ba1e0ff37e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -913,8 +913,8 @@
 #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX		2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH		1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX	3
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX	4
@@ -923,6 +923,8 @@
 #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX	6
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX	7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH	1
 
 #define RX_NORMAL_DESC0_OVT_INDEX		0
 #define RX_NORMAL_DESC0_OVT_WIDTH		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index f6a7161e3b85..75e6e7e6baed 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1658,10 +1658,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 
 	/* Get the header length */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 1);
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
 		if (rdata->rx.hdr_len)
 			pdata->ext_stats.rx_split_header_packets++;
+	} else {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 0);
 	}
 
 	/* Get the RSS hash */
@@ -1684,19 +1689,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		}
 	}
 
-	/* Get the packet length */
-	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
-	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
-		/* Not all the data has been transferred for this packet */
-		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-			       INCOMPLETE, 1);
+	/* Not all the data has been transferred for this packet */
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
 		return 0;
-	}
 
 	/* This is the last of the data for this packet */
 	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-		       INCOMPLETE, 0);
+		       LAST, 1);
+
+	/* Get the packet length */
+	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
 
 	/* Set checksum done indicator as appropriate */
 	if (netdev->features & NETIF_F_RXCSUM)
@@ -2730,8 +2732,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 
 	/* Flush Tx queues */
 	ret = xgbe_flush_tx_queues(pdata);
-	if (ret)
+	if (ret) {
+		netdev_err(pdata->netdev, "error flushing TX queues\n");
 		return ret;
+	}
 
 	/*
 	 * Initialize DMA related features
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 53ce1222b11d..64034ff081a0 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -877,7 +877,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	DBGPR("-->xgbe_start\n");
 
-	hw_if->init(pdata);
+	ret = hw_if->init(pdata);
+	if (ret)
+		return ret;
 
 	ret = phy_if->phy_start(pdata);
 	if (ret)
@@ -1760,13 +1762,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1775,30 +1776,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -1881,8 +1901,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -1892,7 +1912,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -1926,9 +1946,8 @@ read_again:
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -1937,7 +1956,7 @@ read_again:
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -1949,16 +1968,22 @@ read_again:
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -1968,13 +1993,14 @@ read_again:
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2033,7 +2059,7 @@ next_packet:
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index bd377a6b067d..df54475d163b 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -86,9 +86,14 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
 		if (!skb)
 			break;
+
+		/* Workround for the HW RX DMA overflow issue */
+		if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+			skb_reserve(skb, 64);
+
 		dma = dma_map_single(&alx->hw.pdev->dev,
 				     skb->data, alx->rxbuf_size,
 				     DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 8f76f4558a88..2ff465848b65 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1412,7 +1412,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = -EIO;
 
-	netdev->hw_features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
 
 	/* Init PHY as early as possible due to power saving issue  */
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index ecc4a334c507..0a54e7dac0ab 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -608,7 +608,7 @@ static void nb8800_mac_config(struct net_device *dev)
 		mac_mode |= HALF_DUPLEX;
 
 	if (gigabit) {
-		if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+		if (phy_interface_is_rgmii(dev->phydev))
 			mac_mode |= RGMII_MODE;
 
 		mac_mode |= GMAC_MODE;
@@ -1295,11 +1295,10 @@ static int nb8800_tangox_init(struct net_device *dev)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
-		pad_mode = PAD_MODE_RGMII;
-		break;
-
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+		pad_mode = PAD_MODE_RGMII;
 		break;
 
 	default:
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 858106352ce9..8860e74aa28f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -732,11 +732,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct bcm_sysport_cb *cb;
-	struct netdev_queue *txq;
 	u32 hw_ind;
 
-	txq = netdev_get_tx_queue(ndev, ring->index);
-
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -767,9 +764,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	ring->c_index = c_index;
 
-	if (netif_tx_queue_stopped(txq) && pkts_compl)
-		netif_tx_wake_queue(txq);
-
 	netif_dbg(priv, tx_done, ndev,
 		  "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
 		  ring->index, ring->c_index, pkts_compl, bytes_compl);
@@ -781,16 +775,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					   struct bcm_sysport_tx_ring *ring)
 {
+	struct netdev_queue *txq;
 	unsigned int released;
 	unsigned long flags;
 
+	txq = netdev_get_tx_queue(priv->netdev, ring->index);
+
 	spin_lock_irqsave(&ring->lock, flags);
 	released = __bcm_sysport_tx_reclaim(priv, ring);
+	if (released)
+		netif_tx_wake_queue(txq);
+
 	spin_unlock_irqrestore(&ring->lock, flags);
 
 	return released;
 }
 
+/* Locked version of the per-ring TX reclaim, but does not wake the queue */
+static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv,
+				 struct bcm_sysport_tx_ring *ring)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	__bcm_sysport_tx_reclaim(priv, ring);
+	spin_unlock_irqrestore(&ring->lock, flags);
+}
+
 static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcm_sysport_tx_ring *ring =
@@ -1275,7 +1286,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 	napi_disable(&ring->napi);
 	netif_napi_del(&ring->napi);
 
-	bcm_sysport_tx_reclaim(priv, ring);
+	bcm_sysport_tx_clean(priv, ring);
 
 	kfree(ring->cbs);
 	ring->cbs = NULL;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 28f7610b03fe..a5e4b4b93d1b 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -219,7 +219,7 @@ err_dma:
 	dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
 			 DMA_TO_DEVICE);
 
-	while (i > 0) {
+	while (i-- > 0) {
 		int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[index];
 		u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
@@ -255,15 +255,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 	while (ring->start != ring->end) {
 		int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[slot_idx];
-		u32 ctl1;
+		u32 ctl0, ctl1;
 		int len;
 
 		if (slot_idx == empty_slot)
 			break;
 
+		ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
 		ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
 		len = ctl1 & BGMAC_DESC_CTL1_LEN;
-		if (ctl1 & BGMAC_DESC_CTL0_SOF)
+		if (ctl0 & BGMAC_DESC_CTL0_SOF)
 			/* Unmap no longer used buffer */
 			dma_unmap_single(dma_dev, slot->dma_addr, len,
 					 DMA_TO_DEVICE);
@@ -314,6 +315,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 	u32 ctl;
 
 	ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+	/* preserve ONLY bits 16-17 from current hardware value */
+	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
 	if (bgmac->core->id.rev >= 4) {
 		ctl &= ~BGMAC_DMA_RX_BL_MASK;
 		ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -324,7 +329,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 		ctl &= ~BGMAC_DMA_RX_PT_MASK;
 		ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
 	}
-	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
 	ctl |= BGMAC_DMA_RX_ENABLE;
 	ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
 	ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;
@@ -466,6 +470,11 @@ static int bgmac_dma_rx_read(struct bgmac *bgmac, struct bgmac_dma_ring *ring,
 			len -= ETH_FCS_LEN;
 
 			skb = build_skb(buf, BGMAC_RX_ALLOC_SIZE);
+			if (unlikely(!skb)) {
+				bgmac_err(bgmac, "build_skb failed\n");
+				put_page(virt_to_head_page(buf));
+				break;
+			}
 			skb_put(skb, BGMAC_RX_FRAME_OFFSET +
 				BGMAC_RX_BUF_OFFSET + len);
 			skb_pull(skb, BGMAC_RX_FRAME_OFFSET +
@@ -1299,7 +1308,8 @@ static int bgmac_open(struct net_device *net_dev)
 
 	phy_start(bgmac->phy_dev);
 
-	netif_carrier_on(net_dev);
+	netif_start_queue(net_dev);
+
 	return 0;
 }
 
@@ -1573,6 +1583,11 @@ static int bgmac_probe(struct bcma_device *core)
 		dev_warn(&core->dev, "Using random MAC: %pM\n", mac);
 	}
 
+	/* This (reset &) enable is not preset in specs or reference driver but
+	 * Broadcom does it in arch PCI code when enabling fake PCI device.
+	 */
+	bcma_core_enable(core, 0);
+
 	/* Allocation and references */
 	net_dev = alloc_etherdev(sizeof(*bgmac));
 	if (!net_dev)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index c82ab87fcbe8..e5911ccb2148 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1949,7 +1949,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 2e611dc5f162..1c8123816745 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -14819,6 +14819,10 @@ static int bnx2x_get_fc_npiv(struct net_device *dev,
 	}
 
 	offset = SHMEM2_RD(bp, fc_npiv_nvram_tbl_addr[BP_PORT(bp)]);
+	if (!offset) {
+		DP(BNX2X_MSG_MCP, "No FC-NPIV in NVRAM\n");
+		goto out;
+	}
 	DP(BNX2X_MSG_MCP, "Offset of FC-NPIV in NVRAM: %08x\n", offset);
 
 	/* Read the table contents from nvram */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 07f5f239cb65..4744919440e0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2473,7 +2473,8 @@ static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = kzalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+	bp->ntp_fltr_bmap = kcalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+				    sizeof(long),
 				    GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 17f017ab4dac..f971d92f7b41 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1168,6 +1168,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
@@ -1195,15 +1196,15 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			pkts_compl++;
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
-			dma_unmap_single(&dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
-					 tx_cb_ptr->skb->len,
+					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
 			dev->stats.tx_bytes +=
 				dma_unmap_len(tx_cb_ptr, dma_len);
-			dma_unmap_page(&dev->dev,
+			dma_unmap_page(kdev,
 				       dma_unmap_addr(tx_cb_ptr, dma_addr),
 				       dma_unmap_len(tx_cb_ptr, dma_len),
 				       DMA_TO_DEVICE);
@@ -1308,7 +1309,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 	}
 
 	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
-	dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len);
 	length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
 			(priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
 			DMA_TX_APPEND_CRC;
@@ -1754,6 +1755,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 
 static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 {
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *cb;
 	int i;
 
@@ -1761,7 +1763,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 		cb = &priv->rx_cbs[i];
 
 		if (dma_unmap_addr(cb, dma_addr)) {
-			dma_unmap_single(&priv->dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(cb, dma_addr),
 					 priv->rx_buf_len, DMA_FROM_DEVICE);
 			dma_unmap_addr_set(cb, dma_addr, 0);
@@ -3493,7 +3495,8 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_suspend(priv->phydev);
 
 	netif_device_detach(dev);
 
@@ -3590,7 +3593,8 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_resume(priv->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 8bdfe53754ba..e96d1f95bb47 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -220,20 +220,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	udelay(60);
 }
 
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	/* Power up PHY */
-	bcmgenet_phy_power_set(dev, true);
-	/* enable APD */
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-	reg |= EXT_PWR_DN_EN_LD;
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	bcmgenet_mii_reset(dev);
-}
-
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
@@ -281,7 +267,6 @@ int bcmgenet_mii_config(struct net_device *dev)
 
 		if (priv->internal_phy) {
 			phy_name = "internal PHY";
-			bcmgenet_internal_phy_setup(dev);
 		} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 			phy_name = "MoCA";
 			bcmgenet_moca_phy_setup(priv);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ca5ac5d6f4e6..3613469dc5c6 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8722,11 +8722,14 @@ static void tg3_free_consistent(struct tg3 *tp)
 	tg3_mem_rx_release(tp);
 	tg3_mem_tx_release(tp);
 
+	/* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
+	tg3_full_lock(tp, 0);
 	if (tp->hw_stats) {
 		dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
 				  tp->hw_stats, tp->stats_mapping);
 		tp->hw_stats = NULL;
 	}
+	tg3_full_unlock(tp);
 }
 
 /*
@@ -12031,7 +12034,7 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	int ret;
 	u32 offset, len, b_offset, odd_len;
 	u8 *buf;
-	__be32 start, end;
+	__be32 start = 0, end;
 
 	if (tg3_flag(tp, NO_NVRAM) ||
 	    eeprom->magic != TG3_EEPROM_MAGIC)
@@ -18142,14 +18145,14 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We needn't recover from permanent error */
-	if (state == pci_channel_io_frozen)
-		tp->pcierr_recovery = true;
-
 	/* We probably don't have netdev yet */
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	/* We needn't recover from permanent error */
+	if (state == pci_channel_io_frozen)
+		tp->pcierr_recovery = true;
+
 	tg3_phy_stop(tp);
 
 	tg3_netif_stop(tp);
@@ -18246,7 +18249,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
 
 	rtnl_lock();
 
-	if (!netif_running(netdev))
+	if (!netdev || !netif_running(netdev))
 		goto done;
 
 	tg3_full_lock(tp, 0);
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 169059c92f80..8d54e7b41bbf 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -2405,9 +2405,9 @@ static int macb_init(struct platform_device *pdev)
 	if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII)
 		val = GEM_BIT(RGMII);
 	else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII &&
-		 (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII))
+		 (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
 		val = MACB_BIT(RMII);
-	else if (!(bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII))
+	else if (!(bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
 		val = MACB_BIT(MII);
 
 	if (bp->caps & MACB_CAPS_USRIO_HAS_CLKEN)
@@ -2738,7 +2738,7 @@ static int at91ether_init(struct platform_device *pdev)
 }
 
 static const struct macb_config at91sam9260_config = {
-	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII,
+	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
@@ -2751,21 +2751,22 @@ static const struct macb_config pc302gem_config = {
 };
 
 static const struct macb_config sama5d2_config = {
-	.caps = 0,
+	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
 
 static const struct macb_config sama5d3_config = {
-	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE,
+	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE
+	      | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
 
 static const struct macb_config sama5d4_config = {
-	.caps = 0,
+	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 4,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d83b0db77821..3f385ab94988 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -398,7 +398,7 @@
 /* Capability mask bits */
 #define MACB_CAPS_ISR_CLEAR_ON_WRITE		0x00000001
 #define MACB_CAPS_USRIO_HAS_CLKEN		0x00000002
-#define MACB_CAPS_USRIO_DEFAULT_IS_MII		0x00000004
+#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII	0x00000004
 #define MACB_CAPS_NO_GIGABIT_HALF		0x00000008
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index b89504405b72..cc1725616f9d 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2526,7 +2526,7 @@ static void handle_timestamp(struct octeon_device *oct,
 
 	octeon_swap_8B_data(&resp->timestamp, 1);
 
-	if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) {
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) != 0)) {
 		struct skb_shared_hwtstamps ts;
 		u64 ns = resp->timestamp;
 
@@ -2823,7 +2823,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		if (!g) {
 			netif_info(lio, tx_err, lio->netdev,
 				   "Transmit scatter gather: glist null!\n");
-			goto lio_xmit_failed;
+			goto lio_xmit_dma_failed;
 		}
 
 		cmdsetup.s.gather = 1;
@@ -2894,7 +2894,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	else
 		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
 	if (status == IQ_SEND_FAILED)
-		goto lio_xmit_failed;
+		goto lio_xmit_dma_failed;
 
 	netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n");
 
@@ -2908,12 +2908,13 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	return NETDEV_TX_OK;
 
+lio_xmit_dma_failed:
+	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
+			 ndata.datasize, DMA_TO_DEVICE);
 lio_xmit_failed:
 	stats->tx_dropped++;
 	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
 		   iq_no, stats->tx_dropped);
-	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
-			 ndata.datasize, DMA_TO_DEVICE);
 	recv_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 39ca6744a4e6..22471d283a95 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -116,6 +116,15 @@
 #define NIC_PF_INTR_ID_MBOX0		8
 #define NIC_PF_INTR_ID_MBOX1		9
 
+/* Minimum FIFO level before all packets for the CQ are dropped
+ *
+ * This value ensures that once a packet has been "accepted"
+ * for reception it will not get dropped due to non-availability
+ * of CQ descriptor. An errata in HW mandates this value to be
+ * atleast 0x100.
+ */
+#define NICPF_CQM_MIN_DROP_LEVEL       0x100
+
 /* Global timer for CQ timer thresh interrupts
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 5f24d11cb16a..16baaafed26c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -309,6 +309,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 static void nic_init_hw(struct nicpf *nic)
 {
 	int i;
+	u64 cqm_cfg;
 
 	/* Enable NIC HW block */
 	nic_reg_write(nic, NIC_PF_CFG, 0x3);
@@ -345,6 +346,11 @@ static void nic_init_hw(struct nicpf *nic)
 	/* Enable VLAN ethertype matching and stripping */
 	nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7,
 		      (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q);
+
+	/* Check if HW expected value is higher (could be in future chips) */
+	cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG);
+	if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL)
+		nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL);
 }
 
 /* Channel parse index configuration */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index dd536be20193..fab35a593898 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -21,7 +21,7 @@
 #define   NIC_PF_TCP_TIMER			(0x0060)
 #define   NIC_PF_BP_CFG				(0x0080)
 #define   NIC_PF_RRM_CFG			(0x0088)
-#define   NIC_PF_CQM_CF				(0x00A0)
+#define   NIC_PF_CQM_CFG			(0x00A0)
 #define   NIC_PF_CNM_CF				(0x00A8)
 #define   NIC_PF_CNM_STATUS			(0x00B0)
 #define   NIC_PF_CQ_AVG_CFG			(0x00C0)
@@ -170,7 +170,6 @@
 #define   NIC_QSET_SQ_0_7_DOOR			(0x010838)
 #define   NIC_QSET_SQ_0_7_STATUS		(0x010840)
 #define   NIC_QSET_SQ_0_7_DEBUG			(0x010848)
-#define   NIC_QSET_SQ_0_7_CNM_CHG		(0x010860)
 #define   NIC_QSET_SQ_0_7_STAT_0_1		(0x010900)
 
 #define   NIC_QSET_RBDR_0_1_CFG			(0x010C00)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index a12b2e38cf61..ff1d777f3ed9 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -380,7 +380,10 @@ static void nicvf_get_regs(struct net_device *dev,
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q);
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q);
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q);
-		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q);
+		/* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which
+		 * produces bus errors when read
+		 */
+		p[i++] = 0;
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q);
 		reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3);
 		p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index dde8dc720cd3..b7093b9cd1e8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -566,8 +566,7 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cmp_queue *cq,
-				  struct cqe_rx_t *cqe_rx, int cqe_type)
+				  struct cqe_rx_t *cqe_rx)
 {
 	struct sk_buff *skb;
 	struct nicvf *nic = netdev_priv(netdev);
@@ -583,7 +582,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx);
+	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
 	if (err && !cqe_rx->rb_cnt)
 		return;
 
@@ -674,8 +673,7 @@ loop:
 			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq,
-					      cq_desc, CQE_TYPE_RX);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
@@ -1117,7 +1115,6 @@ int nicvf_stop(struct net_device *netdev)
 
 	/* Clear multiqset info */
 	nic->pnicvf = nic;
-	nic->sqs_count = 0;
 
 	return 0;
 }
@@ -1346,6 +1343,9 @@ void nicvf_update_stats(struct nicvf *nic)
 	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
 				  stats->tx_bcast_frames_ok +
 				  stats->tx_mcast_frames_ok;
+	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
+				  stats->rx_bcast_frames +
+				  stats->rx_mcast_frames;
 	drv_stats->rx_drops = stats->rx_drop_red +
 			      stats->rx_drop_overrun;
 	drv_stats->tx_drops = stats->tx_drops;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 206b6a71a545..912ee28ab58b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -550,6 +550,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
 
 	/* Enable Receive queue */
+	memset(&rq_cfg, 0, sizeof(struct rq_cfg));
 	rq_cfg.ena = 1;
 	rq_cfg.tcp_ena = 0;
 	nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
@@ -582,6 +583,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(cq->dmem.phys_base));
 
 	/* Enable Completion queue */
+	memset(&cq_cfg, 0, sizeof(struct cq_cfg));
 	cq_cfg.ena = 1;
 	cq_cfg.reset = 0;
 	cq_cfg.caching = 0;
@@ -630,6 +632,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(sq->dmem.phys_base));
 
 	/* Enable send queue  & set queue size */
+	memset(&sq_cfg, 0, sizeof(struct sq_cfg));
 	sq_cfg.ena = 1;
 	sq_cfg.reset = 0;
 	sq_cfg.ldwb = 0;
@@ -666,6 +669,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
 
 	/* Enable RBDR  & set queue size */
 	/* Buffer size should be in multiples of 128 bytes */
+	memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg));
 	rbdr_cfg.ena = 1;
 	rbdr_cfg.reset = 0;
 	rbdr_cfg.ldwb = 0;
@@ -1410,16 +1414,12 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 }
 
 /* Check for errors in the receive cmp.queue entry */
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx)
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode) {
-		drv_stats->rx_frames_ok++;
+	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
-	}
 
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 033e8306e91c..5652c612e20b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -344,8 +344,7 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 /* Stats */
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx);
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
 int nicvf_check_cqe_tx_errs(struct nicvf *nic,
 			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 9df26c2263bc..42718cc7d4e8 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -549,7 +549,9 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 	}
 
 	/* Clear rcvflt bit (latching high) and read it back */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
 	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
 		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
 		if (bgx->use_training) {
@@ -568,13 +570,6 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	/* Wait for MAC RX to be ready */
-	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
-			 SMU_RX_CTL_STATUS, true)) {
-		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
-		return -1;
-	}
-
 	/* Wait for BGX RX to be idle */
 	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
 		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -587,29 +582,30 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
-		dev_err(&bgx->pdev->dev, "Receive fault\n");
-		return -1;
-	}
-
-	/* Receive link is latching low. Force it high and verify it */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
-	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
-			 SPU_STATUS1_RCV_LNK, false)) {
-		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
-		return -1;
-	}
-
+	/* Clear receive packet disable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
 	cfg &= ~SPU_MISC_CTL_RX_DIS;
 	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
-	return 0;
+
+	/* Check for MAC RX faults */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+	/* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+	cfg &= SMU_RX_CTL_STATUS;
+	if (!cfg)
+		return 0;
+
+	/* Rx local/remote fault seen.
+	 * Do lmac reinit to see if condition recovers
+	 */
+	bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+	return -1;
 }
 
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
-	u64 link;
+	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
 
@@ -619,8 +615,11 @@ static void bgx_poll_for_link(struct work_struct *work)
 	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
 		     SPU_STATUS1_RCV_LNK, false);
 
-	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
-	if (link & SPU_STATUS1_RCV_LNK) {
+	spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+	if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
 			lmac->last_speed = 40000;
@@ -634,9 +633,15 @@ static void bgx_poll_for_link(struct work_struct *work)
 	}
 
 	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up) {
+			if (bgx_xaui_check_link(lmac)) {
+				/* Errors, clear link_up state */
+				lmac->link_up = 0;
+				lmac->last_speed = SPEED_UNKNOWN;
+				lmac->last_duplex = DUPLEX_UNKNOWN;
+			}
+		}
 		lmac->last_link = lmac->link_up;
-		if (lmac->link_up)
-			bgx_xaui_check_link(lmac);
 	}
 
 	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -708,7 +713,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 {
 	struct lmac *lmac;
-	u64 cmrx_cfg;
+	u64 cfg;
 
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
@@ -717,9 +722,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 		destroy_workqueue(lmac->check_link);
 	}
 
-	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	cmrx_cfg &= ~(1 << 15);
-	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	/* Disable packet reception */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_RX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Give chance for Rx/Tx FIFO to get drained */
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+	/* Disable packet transmission */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_TX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Disable serdes lanes */
+        if (!lmac->is_sgmii)
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+        else
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
 	if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179363a1..42010d2e5ddf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
 #define BGX_CMRX_RX_STAT10		0xC0
 #define BGX_CMRX_RX_BP_DROP		0xC8
 #define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMRX_RX_FIFO_LEN		0x108
 #define BGX_CMR_RX_DMACX_CAM		0x200
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(x << 49)
@@ -50,6 +51,7 @@
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
 #define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_FIFO_LEN		0x518
 #define BGX_CMRX_TX_STAT0		0x600
 #define BGX_CMRX_TX_STAT1		0x608
 #define BGX_CMRX_TX_STAT2		0x610
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0d147610a06f..090e00650601 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2714,10 +2714,14 @@ static int cxgb_up(struct adapter *adap)
 		if (err)
 			goto irq_err;
 	}
+
+	mutex_lock(&uld_mutex);
 	enable_rx(adap);
 	t4_sge_start(adap);
 	t4_intr_enable(adap);
 	adap->flags |= FULL_INIT_DONE;
+	mutex_unlock(&uld_mutex);
+
 	notify_ulds(adap, CXGB4_STATE_UP);
 #if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 1795c935ff02..7b8638ddb673 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1052,7 +1052,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 
-	 if (status == MCC_STATUS_UNAUTHORIZED_REQUEST)
+	 if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
 
 	return status;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 8a1d9fffd7d6..26255862d1cf 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5260,9 +5260,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index ff665493ca97..52f2230062e7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -713,6 +713,8 @@ static int ethoc_open(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	napi_enable(&priv->napi);
+
 	ethoc_init_ring(priv, dev->mem_start);
 	ethoc_reset(priv);
 
@@ -725,7 +727,6 @@ static int ethoc_open(struct net_device *dev)
 	}
 
 	phy_start(priv->phy);
-	napi_enable(&priv->napi);
 
 	if (netif_msg_ifup(priv)) {
 		dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n",
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index b2a32209ffbf..ab716042bdd2 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -944,11 +944,11 @@ fec_restart(struct net_device *ndev)
 	 * enet-mac reset will reset mac address registers too,
 	 * so need to reconfigure it.
 	 */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
-		memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
-		writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW);
-		writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH);
-	}
+	memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
+	writel((__force u32)cpu_to_be32(temp_mac[0]),
+	       fep->hwp + FEC_ADDR_LOW);
+	writel((__force u32)cpu_to_be32(temp_mac[1]),
+	       fep->hwp + FEC_ADDR_HIGH);
 
 	/* Clear any outstanding interrupt. */
 	writel(0xffffffff, fep->hwp + FEC_IEVENT);
@@ -1557,9 +1557,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
 	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
-		clear_bit(queue_id, &fep->work_rx);
-		pkt_received += fec_enet_rx_queue(ndev,
+		int ret;
+
+		ret = fec_enet_rx_queue(ndev,
 					budget - pkt_received, queue_id);
+
+		if (ret < budget - pkt_received)
+			clear_bit(queue_id, &fep->work_rx);
+
+		pkt_received += ret;
 	}
 	return pkt_received;
 }
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3e233d924cce..4cd2a7d0124f 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1999,8 +1999,8 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue)
 		if (!rxb->page)
 			continue;
 
-		dma_unmap_single(rx_queue->dev, rxb->dma,
-				 PAGE_SIZE, DMA_FROM_DEVICE);
+		dma_unmap_page(rx_queue->dev, rxb->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
 		__free_page(rxb->page);
 
 		rxb->page = NULL;
@@ -2939,7 +2939,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 				size, GFAR_RXB_TRUESIZE);
 
 	/* try reuse page */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page)))
 		return false;
 
 	/* change offset to the other half */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index bdbd80423b17..9ff2881f933d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -900,9 +900,7 @@
 
 static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	writel(value, reg_addr + reg);
+	writel(value, base + reg);
 }
 
 #define dsaf_write_dev(a, reg, value) \
@@ -910,9 +908,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	return readl(reg_addr + reg);
+	return readl(base + reg);
 }
 
 #define dsaf_read_dev(a, reg) \
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 08cef0dfb5db..2fa54b0b0679 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -105,8 +105,8 @@ int hns_nic_net_xmit_hw(struct net_device *ndev,
 			struct hns_nic_ring_data *ring_data)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
-	struct device *dev = priv->dev;
 	struct hnae_ring *ring = ring_data->ring;
+	struct device *dev = ring_to_dev(ring);
 	struct netdev_queue *dev_queue;
 	struct skb_frag_struct *frag;
 	int buf_num;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 7af870a3c549..2f9b12cf9ee5 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool;
 
 static const char ibmveth_driver_name[] = "ibmveth";
 static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver";
-#define ibmveth_driver_version "1.05"
+#define ibmveth_driver_version "1.06"
 
 MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>");
 MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver");
@@ -137,6 +137,11 @@ static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter)
 	return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK;
 }
 
+static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter)
+{
+	return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_LRG_PKT;
+}
+
 static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
 {
 	return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
@@ -1172,6 +1177,53 @@ map_failed:
 	goto retry_bounce;
 }
 
+static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
+{
+	struct tcphdr *tcph;
+	int offset = 0;
+	int hdr_len;
+
+	/* only TCP packets will be aggregated */
+	if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)skb->data;
+
+		if (iph->protocol == IPPROTO_TCP) {
+			offset = iph->ihl * 4;
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+		} else {
+			return;
+		}
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *iph6 = (struct ipv6hdr *)skb->data;
+
+		if (iph6->nexthdr == IPPROTO_TCP) {
+			offset = sizeof(struct ipv6hdr);
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+		} else {
+			return;
+		}
+	} else {
+		return;
+	}
+	/* if mss is not set through Large Packet bit/mss in rx buffer,
+	 * expect that the mss will be written to the tcp header checksum.
+	 */
+	tcph = (struct tcphdr *)(skb->data + offset);
+	if (lrg_pkt) {
+		skb_shinfo(skb)->gso_size = mss;
+	} else if (offset) {
+		skb_shinfo(skb)->gso_size = ntohs(tcph->check);
+		tcph->check = 0;
+	}
+
+	if (skb_shinfo(skb)->gso_size) {
+		hdr_len = offset + tcph->doff * 4;
+		skb_shinfo(skb)->gso_segs =
+				DIV_ROUND_UP(skb->len - hdr_len,
+					     skb_shinfo(skb)->gso_size);
+	}
+}
+
 static int ibmveth_poll(struct napi_struct *napi, int budget)
 {
 	struct ibmveth_adapter *adapter =
@@ -1180,6 +1232,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	int frames_processed = 0;
 	unsigned long lpar_rc;
 	struct iphdr *iph;
+	u16 mss = 0;
 
 restart_poll:
 	while (frames_processed < budget) {
@@ -1197,9 +1250,21 @@ restart_poll:
 			int length = ibmveth_rxq_frame_length(adapter);
 			int offset = ibmveth_rxq_frame_offset(adapter);
 			int csum_good = ibmveth_rxq_csum_good(adapter);
+			int lrg_pkt = ibmveth_rxq_large_packet(adapter);
 
 			skb = ibmveth_rxq_get_buffer(adapter);
 
+			/* if the large packet bit is set in the rx queue
+			 * descriptor, the mss will be written by PHYP eight
+			 * bytes from the start of the rx buffer, which is
+			 * skb->data at this stage
+			 */
+			if (lrg_pkt) {
+				__be64 *rxmss = (__be64 *)(skb->data + 8);
+
+				mss = (u16)be64_to_cpu(*rxmss);
+			}
+
 			new_skb = NULL;
 			if (length < rx_copybreak)
 				new_skb = netdev_alloc_skb(netdev, length);
@@ -1233,11 +1298,15 @@ restart_poll:
 					if (iph->check == 0xffff) {
 						iph->check = 0;
 						iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
-						adapter->rx_large_packets++;
 					}
 				}
 			}
 
+			if (length > netdev->mtu + ETH_HLEN) {
+				ibmveth_rx_mss_helper(skb, mss, lrg_pkt);
+				adapter->rx_large_packets++;
+			}
+
 			napi_gro_receive(napi, skb);	/* send it up */
 
 			netdev->stats.rx_packets++;
@@ -1533,8 +1602,11 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
-	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
-		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	netdev->hw_features = NETIF_F_SG;
+	if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) {
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				       NETIF_F_RXCSUM;
+	}
 
 	netdev->features |= netdev->hw_features;
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 4eade67fe30c..7acda04d034e 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -209,6 +209,7 @@ struct ibmveth_rx_q_entry {
 #define IBMVETH_RXQ_TOGGLE		0x80000000
 #define IBMVETH_RXQ_TOGGLE_SHIFT	31
 #define IBMVETH_RXQ_VALID		0x40000000
+#define IBMVETH_RXQ_LRG_PKT		0x04000000
 #define IBMVETH_RXQ_NO_CSUM		0x02000000
 #define IBMVETH_RXQ_CSUM_GOOD		0x01000000
 #define IBMVETH_RXQ_OFF_MASK		0x0000FFFF
diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h
index 69707108d23c..98fe5a2cd6e3 100644
--- a/drivers/net/ethernet/intel/e1000/e1000.h
+++ b/drivers/net/ethernet/intel/e1000/e1000.h
@@ -213,8 +213,11 @@ struct e1000_rx_ring {
 };
 
 #define E1000_DESC_UNUSED(R)						\
-	((((R)->next_to_clean > (R)->next_to_use)			\
-	  ? 0 : (R)->count) + (R)->next_to_clean - (R)->next_to_use - 1)
+({									\
+	unsigned int clean = smp_load_acquire(&(R)->next_to_clean);	\
+	unsigned int use = READ_ONCE((R)->next_to_use);			\
+	(clean > use ? 0 : (R)->count) + clean - use - 1;		\
+})
 
 #define E1000_RX_DESC_EXT(R, i)						\
 	(&(((union e1000_rx_desc_extended *)((R).desc))[i]))
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index fd7be860c201..068023595d84 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3876,7 +3876,10 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 		eop_desc = E1000_TX_DESC(*tx_ring, eop);
 	}
 
-	tx_ring->next_to_clean = i;
+	/* Synchronize with E1000_DESC_UNUSED called from e1000_xmit_frame,
+	 * which will reuse the cleaned buffers.
+	 */
+	smp_store_release(&tx_ring->next_to_clean, i);
 
 	netdev_completed_queue(netdev, pkts_compl, bytes_compl);
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 0a854a47d31a..80ec587d510e 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1959,8 +1959,10 @@ static irqreturn_t e1000_intr_msix_rx(int __always_unused irq, void *data)
 	 * previous interrupt.
 	 */
 	if (rx_ring->set_itr) {
-		writel(1000000000 / (rx_ring->itr_val * 256),
-		       rx_ring->itr_register);
+		u32 itr = rx_ring->itr_val ?
+			  1000000000 / (rx_ring->itr_val * 256) : 0;
+
+		writel(itr, rx_ring->itr_register);
 		rx_ring->set_itr = 0;
 	}
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 14440200499b..48809e5d3f79 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -33,7 +33,7 @@
 #include "fm10k_pf.h"
 #include "fm10k_vf.h"
 
-#define FM10K_MAX_JUMBO_FRAME_SIZE	15358	/* Maximum supported size 15K */
+#define FM10K_MAX_JUMBO_FRAME_SIZE	15342	/* Maximum supported size 15K */
 
 #define MAX_QUEUES	FM10K_MAX_QUEUES_PF
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index e76a44cf330c..09281558bfbc 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1428,6 +1428,10 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	fm10k_for_each_ring(ring, q_vector->tx)
 		clean_complete &= fm10k_clean_tx_irq(q_vector, ring);
 
+	/* Handle case where we are called by netpoll with a budget of 0 */
+	if (budget <= 0)
+		return budget;
+
 	/* attempt to distribute budget to each queue fairly, but don't
 	 * allow the budget to go below 1 because we'll exit polling
 	 */
@@ -1966,8 +1970,10 @@ int fm10k_init_queueing_scheme(struct fm10k_intfc *interface)
 
 	/* Allocate memory for queues */
 	err = fm10k_alloc_q_vectors(interface);
-	if (err)
+	if (err) {
+		fm10k_reset_msix_capability(interface);
 		return err;
+	}
 
 	/* Map rings to devices, and map devices to physical queues */
 	fm10k_assign_rings(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 74be792f3f1b..7f3fb51bc37b 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -159,13 +159,30 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
 
 	fm10k_mbx_free_irq(interface);
 
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
 	/* delay any future reset requests */
 	interface->last_reset = jiffies + (10 * HZ);
 
 	/* reset and initialize the hardware so it is in a known state */
-	err = hw->mac.ops.reset_hw(hw) ? : hw->mac.ops.init_hw(hw);
-	if (err)
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&interface->pdev->dev, "reset_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
+	if (err) {
 		dev_err(&interface->pdev->dev, "init_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = fm10k_init_queueing_scheme(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err);
+		goto reinit_err;
+	}
 
 	/* reassociate interrupts */
 	fm10k_mbx_request_irq(interface);
@@ -193,6 +210,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
 
 	fm10k_iov_resume(interface->pdev);
 
+reinit_err:
+	if (err)
+		netif_device_detach(netdev);
+
 	rtnl_unlock();
 
 	clear_bit(__FM10K_RESETTING, &interface->state);
@@ -1101,6 +1122,10 @@ void fm10k_mbx_free_irq(struct fm10k_intfc *interface)
 	struct fm10k_hw *hw = &interface->hw;
 	int itr_reg;
 
+	/* no mailbox IRQ to free if MSI-X is not enabled */
+	if (!interface->msix_entries)
+		return;
+
 	/* disconnect the mailbox */
 	hw->mbx.ops.disconnect(hw, &hw->mbx);
 
@@ -1423,10 +1448,15 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface)
 		err = fm10k_mbx_request_irq_pf(interface);
 	else
 		err = fm10k_mbx_request_irq_vf(interface);
+	if (err)
+		return err;
 
 	/* connect mailbox */
-	if (!err)
-		err = hw->mbx.ops.connect(hw, &hw->mbx);
+	err = hw->mbx.ops.connect(hw, &hw->mbx);
+
+	/* if the mailbox failed to connect, then free IRQ */
+	if (err)
+		fm10k_mbx_free_irq(interface);
 
 	return err;
 }
@@ -1684,7 +1714,13 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
 	interface->last_reset = jiffies + (10 * HZ);
 
 	/* reset and initialize the hardware so it is in a known state */
-	err = hw->mac.ops.reset_hw(hw) ? : hw->mac.ops.init_hw(hw);
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&pdev->dev, "reset_hw failed: %d\n", err);
+		return err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
 	if (err) {
 		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
 		return err;
@@ -2071,8 +2107,10 @@ static int fm10k_resume(struct pci_dev *pdev)
 
 	/* reset hardware to known state */
 	err = hw->mac.ops.init_hw(&interface->hw);
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
 		return err;
+	}
 
 	/* reset statistics starting values */
 	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
@@ -2185,6 +2223,9 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		fm10k_close(netdev);
 
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
 	fm10k_mbx_free_irq(interface);
 
 	pci_disable_device(pdev);
@@ -2248,11 +2289,21 @@ static void fm10k_io_resume(struct pci_dev *pdev)
 	int err = 0;
 
 	/* reset hardware to known state */
-	hw->mac.ops.init_hw(&interface->hw);
+	err = hw->mac.ops.init_hw(&interface->hw);
+	if (err) {
+		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
+		return;
+	}
 
 	/* reset statistics starting values */
 	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
 
+	err = fm10k_init_queueing_scheme(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err);
+		return;
+	}
+
 	/* reassociate interrupts */
 	fm10k_mbx_request_irq(interface);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 318a212f0a78..35afd711d144 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -77,6 +77,7 @@ struct fm10k_hw;
 #define FM10K_PCIE_SRIOV_CTRL_VFARI		0x10
 
 #define FM10K_ERR_PARAM				-2
+#define FM10K_ERR_NO_RESOURCES			-3
 #define FM10K_ERR_REQUESTS_PENDING		-4
 #define FM10K_ERR_RESET_REQUESTED		-5
 #define FM10K_ERR_DMA_PENDING			-6
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index 36c8b0aa08fd..d512575c33f3 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -103,7 +103,14 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 	s32 err;
 	u16 i;
 
-	/* assume we always have at least 1 queue */
+	/* verify we have at least 1 queue */
+	if (!~fm10k_read_reg(hw, FM10K_TXQCTL(0)) ||
+	    !~fm10k_read_reg(hw, FM10K_RXQCTL(0))) {
+		err = FM10K_ERR_NO_RESOURCES;
+		goto reset_max_queues;
+	}
+
+	/* determine how many queues we have */
 	for (i = 1; tqdloc0 && (i < FM10K_MAX_QUEUES_POOL); i++) {
 		/* verify the Descriptor cache offsets are increasing */
 		tqdloc = ~fm10k_read_reg(hw, FM10K_TQDLOC(i));
@@ -119,7 +126,7 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 	/* shut down queues we own and reset DMA configuration */
 	err = fm10k_disable_queues_generic(hw, i);
 	if (err)
-		return err;
+		goto reset_max_queues;
 
 	/* record maximum queue count */
 	hw->mac.max_queues = i;
@@ -129,6 +136,11 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 			       FM10K_TXQCTL_VID_MASK) >> FM10K_TXQCTL_VID_SHIFT;
 
 	return 0;
+
+reset_max_queues:
+	hw->mac.max_queues = 0;
+
+	return err;
 }
 
 /* This structure defines the attibutes to be parsed below */
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 4dd3e26129b4..7e258a83ccab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -767,6 +767,8 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid);
 int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
 struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 					     bool is_vf, bool is_netdev);
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+			  bool is_vf, bool is_netdev);
 bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
 struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
 				      bool is_vf, bool is_netdev);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 2d74c6e4d7b6..1cf715c72683 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -302,13 +302,15 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
 	struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
-	u16 len = le16_to_cpu(aq_desc->datalen);
+	u16 len;
 	u8 *buf = (u8 *)buffer;
 	u16 i = 0;
 
 	if ((!(mask & hw->debug_mask)) || (desc == NULL))
 		return;
 
+	len = le16_to_cpu(aq_desc->datalen);
+
 	i40e_debug(hw, mask,
 		   "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
 		   le16_to_cpu(aq_desc->opcode),
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 3f385ffe420f..488a50d59dca 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2164,8 +2164,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
 			break;
@@ -2176,8 +2175,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
 			break;
@@ -2188,9 +2186,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
@@ -2202,9 +2198,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4a9873ec28c7..4edbab6ca7ef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1317,6 +1317,42 @@ struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 }
 
 /**
+ * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS
+ * @vsi: the VSI to be searched
+ * @macaddr: the mac address to be removed
+ * @is_vf: true if it is a VF
+ * @is_netdev: true if it is a netdev
+ *
+ * Removes a given MAC address from a VSI, regardless of VLAN
+ *
+ * Returns 0 for success, or error
+ **/
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+			  bool is_vf, bool is_netdev)
+{
+	struct i40e_mac_filter *f = NULL;
+	int changed = 0;
+
+	WARN(!spin_is_locked(&vsi->mac_filter_list_lock),
+	     "Missing mac_filter_list_lock\n");
+	list_for_each_entry(f, &vsi->mac_filter_list, list) {
+		if ((ether_addr_equal(macaddr, f->macaddr)) &&
+		    (is_vf == f->is_vf) &&
+		    (is_netdev == f->is_netdev)) {
+			f->counter--;
+			f->changed = true;
+			changed = 1;
+		}
+	}
+	if (changed) {
+		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+		vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+		return 0;
+	}
+	return -ENOENT;
+}
+
+/**
  * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM
  * @vsi: the PF Main VSI - inappropriate for any other VSI
  * @macaddr: the MAC address
@@ -1547,9 +1583,11 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
-	i40e_sync_vsi_filters(vsi, false);
 	ether_addr_copy(netdev->dev_addr, addr->sa_data);
-
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
 	return 0;
 }
 
@@ -1935,11 +1973,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 
 	/* Now process 'del_list' outside the lock */
 	if (!list_empty(&tmp_del_list)) {
+		int del_list_size;
+
 		filter_list_len = pf->hw.aq.asq_buf_size /
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
-		del_list = kcalloc(filter_list_len,
-			    sizeof(struct i40e_aqc_remove_macvlan_element_data),
-			    GFP_KERNEL);
+		del_list_size = filter_list_len *
+			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
+		del_list = kzalloc(del_list_size, GFP_KERNEL);
 		if (!del_list) {
 			i40e_cleanup_add_list(&tmp_add_list);
 
@@ -1971,7 +2011,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 						  NULL);
 				aq_err = pf->hw.aq.asq_last_status;
 				num_del = 0;
-				memset(del_list, 0, sizeof(*del_list));
+				memset(del_list, 0, del_list_size);
 
 				if (ret && aq_err != I40E_AQ_RC_ENOENT)
 					dev_err(&pf->pdev->dev,
@@ -2004,13 +2044,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 	}
 
 	if (!list_empty(&tmp_add_list)) {
+		int add_list_size;
 
 		/* do all the adds now */
 		filter_list_len = pf->hw.aq.asq_buf_size /
 			       sizeof(struct i40e_aqc_add_macvlan_element_data),
-		add_list = kcalloc(filter_list_len,
-			       sizeof(struct i40e_aqc_add_macvlan_element_data),
-			       GFP_KERNEL);
+		add_list_size = filter_list_len *
+			       sizeof(struct i40e_aqc_add_macvlan_element_data);
+		add_list = kzalloc(add_list_size, GFP_KERNEL);
 		if (!add_list) {
 			/* Purge element from temporary lists */
 			i40e_cleanup_add_list(&tmp_add_list);
@@ -2048,7 +2089,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 
 				if (ret)
 					break;
-				memset(add_list, 0, sizeof(*add_list));
+				memset(add_list, 0, add_list_size);
 			}
 			/* Entries from tmp_add_list were cloned from MAC
 			 * filter list, hence clean those cloned entries
@@ -2112,12 +2153,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 			 */
 			if (pf->cur_promisc != cur_promisc) {
 				pf->cur_promisc = cur_promisc;
-				if (grab_rtnl)
-					i40e_do_reset_safe(pf,
-						BIT(__I40E_PF_RESET_REQUESTED));
-				else
-					i40e_do_reset(pf,
-						BIT(__I40E_PF_RESET_REQUESTED));
+				set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
 			}
 		} else {
 			ret = i40e_aq_set_vsi_unicast_promiscuous(
@@ -2377,16 +2413,13 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 		}
 	}
 
-	/* Make sure to release before sync_vsi_filter because that
-	 * function will lock/unlock as necessary
-	 */
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		return 0;
-
-	return i40e_sync_vsi_filters(vsi, false);
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
+	return 0;
 }
 
 /**
@@ -2459,16 +2492,13 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
 		}
 	}
 
-	/* Make sure to release before sync_vsi_filter because that
-	 * function with lock/unlock as necessary
-	 */
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		return 0;
-
-	return i40e_sync_vsi_filters(vsi, false);
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
+	return 0;
 }
 
 /**
@@ -2711,6 +2741,11 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 		netif_set_xps_queue(ring->netdev, mask, ring->queue_index);
 		free_cpumask_var(mask);
 	}
+
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
 }
 
 /**
@@ -6685,6 +6720,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	struct i40e_hw *hw = &pf->hw;
 	u8 set_fc_aq_fail = 0;
 	i40e_status ret;
+	u32 val;
 	u32 v;
 
 	/* Now we wait for GRST to settle out.
@@ -6823,6 +6859,20 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		}
 	}
 
+	/* Reconfigure hardware for allowing smaller MSS in the case
+	 * of TSO, so that we avoid the MDD being fired and causing
+	 * a reset in the case of small MSS+TSO.
+	 */
+#define I40E_REG_MSS          0x000E64DC
+#define I40E_REG_MSS_MIN_MASK 0x3FF0000
+#define I40E_64BYTE_MSS       0x400000
+	val = rd32(hw, I40E_REG_MSS);
+	if ((val & I40E_REG_MSS_MIN_MASK) > I40E_64BYTE_MSS) {
+		val &= ~I40E_REG_MSS_MIN_MASK;
+		val |= I40E_64BYTE_MSS;
+		wr32(hw, I40E_REG_MSS, val);
+	}
+
 	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
 	    (pf->hw.aq.fw_maj_ver < 4)) {
 		msleep(75);
@@ -8545,7 +8595,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		return 0;
 
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode,
-				       nlflags, 0, 0, filter_mask, NULL);
+				       0, 0, nlflags, filter_mask, NULL);
 }
 
 #define I40E_MAX_TUNNEL_HDR_LEN 80
@@ -10183,6 +10233,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	u16 link_status;
 	int err;
 	u32 len;
+	u32 val;
 	u32 i;
 	u8 set_fc_aq_fail;
 
@@ -10493,6 +10544,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 i40e_stat_str(&pf->hw, err),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 
+	/* Reconfigure hardware for allowing smaller MSS in the case
+	 * of TSO, so that we avoid the MDD being fired and causing
+	 * a reset in the case of small MSS+TSO.
+	 */
+	val = rd32(hw, I40E_REG_MSS);
+	if ((val & I40E_REG_MSS_MIN_MASK) > I40E_64BYTE_MSS) {
+		val &= ~I40E_REG_MSS_MIN_MASK;
+		val |= I40E_64BYTE_MSS;
+		wr32(hw, I40E_REG_MSS, val);
+	}
+
 	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
 	    (pf->hw.aq.fw_maj_ver < 4)) {
 		msleep(75);
@@ -10791,6 +10853,12 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
 
 	dev_info(&pdev->dev, "%s: error %d\n", __func__, error);
 
+	if (!pf) {
+		dev_info(&pdev->dev,
+			 "Cannot recover - error happened during device probe\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
 	/* shutdown all operations */
 	if (!test_bit(__I40E_SUSPENDED, &pf->state)) {
 		rtnl_lock();
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 635b3ac17877..26c55bba4bf3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -235,6 +235,9 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 				 "Filter deleted for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 	}
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -312,6 +315,9 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				 fd_data->pctype, fd_data->fd_id);
 	}
 
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -387,6 +393,9 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		}
 	}
 
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -526,11 +535,7 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 					    struct i40e_tx_buffer *tx_buffer)
 {
 	if (tx_buffer->skb) {
-		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
-			kfree(tx_buffer->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buffer->skb);
-
+		dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
 					 dma_unmap_addr(tx_buffer, dma),
@@ -542,6 +547,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 			       dma_unmap_len(tx_buffer, len),
 			       DMA_TO_DEVICE);
 	}
+
+	if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
+		kfree(tx_buffer->raw_buf);
+
 	tx_buffer->next_to_watch = NULL;
 	tx_buffer->skb = NULL;
 	dma_unmap_len_set(tx_buffer, len, 0);
@@ -1416,31 +1425,12 @@ checksum_fail:
 }
 
 /**
- * i40e_rx_hash - returns the hash value from the Rx descriptor
- * @ring: descriptor ring
- * @rx_desc: specific descriptor
- **/
-static inline u32 i40e_rx_hash(struct i40e_ring *ring,
-			       union i40e_rx_desc *rx_desc)
-{
-	const __le64 rss_mask =
-		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
-			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
-
-	if ((ring->netdev->features & NETIF_F_RXHASH) &&
-	    (rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask)
-		return le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-	else
-		return 0;
-}
-
-/**
- * i40e_ptype_to_hash - get a hash type
+ * i40e_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
  * Returns a hash type to be used by skb_set_hash
  **/
-static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+static inline enum pkt_hash_types i40e_ptype_to_htype(u8 ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
 
@@ -1458,6 +1448,30 @@ static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
 }
 
 /**
+ * i40e_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ **/
+static inline void i40e_rx_hash(struct i40e_ring *ring,
+				union i40e_rx_desc *rx_desc,
+				struct sk_buff *skb,
+				u8 rx_ptype)
+{
+	u32 hash;
+	const __le64 rss_mask  =
+		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
+			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
+
+	if (ring->netdev->features & NETIF_F_RXHASH)
+		return;
+
+	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
+		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+		skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+	}
+}
+
+/**
  * i40e_clean_rx_irq_ps - Reclaim resources after receive; packet split
  * @rx_ring:  rx ring to clean
  * @budget:   how many cleans we're allowed
@@ -1606,8 +1620,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+
 		if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) {
 			i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status &
 					   I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
@@ -1736,8 +1750,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 		if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) {
 			i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status &
 					   I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 44462b40f2d7..e116d9a99b8e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -549,12 +549,15 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 			i40e_vsi_add_pvid(vsi, vf->port_vlan_id);
 
 		spin_lock_bh(&vsi->mac_filter_list_lock);
-		f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
-				    vf->port_vlan_id ? vf->port_vlan_id : -1,
-				    true, false);
-		if (!f)
-			dev_info(&pf->pdev->dev,
-				 "Could not allocate VF MAC addr\n");
+		if (is_valid_ether_addr(vf->default_lan_addr.addr)) {
+			f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
+				       vf->port_vlan_id ? vf->port_vlan_id : -1,
+				       true, false);
+			if (!f)
+				dev_info(&pf->pdev->dev,
+					 "Could not add MAC filter %pM for VF %d\n",
+					vf->default_lan_addr.addr, vf->vf_id);
+		}
 		f = i40e_add_filter(vsi, brdcast,
 				    vf->port_vlan_id ? vf->port_vlan_id : -1,
 				    true, false);
@@ -1680,8 +1683,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* delete addresses from the list */
 	for (i = 0; i < al->num_elements; i++)
-		i40e_del_filter(vsi, al->list[i].addr,
-				I40E_VLAN_ANY, true, false);
+		if (i40e_del_mac_all_vlan(vsi, al->list[i].addr, true, false)) {
+			ret = I40E_ERR_INVALID_MAC_ADDR;
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
+			goto error_param;
+		}
+
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 47e9a90d6b10..39db70a597ed 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -51,11 +51,7 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 					    struct i40e_tx_buffer *tx_buffer)
 {
 	if (tx_buffer->skb) {
-		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
-			kfree(tx_buffer->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buffer->skb);
-
+		dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
 					 dma_unmap_addr(tx_buffer, dma),
@@ -67,6 +63,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 			       dma_unmap_len(tx_buffer, len),
 			       DMA_TO_DEVICE);
 	}
+
+	if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
+		kfree(tx_buffer->raw_buf);
+
 	tx_buffer->next_to_watch = NULL;
 	tx_buffer->skb = NULL;
 	dma_unmap_len_set(tx_buffer, len, 0);
@@ -245,16 +245,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
-	/* check to see if there are any non-cache aligned descriptors
-	 * waiting to be written back, and kick the hardware to force
-	 * them to be written back in case of napi polling
-	 */
-	if (budget &&
-	    !((i & WB_STRIDE) == WB_STRIDE) &&
-	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
-	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
-		tx_ring->arm_wb = true;
-
 	netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
 						      tx_ring->queue_index),
 				  total_packets, total_bytes);
@@ -889,31 +879,12 @@ checksum_fail:
 }
 
 /**
- * i40e_rx_hash - returns the hash value from the Rx descriptor
- * @ring: descriptor ring
- * @rx_desc: specific descriptor
- **/
-static inline u32 i40e_rx_hash(struct i40e_ring *ring,
-			       union i40e_rx_desc *rx_desc)
-{
-	const __le64 rss_mask =
-		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
-			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
-
-	if ((ring->netdev->features & NETIF_F_RXHASH) &&
-	    (rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask)
-		return le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-	else
-		return 0;
-}
-
-/**
- * i40e_ptype_to_hash - get a hash type
+ * i40e_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
  * Returns a hash type to be used by skb_set_hash
  **/
-static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+static inline enum pkt_hash_types i40e_ptype_to_htype(u8 ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
 
@@ -931,6 +902,30 @@ static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
 }
 
 /**
+ * i40e_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ **/
+static inline void i40e_rx_hash(struct i40e_ring *ring,
+				union i40e_rx_desc *rx_desc,
+				struct sk_buff *skb,
+				u8 rx_ptype)
+{
+	u32 hash;
+	const __le64 rss_mask  =
+		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
+			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
+
+	if (ring->netdev->features & NETIF_F_RXHASH)
+		return;
+
+	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
+		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+		skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+	}
+}
+
+/**
  * i40e_clean_rx_irq_ps - Reclaim resources after receive; packet split
  * @rx_ring:  rx ring to clean
  * @budget:   how many cleans we're allowed
@@ -1071,8 +1066,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
@@ -1189,8 +1184,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
@@ -1770,6 +1764,9 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u32 td_tag = 0;
 	dma_addr_t dma;
 	u16 gso_segs;
+	u16 desc_count = 0;
+	bool tail_bump = true;
+	bool do_rs = false;
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -1810,6 +1807,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 			tx_desc++;
 			i++;
+			desc_count++;
+
 			if (i == tx_ring->count) {
 				tx_desc = I40E_TX_DESC(tx_ring, 0);
 				i = 0;
@@ -1829,6 +1828,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 		tx_desc++;
 		i++;
+		desc_count++;
+
 		if (i == tx_ring->count) {
 			tx_desc = I40E_TX_DESC(tx_ring, 0);
 			i = 0;
@@ -1843,35 +1844,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		tx_bi = &tx_ring->tx_bi[i];
 	}
 
-	/* Place RS bit on last descriptor of any packet that spans across the
-	 * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
-	 */
 #define WB_STRIDE 0x3
-	if (((i & WB_STRIDE) != WB_STRIDE) &&
-	    (first <= &tx_ring->tx_bi[i]) &&
-	    (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(td_cmd, td_offset, size, td_tag) |
-			cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP <<
-					 I40E_TXD_QW1_CMD_SHIFT);
-	} else {
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(td_cmd, td_offset, size, td_tag) |
-			cpu_to_le64((u64)I40E_TXD_CMD <<
-					 I40E_TXD_QW1_CMD_SHIFT);
-	}
-
-	netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
-						 tx_ring->queue_index),
-			     first->bytecount);
-
-	/* Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch.  (Only
-	 * applicable for weak-ordered memory model archs,
-	 * such as IA-64).
-	 */
-	wmb();
-
 	/* set next_to_watch value indicating a packet is present */
 	first->next_to_watch = tx_desc;
 
@@ -1881,15 +1854,78 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	tx_ring->next_to_use = i;
 
+	netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
+						 tx_ring->queue_index),
+						 first->bytecount);
 	i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	/* Algorithm to optimize tail and RS bit setting:
+	 * if xmit_more is supported
+	 *	if xmit_more is true
+	 *		do not update tail and do not mark RS bit.
+	 *	if xmit_more is false and last xmit_more was false
+	 *		if every packet spanned less than 4 desc
+	 *			then set RS bit on 4th packet and update tail
+	 *			on every packet
+	 *		else
+	 *			update tail and set RS bit on every packet.
+	 *	if xmit_more is false and last_xmit_more was true
+	 *		update tail and set RS bit.
+	 * else (kernel < 3.18)
+	 *	if every packet spanned less than 4 desc
+	 *		then set RS bit on 4th packet and update tail
+	 *		on every packet
+	 *	else
+	 *		set RS bit on EOP for every packet and update tail
+	 *
+	 * Optimization: wmb to be issued only in case of tail update.
+	 * Also optimize the Descriptor WB path for RS bit with the same
+	 * algorithm.
+	 *
+	 * Note: If there are less than 4 packets
+	 * pending and interrupts were disabled the service task will
+	 * trigger a force WB.
+	 */
+	if (skb->xmit_more  &&
+	    !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						    tx_ring->queue_index))) {
+		tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
+		tail_bump = false;
+	} else if (!skb->xmit_more &&
+		   !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						       tx_ring->queue_index)) &&
+		   (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) &&
+		   (tx_ring->packet_stride < WB_STRIDE) &&
+		   (desc_count < WB_STRIDE)) {
+		tx_ring->packet_stride++;
+	} else {
+		tx_ring->packet_stride = 0;
+		tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
+		do_rs = true;
+	}
+	if (do_rs)
+		tx_ring->packet_stride = 0;
+
+	tx_desc->cmd_type_offset_bsz =
+			build_ctob(td_cmd, td_offset, size, td_tag) |
+			cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD :
+						  I40E_TX_DESC_CMD_EOP) <<
+						  I40E_TXD_QW1_CMD_SHIFT);
+
 	/* notify HW of packet */
-	if (!skb->xmit_more ||
-	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
-						   tx_ring->queue_index)))
-		writel(i, tx_ring->tail);
-	else
+	if (!tail_bump)
 		prefetchw(tx_desc + 1);
 
+	if (tail_bump) {
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(i, tx_ring->tail);
+	}
+
 	return;
 
 dma_error:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index ebc1bf77f036..998976844e4e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -267,6 +267,8 @@ struct i40e_ring {
 
 	bool ring_active;		/* is ring online or not */
 	bool arm_wb;		/* do something to arm write back */
+	u8 packet_stride;
+#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
 
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 4790437a50ac..2ac62efc36f7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -477,54 +477,30 @@ static int i40evf_set_rss_hash_opt(struct i40evf_adapter *adapter,
 
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3))
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
-		default:
+		else
 			return -EINVAL;
-		}
 		break;
 	case TCP_V6_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3))
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
-		default:
+		else
 			return -EINVAL;
-		}
 		break;
 	case UDP_V4_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
-		default:
+		} else {
 			return -EINVAL;
 		}
 		break;
 	case UDP_V6_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
-		default:
+		} else {
 			return -EINVAL;
 		}
 		break;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 99d2cffae0cd..5f03ab3dfa19 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -1864,6 +1864,9 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter)
 {
 	int i;
 
+	if (!adapter->tx_rings)
+		return;
+
 	for (i = 0; i < adapter->num_active_queues; i++)
 		if (adapter->tx_rings[i]->desc)
 			i40evf_free_tx_resources(adapter->tx_rings[i]);
@@ -1932,6 +1935,9 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter)
 {
 	int i;
 
+	if (!adapter->rx_rings)
+		return;
+
 	for (i = 0; i < adapter->num_active_queues; i++)
 		if (adapter->rx_rings[i]->desc)
 			i40evf_free_rx_resources(adapter->rx_rings[i]);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index 32e620e1eb5c..5de3f52fd31f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -391,6 +391,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_ether_addr_list *veal;
 	int len, i = 0, count = 0;
 	struct i40evf_mac_filter *f;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -415,7 +416,9 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
 			sizeof(struct i40e_virtchnl_ether_addr);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_ether_addr_list) +
+		      (count * sizeof(struct i40e_virtchnl_ether_addr));
+		more = true;
 	}
 
 	veal = kzalloc(len, GFP_ATOMIC);
@@ -431,7 +434,8 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 			f->add = false;
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS,
 			   (u8 *)veal, len);
 	kfree(veal);
@@ -450,6 +454,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_ether_addr_list *veal;
 	struct i40evf_mac_filter *f, *ftmp;
 	int len, i = 0, count = 0;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -474,7 +479,9 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
 			sizeof(struct i40e_virtchnl_ether_addr);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_ether_addr_list) +
+		      (count * sizeof(struct i40e_virtchnl_ether_addr));
+		more = true;
 	}
 	veal = kzalloc(len, GFP_ATOMIC);
 	if (!veal)
@@ -490,7 +497,8 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 			kfree(f);
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS,
 			   (u8 *)veal, len);
 	kfree(veal);
@@ -509,6 +517,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vlan_filter_list *vvfl;
 	int len, i = 0, count = 0;
 	struct i40evf_vlan_filter *f;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -534,7 +543,9 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
 			sizeof(u16);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
+		      (count * sizeof(u16));
+		more = true;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
 	if (!vvfl)
@@ -549,7 +560,8 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 			f->add = false;
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len);
 	kfree(vvfl);
 }
@@ -567,6 +579,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vlan_filter_list *vvfl;
 	struct i40evf_vlan_filter *f, *ftmp;
 	int len, i = 0, count = 0;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -592,7 +605,9 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
 			sizeof(u16);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
+		      (count * sizeof(u16));
+		more = true;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
 	if (!vvfl)
@@ -608,7 +623,8 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 			kfree(f);
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len);
 	kfree(vvfl);
 }
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 7a73510e547c..97bf0c3d5c69 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -294,6 +294,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	case I210_I_PHY_ID:
 		phy->type		= e1000_phy_i210;
 		phy->ops.check_polarity	= igb_check_polarity_m88;
+		phy->ops.get_cfg_done	= igb_get_cfg_done_i210;
 		phy->ops.get_phy_info	= igb_get_phy_info_m88;
 		phy->ops.get_cable_length = igb_get_cable_length_m88_gen2;
 		phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82580;
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 65d931669f81..29f59c76878a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -900,3 +900,30 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw)
 	wr32(E1000_MDICNFG, mdicnfg);
 	return ret_val;
 }
+
+/**
+ *  igb_get_cfg_done_i210 - Read config done bit
+ *  @hw: pointer to the HW structure
+ *
+ *  Read the management control register for the config done bit for
+ *  completion status.  NOTE: silicon which is EEPROM-less will fail trying
+ *  to read the config done bit, so an error is *ONLY* logged and returns
+ *  0.  If we were to return with error, EEPROM-less silicon
+ *  would not be able to be reset or change link.
+ **/
+s32 igb_get_cfg_done_i210(struct e1000_hw *hw)
+{
+	s32 timeout = PHY_CFG_TIMEOUT;
+	u32 mask = E1000_NVM_CFG_DONE_PORT_0;
+
+	while (timeout) {
+		if (rd32(E1000_EEMNGCTL_I210) & mask)
+			break;
+		usleep_range(1000, 2000);
+		timeout--;
+	}
+	if (!timeout)
+		hw_dbg("MNG configuration cycle has not completed.\n");
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 3442b6357d01..eaa68a50cb3b 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -34,6 +34,7 @@ s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data);
 s32 igb_init_nvm_params_i210(struct e1000_hw *hw);
 bool igb_get_flash_presence_i210(struct e1000_hw *hw);
 s32 igb_pll_workaround_i210(struct e1000_hw *hw);
+s32 igb_get_cfg_done_i210(struct e1000_hw *hw);
 
 #define E1000_STM_OPCODE		0xDB00
 #define E1000_EEPROM_FLASH_SIZE_WORD	0x11
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 23ec28f43f6d..afaa98d1d4e4 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -77,6 +77,10 @@ s32 igb_get_phy_id(struct e1000_hw *hw)
 	s32 ret_val = 0;
 	u16 phy_id;
 
+	/* ensure PHY page selection to fix misconfigured i210 */
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
+		phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0);
+
 	ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id);
 	if (ret_val)
 		goto out;
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 4af2870e49f8..0fdcd4d1b982 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -66,6 +66,7 @@
 #define E1000_PBA      0x01000  /* Packet Buffer Allocation - RW */
 #define E1000_PBS      0x01008  /* Packet Buffer Size */
 #define E1000_EEMNGCTL 0x01010  /* MNG EEprom Control */
+#define E1000_EEMNGCTL_I210 0x12030  /* MNG EEprom Control */
 #define E1000_EEARBC_I210 0x12024  /* EEPROM Auto Read Bus Control */
 #define E1000_EEWR     0x0102C  /* EEPROM Write Register - RW */
 #define E1000_I2CCMD   0x01028  /* SFPI2C Command Register - RW */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 1a2f1cc44b28..e3cb93bdb21a 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -389,6 +389,8 @@ struct igb_adapter {
 	u16 link_speed;
 	u16 link_duplex;
 
+	u8 __iomem *io_addr; /* Mainly for iounmap use */
+
 	struct work_struct reset_task;
 	struct work_struct watchdog_task;
 	bool fc_autoneg;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ea7b09887245..fa3b4cbea23b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2294,9 +2294,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	err = -EIO;
-	hw->hw_addr = pci_iomap(pdev, 0, 0);
-	if (!hw->hw_addr)
+	adapter->io_addr = pci_iomap(pdev, 0, 0);
+	if (!adapter->io_addr)
 		goto err_ioremap;
+	/* hw->hw_addr can be altered, we'll use adapter->io_addr for unmap */
+	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igb_netdev_ops;
 	igb_set_ethtool_ops(netdev);
@@ -2656,7 +2658,7 @@ err_sw_init:
 #ifdef CONFIG_PCI_IOV
 	igb_disable_sriov(pdev);
 #endif
-	pci_iounmap(pdev, hw->hw_addr);
+	pci_iounmap(pdev, adapter->io_addr);
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
@@ -2823,7 +2825,7 @@ static void igb_remove(struct pci_dev *pdev)
 
 	igb_clear_interrupt_scheme(adapter);
 
-	pci_iounmap(pdev, hw->hw_addr);
+	pci_iounmap(pdev, adapter->io_addr);
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
 	pci_release_selected_regions(pdev,
@@ -2856,6 +2858,13 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
 		return;
 
+	/* Of the below we really only want the effect of getting
+	 * IGB_FLAG_HAS_MSIX set (if available), without which
+	 * igb_enable_sriov() has no effect.
+	 */
+	igb_set_interrupt_capability(adapter, true);
+	igb_reset_interrupt_capability(adapter);
+
 	pci_sriov_set_totalvfs(pdev, 7);
 	igb_enable_sriov(pdev, max_vfs);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index aed8d029b23d..cd9b284bc83b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2786,7 +2786,8 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 	ixgbe_for_each_ring(ring, q_vector->tx)
 		clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring);
 
-	if (!ixgbe_qv_lock_napi(q_vector))
+	/* Exit if we are called by netpoll or busy polling is active */
+	if ((budget <= 0) || !ixgbe_qv_lock_napi(q_vector))
 		return budget;
 
 	/* attempt to distribute budget to each queue fairly, but don't allow
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 060dd3922974..1257b18e6b90 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme)
 }
 
 static inline void
-jme_clear_pm(struct jme_adapter *jme)
+jme_clear_pm_enable_wol(struct jme_adapter *jme)
 {
 	jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs);
 }
 
+static inline void
+jme_clear_pm_disable_wol(struct jme_adapter *jme)
+{
+	jwrite32(jme, JME_PMCS, PMCS_STMASK);
+}
+
 static int
 jme_reload_eeprom(struct jme_adapter *jme)
 {
@@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev)
 	struct jme_adapter *jme = netdev_priv(netdev);
 	int rc;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	JME_NAPI_ENABLE(jme);
 
 	tasklet_init(&jme->linkch_task, jme_link_change_tasklet,
@@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme)
 static void
 jme_powersave_phy(struct jme_adapter *jme)
 {
-	if (jme->reg_pmcs) {
+	if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) {
 		jme_set_100m_half(jme);
 		if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN))
 			jme_wait_link(jme);
-		jme_clear_pm(jme);
+		jme_clear_pm_enable_wol(jme);
 	} else {
 		jme_phy_off(jme);
 	}
@@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev,
 	if (wol->wolopts & WAKE_MAGIC)
 		jme->reg_pmcs |= PMCS_MFEN;
 
-	jwrite32(jme, JME_PMCS, jme->reg_pmcs);
-	device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs));
-
 	return 0;
 }
 
@@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev,
 	jme->mii_if.mdio_read = jme_mdio_read;
 	jme->mii_if.mdio_write = jme_mdio_write;
 
-	jme_clear_pm(jme);
-	device_set_wakeup_enable(&pdev->dev, true);
+	jme_clear_pm_disable_wol(jme);
+	device_init_wakeup(&pdev->dev, true);
 
 	jme_set_phyfifo_5level(jme);
 	jme->pcirev = pdev->revision;
@@ -3304,7 +3307,7 @@ jme_resume(struct device *dev)
 	if (!netif_running(netdev))
 		return 0;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	jme_phy_on(jme);
 	if (test_bit(JME_FLAG_SSET, &jme->flags))
 		jme_set_settings(netdev, &jme->old_ecmd);
@@ -3312,13 +3315,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index d74f5f4e5782..07eabf72c480 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,10 +900,10 @@ static void korina_restart_task(struct work_struct *work)
 				DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
 				&lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
+	korina_free_ring(dev);
+
 	if (korina_init(dev) < 0) {
 		printk(KERN_ERR "%s: cannot restart device\n", dev->name);
 		return;
@@ -1064,12 +1064,12 @@ static int korina_close(struct net_device *dev)
 	tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
 	writel(tmp, &lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
 	cancel_work_sync(&lp->restart_task);
 
+	korina_free_ring(dev);
+
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
 	free_irq(lp->ovr_irq, dev);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ed622fa29dfa..15056f06754a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -226,7 +226,7 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		1
+#define MVNETA_TXDONE_COAL_PKTS		0	/* interrupt per packet */
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
@@ -2446,7 +2446,7 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 	mvneta_port_enable(pp);
 
 	/* Enable polling on the port */
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_enable(&port->napi);
@@ -2472,7 +2472,7 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	phy_stop(pp->phy_dev);
 
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_disable(&port->napi);
@@ -2902,13 +2902,11 @@ err_cleanup_rxqs:
 static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int cpu;
 
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
 	unregister_cpu_notifier(&pp->cpu_notifier);
-	for_each_present_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
@@ -3404,7 +3402,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
-	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
 	dev->gso_max_segs = MVNETA_MAX_TSO_SEGS;
 
 	err = register_netdev(dev);
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index a4beccf1fd46..0e67145bc418 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -772,6 +772,17 @@ struct mvpp2_rx_desc {
 	u32 reserved8;
 };
 
+struct mvpp2_txq_pcpu_buf {
+	/* Transmitted SKB */
+	struct sk_buff *skb;
+
+	/* Physical address of transmitted buffer */
+	dma_addr_t phys;
+
+	/* Size transmitted */
+	size_t size;
+};
+
 /* Per-CPU Tx queue control */
 struct mvpp2_txq_pcpu {
 	int cpu;
@@ -787,11 +798,8 @@ struct mvpp2_txq_pcpu {
 	/* Number of Tx DMA descriptors reserved for each CPU */
 	int reserved_num;
 
-	/* Array of transmitted skb */
-	struct sk_buff **tx_skb;
-
-	/* Array of transmitted buffers' physical addresses */
-	dma_addr_t *tx_buffs;
+	/* Infos about transmitted buffers */
+	struct mvpp2_txq_pcpu_buf *buffs;
 
 	/* Index of last TX DMA descriptor that was inserted */
 	int txq_put_index;
@@ -981,10 +989,11 @@ static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
 			      struct sk_buff *skb,
 			      struct mvpp2_tx_desc *tx_desc)
 {
-	txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb;
-	if (skb)
-		txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] =
-							 tx_desc->buf_phys_addr;
+	struct mvpp2_txq_pcpu_buf *tx_buf =
+		txq_pcpu->buffs + txq_pcpu->txq_put_index;
+	tx_buf->skb = skb;
+	tx_buf->size = tx_desc->data_size;
+	tx_buf->phys = tx_desc->buf_phys_addr + tx_desc->packet_offset;
 	txq_pcpu->txq_put_index++;
 	if (txq_pcpu->txq_put_index == txq_pcpu->size)
 		txq_pcpu->txq_put_index = 0;
@@ -4403,17 +4412,16 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 	int i;
 
 	for (i = 0; i < num; i++) {
-		dma_addr_t buf_phys_addr =
-				    txq_pcpu->tx_buffs[txq_pcpu->txq_get_index];
-		struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index];
+		struct mvpp2_txq_pcpu_buf *tx_buf =
+			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
 		mvpp2_txq_inc_get(txq_pcpu);
 
-		dma_unmap_single(port->dev->dev.parent, buf_phys_addr,
-				 skb_headlen(skb), DMA_TO_DEVICE);
-		if (!skb)
+		dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
+				 tx_buf->size, DMA_TO_DEVICE);
+		if (!tx_buf->skb)
 			continue;
-		dev_kfree_skb_any(skb);
+		dev_kfree_skb_any(tx_buf->skb);
 	}
 }
 
@@ -4664,15 +4672,10 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
 		txq_pcpu->size = txq->size;
-		txq_pcpu->tx_skb = kmalloc(txq_pcpu->size *
-					   sizeof(*txq_pcpu->tx_skb),
-					   GFP_KERNEL);
-		if (!txq_pcpu->tx_skb)
-			goto error;
-
-		txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size *
-					     sizeof(dma_addr_t), GFP_KERNEL);
-		if (!txq_pcpu->tx_buffs)
+		txq_pcpu->buffs = kmalloc(txq_pcpu->size *
+					  sizeof(struct mvpp2_txq_pcpu_buf),
+					  GFP_KERNEL);
+		if (!txq_pcpu->buffs)
 			goto error;
 
 		txq_pcpu->count = 0;
@@ -4686,8 +4689,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 error:
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
-		kfree(txq_pcpu->tx_skb);
-		kfree(txq_pcpu->tx_buffs);
+		kfree(txq_pcpu->buffs);
 	}
 
 	dma_free_coherent(port->dev->dev.parent,
@@ -4706,8 +4708,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
 
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
-		kfree(txq_pcpu->tx_skb);
-		kfree(txq_pcpu->tx_buffs);
+		kfree(txq_pcpu->buffs);
 	}
 
 	if (txq->descs)
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 5606a043063e..4b62aa1f9ff8 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume);
 
 static void sky2_shutdown(struct pci_dev *pdev)
 {
+	struct sky2_hw *hw = pci_get_drvdata(pdev);
+	int port;
+
+	for (port = 0; port < hw->ports; port++) {
+		struct net_device *ndev = hw->dev[port];
+
+		rtnl_lock();
+		if (netif_running(ndev)) {
+			dev_close(ndev);
+			netif_device_detach(ndev);
+		}
+		rtnl_unlock();
+	}
 	sky2_suspend(&pdev->dev);
 	pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
 	pci_set_power_state(pdev, PCI_D3hot);
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 715de8affcc9..e203d0c4e5a3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	return -ETIMEDOUT;
 }
 
-static int mlx4_comm_internal_err(u32 slave_read)
+int mlx4_comm_internal_err(u32 slave_read)
 {
 	return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
 		(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 3348e646db70..6eba58044456 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -101,13 +101,19 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
 {
 	struct mlx4_cq *cq;
 
+	rcu_read_lock();
 	cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
 			       cqn & (dev->caps.num_cqs - 1));
+	rcu_read_unlock();
+
 	if (!cq) {
 		mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
 		return;
 	}
 
+	/* Acessing the CQ outside of rcu_read_lock is safe, because
+	 * the CQ is freed only after interrupt handling is completed.
+	 */
 	++cq->arm_sn;
 
 	cq->comp(cq);
@@ -118,23 +124,19 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
 	struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
 	struct mlx4_cq *cq;
 
-	spin_lock(&cq_table->lock);
-
+	rcu_read_lock();
 	cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1));
-	if (cq)
-		atomic_inc(&cq->refcount);
-
-	spin_unlock(&cq_table->lock);
+	rcu_read_unlock();
 
 	if (!cq) {
-		mlx4_warn(dev, "Async event for bogus CQ %08x\n", cqn);
+		mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn);
 		return;
 	}
 
+	/* Acessing the CQ outside of rcu_read_lock is safe, because
+	 * the CQ is freed only after interrupt handling is completed.
+	 */
 	cq->event(cq, event_type);
-
-	if (atomic_dec_and_test(&cq->refcount))
-		complete(&cq->free);
 }
 
 static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
@@ -301,9 +303,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	if (err)
 		return err;
 
-	spin_lock_irq(&cq_table->lock);
+	spin_lock(&cq_table->lock);
 	err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
-	spin_unlock_irq(&cq_table->lock);
+	spin_unlock(&cq_table->lock);
 	if (err)
 		goto err_icm;
 
@@ -347,9 +349,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	return 0;
 
 err_radix:
-	spin_lock_irq(&cq_table->lock);
+	spin_lock(&cq_table->lock);
 	radix_tree_delete(&cq_table->tree, cq->cqn);
-	spin_unlock_irq(&cq_table->lock);
+	spin_unlock(&cq_table->lock);
 
 err_icm:
 	mlx4_cq_free_icm(dev, cq->cqn);
@@ -368,15 +370,15 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 	if (err)
 		mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);
 
+	spin_lock(&cq_table->lock);
+	radix_tree_delete(&cq_table->tree, cq->cqn);
+	spin_unlock(&cq_table->lock);
+
 	synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq);
 	if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq !=
 	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
 		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 
-	spin_lock_irq(&cq_table->lock);
-	radix_tree_delete(&cq_table->tree, cq->cqn);
-	spin_unlock_irq(&cq_table->lock);
-
 	if (atomic_dec_and_test(&cq->refcount))
 		complete(&cq->free);
 	wait_for_completion(&cq->free);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 67e9633ea9c7..232191417b93 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2282,7 +2282,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 	struct mlx4_en_dev *mdev = en_priv->mdev;
 	u64 mac_u64 = mlx4_mac_to_u64(mac);
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index e7a5000aa12c..82bf1b539d87 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -439,8 +439,14 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
 		ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn;
 
 		ring->stride = stride;
-		if (ring->stride <= TXBB_SIZE)
+		if (ring->stride <= TXBB_SIZE) {
+			/* Stamp first unused send wqe */
+			__be32 *ptr = (__be32 *)ring->buf;
+			__be32 stamp = cpu_to_be32(1 << STAMP_SHIFT);
+			*ptr = stamp;
+			/* Move pointer to start of rx section */
 			ring->buf += TXBB_SIZE;
+		}
 
 		ring->log_stride = ffs(ring->stride) - 1;
 		ring->buf_size = ring->size * ring->stride;
@@ -502,8 +508,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 		return;
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
-		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+			local_bh_disable();
 			napi_reschedule(&priv->rx_cq[ring]->napi);
+			local_bh_enable();
+		}
 	}
 }
 
@@ -704,7 +713,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 
 	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4421bf5463f6..e4019a803a9c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -400,7 +400,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 packets = 0;
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
-	u64 timestamp = 0;
 	int done = 0;
 	int budget = priv->tx_work_limit;
 	u32 last_nr_txbb;
@@ -440,9 +439,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
 		do {
+			u64 timestamp = 0;
+
 			txbbs_skipped += last_nr_txbb;
 			ring_index = (ring_index + last_nr_txbb) & size_mask;
-			if (ring->tx_info[ring_index].ts_requested)
+
+			if (unlikely(ring->tx_info[ring_index].ts_requested))
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 603d1c3d3b2e..ff77b8b608bd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -542,8 +542,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			break;
 
 		case MLX4_EVENT_TYPE_SRQ_LIMIT:
-			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
-				 __func__);
+			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
+				 __func__, be32_to_cpu(eqe->event.srq.srqn),
+				 eq->eqn);
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
 			if (mlx4_is_master(dev)) {
 				/* forward only to slave owning the SRQ */
@@ -558,15 +559,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						  eq->eqn, eq->cons_index, ret);
 					break;
 				}
-				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
-					  __func__, slave,
-					  be32_to_cpu(eqe->event.srq.srqn),
-					  eqe->type, eqe->subtype);
+				if (eqe->type ==
+				    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+					mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+						  __func__, slave,
+						  be32_to_cpu(eqe->event.srq.srqn),
+						  eqe->type, eqe->subtype);
 
 				if (!ret && slave != dev->caps.function) {
-					mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
-						  __func__, eqe->type,
-						  eqe->subtype, slave);
+					if (eqe->type ==
+					    MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)
+						mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+							  __func__, eqe->type,
+							  eqe->subtype, slave);
 					mlx4_slave_event(dev, slave, eqe);
 					break;
 				}
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 2a9dd460a95f..e1f9e7cebf8f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -118,8 +118,13 @@ static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
 	if (!buf)
 		return -ENOMEM;
 
+	if (offset_in_page(buf)) {
+		dma_free_coherent(dev, PAGE_SIZE << order,
+				  buf, sg_dma_address(mem));
+		return -ENOMEM;
+	}
+
 	sg_set_buf(mem, buf, PAGE_SIZE << order);
-	BUG_ON(mem->offset);
 	sg_dma_len(mem) = PAGE_SIZE << order;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0472941af820..1a134e08f010 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -218,6 +218,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	struct mlx4_interface *intf;
 
 	mlx4_stop_catas_poll(dev);
+	if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION &&
+	    mlx4_is_slave(dev)) {
+		/* In mlx4_remove_one on a VF */
+		u32 slave_read =
+			swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read));
+
+		if (mlx4_comm_internal_err(slave_read)) {
+			mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n",
+				 __func__);
+			mlx4_enter_error_state(dev->persist);
+		}
+	}
 	mutex_lock(&intf_mutex);
 
 	list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index e1cf9036af22..f5fdbd53d052 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1205,6 +1205,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type);
 void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 
 void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
+int mlx4_comm_internal_err(u32 slave_read);
 
 int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 		    enum mlx4_port_type *type);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index cad6c44df91c..d1fc7fa87b05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2955,6 +2955,9 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 		put_res(dev, slave, srqn, RES_SRQ);
 		qp->srq = srq;
 	}
+
+	/* Save param3 for dynamic changes from VST back to VGT */
+	qp->param3 = qpc->param3;
 	put_res(dev, slave, rcqn, RES_CQ);
 	put_res(dev, slave, mtt_base, RES_MTT);
 	res_end_move(dev, slave, RES_QP, qpn);
@@ -3132,7 +3135,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_RTS2RTS:
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
-			if (slave != mlx4_master_func_num(dev))
+			if (slave != mlx4_master_func_num(dev)) {
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
@@ -3151,6 +3154,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
 				}
+			}
 			break;
 		default:
 			break;
@@ -3746,7 +3750,6 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
 	int qpn = vhcr->in_modifier & 0x7fffff;
 	struct res_qp *qp;
 	u8 orig_sched_queue;
-	__be32	orig_param3 = qpc->param3;
 	u8 orig_vlan_control = qpc->pri_path.vlan_control;
 	u8 orig_fvl_rx = qpc->pri_path.fvl_rx;
 	u8 orig_pri_path_fl = qpc->pri_path.fl;
@@ -3788,7 +3791,6 @@ out:
 	 */
 	if (!err) {
 		qp->sched_queue = orig_sched_queue;
-		qp->param3	= orig_param3;
 		qp->vlan_control = orig_vlan_control;
 		qp->fvl_rx	=  orig_fvl_rx;
 		qp->pri_path_fl = orig_pri_path_fl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 037fc4cdf5af..6c66d2979795 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -143,13 +143,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
 	return cmd->cmd_buf + (idx << cmd->log_stride);
 }
 
-static u8 xor8_buf(void *buf, int len)
+static u8 xor8_buf(void *buf, size_t offset, int len)
 {
 	u8 *ptr = buf;
 	u8 sum = 0;
 	int i;
+	int end = len + offset;
 
-	for (i = 0; i < len; i++)
+	for (i = offset; i < end; i++)
 		sum ^= ptr[i];
 
 	return sum;
@@ -157,41 +158,49 @@ static u8 xor8_buf(void *buf, int len)
 
 static int verify_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+	int xor_len = sizeof(*block) - sizeof(block->data) - 1;
+
+	if (xor8_buf(block, rsvd0_off, xor_len) != 0xff)
 		return -EINVAL;
 
-	if (xor8_buf(block, sizeof(*block)) != 0xff)
+	if (xor8_buf(block, 0, sizeof(*block)) != 0xff)
 		return -EINVAL;
 
 	return 0;
 }
 
-static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token,
-			   int csum)
+static void calc_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	block->token = token;
-	if (csum) {
-		block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) -
-					    sizeof(block->data) - 2);
-		block->sig = ~xor8_buf(block, sizeof(*block) - 1);
-	}
+	int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2;
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+
+	block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len);
+	block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1);
 }
 
-static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum)
+static void calc_chain_sig(struct mlx5_cmd_msg *msg)
 {
 	struct mlx5_cmd_mailbox *next = msg->next;
-
-	while (next) {
-		calc_block_sig(next->buf, token, csum);
+	int size = msg->len;
+	int blen = size - min_t(int, sizeof(msg->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
+
+	for (i = 0; i < n && next; i++)  {
+		calc_block_sig(next->buf);
 		next = next->next;
 	}
 }
 
 static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
 {
-	ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay));
-	calc_chain_sig(ent->in, ent->token, csum);
-	calc_chain_sig(ent->out, ent->token, csum);
+	ent->lay->sig = ~xor8_buf(ent->lay, 0,  sizeof(*ent->lay));
+	if (csum) {
+		calc_chain_sig(ent->in);
+		calc_chain_sig(ent->out);
+	}
 }
 
 static void poll_timeout(struct mlx5_cmd_work_ent *ent)
@@ -222,12 +231,17 @@ static int verify_signature(struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd_mailbox *next = ent->out->next;
 	int err;
 	u8 sig;
+	int size = ent->out->len;
+	int blen = size - min_t(int, sizeof(ent->out->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
 
-	sig = xor8_buf(ent->lay, sizeof(*ent->lay));
+	sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
 	if (sig != 0xff)
 		return -EINVAL;
 
-	while (next) {
+	for (i = 0; i < n && next; i++) {
 		err = verify_block_sig(next->buf);
 		if (err)
 			return err;
@@ -616,6 +630,10 @@ static void dump_command(struct mlx5_core_dev *dev,
 		pr_debug("\n");
 }
 
+static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
+static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
+			      struct mlx5_cmd_msg *msg);
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -624,16 +642,27 @@ static void cmd_work_handler(struct work_struct *work)
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
+	int alloc_ret;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
-		ent->idx = alloc_ent(cmd);
-		if (ent->idx < 0) {
+		alloc_ret = alloc_ent(cmd);
+		if (alloc_ret < 0) {
+			if (ent->callback) {
+				ent->callback(-EAGAIN, ent->context);
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+				free_cmd(ent);
+			} else {
+				ent->ret = -EAGAIN;
+				complete(&ent->done);
+			}
 			mlx5_core_err(dev, "failed to allocate command entry\n");
 			up(sem);
 			return;
 		}
+		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
@@ -641,7 +670,6 @@ static void cmd_work_handler(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
-	ent->token = alloc_token(cmd);
 	cmd->ent_arr[ent->idx] = ent;
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
@@ -755,7 +783,8 @@ static u8 *get_status_ptr(struct mlx5_outbox_hdr *out)
 static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 			   struct mlx5_cmd_msg *out, void *uout, int uout_size,
 			   mlx5_cmd_cbk_t callback,
-			   void *context, int page_queue, u8 *status)
+			   void *context, int page_queue, u8 *status,
+			   u8 token)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -772,6 +801,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (IS_ERR(ent))
 		return PTR_ERR(ent);
 
+	ent->token = token;
+
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -844,7 +875,8 @@ static const struct file_operations fops = {
 	.write	= dbg_write,
 };
 
-static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
+static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size,
+			    u8 token)
 {
 	struct mlx5_cmd_prot_block *block;
 	struct mlx5_cmd_mailbox *next;
@@ -870,6 +902,7 @@ static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
 		memcpy(block->data, from, copy);
 		from += copy;
 		size -= copy;
+		block->token = token;
 		next = next->next;
 	}
 
@@ -939,7 +972,8 @@ static void free_cmd_box(struct mlx5_core_dev *dev,
 }
 
 static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
-					       gfp_t flags, int size)
+					       gfp_t flags, int size,
+					       u8 token)
 {
 	struct mlx5_cmd_mailbox *tmp, *head = NULL;
 	struct mlx5_cmd_prot_block *block;
@@ -968,6 +1002,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
 		tmp->next = head;
 		block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
 		block->block_num = cpu_to_be32(n - i - 1);
+		block->token = token;
 		head = tmp;
 	}
 	msg->next = head;
@@ -1351,7 +1386,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 	}
 
 	if (IS_ERR(msg))
-		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
+		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
 
 	return msg;
 }
@@ -1376,6 +1411,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	int err;
 	u8 status = 0;
 	u32 drv_synd;
+	u8 token;
 
 	if (pci_channel_offline(dev->pdev) ||
 	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -1394,20 +1430,22 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		return err;
 	}
 
-	err = mlx5_copy_to_msg(inb, in, in_size);
+	token = alloc_token(&dev->cmd);
+
+	err = mlx5_copy_to_msg(inb, in, in_size, token);
 	if (err) {
 		mlx5_core_warn(dev, "err %d\n", err);
 		goto out_in;
 	}
 
-	outb = mlx5_alloc_cmd_msg(dev, gfp, out_size);
+	outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token);
 	if (IS_ERR(outb)) {
 		err = PTR_ERR(outb);
 		goto out_in;
 	}
 
 	err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
-			      pages_queue, &status);
+			      pages_queue, &status, token);
 	if (err)
 		goto out_out;
 
@@ -1475,7 +1513,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev)
 	INIT_LIST_HEAD(&cmd->cache.med.head);
 
 	for (i = 0; i < NUM_LONG_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE);
+		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
 		if (IS_ERR(msg)) {
 			err = PTR_ERR(msg);
 			goto ex_err;
@@ -1485,7 +1523,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev)
 	}
 
 	for (i = 0; i < NUM_MED_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE);
+		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
 		if (IS_ERR(msg)) {
 			err = PTR_ERR(msg);
 			goto ex_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 2e022e900939..7cc9df717323 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -399,6 +399,9 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
+		return -ENOTSUPP;
+
 	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation_usec;
 	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts;
 	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation_usec;
@@ -416,11 +419,18 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	int tc;
 	int i;
 
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		return -ENOTSUPP;
+
+	mutex_lock(&priv->state_lock);
 	priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs;
 	priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames;
 	priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs;
 	priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames;
 
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
 	for (i = 0; i < priv->params.num_channels; ++i) {
 		c = priv->channel[i];
 
@@ -436,6 +446,8 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 					       coal->rx_max_coalesced_frames);
 	}
 
+out:
+	mutex_unlock(&priv->state_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1203d892e842..90e876ecc720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -863,12 +863,10 @@ static int mlx5e_open_cq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_cq;
 
-	err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
-					     moderation_usecs,
-					     moderation_frames);
-	if (err)
-		goto err_destroy_cq;
-
+	if (MLX5_CAP_GEN(mdev, cq_moderation))
+		mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
+					       moderation_usecs,
+					       moderation_frames);
 	return 0;
 
 err_destroy_cq:
@@ -1372,7 +1370,7 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	int hw_mtu;
+	u16 hw_mtu;
 	int err;
 
 	err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1);
@@ -1891,22 +1889,27 @@ static int mlx5e_set_features(struct net_device *netdev,
 	return err;
 }
 
+#define MXL5_HW_MIN_MTU 64
+#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN)
+
 static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	bool was_opened;
-	int max_mtu;
+	u16 max_mtu;
+	u16 min_mtu;
 	int err = 0;
 
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 
 	max_mtu = MLX5E_HW2SW_MTU(max_mtu);
+	min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU);
 
-	if (new_mtu > max_mtu) {
+	if (new_mtu > max_mtu || new_mtu < min_mtu) {
 		netdev_err(netdev,
-			   "%s: Bad MTU (%d) > (%d) Max\n",
-			   __func__, new_mtu, max_mtu);
+			   "%s: Bad MTU (%d), valid range is: [%d..%d]\n",
+			   __func__, new_mtu, min_mtu, max_mtu);
 		return -EINVAL;
 	}
 
@@ -1958,6 +1961,8 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
 	}
 	if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
 		mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		mlx5_core_warn(mdev, "CQ modiration is not supported\n");
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index cf0098596e85..e9408f5e2a1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -197,6 +197,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		/* Subtract one since we already counted this as one
+		 * "regular" packet in mlx5e_complete_rx_cqe()
+		 */
+		rq->stats.packets += lro_num_seg - 1;
 		rq->stats.lro_packets++;
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6cf6d93d8831..f5c1f4acc57b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -85,7 +85,7 @@ static struct mlx5_profile profile[] = {
 	[2] = {
 		.mask		= MLX5_PROF_MASK_QP_SIZE |
 				  MLX5_PROF_MASK_MR_CACHE,
-		.log_max_qp	= 17,
+		.log_max_qp	= 18,
 		.mr_cache[0]	= {
 			.size	= 500,
 			.limit	= 250
@@ -153,8 +153,9 @@ static struct mlx5_profile profile[] = {
 	},
 };
 
-#define FW_INIT_TIMEOUT_MILI	2000
-#define FW_INIT_WAIT_MS		2
+#define FW_INIT_TIMEOUT_MILI		2000
+#define FW_INIT_WAIT_MS			2
+#define FW_PRE_INIT_TIMEOUT_MILI	10000
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
 {
@@ -432,6 +433,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
 		 to_fw_pkey_sz(128));
 
+	/* Check log_max_qp from HCA caps to set in current profile */
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
+			       profile[prof_sel].log_max_qp,
+			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
 			 prof->log_max_qp);
@@ -505,7 +513,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int numa_node           = priv->numa_node;
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
@@ -513,7 +520,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 		return -ENOMEM;
 	}
 
-	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
 	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
@@ -928,6 +935,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	 */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
+	/* wait for firmware to accept initialization segments configurations
+	 */
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	if (err) {
+		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			FW_PRE_INIT_TIMEOUT_MILI);
+		goto out;
+	}
+
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index a87e773e93f3..53a793bc2e3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -246,8 +246,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
-static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
-				int *max_mtu, int *oper_mtu, u8 port)
+static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
+				u16 *max_mtu, u16 *oper_mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -267,7 +267,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
 		*admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu);
 }
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -282,14 +282,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu,
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port);
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu);
 
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index 142f33d978c5..a0fbe00dd690 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -206,21 +206,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1);
 /* pci_eqe_cmd_token
  * Command completion event - token
  */
-MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16);
+MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16);
 
 /* pci_eqe_cmd_status
  * Command completion event - status
  */
-MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8);
+MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8);
 
 /* pci_eqe_cmd_out_param_h
  * Command completion event - output parameter - higher part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32);
 
 /* pci_eqe_cmd_out_param_l
  * Command completion event - output parameter - lower part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3be4a2355ead..cb165c2d4803 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -390,6 +390,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 
 	if (eth_skb_pad(skb)) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4365c8bccc6d..605f6410f867 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -61,6 +61,8 @@ struct mlxsw_sp {
 #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100
 		unsigned int interval; /* ms */
 	} fdb_notify;
+#define MLXSW_SP_MIN_AGEING_TIME 10
+#define MLXSW_SP_MAX_AGEING_TIME 1000000
 #define MLXSW_SP_DEFAULT_AGEING_TIME 300
 	u32 ageing_time;
 	struct {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 7dbeafa65934..d4c4c2b5156c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -232,8 +232,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t);
 	u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000;
 
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (ageing_time < MLXSW_SP_MIN_AGEING_TIME ||
+		    ageing_time > MLXSW_SP_MAX_AGEING_TIME)
+			return -ERANGE;
+		else
+			return 0;
+	}
 
 	return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index d85960cfb694..fb2d9a82ce3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -313,6 +313,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
 	len = skb->len;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 50d5604833ed..e0993eba5df3 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2223,8 +2223,6 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-#ifdef CONFIG_PCI_MSI
-
 static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
 {
 	struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id;
@@ -2442,16 +2440,13 @@ static void vxge_rem_msix_isr(struct vxgedev *vdev)
 	if (vdev->config.intr_type == MSI_X)
 		pci_disable_msix(vdev->pdev);
 }
-#endif
 
 static void vxge_rem_isr(struct vxgedev *vdev)
 {
-#ifdef CONFIG_PCI_MSI
-	if (vdev->config.intr_type == MSI_X) {
+	if (IS_ENABLED(CONFIG_PCI_MSI) &&
+	    vdev->config.intr_type == MSI_X) {
 		vxge_rem_msix_isr(vdev);
-	} else
-#endif
-	if (vdev->config.intr_type == INTA) {
+	} else if (vdev->config.intr_type == INTA) {
 			synchronize_irq(vdev->pdev->irq);
 			free_irq(vdev->pdev->irq, vdev);
 	}
@@ -2460,11 +2455,10 @@ static void vxge_rem_isr(struct vxgedev *vdev)
 static int vxge_add_isr(struct vxgedev *vdev)
 {
 	int ret = 0;
-#ifdef CONFIG_PCI_MSI
 	int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0;
 	int pci_fun = PCI_FUNC(vdev->pdev->devfn);
 
-	if (vdev->config.intr_type == MSI_X)
+	if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X)
 		ret = vxge_enable_msix(vdev);
 
 	if (ret) {
@@ -2475,7 +2469,7 @@ static int vxge_add_isr(struct vxgedev *vdev)
 		vdev->config.intr_type = INTA;
 	}
 
-	if (vdev->config.intr_type == MSI_X) {
+	if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) {
 		for (intr_idx = 0;
 		     intr_idx < (vdev->no_of_vpath *
 			VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) {
@@ -2576,9 +2570,8 @@ static int vxge_add_isr(struct vxgedev *vdev)
 		vdev->vxge_entries[intr_cnt].in_use = 1;
 		vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[0];
 	}
-INTA_MODE:
-#endif
 
+INTA_MODE:
 	if (vdev->config.intr_type == INTA) {
 		snprintf(vdev->desc[0], VXGE_INTR_STRLEN,
 			"%s:vxge:INTA", vdev->ndev->name);
@@ -3889,12 +3882,12 @@ static void vxge_device_config_init(struct vxge_hw_device_config *device_config,
 	if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT)
 		max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT;
 
-#ifndef CONFIG_PCI_MSI
-	vxge_debug_init(VXGE_ERR,
-		"%s: This Kernel does not support "
-		"MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
-	*intr_type = INTA;
-#endif
+	if (!IS_ENABLED(CONFIG_PCI_MSI)) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: This Kernel does not support "
+			"MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
+		*intr_type = INTA;
+	}
 
 	/* Configure whether MSI-X or IRQL. */
 	switch (*intr_type) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 3dd548ab8df1..40365cb1abe6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -794,13 +794,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 			 * in a bitmap and increasing the chain consumer only
 			 * for the first successive completed entries.
 			 */
-			bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+			__set_bit(pos, p_spq->p_comp_bitmap);
 
 			while (test_bit(p_spq->comp_bitmap_idx,
 					p_spq->p_comp_bitmap)) {
-				bitmap_clear(p_spq->p_comp_bitmap,
-					     p_spq->comp_bitmap_idx,
-					     SPQ_RING_SIZE);
+				__clear_bit(p_spq->comp_bitmap_idx,
+					    p_spq->p_comp_bitmap);
 				p_spq->comp_bitmap_idx++;
 				qed_chain_return_produced(&p_spq->chain);
 			}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 46bbea8e023c..55007f1e6bbc 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -566,6 +566,7 @@ struct qlcnic_adapter_stats {
 	u64  tx_dma_map_error;
 	u64  spurious_intr;
 	u64  mac_filter_limit_overrun;
+	u64  mbx_spurious_intr;
 };
 
 /*
@@ -1099,7 +1100,7 @@ struct qlcnic_mailbox {
 	unsigned long		status;
 	spinlock_t		queue_lock;	/* Mailbox queue lock */
 	spinlock_t		aen_lock;	/* Mailbox response/AEN lock */
-	atomic_t		rsp_status;
+	u32			rsp_status;
 	u32			num_cmds;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 37a731be7d39..f9640d5ce6ba 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -491,7 +491,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter)
 
 static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx)
 {
-	atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED);
+	mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	complete(&mbx->completion);
 }
 
@@ -510,7 +510,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter)
 	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
 	} else {
-		if (atomic_read(&mbx->rsp_status) != rsp_status)
+		if (mbx->rsp_status != rsp_status)
 			qlcnic_83xx_notify_mbx_response(mbx);
 	}
 out:
@@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter)
 		if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
 		} else {
-			if (atomic_read(&mbx->rsp_status) != rsp_status)
+			if (mbx->rsp_status != rsp_status)
 				qlcnic_83xx_notify_mbx_response(mbx);
 		}
 	}
@@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 
 static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 {
+	u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	struct qlcnic_adapter *adapter = data;
 	struct qlcnic_mailbox *mbx;
-	u32 mask, resp, event;
 	unsigned long flags;
 
 	mbx = adapter->ahw->mailbox;
@@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 		goto out;
 
 	event = readl(QLCNIC_MBX_FW(adapter->ahw, 0));
-	if (event &  QLCNIC_MBX_ASYNC_EVENT)
+	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
-	else
-		qlcnic_83xx_notify_mbx_response(mbx);
+	} else {
+		if (mbx->rsp_status != rsp_status)
+			qlcnic_83xx_notify_mbx_response(mbx);
+		else
+			adapter->stats.mbx_spurious_intr++;
+	}
 
 out:
 	mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK);
@@ -4050,10 +4054,10 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct qlcnic_adapter *adapter = mbx->adapter;
 	const struct qlcnic_mbx_ops *mbx_ops = mbx->ops;
 	struct device *dev = &adapter->pdev->dev;
-	atomic_t *rsp_status = &mbx->rsp_status;
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
+	unsigned long flags;
 
 	ahw = adapter->ahw;
 
@@ -4063,7 +4067,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
-		atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT);
+		spin_lock_irqsave(&mbx->aen_lock, flags);
+		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
+		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
 		spin_lock(&mbx->queue_lock);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 494e8105adee..0a2318cad34d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = {
 	 QLC_OFF(stats.mac_filter_limit_overrun)},
 	{"spurious intr", QLC_SIZEOF(stats.spurious_intr),
 	 QLC_OFF(stats.spurious_intr)},
-
+	{"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr),
+	 QLC_OFF(stats.mbx_spurious_intr)},
 };
 
 static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = {
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 997976426799..b28e73ea2c25 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev,
 		return;
 	}
 	skb_reserve(new_skb, NET_IP_ALIGN);
+
+	pci_dma_sync_single_for_cpu(qdev->pdev,
+				    dma_unmap_addr(sbq_desc, mapaddr),
+				    dma_unmap_len(sbq_desc, maplen),
+				    PCI_DMA_FROMDEVICE);
+
 	memcpy(skb_put(new_skb, length), skb->data, length);
+
+	pci_dma_sync_single_for_device(qdev->pdev,
+				       dma_unmap_addr(sbq_desc, mapaddr),
+				       dma_unmap_len(sbq_desc, maplen),
+				       PCI_DMA_FROMDEVICE);
 	skb = new_skb;
 
 	/* Frame error, so drop the packet. */
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 689a4a5c8dcf..1ef03939d25f 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 79ef799f88ab..c5ea1018cb47 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -326,6 +326,7 @@ enum cfg_version {
 static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 467d41698fd5..585e90f8341d 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -171,34 +171,67 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = ravb_get_mdio_data,
 };
 
-/* Free skb's and DMA buffers for Ethernet AVB */
-static void ravb_ring_free(struct net_device *ndev, int q)
+/* Free TX skb function for AVB-IP */
+static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int ring_size;
-	int i;
+	struct net_device_stats *stats = &priv->stats[q];
+	struct ravb_tx_desc *desc;
+	int free_num = 0;
+	int entry;
+	u32 size;
 
-	/* Free RX skb ringbuffer */
-	if (priv->rx_skb[q]) {
-		for (i = 0; i < priv->num_rx_ring[q]; i++)
-			dev_kfree_skb(priv->rx_skb[q][i]);
-	}
-	kfree(priv->rx_skb[q]);
-	priv->rx_skb[q] = NULL;
+	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
+		bool txed;
 
-	/* Free TX skb ringbuffer */
-	if (priv->tx_skb[q]) {
-		for (i = 0; i < priv->num_tx_ring[q]; i++)
-			dev_kfree_skb(priv->tx_skb[q][i]);
+		entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
+					     NUM_TX_DESC);
+		desc = &priv->tx_ring[q][entry];
+		txed = desc->die_dt == DT_FEMPTY;
+		if (free_txed_only && !txed)
+			break;
+		/* Descriptor type must be checked before all other reads */
+		dma_rmb();
+		size = le16_to_cpu(desc->ds_tagl) & TX_DS;
+		/* Free the original skb. */
+		if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
+			dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
+					 size, DMA_TO_DEVICE);
+			/* Last packet descriptor? */
+			if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
+				entry /= NUM_TX_DESC;
+				dev_kfree_skb_any(priv->tx_skb[q][entry]);
+				priv->tx_skb[q][entry] = NULL;
+				if (txed)
+					stats->tx_packets++;
+			}
+			free_num++;
+		}
+		if (txed)
+			stats->tx_bytes += size;
+		desc->die_dt = DT_EEMPTY;
 	}
-	kfree(priv->tx_skb[q]);
-	priv->tx_skb[q] = NULL;
+	return free_num;
+}
 
-	/* Free aligned TX buffers */
-	kfree(priv->tx_align[q]);
-	priv->tx_align[q] = NULL;
+/* Free skb's and DMA buffers for Ethernet AVB */
+static void ravb_ring_free(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int ring_size;
+	int i;
 
 	if (priv->rx_ring[q]) {
+		for (i = 0; i < priv->num_rx_ring[q]; i++) {
+			struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
+
+			if (!dma_mapping_error(ndev->dev.parent,
+					       le32_to_cpu(desc->dptr)))
+				dma_unmap_single(ndev->dev.parent,
+						 le32_to_cpu(desc->dptr),
+						 PKT_BUF_SZ,
+						 DMA_FROM_DEVICE);
+		}
 		ring_size = sizeof(struct ravb_ex_rx_desc) *
 			    (priv->num_rx_ring[q] + 1);
 		dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
@@ -207,12 +240,32 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	}
 
 	if (priv->tx_ring[q]) {
+		ravb_tx_free(ndev, q, false);
+
 		ring_size = sizeof(struct ravb_tx_desc) *
 			    (priv->num_tx_ring[q] * NUM_TX_DESC + 1);
 		dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q],
 				  priv->tx_desc_dma[q]);
 		priv->tx_ring[q] = NULL;
 	}
+
+	/* Free RX skb ringbuffer */
+	if (priv->rx_skb[q]) {
+		for (i = 0; i < priv->num_rx_ring[q]; i++)
+			dev_kfree_skb(priv->rx_skb[q][i]);
+	}
+	kfree(priv->rx_skb[q]);
+	priv->rx_skb[q] = NULL;
+
+	/* Free aligned TX buffers */
+	kfree(priv->tx_align[q]);
+	priv->tx_align[q] = NULL;
+
+	/* Free TX skb ringbuffer.
+	 * SKBs are freed by ravb_tx_free() call above.
+	 */
+	kfree(priv->tx_skb[q]);
+	priv->tx_skb[q] = NULL;
 }
 
 /* Format skb and descriptor buffer for Ethernet AVB */
@@ -420,44 +473,6 @@ static int ravb_dmac_init(struct net_device *ndev)
 	return 0;
 }
 
-/* Free TX skb function for AVB-IP */
-static int ravb_tx_free(struct net_device *ndev, int q)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	struct net_device_stats *stats = &priv->stats[q];
-	struct ravb_tx_desc *desc;
-	int free_num = 0;
-	int entry;
-	u32 size;
-
-	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
-		entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
-					     NUM_TX_DESC);
-		desc = &priv->tx_ring[q][entry];
-		if (desc->die_dt != DT_FEMPTY)
-			break;
-		/* Descriptor type must be checked before all other reads */
-		dma_rmb();
-		size = le16_to_cpu(desc->ds_tagl) & TX_DS;
-		/* Free the original skb. */
-		if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
-			dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
-					 size, DMA_TO_DEVICE);
-			/* Last packet descriptor? */
-			if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
-				entry /= NUM_TX_DESC;
-				dev_kfree_skb_any(priv->tx_skb[q][entry]);
-				priv->tx_skb[q][entry] = NULL;
-				stats->tx_packets++;
-			}
-			free_num++;
-		}
-		stats->tx_bytes += size;
-		desc->die_dt = DT_EEMPTY;
-	}
-	return free_num;
-}
-
 static void ravb_get_tx_tstamp(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -797,7 +812,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 			spin_lock_irqsave(&priv->lock, flags);
 			/* Clear TX interrupt */
 			ravb_write(ndev, ~mask, TIS);
-			ravb_tx_free(ndev, q);
+			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
 			mmiowb();
 			spin_unlock_irqrestore(&priv->lock, flags);
@@ -1330,6 +1345,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
 		 entry / NUM_TX_DESC * DPTR_ALIGN;
 	len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data;
+	/* Zero length DMA descriptors are problematic as they seem to
+	 * terminate DMA transfers. Avoid them by simply using a length of
+	 * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN.
+	 *
+	 * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of
+	 * data by the call to skb_put_padto() above this is safe with
+	 * respect to both the length of the first DMA descriptor (len)
+	 * overflowing the available data and the length of the second DMA
+	 * descriptor (skb->len - len) being negative.
+	 */
+	if (len == 0)
+		len = DPTR_ALIGN;
+
 	memcpy(buffer, skb->data, len);
 	dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE);
 	if (dma_mapping_error(ndev->dev.parent, dma_addr))
@@ -1380,7 +1408,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	priv->cur_tx[q] += NUM_TX_DESC;
 	if (priv->cur_tx[q] - priv->dirty_tx[q] >
-	    (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q))
+	    (priv->num_tx_ring[q] - 1) * NUM_TX_DESC &&
+	    !ravb_tx_free(ndev, q, true))
 		netif_stop_subqueue(ndev, q);
 
 exit:
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 6a8fc0f341ff..479af106aaeb 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -750,6 +750,7 @@ static struct sh_eth_cpu_data sh7734_data = {
 	.tsu		= 1,
 	.hw_crc		= 1,
 	.select_mii	= 1,
+	.shift_rd0	= 1,
 };
 
 /* SH7763 */
@@ -818,6 +819,7 @@ static struct sh_eth_cpu_data r8a7740_data = {
 	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
+	.hw_crc		= 1,
 	.tsu		= 1,
 	.select_mii	= 1,
 	.shift_rd0	= 1,
@@ -832,7 +834,7 @@ static struct sh_eth_cpu_data r7s72100_data = {
 
 	.ecsr_value	= ECSR_ICD,
 	.ecsipr_value	= ECSIPR_ICDIP,
-	.eesipr_value	= 0xff7f009f,
+	.eesipr_value	= 0xe77f009f,
 
 	.tx_check	= EESR_TC1 | EESR_FTC,
 	.eesr_err_check	= EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT |
@@ -1185,11 +1187,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		sh_eth_set_receive_align(skb);
 
-		/* RX descriptor */
-		rxdesc = &mdp->rx_ring[i];
 		/* The size of the buffer is a multiple of 32 bytes. */
 		buf_len = ALIGN(mdp->rx_buf_sz, 32);
-		rxdesc->len = cpu_to_edmac(mdp, buf_len << 16);
 		dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len,
 					  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&ndev->dev, dma_addr)) {
@@ -1197,6 +1196,10 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		}
 		mdp->rx_skbuff[i] = skb;
+
+		/* RX descriptor */
+		rxdesc = &mdp->rx_ring[i];
+		rxdesc->len = cpu_to_edmac(mdp, buf_len << 16);
 		rxdesc->addr = cpu_to_edmac(mdp, dma_addr);
 		rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP);
 
@@ -1212,7 +1215,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	mdp->dirty_rx = (u32) (i - mdp->num_rx_ring);
 
 	/* Mark the last entry as wrapping the ring. */
-	rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE);
+	if (rxdesc)
+		rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE);
 
 	memset(mdp->tx_ring, 0, tx_ringsize);
 
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 52ec3d6e056a..3920c3eb6006 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -239,6 +239,7 @@ struct rocker {
 	struct {
 		u64 id;
 	} hw;
+	unsigned long ageing_time;
 	spinlock_t cmd_ring_lock;		/* for cmd ring accesses */
 	struct rocker_dma_ring_info cmd_ring;
 	struct rocker_dma_ring_info event_ring;
@@ -3704,7 +3705,7 @@ static void rocker_fdb_cleanup(unsigned long data)
 	struct rocker_port *rocker_port;
 	struct rocker_fdb_tbl_entry *entry;
 	struct hlist_node *tmp;
-	unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME;
+	unsigned long next_timer = jiffies + rocker->ageing_time;
 	unsigned long expires;
 	unsigned long lock_flags;
 	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE |
@@ -4367,8 +4368,12 @@ static int rocker_port_bridge_ageing_time(struct rocker_port *rocker_port,
 					  struct switchdev_trans *trans,
 					  u32 ageing_time)
 {
+	struct rocker *rocker = rocker_port->rocker;
+
 	if (!switchdev_trans_ph_prepare(trans)) {
 		rocker_port->ageing_time = clock_t_to_jiffies(ageing_time);
+		if (rocker_port->ageing_time < rocker->ageing_time)
+			rocker->ageing_time = rocker_port->ageing_time;
 		mod_timer(&rocker_port->rocker->fdb_cleanup_timer, jiffies);
 	}
 
@@ -4470,7 +4475,7 @@ static int rocker_port_obj_add(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, trans,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id, 0);
+					   fib4->fi, fib4->tb_id, 0);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
 		err = rocker_port_fdb_add(rocker_port, trans,
@@ -4542,7 +4547,7 @@ static int rocker_port_obj_del(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, NULL,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id,
+					   fib4->fi, fib4->tb_id,
 					   ROCKER_OP_FLAG_REMOVE);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
@@ -5206,10 +5211,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_init_tbls;
 	}
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
 	setup_timer(&rocker->fdb_cleanup_timer, rocker_fdb_cleanup,
 		    (unsigned long) rocker);
 	mod_timer(&rocker->fdb_cleanup_timer, jiffies);
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
+
 	err = rocker_probe_ports(rocker);
 	if (err) {
 		dev_err(&pdev->dev, "failed to probe ports\n");
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index e6a084a6be12..cbe9a330117a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -619,6 +619,17 @@ fail:
 	return rc;
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	/* All our existing PIO buffers went away */
+	efx_for_each_channel(channel, efx)
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			tx_queue->piobuf = NULL;
+}
+
 #else /* !EFX_USE_PIO */
 
 static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
 {
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
 #endif /* EFX_USE_PIO */
 
 static void efx_ef10_remove(struct efx_nic *efx)
@@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->must_realloc_vis = true;
 	nic_data->must_restore_filters = true;
 	nic_data->must_restore_piobufs = true;
+	efx_ef10_forget_old_piobufs(efx);
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
 	/* Driver-created vswitches and vports must be re-created */
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index d790cb8d9db3..8e832ba8ab24 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -2796,6 +2796,11 @@ const struct efx_nic_type falcon_a1_nic_type = {
 	.timer_period_max =  1 << FRF_AB_TC_TIMER_VAL_WIDTH,
 	.offload_features = NETIF_F_IP_CSUM,
 	.mcdi_max_ver = -1,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };
 
 const struct efx_nic_type falcon_b0_nic_type = {
@@ -2897,4 +2902,9 @@ const struct efx_nic_type falcon_b0_nic_type = {
 	.offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE,
 	.mcdi_max_ver = -1,
 	.max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 0e2fc1a844ab..23a038810083 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -540,7 +540,7 @@ static inline void  smc_rcv(struct net_device *dev)
 #define smc_special_lock(lock, flags)		spin_lock_irqsave(lock, flags)
 #define smc_special_unlock(lock, flags) 	spin_unlock_irqrestore(lock, flags)
 #else
-#define smc_special_trylock(lock, flags)	(flags == flags)
+#define smc_special_trylock(lock, flags)	((void)flags, true)
 #define smc_special_lock(lock, flags)   	do { flags = 0; } while (0)
 #define smc_special_unlock(lock, flags)	do { flags = 0; } while (0)
 #endif
@@ -2269,6 +2269,13 @@ static int smc_drv_probe(struct platform_device *pdev)
 	if (pd) {
 		memcpy(&lp->cfg, pd, sizeof(lp->cfg));
 		lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags);
+
+		if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) {
+			dev_err(&pdev->dev,
+				"at least one of 8-bit or 16-bit access support is required.\n");
+			ret = -ENXIO;
+			goto out_free_netdev;
+		}
 	}
 
 #if IS_BUILTIN(CONFIG_OF)
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index a3c129e1e40a..29df0465daf4 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -37,6 +37,27 @@
 #include <linux/smc91x.h>
 
 /*
+ * Any 16-bit access is performed with two 8-bit accesses if the hardware
+ * can't do it directly. Most registers are 16-bit so those are mandatory.
+ */
+#define SMC_outw_b(x, a, r)						\
+	do {								\
+		unsigned int __val16 = (x);				\
+		unsigned int __reg = (r);				\
+		SMC_outb(__val16, a, __reg);				\
+		SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT));	\
+	} while (0)
+
+#define SMC_inw_b(a, r)							\
+	({								\
+		unsigned int __val16;					\
+		unsigned int __reg = r;					\
+		__val16  = SMC_inb(a, __reg);				\
+		__val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \
+		__val16;						\
+	})
+
+/*
  * Define your architecture specific bus configuration parameters here.
  */
 
@@ -55,10 +76,30 @@
 #define SMC_IO_SHIFT		(lp->io_shift)
 
 #define SMC_inb(a, r)		readb((a) + (r))
-#define SMC_inw(a, r)		readw((a) + (r))
+#define SMC_inw(a, r)							\
+	({								\
+		unsigned int __smc_r = r;				\
+		SMC_16BIT(lp) ? readw((a) + __smc_r) :			\
+		SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) :			\
+		({ BUG(); 0; });					\
+	})
+
 #define SMC_inl(a, r)		readl((a) + (r))
 #define SMC_outb(v, a, r)	writeb(v, (a) + (r))
+#define SMC_outw(v, a, r)						\
+	do {								\
+		unsigned int __v = v, __smc_r = r;			\
+		if (SMC_16BIT(lp))					\
+			__SMC_outw(__v, a, __smc_r);			\
+		else if (SMC_8BIT(lp))					\
+			SMC_outw_b(__v, a, __smc_r);			\
+		else							\
+			BUG();						\
+	} while (0)
+
 #define SMC_outl(v, a, r)	writel(v, (a) + (r))
+#define SMC_insb(a, r, p, l)	readsb((a) + (r), p, l)
+#define SMC_outsb(a, r, p, l)	writesb((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_insl(a, r, p, l)	readsl((a) + (r), p, l)
@@ -66,7 +107,7 @@
 #define SMC_IRQ_FLAGS		(-1)	/* from resource */
 
 /* We actually can't write halfwords properly if not word aligned */
-static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
+static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 {
 	if ((machine_is_mainstone() || machine_is_stargate2() ||
 	     machine_is_pxa_idp()) && reg & 2) {
@@ -405,24 +446,8 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma,
 
 #if ! SMC_CAN_USE_16BIT
 
-/*
- * Any 16-bit access is performed with two 8-bit accesses if the hardware
- * can't do it directly. Most registers are 16-bit so those are mandatory.
- */
-#define SMC_outw(x, ioaddr, reg)					\
-	do {								\
-		unsigned int __val16 = (x);				\
-		SMC_outb( __val16, ioaddr, reg );			\
-		SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\
-	} while (0)
-#define SMC_inw(ioaddr, reg)						\
-	({								\
-		unsigned int __val16;					\
-		__val16 =  SMC_inb( ioaddr, reg );			\
-		__val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \
-		__val16;						\
-	})
-
+#define SMC_outw(x, ioaddr, reg)	SMC_outw_b(x, ioaddr, reg)
+#define SMC_inw(ioaddr, reg)		SMC_inw_b(ioaddr, reg)
 #define SMC_insw(a, r, p, l)		BUG()
 #define SMC_outsw(a, r, p, l)		BUG()
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a5b869eb4678..4b100ef4af9f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2939,12 +2939,6 @@ int stmmac_dvr_probe(struct device *device,
 	spin_lock_init(&priv->lock);
 	spin_lock_init(&priv->tx_lock);
 
-	ret = register_netdev(ndev);
-	if (ret) {
-		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
-		goto error_netdev_register;
-	}
-
 	/* If a specific clk_csr value is passed from the platform
 	 * this means that the CSR Clock Range selection cannot be
 	 * changed at run-time and it is fixed. Viceversa the driver'll try to
@@ -2969,11 +2963,21 @@ int stmmac_dvr_probe(struct device *device,
 		}
 	}
 
-	return 0;
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
+			   __func__, ret);
+		goto error_netdev_register;
+	}
+
+	return ret;
 
-error_mdio_register:
-	unregister_netdev(ndev);
 error_netdev_register:
+	if (priv->pcs != STMMAC_PCS_RGMII &&
+	    priv->pcs != STMMAC_PCS_TBI &&
+	    priv->pcs != STMMAC_PCS_RTBI)
+		stmmac_mdio_unregister(ndev);
+error_mdio_register:
 	netif_napi_del(&priv->napi);
 error_hw_init:
 	clk_disable_unprepare(priv->pclk);
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 77d26fe286c0..7e8bce46e6b4 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -549,7 +549,8 @@ fatal_error:
 
 static int cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	int queue, len;
+	int queue;
+	unsigned int len;
 	struct cpmac_desc *desc;
 	struct cpmac_priv *priv = netdev_priv(dev);
 
@@ -559,7 +560,7 @@ static int cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_padto(skb, ETH_ZLEN)))
 		return NETDEV_TX_OK;
 
-	len = max(skb->len, ETH_ZLEN);
+	len = max_t(unsigned int, skb->len, ETH_ZLEN);
 	queue = skb_get_queue_mapping(skb);
 	netif_stop_subqueue(dev, queue);
 
@@ -1236,7 +1237,7 @@ int cpmac_init(void)
 		goto fail_alloc;
 	}
 
-#warning FIXME: unhardcode gpio&reset bits
+	/* FIXME: unhardcode gpio&reset bits */
 	ar7_gpio_disable(26);
 	ar7_gpio_disable(27);
 	ar7_device_reset(AR7_RESET_BIT_CPMAC_LO);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index cf468c87ce57..4cb8b85cbf2c 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -100,6 +100,14 @@
 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
 #define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
 
+#ifdef __BIG_ENDIAN
+#define xemaclite_readl		ioread32be
+#define xemaclite_writel	iowrite32be
+#else
+#define xemaclite_readl		ioread32
+#define xemaclite_writel	iowrite32
+#endif
+
 /**
  * struct net_local - Our private per device data
  * @ndev:		instance of the network device
@@ -158,15 +166,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Enable the Tx interrupts for the first Buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Enable the Rx interrupts for the first buffer */
-	__raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
 
 	/* Enable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 }
 
 /**
@@ -181,17 +189,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Disable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 
 	/* Disable the Tx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Disable the Rx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
-		     drvdata->base_addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
+			 drvdata->base_addr + XEL_RSR_OFFSET);
 }
 
 /**
@@ -323,7 +331,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 		byte_count = ETH_FRAME_LEN;
 
 	/* Check if the expected buffer is available */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 	     XEL_TSR_XMIT_ACTIVE_MASK)) == 0) {
 
@@ -336,7 +344,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 
 		addr = (void __iomem __force *)((u32 __force)addr ^
 						 XEL_BUFFER_OFFSET);
-		reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 
 		if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 		     XEL_TSR_XMIT_ACTIVE_MASK)) != 0)
@@ -347,16 +355,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 	/* Write the frame to the buffer */
 	xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
 
-	__raw_writel((byte_count & XEL_TPLR_LENGTH_MASK),
-		     addr + XEL_TPLR_OFFSET);
+	xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
+			 addr + XEL_TPLR_OFFSET);
 
 	/* Update the Tx Status Register to indicate that there is a
 	 * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
 	 * is used by the interrupt handler to check whether a frame
 	 * has been transmitted */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
-	__raw_writel(reg_data, addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
 
 	return 0;
 }
@@ -371,7 +379,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
  *
  * Return:	Total number of bytes received
  */
-static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
+static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 {
 	void __iomem *addr;
 	u16 length, proto_type;
@@ -381,7 +389,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 	addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use);
 
 	/* Verify which buffer has valid data */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 
 	if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) {
 		if (drvdata->rx_ping_pong != 0)
@@ -398,27 +406,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 			return 0;	/* No data was available */
 
 		/* Verify that buffer has valid data */
-		reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 		if ((reg_data & XEL_RSR_RECV_DONE_MASK) !=
 		     XEL_RSR_RECV_DONE_MASK)
 			return 0;	/* No data was available */
 	}
 
 	/* Get the protocol type of the ethernet frame that arrived */
-	proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET +
+	proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
 			XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
 			XEL_RPLR_LENGTH_MASK);
 
 	/* Check if received ethernet frame is a raw ethernet frame
 	 * or an IP packet or an ARP packet */
-	if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) {
+	if (proto_type > ETH_DATA_LEN) {
 
 		if (proto_type == ETH_P_IP) {
-			length = ((ntohl(__raw_readl(addr +
+			length = ((ntohl(xemaclite_readl(addr +
 					XEL_HEADER_IP_LENGTH_OFFSET +
 					XEL_RXBUFF_OFFSET)) >>
 					XEL_HEADER_SHIFT) &
 					XEL_RPLR_LENGTH_MASK);
+			length = min_t(u16, length, ETH_DATA_LEN);
 			length += ETH_HLEN + ETH_FCS_LEN;
 
 		} else if (proto_type == ETH_P_ARP)
@@ -431,14 +440,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 		/* Use the length in the frame, plus the header and trailer */
 		length = proto_type + ETH_HLEN + ETH_FCS_LEN;
 
+	if (WARN_ON(length > maxlen))
+		length = maxlen;
+
 	/* Read from the EmacLite device */
 	xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
 				data, length);
 
 	/* Acknowledge the frame */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 	reg_data &= ~XEL_RSR_RECV_DONE_MASK;
-	__raw_writel(reg_data, addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET);
 
 	return length;
 }
@@ -465,14 +477,14 @@ static void xemaclite_update_address(struct net_local *drvdata,
 
 	xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
 
-	__raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
+	xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
 
 	/* Update the MAC address in the EmacLite */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
 
 	/* Wait for EmacLite to finish with the MAC address update */
-	while ((__raw_readl(addr + XEL_TSR_OFFSET) &
+	while ((xemaclite_readl(addr + XEL_TSR_OFFSET) &
 		XEL_TSR_PROG_MAC_ADDR) != 0)
 		;
 }
@@ -605,7 +617,7 @@ static void xemaclite_rx_handler(struct net_device *dev)
 
 	skb_reserve(skb, 2);
 
-	len = xemaclite_recv_data(lp, (u8 *) skb->data);
+	len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
 
 	if (!len) {
 		dev->stats.rx_errors++;
@@ -642,32 +654,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
 	u32 tx_status;
 
 	/* Check if there is Rx Data available */
-	if ((__raw_readl(base_addr + XEL_RSR_OFFSET) &
+	if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) &
 			 XEL_RSR_RECV_DONE_MASK) ||
-	    (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
+	    (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
 			 & XEL_RSR_RECV_DONE_MASK))
 
 		xemaclite_rx_handler(dev);
 
 	/* Check if the Transmission for the first buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
 
 	/* Check if the Transmission for the second buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
-			     XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
+				 XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
@@ -700,7 +712,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	/* wait for the MDIO interface to not be busy or timeout
 	   after some time.
 	*/
-	while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
+	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
 		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
@@ -736,17 +748,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	 * MDIO Address register. Set the Status bit in the MDIO Control
 	 * register to start a MDIO read transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(XEL_MDIOADDR_OP_MASK |
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOADDR_OP_MASK |
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	if (xemaclite_mdio_wait(lp))
 		return -ETIMEDOUT;
 
-	rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET);
+	rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
 
 	dev_dbg(&lp->ndev->dev,
 		"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
@@ -783,13 +795,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 	 * Data register. Finally, set the Status bit in the MDIO Control
 	 * register to start a MDIO write transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(~XEL_MDIOADDR_OP_MASK &
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(~XEL_MDIOADDR_OP_MASK &
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	return 0;
 }
@@ -836,8 +848,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
 	/* Enable the MDIO bus by asserting the enable bit in MDIO Control
 	 * register.
 	 */
-	__raw_writel(XEL_MDIOCTRL_MDIOEN_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	bus = mdiobus_alloc();
 	if (!bus) {
@@ -1141,8 +1153,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 		dev_warn(dev, "No MAC address found\n");
 
 	/* Clear the Tx CSR's in case this is a restart */
-	__raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 
 	/* Set the MAC address in the EmacLite device */
 	xemaclite_update_address(lp, ndev->dev_addr);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 58efdec12f30..f0961cbaf87e 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -310,15 +310,15 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Geneve and inner Ethernet header to be present */
 	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
-		goto error;
+		goto drop;
 
 	/* Return packets with reserved bits set */
 	geneveh = geneve_hdr(skb);
 	if (unlikely(geneveh->ver != GENEVE_VER))
-		goto error;
+		goto drop;
 
 	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
-		goto error;
+		goto drop;
 
 	opts_len = geneveh->opt_len * 4;
 	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
@@ -336,10 +336,6 @@ drop:
 	/* Consume bad packet */
 	kfree_skb(skb);
 	return 0;
-
-error:
-	/* Let the UDP layer deal with the skb */
-	return 1;
 }
 
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
@@ -444,7 +440,7 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, gh_len);
 	skb_gro_postpull_rcsum(skb, gh, gh_len);
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -819,7 +815,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs4 = geneve->sock4;
 	struct rtable *rt = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi4 fl4;
 	__u8 tos, ttl;
@@ -846,8 +841,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -863,7 +856,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		tos = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
@@ -873,7 +866,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
 			ttl = 1;
@@ -907,7 +900,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs6 = geneve->sock6;
 	struct dst_entry *dst = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi6 fl6;
 	__u8 prio, ttl;
@@ -931,8 +923,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -949,7 +939,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		prio = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 	} else {
 		udp_csum = false;
@@ -958,7 +948,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, iip, skb);
+		prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && ipv6_addr_is_multicast(&fl6.daddr))
 			ttl = 1;
@@ -998,6 +988,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	return geneve_xmit_skb(skb, dev, info);
 }
 
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* GENEVE overhead is not fixed, so we can't enforce a more
+	 * precise max MTU.
+	 */
+	if (new_mtu < 68 || new_mtu > IP_MAX_MTU)
+		return -EINVAL;
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1042,7 +1043,7 @@ static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_stop		= geneve_stop,
 	.ndo_start_xmit		= geneve_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= geneve_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
@@ -1349,11 +1350,21 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
 			       0, 0, 0, htons(dst_port), true);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = geneve_change_mtu(dev, IP_MAX_MTU);
+	if (err)
+		goto err;
+
 	return dev;
+
+ err:
+	free_netdev(dev);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 85828f153445..0758d0816840 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -648,8 +648,8 @@ static void ax_setup(struct net_device *dev)
 {
 	/* Finish setting up the DEVICE info. */
 	dev->mtu             = AX_MTU;
-	dev->hard_header_len = 0;
-	dev->addr_len        = 0;
+	dev->hard_header_len = AX25_MAX_HEADER_LEN;
+	dev->addr_len        = AX25_ADDR_LEN;
 	dev->type            = ARPHRD_AX25;
 	dev->tx_queue_len    = 10;
 	dev->header_ops      = &ax25_header_ops;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 409b48e1e589..c8a7802d2953 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -40,6 +40,8 @@
 
 #include "hyperv_net.h"
 
+/* Restrict GSO size to account for NVGRE */
+#define NETVSC_GSO_MAX_SIZE	62768
 
 #define RING_SIZE_MIN 64
 static int ring_size = 128;
@@ -195,65 +197,6 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 	return ppi;
 }
 
-union sub_key {
-	u64 k;
-	struct {
-		u8 pad[3];
-		u8 kb;
-		u32 ka;
-	};
-};
-
-/* Toeplitz hash function
- * data: network byte order
- * return: host byte order
- */
-static u32 comp_hash(u8 *key, int klen, void *data, int dlen)
-{
-	union sub_key subk;
-	int k_next = 4;
-	u8 dt;
-	int i, j;
-	u32 ret = 0;
-
-	subk.k = 0;
-	subk.ka = ntohl(*(u32 *)key);
-
-	for (i = 0; i < dlen; i++) {
-		subk.kb = key[k_next];
-		k_next = (k_next + 1) % klen;
-		dt = ((u8 *)data)[i];
-		for (j = 0; j < 8; j++) {
-			if (dt & 0x80)
-				ret ^= subk.ka;
-			dt <<= 1;
-			subk.k <<= 1;
-		}
-	}
-
-	return ret;
-}
-
-static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
-{
-	struct flow_keys flow;
-	int data_len;
-
-	if (!skb_flow_dissect_flow_keys(skb, &flow, 0) ||
-	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
-	      flow.basic.n_proto == htons(ETH_P_IPV6)))
-		return false;
-
-	if (flow.basic.ip_proto == IPPROTO_TCP)
-		data_len = 12;
-	else
-		data_len = 8;
-
-	*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len);
-
-	return true;
-}
-
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 			void *accel_priv, select_queue_fallback_t fallback)
 {
@@ -266,11 +209,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
 		return 0;
 
-	if (netvsc_set_hash(&hash, skb)) {
-		q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
-			ndev->real_num_tx_queues;
-		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
-	}
+	hash = skb_get_hash(skb);
+	q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+		ndev->real_num_tx_queues;
 
 	return q_idx;
 }
@@ -1139,6 +1080,7 @@ static int netvsc_probe(struct hv_device *dev,
 	nvdev = hv_get_drvdata(dev);
 	netif_set_real_num_tx_queues(net, nvdev->num_chn);
 	netif_set_real_num_rx_queues(net, nvdev->num_chn);
+	netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE);
 
 	ret = register_netdev(net);
 	if (ret != 0) {
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 199a94a9c8bc..3a429f1a8002 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -110,13 +110,26 @@ static int atusb_read_reg(struct atusb *atusb, uint8_t reg)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
 	int ret;
+	uint8_t *buffer;
 	uint8_t value;
 
+	buffer = kmalloc(1, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
 	dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg);
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_REG_READ, ATUSB_REQ_FROM_DEV,
-				0, reg, &value, 1, 1000);
-	return ret >= 0 ? value : ret;
+				0, reg, buffer, 1, 1000);
+
+	if (ret >= 0) {
+		value = buffer[0];
+		kfree(buffer);
+		return value;
+	} else {
+		kfree(buffer);
+		return ret;
+	}
 }
 
 static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
@@ -517,9 +530,13 @@ static struct ieee802154_ops atusb_ops = {
 static int atusb_get_and_show_revision(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
-	unsigned char buffer[3];
+	unsigned char *buffer;
 	int ret;
 
+	buffer = kmalloc(3, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
 	/* Get a couple of the ATMega Firmware values */
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0,
@@ -535,15 +552,20 @@ static int atusb_get_and_show_revision(struct atusb *atusb)
 		dev_info(&usb_dev->dev, "Please update to version 0.2 or newer");
 	}
 
+	kfree(buffer);
 	return ret;
 }
 
 static int atusb_get_and_show_build(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
-	char build[ATUSB_BUILD_SIZE + 1];
+	char *build;
 	int ret;
 
+	build = kmalloc(ATUSB_BUILD_SIZE + 1, GFP_KERNEL);
+	if (!build)
+		return -ENOMEM;
+
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0,
 				build, ATUSB_BUILD_SIZE, 1000);
@@ -552,6 +574,7 @@ static int atusb_get_and_show_build(struct atusb *atusb)
 		dev_info(&usb_dev->dev, "Firmware: build %s\n", build);
 	}
 
+	kfree(build);
 	return ret;
 }
 
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 860d4aed8274..43617ded3773 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -30,7 +30,7 @@
 static int numlbs = 2;
 
 static LIST_HEAD(fakelb_phys);
-static DEFINE_SPINLOCK(fakelb_phys_lock);
+static DEFINE_MUTEX(fakelb_phys_lock);
 
 static LIST_HEAD(fakelb_ifup_phys);
 static DEFINE_RWLOCK(fakelb_ifup_phys_lock);
@@ -180,9 +180,9 @@ static int fakelb_add_one(struct device *dev)
 	if (err)
 		goto err_reg;
 
-	spin_lock(&fakelb_phys_lock);
+	mutex_lock(&fakelb_phys_lock);
 	list_add_tail(&phy->list, &fakelb_phys);
-	spin_unlock(&fakelb_phys_lock);
+	mutex_unlock(&fakelb_phys_lock);
 
 	return 0;
 
@@ -214,10 +214,10 @@ static int fakelb_probe(struct platform_device *pdev)
 	return 0;
 
 err_slave:
-	spin_lock(&fakelb_phys_lock);
+	mutex_lock(&fakelb_phys_lock);
 	list_for_each_entry_safe(phy, tmp, &fakelb_phys, list)
 		fakelb_del(phy);
-	spin_unlock(&fakelb_phys_lock);
+	mutex_unlock(&fakelb_phys_lock);
 	return err;
 }
 
@@ -225,10 +225,10 @@ static int fakelb_remove(struct platform_device *pdev)
 {
 	struct fakelb_phy *phy, *tmp;
 
-	spin_lock(&fakelb_phys_lock);
+	mutex_lock(&fakelb_phys_lock);
 	list_for_each_entry_safe(phy, tmp, &fakelb_phys, list)
 		fakelb_del(phy);
-	spin_unlock(&fakelb_phys_lock);
+	mutex_unlock(&fakelb_phys_lock);
 	return 0;
 }
 
diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c
index 25f21968fa5c..de2ea9f2f966 100644
--- a/drivers/net/irda/irda-usb.c
+++ b/drivers/net/irda/irda-usb.c
@@ -1077,7 +1077,7 @@ static int stir421x_patch_device(struct irda_usb_cb *self)
          * are "42101001.sb" or "42101002.sb"
          */
         sprintf(stir421x_fw_name, "4210%4X.sb",
-                self->usbdev->descriptor.bcdDevice);
+		le16_to_cpu(self->usbdev->descriptor.bcdDevice));
         ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev);
         if (ret < 0)
                 return ret;
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 696852eb23c3..7a3f990c1935 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -430,16 +430,6 @@ static int irtty_open(struct tty_struct *tty)
 
 	/* Module stuff handled via irda_ldisc.owner - Jean II */
 
-	/* First make sure we're not already connected. */
-	if (tty->disc_data != NULL) {
-		priv = tty->disc_data;
-		if (priv && priv->magic == IRTTY_MAGIC) {
-			ret = -EEXIST;
-			goto out;
-		}
-		tty->disc_data = NULL;		/* ### */
-	}
-
 	/* stop the underlying  driver */
 	irtty_stop_receiver(tty, TRUE);
 	if (tty->ops->stop)
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index bca6a1e72d1d..e1bb802d4a4d 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -141,9 +141,19 @@ static int mcs_set_reg(struct mcs_cb *mcs, __u16 reg, __u16 val)
 static int mcs_get_reg(struct mcs_cb *mcs, __u16 reg, __u16 * val)
 {
 	struct usb_device *dev = mcs->usbdev;
-	int ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
-				  MCS_RD_RTYPE, 0, reg, val, 2,
-				  msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+	void *dmabuf;
+	int ret;
+
+	dmabuf = kmalloc(sizeof(__u16), GFP_KERNEL);
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
+			      MCS_RD_RTYPE, 0, reg, dmabuf, 2,
+			      msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+
+	memcpy(val, dmabuf, sizeof(__u16));
+	kfree(dmabuf);
 
 	return ret;
 }
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index dc7d970bd1c0..effcdbfb06e9 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev)
 {
 	dev->mtu		= 64 * 1024;
 	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
 	dev->addr_len		= ETH_ALEN;	/* 6	*/
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 06c8bfeaccd6..40cd86614677 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1110,6 +1110,7 @@ static int macvlan_port_create(struct net_device *dev)
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
@@ -1118,7 +1119,15 @@ static void macvlan_port_destroy(struct net_device *dev)
 	 * but we need to cancel it and purge left skbs if any.
 	 */
 	cancel_work_sync(&port->bc_work);
-	__skb_queue_purge(&port->bc_queue);
+
+	while ((skb = __skb_dequeue(&port->bc_queue))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		if (src)
+			dev_put(src->dev);
+
+		kfree_skb(skb);
+	}
 
 	kfree_rcu(port, rcu);
 }
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0fc521941c71..79de9608ac48 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -725,7 +725,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	ssize_t n;
 
 	if (q->flags & IFF_VNET_HDR) {
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
 		err = -EINVAL;
 		if (len < vnet_hdr_len)
@@ -760,6 +760,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
+		else if (copylen < ETH_HLEN)
+			copylen = ETH_HLEN;
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -769,10 +771,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
+		linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (linear > good_linear)
 			linear = good_linear;
-		else
-			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		else if (linear < ETH_HLEN)
+			linear = ETH_HLEN;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
@@ -862,7 +865,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 86b28052bf06..9b709f78bb03 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver");
 MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
 MODULE_LICENSE("GPL");
 
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		reg &= ~MII_BCM63XX_IR_GMASK;
+	else
+		reg |= MII_BCM63XX_IR_GMASK;
+
+	err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	return err;
+}
+
 static int bcm63xx_config_init(struct phy_device *phydev)
 {
 	int reg, err;
@@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 	.driver		= { .owner = THIS_MODULE },
 }, {
 	/* same phy as above, with just a different OUI */
@@ -68,7 +85,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 	.driver		= { .owner = THIS_MODULE },
 } };
 
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e6cefd0e3262..e83acc608678 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -907,7 +907,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	if (overflow) {
 		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
 		while (skb) {
-			skb_complete_tx_timestamp(skb, NULL);
+			kfree_skb(skb);
 			skb = skb_dequeue(&dp83640->tx_queue);
 		}
 		return;
@@ -1436,8 +1436,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->rx_queue, skb);
 		schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT);
-	} else {
-		netif_rx_ni(skb);
 	}
 
 	return true;
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 32f10662f4ac..7242dd4b3238 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -29,6 +29,7 @@
 #define MII_DP83867_MICR	0x12
 #define MII_DP83867_ISR		0x13
 #define DP83867_CTRL		0x1f
+#define DP83867_CFG3		0x1e
 
 /* Extended Registers */
 #define DP83867_RGMIICTL	0x0032
@@ -89,6 +90,8 @@ static int dp83867_config_intr(struct phy_device *phydev)
 		micr_status |=
 			(MII_DP83867_MICR_AN_ERR_INT_EN |
 			MII_DP83867_MICR_SPEED_CHNG_INT_EN |
+			MII_DP83867_MICR_AUTONEG_COMP_INT_EN |
+			MII_DP83867_MICR_LINK_STS_CHNG_INT_EN |
 			MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN |
 			MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN);
 
@@ -184,6 +187,13 @@ static int dp83867_config_init(struct phy_device *phydev)
 				       DP83867_DEVADDR, phydev->addr, delay);
 	}
 
+	/* Enable Interrupt output INT_OE in CFG3 register */
+	if (phy_interrupt_is_valid(phydev)) {
+		val = phy_read(phydev, DP83867_CFG3);
+		val |= BIT(7);
+		phy_write(phydev, DP83867_CFG3, val);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 0240552b50f3..ebec2dceff45 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -203,34 +203,6 @@ static int marvell_config_aneg(struct phy_device *phydev)
 {
 	int err;
 
-	/* The Marvell PHY has an errata which requires
-	 * that certain registers get written in order
-	 * to restart autonegotiation */
-	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x1f);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x200c);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x5);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x100);
-	if (err < 0)
-		return err;
-
 	err = marvell_set_polarity(phydev, phydev->mdix);
 	if (err < 0)
 		return err;
@@ -264,6 +236,42 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* This Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x1f);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x200c);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x5);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x100);
+	if (err < 0)
+		return err;
+
+	return marvell_config_aneg(phydev);
+}
+
 #ifdef CONFIG_OF_MDIO
 /*
  * Set and/or override some configuration registers based on the
@@ -814,8 +822,6 @@ static int marvell_read_status(struct phy_device *phydev)
 		phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) |
 					 mii_lpa_to_ethtool_lpa_t(lpa);
 
-		lpa &= adv;
-
 		if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
 			phydev->duplex = DUPLEX_FULL;
 		else
@@ -993,7 +999,7 @@ static struct phy_driver marvell_drivers[] = {
 		.name = "Marvell 88E1101",
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index c0b4e65267af..46fe1ae919a3 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -81,8 +81,6 @@ static int iproc_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	if (rc)
 		return rc;
 
-	iproc_mdio_config_clk(priv->base);
-
 	/* Prepare the read operation */
 	cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
 		(reg << MII_DATA_RA_SHIFT) |
@@ -112,8 +110,6 @@ static int iproc_mdio_write(struct mii_bus *bus, int phy_id,
 	if (rc)
 		return rc;
 
-	iproc_mdio_config_clk(priv->base);
-
 	/* Prepare the write operation */
 	cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
 		(reg << MII_DATA_RA_SHIFT) |
@@ -163,6 +159,8 @@ static int iproc_mdio_probe(struct platform_device *pdev)
 	bus->read = iproc_mdio_read;
 	bus->write = iproc_mdio_write;
 
+	iproc_mdio_config_clk(priv->base);
+
 	rc = of_mdiobus_register(bus, pdev->dev.of_node);
 	if (rc) {
 		dev_err(&pdev->dev, "MDIO bus registration failed\n");
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index e13ad6cdcc22..c8b85f1069ff 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -539,6 +539,8 @@ static int ksz9031_read_status(struct phy_device *phydev)
 	if ((regval & 0xFF) == 0xFF) {
 		phy_init_hw(phydev);
 		phydev->link = 0;
+		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
+			phydev->drv->config_intr(phydev);
 	}
 
 	return 0;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 47cd306dbb3c..49d9f0a789fe 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -538,9 +538,12 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP)
+	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
+
+	/* Now we can run the state machine synchronously */
+	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
@@ -640,8 +643,10 @@ phy_err:
 int phy_start_interrupts(struct phy_device *phydev)
 {
 	atomic_set(&phydev->irq_disable, 0);
-	if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
-			phydev) < 0) {
+	if (request_irq(phydev->irq, phy_interrupt,
+				IRQF_SHARED,
+				"phy_interrupt",
+				phydev) < 0) {
 		pr_warn("%s: Can't get IRQ %d (PHY)\n",
 			phydev->bus->name, phydev->irq);
 		phydev->irq = PHY_POLL;
@@ -916,6 +921,15 @@ void phy_state_machine(struct work_struct *work)
 			if (old_link != phydev->link)
 				phydev->state = PHY_CHANGELINK;
 		}
+		/*
+		 * Failsafe: check that nobody set phydev->link=0 between two
+		 * poll cycles, otherwise we won't leave RUNNING state as long
+		 * as link remains down.
+		 */
+		if (!phydev->link && phydev->state == PHY_RUNNING) {
+			phydev->state = PHY_CHANGELINK;
+			dev_err(&phydev->dev, "no link in PHY_RUNNING\n");
+		}
 		break;
 	case PHY_CHANGELINK:
 		err = phy_read_status(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0bfbabad4431..8179727d3423 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1368,6 +1368,8 @@ static int phy_remove(struct device *dev)
 {
 	struct phy_device *phydev = to_phy_device(dev);
 
+	cancel_delayed_work_sync(&phydev->state_queue);
+
 	mutex_lock(&phydev->lock);
 	phydev->state = PHY_DOWN;
 	mutex_unlock(&phydev->lock);
@@ -1442,7 +1444,7 @@ static struct phy_driver genphy_driver[] = {
 	.phy_id		= 0xffffffff,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Generic PHY",
-	.soft_reset	= genphy_soft_reset,
+	.soft_reset	= genphy_no_soft_reset,
 	.config_init	= genphy_config_init,
 	.features	= PHY_GBIT_FEATURES | SUPPORTED_MII |
 			  SUPPORTED_AUI | SUPPORTED_FIBRE |
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9a863c6a6a33..e5bb870b5461 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -567,7 +567,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 
 static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct ppp_file *pf = file->private_data;
+	struct ppp_file *pf;
 	struct ppp *ppp;
 	int err = -EFAULT, val, val2, i;
 	struct ppp_idle idle;
@@ -577,9 +577,14 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
 
-	if (!pf)
-		return ppp_unattached_ioctl(current->nsproxy->net_ns,
-					pf, file, cmd, arg);
+	mutex_lock(&ppp_mutex);
+
+	pf = file->private_data;
+	if (!pf) {
+		err = ppp_unattached_ioctl(current->nsproxy->net_ns,
+					   pf, file, cmd, arg);
+		goto out;
+	}
 
 	if (cmd == PPPIOCDETACH) {
 		/*
@@ -594,7 +599,6 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		 * this fd and reopening /dev/ppp.
 		 */
 		err = -EINVAL;
-		mutex_lock(&ppp_mutex);
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
 			rtnl_lock();
@@ -608,15 +612,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		} else
 			pr_warn("PPPIOCDETACH file->f_count=%ld\n",
 				atomic_long_read(&file->f_count));
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind == CHANNEL) {
 		struct channel *pch;
 		struct ppp_channel *chan;
 
-		mutex_lock(&ppp_mutex);
 		pch = PF_TO_CHANNEL(pf);
 
 		switch (cmd) {
@@ -638,17 +640,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				err = chan->ops->ioctl(chan, cmd, arg);
 			up_read(&pch->chan_sem);
 		}
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind != INTERFACE) {
 		/* can't happen */
 		pr_err("PPP: not interface or channel??\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	mutex_lock(&ppp_mutex);
 	ppp = PF_TO_PPP(pf);
 	switch (cmd) {
 	case PPPIOCSMRU:
@@ -823,7 +824,10 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		err = -ENOTTY;
 	}
+
+out:
 	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
@@ -836,7 +840,6 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	struct ppp_net *pn;
 	int __user *p = (int __user *)arg;
 
-	mutex_lock(&ppp_mutex);
 	switch (cmd) {
 	case PPPIOCNEWUNIT:
 		/* Create a new ppp unit */
@@ -886,7 +889,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	default:
 		err = -ENOTTY;
 	}
-	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
@@ -2290,7 +2293,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan)
 
 	pch->ppp = NULL;
 	pch->chan = chan;
-	pch->chan_net = net;
+	pch->chan_net = get_net(net);
 	chan->ppp = pch;
 	init_ppp_file(&pch->file, CHANNEL);
 	pch->file.hdrlen = chan->hdrlen;
@@ -2803,6 +2806,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 out2:
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 	free_netdev(dev);
 out1:
 	*retp = ret;
@@ -2978,6 +2982,9 @@ ppp_disconnect_channel(struct channel *pch)
  */
 static void ppp_destroy_channel(struct channel *pch)
 {
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
+
 	atomic_dec(&channel_count);
 
 	if (!pch->file.dead) {
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 01f08a7751f7..e7034c55e796 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -280,7 +280,7 @@ static void rionet_outb_msg_event(struct rio_mport *mport, void *dev_id, int mbo
 	struct net_device *ndev = dev_id;
 	struct rionet_private *rnet = netdev_priv(ndev);
 
-	spin_lock(&rnet->lock);
+	spin_lock(&rnet->tx_lock);
 
 	if (netif_msg_intr(rnet))
 		printk(KERN_INFO
@@ -299,7 +299,7 @@ static void rionet_outb_msg_event(struct rio_mport *mport, void *dev_id, int mbo
 	if (rnet->tx_cnt < RIONET_TX_RING_SIZE)
 		netif_wake_queue(ndev);
 
-	spin_unlock(&rnet->lock);
+	spin_unlock(&rnet->tx_lock);
 }
 
 static int rionet_open(struct net_device *ndev)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 59fefca74263..a5f392ae30d5 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -969,7 +969,7 @@ static void team_port_disable(struct team *team,
 			    NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
 			    NETIF_F_HIGHDMA | NETIF_F_LRO)
 
-static void __team_compute_features(struct team *team)
+static void ___team_compute_features(struct team *team)
 {
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -993,15 +993,20 @@ static void __team_compute_features(struct team *team)
 	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
 		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+}
 
+static void __team_compute_features(struct team *team)
+{
+	___team_compute_features(team);
 	netdev_change_features(team->dev);
 }
 
 static void team_compute_features(struct team *team)
 {
 	mutex_lock(&team->lock);
-	__team_compute_features(team);
+	___team_compute_features(team);
 	mutex_unlock(&team->lock);
+	netdev_change_features(team->dev);
 }
 
 static int team_port_enter(struct team *team, struct team_port *port)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f0db770e8b2f..c31d8e74f131 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -567,11 +567,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -621,11 +623,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 
 	/* Re-attach the filter to persist device */
 	if (!skip_filter && (tun->filter_attached == true)) {
-		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		err = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (!err)
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -1000,7 +1004,6 @@ static void tun_net_init(struct net_device *dev)
 		/* Zero header length */
 		dev->type = ARPHRD_NONE;
 		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 
 	case IFF_TAP:
@@ -1012,7 +1015,6 @@ static void tun_net_init(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 	}
 }
@@ -1106,9 +1108,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		n = copy_from_iter(&gso, sizeof(gso), from);
 		if (n != sizeof(gso))
@@ -1120,7 +1124,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1299,7 +1303,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 
@@ -1409,9 +1413,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
@@ -1463,6 +1464,8 @@ static void tun_setup(struct net_device *dev)
 
 	dev->ethtool_ops = &tun_ethtool_ops;
 	dev->destructor = tun_free_netdev;
+	/* We prefer our own queue length */
+	dev->tx_queue_len = TUN_READQ_SIZE;
 }
 
 /* Trivial set of netlink ops to allow deleting tun or tap
@@ -1804,7 +1807,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n)
 
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		sk_detach_filter(tfile->socket.sk);
+		__sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held());
 	}
 
 	tun->filter_attached = false;
@@ -1817,7 +1820,8 @@ static int tun_attach_filter(struct tun_struct *tun)
 
 	for (i = 0; i < tun->numqueues; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (ret) {
 			tun_detach_filter(tun, i);
 			return ret;
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index bd9acff1eb7b..7fbd8f044207 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -66,7 +66,7 @@ int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb,
 	 * buffer.
 	 */
 	if (rx->remaining && (rx->remaining + sizeof(u32) <= skb->len)) {
-		offset = ((rx->remaining + 1) & 0xfffe) + sizeof(u32);
+		offset = ((rx->remaining + 1) & 0xfffe);
 		rx->header = get_unaligned_le32(skb->data + offset);
 		offset = 0;
 
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 4e2b26a88b15..2aa1a1d29cb4 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -777,7 +777,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct net_device *netdev;
 	struct catc *catc;
 	u8 broadcast[ETH_ALEN];
-	int i, pktsz;
+	int pktsz, ret;
 
 	if (usb_set_interface(usbdev,
 			intf->altsetting->desc.bInterfaceNumber, 1)) {
@@ -812,12 +812,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	if ((!catc->ctrl_urb) || (!catc->tx_urb) || 
 	    (!catc->rx_urb) || (!catc->irq_urb)) {
 		dev_err(&intf->dev, "No free urbs available.\n");
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail_free;
 	}
 
 	/* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */
@@ -845,15 +841,24 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
                 catc->irq_buf, 2, catc_irq_done, catc, 1);
 
 	if (!catc->is_f5u011) {
+		u32 *buf;
+		int i;
+
 		dev_dbg(dev, "Checking memory size\n");
 
-		i = 0x12345678;
-		catc_write_mem(catc, 0x7a80, &i, 4);
-		i = 0x87654321;	
-		catc_write_mem(catc, 0xfa80, &i, 4);
-		catc_read_mem(catc, 0x7a80, &i, 4);
+		buf = kmalloc(4, GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto fail_free;
+		}
+
+		*buf = 0x12345678;
+		catc_write_mem(catc, 0x7a80, buf, 4);
+		*buf = 0x87654321;
+		catc_write_mem(catc, 0xfa80, buf, 4);
+		catc_read_mem(catc, 0x7a80, buf, 4);
 	  
-		switch (i) {
+		switch (*buf) {
 		case 0x12345678:
 			catc_set_reg(catc, TxBufCount, 8);
 			catc_set_reg(catc, RxBufCount, 32);
@@ -868,6 +873,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 			dev_dbg(dev, "32k Memory\n");
 			break;
 		}
+
+		kfree(buf);
 	  
 		dev_dbg(dev, "Getting MAC from SEEROM.\n");
 	  
@@ -914,16 +921,21 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	usb_set_intfdata(intf, catc);
 
 	SET_NETDEV_DEV(netdev, &intf->dev);
-	if (register_netdev(netdev) != 0) {
-		usb_set_intfdata(intf, NULL);
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -EIO;
-	}
+	ret = register_netdev(netdev);
+	if (ret)
+		goto fail_clear_intfdata;
+
 	return 0;
+
+fail_clear_intfdata:
+	usb_set_intfdata(intf, NULL);
+fail_free:
+	usb_free_urb(catc->ctrl_urb);
+	usb_free_urb(catc->tx_urb);
+	usb_free_urb(catc->rx_urb);
+	usb_free_urb(catc->irq_urb);
+	free_netdev(netdev);
+	return ret;
 }
 
 static void catc_disconnect(struct usb_interface *intf)
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 3da70bf9936a..8c408aa2f208 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -160,6 +160,12 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 	info->u = header.usb_cdc_union_desc;
 	info->header = header.usb_cdc_header_desc;
 	info->ether = header.usb_cdc_ether_desc;
+	if (!info->u) {
+		if (rndis)
+			goto skip;
+		else /* in that case a quirk is mandatory */
+			goto bad_desc;
+	}
 	/* we need a master/control interface (what we're
 	 * probed with) and a slave/data interface; union
 	 * descriptors sort this all out.
@@ -256,7 +262,7 @@ skip:
 			goto bad_desc;
 		}
 
-	} else if (!info->header || !info->u || (!rndis && !info->ether)) {
+	} else if (!info->header || (!rndis && !info->ether)) {
 		dev_dbg(&intf->dev, "missing cdc %s%s%sdescriptor\n",
 			info->header ? "" : "header ",
 			info->u ? "" : "union ",
@@ -456,6 +462,7 @@ static const struct driver_info wwan_info = {
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
 #define NVIDIA_VENDOR_ID	0x0955
+#define HP_VENDOR_ID		0x03f0
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -602,6 +609,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* HP lt2523 (Novatel E371) - handled by qmi_wwan */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* AnyDATA ADU960S - handled by qmi_wwan */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM,
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index bdd83d95ec0a..96a5028621c8 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -617,8 +617,13 @@ static const struct usb_device_id mbim_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
-	/* Huawei E3372 fails unless NDP comes after the IP packets */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+
+	/* Some Huawei devices, ME906s-158 (12d1:15c1) and E3372
+	 * (12d1:157d), are known to fail unless the NDP is placed
+	 * after the IP packets.  Applying the quirk to all Huawei
+	 * devices is broader than necessary, but harmless.
+	 */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end,
 	},
 	/* default entry */
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index e8a1144c5a8b..e0e94b855bbe 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -794,7 +794,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
-	/* reset data interface */
+	/* Reset data interface. Some devices will not reset properly
+	 * unless they are configured first.  Toggle the altsetting to
+	 * force a reset
+	 */
+	usb_set_interface(dev->udev, iface_no, data_altsetting);
 	temp = usb_set_interface(dev->udev, iface_no, 0);
 	if (temp) {
 		dev_dbg(&intf->dev, "set interface failed\n");
@@ -805,6 +809,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
@@ -941,8 +952,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
 
 static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
-
 	/* MBIM backwards compatible function? */
 	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
@@ -951,16 +960,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	 * Additionally, generic NCM devices are assumed to accept arbitrarily
 	 * placed NDP.
 	 */
-	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
-
-	/*
-	 * We should get an event when network connection is "connected" or
-	 * "disconnected". Set network connection in "disconnected" state
-	 * (carrier is OFF) during attach, so the IP network stack does not
-	 * start IPv6 negotiation and more.
-	 */
-	usbnet_link_change(dev, 0, 0);
-	return ret;
+	return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
 }
 
 static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max)
@@ -1543,7 +1543,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
-	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
+	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+			| FLAG_LINK_INTR,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1556,7 +1557,7 @@ static const struct driver_info cdc_ncm_info = {
 static const struct driver_info wwan_info = {
 	.description = "Mobile Broadband Network Device",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN,
+			| FLAG_LINK_INTR | FLAG_WWAN,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1569,7 +1570,7 @@ static const struct driver_info wwan_info = {
 static const struct driver_info wwan_noarp_info = {
 	.description = "Mobile Broadband Network Device (NO ARP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN | FLAG_NOARP,
+			| FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index f64b25c221e8..cd93220c9b45 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -1009,6 +1009,7 @@ static int kaweth_probe(
 	struct net_device *netdev;
 	const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 	int result = 0;
+	int rv = -EIO;
 
 	dev_dbg(dev,
 		"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -1029,6 +1030,7 @@ static int kaweth_probe(
 	kaweth = netdev_priv(netdev);
 	kaweth->dev = udev;
 	kaweth->net = netdev;
+	kaweth->intf = intf;
 
 	spin_lock_init(&kaweth->device_lock);
 	init_waitqueue_head(&kaweth->term_wait);
@@ -1048,6 +1050,10 @@ static int kaweth_probe(
 		/* Download the firmware */
 		dev_info(dev, "Downloading firmware...\n");
 		kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL);
+		if (!kaweth->firmware_buf) {
+			rv = -ENOMEM;
+			goto err_free_netdev;
+		}
 		if ((result = kaweth_download_firmware(kaweth,
 						      "kaweth/new_code.bin",
 						      100,
@@ -1139,8 +1145,6 @@ err_fw:
 
 	dev_dbg(dev, "Initializing net device.\n");
 
-	kaweth->intf = intf;
-
 	kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!kaweth->tx_urb)
 		goto err_free_netdev;
@@ -1204,7 +1208,7 @@ err_only_tx:
 err_free_netdev:
 	free_netdev(netdev);
 
-	return -EIO;
+	return rv;
 }
 
 /****************************************************************
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index f84080215915..17fac0121e56 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -126,40 +126,61 @@ static void async_ctrl_callback(struct urb *urb)
 
 static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0,
-			      indx, data, size, 1000);
+			      indx, buf, size, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	else if (ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
 	return ret;
 }
 
-static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
+static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
+			 const void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0,
-			      indx, data, size, 100);
+			      indx, buf, size, 100);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
 static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(&data, 1, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data,
-			      indx, &data, 1, 1000);
+			      indx, buf, 1, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 982e0acd1a36..958af3b1af7f 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -485,6 +485,13 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt2523 (Novatel E371) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d,
+					      USB_CLASS_COMM,
+					      USB_CDC_SUBCLASS_ETHERNET,
+					      USB_CDC_PROTO_NONE),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
@@ -699,6 +706,8 @@ static const struct usb_device_id products[] = {
 	{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(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
+	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
 	{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 */
@@ -718,8 +727,12 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
 	{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 */
@@ -744,6 +757,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
+	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2fb637ad594a..1c27e6fb99f9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1645,7 +1645,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
 	u8 checksum = CHECKSUM_NONE;
 	u32 opts2, opts3;
 
-	if (tp->version == RTL_VER_01)
+	if (!(tp->netdev->features & NETIF_F_RXCSUM))
 		goto return_result;
 
 	opts2 = le32_to_cpu(rx_desc->opts2);
@@ -1851,6 +1851,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
 		napi_complete(napi);
 		if (!list_empty(&tp->rx_done))
 			napi_schedule(napi);
+		else if (!skb_queue_empty(&tp->tx_queue) &&
+			 !list_empty(&tp->tx_free))
+			napi_schedule(napi);
 	}
 
 	return work_done;
@@ -2990,10 +2993,13 @@ static void set_carrier(struct r8152 *tp)
 		if (!netif_carrier_ok(netdev)) {
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+			netif_stop_queue(netdev);
 			napi_disable(&tp->napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
 			napi_enable(&tp->napi);
+			netif_wake_queue(netdev);
+			netif_info(tp, link, netdev, "carrier on\n");
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -3001,6 +3007,7 @@ static void set_carrier(struct r8152 *tp)
 			napi_disable(&tp->napi);
 			tp->rtl_ops.disable(tp);
 			napi_enable(&tp->napi);
+			netif_info(tp, link, netdev, "carrier off\n");
 		}
 	}
 }
@@ -3385,12 +3392,12 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	if (!netif_running(netdev))
 		return 0;
 
+	netif_stop_queue(netdev);
 	napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
 	if (netif_carrier_ok(netdev)) {
-		netif_stop_queue(netdev);
 		mutex_lock(&tp->control);
 		tp->rtl_ops.disable(tp);
 		mutex_unlock(&tp->control);
@@ -3415,12 +3422,14 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	if (netif_carrier_ok(netdev)) {
 		mutex_lock(&tp->control);
 		tp->rtl_ops.enable(tp);
+		rtl_start_rx(tp);
 		rtl8152_set_rx_mode(netdev);
 		mutex_unlock(&tp->control);
-		netif_wake_queue(netdev);
 	}
 
 	napi_enable(&tp->napi);
+	netif_wake_queue(netdev);
+	usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 
 	return 0;
 }
@@ -3442,43 +3451,93 @@ static bool delay_autosuspend(struct r8152 *tp)
 	 */
 	if (!sw_linking && tp->rtl_ops.in_nway(tp))
 		return true;
+	else if (!skb_queue_empty(&tp->tx_queue))
+		return true;
 	else
 		return false;
 }
 
-static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+static int rtl8152_rumtime_suspend(struct r8152 *tp)
 {
-	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev = tp->netdev;
 	int ret = 0;
 
-	mutex_lock(&tp->control);
+	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		u32 rcr = 0;
 
-	if (PMSG_IS_AUTO(message)) {
-		if (netif_running(netdev) && delay_autosuspend(tp)) {
+		if (delay_autosuspend(tp)) {
 			ret = -EBUSY;
 			goto out1;
 		}
 
-		set_bit(SELECTIVE_SUSPEND, &tp->flags);
-	} else {
-		netif_device_detach(netdev);
+		if (netif_carrier_ok(netdev)) {
+			u32 ocp_data;
+
+			rcr = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
+			ocp_data = rcr & ~RCR_ACPT_ALL;
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
+			rxdy_gated_en(tp, true);
+			ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA,
+						 PLA_OOB_CTRL);
+			if (!(ocp_data & RXFIFO_EMPTY)) {
+				rxdy_gated_en(tp, false);
+				ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+				ret = -EBUSY;
+				goto out1;
+			}
+		}
+
+		clear_bit(WORK_ENABLE, &tp->flags);
+		usb_kill_urb(tp->intr_urb);
+
+		rtl_runtime_suspend_enable(tp, true);
+
+		if (netif_carrier_ok(netdev)) {
+			napi_disable(&tp->napi);
+			rtl_stop_rx(tp);
+			rxdy_gated_en(tp, false);
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+			napi_enable(&tp->napi);
+		}
 	}
 
+	set_bit(SELECTIVE_SUSPEND, &tp->flags);
+
+out1:
+	return ret;
+}
+
+static int rtl8152_system_suspend(struct r8152 *tp)
+{
+	struct net_device *netdev = tp->netdev;
+	int ret = 0;
+
+	netif_device_detach(netdev);
+
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
 		napi_disable(&tp->napi);
-		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_stop_rx(tp);
-			rtl_runtime_suspend_enable(tp, true);
-		} else {
-			cancel_delayed_work_sync(&tp->schedule);
-			tp->rtl_ops.down(tp);
-		}
+		cancel_delayed_work_sync(&tp->schedule);
+		tp->rtl_ops.down(tp);
 		napi_enable(&tp->napi);
 	}
-out1:
+
+	return ret;
+}
+
+static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	int ret;
+
+	mutex_lock(&tp->control);
+
+	if (PMSG_IS_AUTO(message))
+		ret = rtl8152_rumtime_suspend(tp);
+	else
+		ret = rtl8152_system_suspend(tp);
+
 	mutex_unlock(&tp->control);
 
 	return ret;
@@ -4173,6 +4232,11 @@ static int rtl8152_probe(struct usb_interface *intf,
 				NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
 				NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
 
+	if (tp->version == RTL_VER_01) {
+		netdev->features &= ~NETIF_F_RXCSUM;
+		netdev->hw_features &= ~NETIF_F_RXCSUM;
+	}
+
 	netdev->ethtool_ops = &ops;
 	netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
 
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index d37b7dce2d40..39672984dde1 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -155,16 +155,36 @@ static const char driver_name [] = "rtl8150";
 */
 static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
 {
-	return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
+			      indx, 0, buf, size, 500);
+	if (ret > 0 && ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
+	return ret;
 }
 
-static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
+static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data)
 {
-	return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
+			      indx, 0, buf, size, 500);
+	kfree(buf);
+	return ret;
 }
 
 static void async_set_reg_cb(struct urb *urb)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index a251588762ec..0b5a84c9022c 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -73,8 +73,6 @@ static	atomic_t iface_counter = ATOMIC_INIT(0);
 /* Private data structure */
 struct sierra_net_data {
 
-	u8 ethr_hdr_tmpl[ETH_HLEN]; /* ethernet header template for rx'd pkts */
-
 	u16 link_up;		/* air link up or down */
 	u8 tx_hdr_template[4];	/* part of HIP hdr for tx'd packets */
 
@@ -122,6 +120,7 @@ struct param {
 
 /* LSI Protocol types */
 #define SIERRA_NET_PROTOCOL_UMTS      0x01
+#define SIERRA_NET_PROTOCOL_UMTS_DS   0x04
 /* LSI Coverage */
 #define SIERRA_NET_COVERAGE_NONE      0x00
 #define SIERRA_NET_COVERAGE_NOPACKET  0x01
@@ -129,7 +128,8 @@ struct param {
 /* LSI Session */
 #define SIERRA_NET_SESSION_IDLE       0x00
 /* LSI Link types */
-#define SIERRA_NET_AS_LINK_TYPE_IPv4  0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV4  0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV6  0x02
 
 struct lsi_umts {
 	u8 protocol;
@@ -137,9 +137,14 @@ struct lsi_umts {
 	__be16 length;
 	/* eventually use a union for the rest - assume umts for now */
 	u8 coverage;
-	u8 unused2[41];
+	u8 network_len; /* network name len */
+	u8 network[40]; /* network name (UCS2, bigendian) */
 	u8 session_state;
 	u8 unused3[33];
+} __packed;
+
+struct lsi_umts_single {
+	struct lsi_umts lsi;
 	u8 link_type;
 	u8 pdp_addr_len; /* NW-supplied PDP address len */
 	u8 pdp_addr[16]; /* NW-supplied PDP address (bigendian)) */
@@ -158,10 +163,31 @@ struct lsi_umts {
 	u8 reserved[8];
 } __packed;
 
+struct lsi_umts_dual {
+	struct lsi_umts lsi;
+	u8 pdp_addr4_len; /* NW-supplied PDP IPv4 address len */
+	u8 pdp_addr4[4];  /* NW-supplied PDP IPv4 address (bigendian)) */
+	u8 pdp_addr6_len; /* NW-supplied PDP IPv6 address len */
+	u8 pdp_addr6[16]; /* NW-supplied PDP IPv6 address (bigendian)) */
+	u8 unused4[23];
+	u8 dns1_addr4_len; /* NW-supplied 1st DNS v4 address len (bigendian) */
+	u8 dns1_addr4[4];  /* NW-supplied 1st DNS v4 address */
+	u8 dns1_addr6_len; /* NW-supplied 1st DNS v6 address len */
+	u8 dns1_addr6[16]; /* NW-supplied 1st DNS v6 address (bigendian)*/
+	u8 dns2_addr4_len; /* NW-supplied 2nd DNS v4 address len (bigendian) */
+	u8 dns2_addr4[4];  /* NW-supplied 2nd DNS v4 address */
+	u8 dns2_addr6_len; /* NW-supplied 2nd DNS v6 address len */
+	u8 dns2_addr6[16]; /* NW-supplied 2nd DNS v6 address (bigendian)*/
+	u8 unused5[68];
+} __packed;
+
 #define SIERRA_NET_LSI_COMMON_LEN      4
-#define SIERRA_NET_LSI_UMTS_LEN        (sizeof(struct lsi_umts))
+#define SIERRA_NET_LSI_UMTS_LEN        (sizeof(struct lsi_umts_single))
 #define SIERRA_NET_LSI_UMTS_STATUS_LEN \
 	(SIERRA_NET_LSI_UMTS_LEN - SIERRA_NET_LSI_COMMON_LEN)
+#define SIERRA_NET_LSI_UMTS_DS_LEN     (sizeof(struct lsi_umts_dual))
+#define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \
+	(SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN)
 
 /* Forward definitions */
 static void sierra_sync_timer(unsigned long syncdata);
@@ -191,10 +217,11 @@ static inline void sierra_net_set_private(struct usbnet *dev,
 	dev->data[0] = (unsigned long)priv;
 }
 
-/* is packet IPv4 */
+/* is packet IPv4/IPv6 */
 static inline int is_ip(struct sk_buff *skb)
 {
-	return skb->protocol == cpu_to_be16(ETH_P_IP);
+	return skb->protocol == cpu_to_be16(ETH_P_IP) ||
+	       skb->protocol == cpu_to_be16(ETH_P_IPV6);
 }
 
 /*
@@ -350,49 +377,54 @@ static inline int sierra_net_is_valid_addrlen(u8 len)
 static int sierra_net_parse_lsi(struct usbnet *dev, char *data, int datalen)
 {
 	struct lsi_umts *lsi = (struct lsi_umts *)data;
+	u32 expected_length;
 
-	if (datalen < sizeof(struct lsi_umts)) {
-		netdev_err(dev->net, "%s: Data length %d, exp %Zu\n",
-				__func__, datalen,
-				sizeof(struct lsi_umts));
+	if (datalen < sizeof(struct lsi_umts_single)) {
+		netdev_err(dev->net, "%s: Data length %d, exp >= %Zu\n",
+			   __func__, datalen, sizeof(struct lsi_umts_single));
 		return -1;
 	}
 
-	if (lsi->length != cpu_to_be16(SIERRA_NET_LSI_UMTS_STATUS_LEN)) {
-		netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
-				__func__, be16_to_cpu(lsi->length),
-				(u32)SIERRA_NET_LSI_UMTS_STATUS_LEN);
-		return -1;
+	/* Validate the session state */
+	if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
+		netdev_err(dev->net, "Session idle, 0x%02x\n",
+			   lsi->session_state);
+		return 0;
 	}
 
 	/* Validate the protocol  - only support UMTS for now */
-	if (lsi->protocol != SIERRA_NET_PROTOCOL_UMTS) {
+	if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS) {
+		struct lsi_umts_single *single = (struct lsi_umts_single *)lsi;
+
+		/* Validate the link type */
+		if (single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV4 &&
+		    single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV6) {
+			netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
+				   single->link_type);
+			return -1;
+		}
+		expected_length = SIERRA_NET_LSI_UMTS_STATUS_LEN;
+	} else if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS_DS) {
+		expected_length = SIERRA_NET_LSI_UMTS_DS_STATUS_LEN;
+	} else {
 		netdev_err(dev->net, "Protocol unsupported, 0x%02x\n",
-			lsi->protocol);
+			   lsi->protocol);
 		return -1;
 	}
 
-	/* Validate the link type */
-	if (lsi->link_type != SIERRA_NET_AS_LINK_TYPE_IPv4) {
-		netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
-			lsi->link_type);
+	if (be16_to_cpu(lsi->length) != expected_length) {
+		netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
+			   __func__, be16_to_cpu(lsi->length), expected_length);
 		return -1;
 	}
 
 	/* Validate the coverage */
-	if (lsi->coverage == SIERRA_NET_COVERAGE_NONE
-	   || lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
+	if (lsi->coverage == SIERRA_NET_COVERAGE_NONE ||
+	    lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
 		netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage);
 		return 0;
 	}
 
-	/* Validate the session state */
-	if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
-		netdev_err(dev->net, "Session idle, 0x%02x\n",
-			lsi->session_state);
-		return 0;
-	}
-
 	/* Set link_sense true */
 	return 1;
 }
@@ -662,7 +694,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 	u8	numendpoints;
 	u16	fwattr = 0;
 	int	status;
-	struct ethhdr *eth;
 	struct sierra_net_data *priv;
 	static const u8 sync_tmplate[sizeof(priv->sync_msg)] = {
 		0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00};
@@ -700,11 +731,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter);
 	dev->net->dev_addr[ETH_ALEN-1] = ifacenum;
 
-	/* we will have to manufacture ethernet headers, prepare template */
-	eth = (struct ethhdr *)priv->ethr_hdr_tmpl;
-	memcpy(&eth->h_dest, dev->net->dev_addr, ETH_ALEN);
-	eth->h_proto = cpu_to_be16(ETH_P_IP);
-
 	/* prepare shutdown message template */
 	memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg));
 	/* set context index initially to 0 - prepares tx hdr template */
@@ -833,9 +859,14 @@ static int sierra_net_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 		skb_pull(skb, hh.hdrlen);
 
-		/* We are going to accept this packet, prepare it */
-		memcpy(skb->data, sierra_net_get_private(dev)->ethr_hdr_tmpl,
-			ETH_HLEN);
+		/* We are going to accept this packet, prepare it.
+		 * In case protocol is IPv6, keep it, otherwise force IPv4.
+		 */
+		skb_reset_mac_header(skb);
+		if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IPV6))
+			eth_hdr(skb)->h_proto = cpu_to_be16(ETH_P_IP);
+		eth_zero_addr(eth_hdr(skb)->h_source);
+		memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN);
 
 		/* Last packet in batch handled by usbnet */
 		if (hh.payload_len.word == skb->len)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 0744bf2ef2d6..c2ea4e5666fb 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1766,6 +1766,13 @@ out3:
 	if (info->unbind)
 		info->unbind (dev, udev);
 out1:
+	/* subdrivers must undo all they did in bind() if they
+	 * fail it, but we may fail later and a deferred kevent
+	 * may trigger an error resubmitting itself and, worse,
+	 * schedule a timer. So we kill it all just in case.
+	 */
+	cancel_work_sync(&dev->kevent);
+	del_timer_sync(&dev->delay);
 	free_netdev(net);
 out:
 	return status;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f94ab786088f..8dfc75250583 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -47,8 +47,16 @@ module_param(gso, bool, 0444);
  */
 DECLARE_EWMA(pkt_len, 1, 64)
 
+/* With mergeable buffers we align buffer address and use the low bits to
+ * encode its true size. Buffer size is up to 1 page so we need to align to
+ * square root of page size to ensure we reserve enough bits to encode the true
+ * size.
+ */
+#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
+
 /* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
+				   1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
 
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
@@ -1415,6 +1423,7 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= virtnet_busy_poll,
 #endif
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
@@ -1465,6 +1474,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 		netif_napi_del(&vi->rq[i].napi);
 	}
 
+	/* We called napi_hash_del() before netif_napi_del(),
+	 * we need to respect an RCU grace period before freeing vi->rq
+	 */
+	synchronize_net();
+
 	kfree(vi->rq);
 	kfree(vi->sq);
 }
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 0a242b200df4..ac945f8781ac 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -114,20 +114,23 @@ static struct dst_ops vrf_dst_ops = {
 #if IS_ENABLED(CONFIG_IPV6)
 static bool check_ipv6_frame(const struct sk_buff *skb)
 {
-	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data;
-	size_t hlen = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h;
+	struct ipv6hdr _ipv6h;
 	bool rc = true;
 
-	if (skb->len < hlen)
+	ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h);
+	if (!ipv6h)
 		goto out;
 
 	if (ipv6h->nexthdr == NEXTHDR_ICMP) {
 		const struct icmp6hdr *icmph;
+		struct icmp6hdr _icmph;
 
-		if (skb->len < hlen + sizeof(*icmph))
+		icmph = skb_header_pointer(skb, sizeof(_ipv6h),
+					   sizeof(_icmph), &_icmph);
+		if (!icmph)
 			goto out;
 
-		icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h));
 		switch (icmph->icmp6_type) {
 		case NDISC_ROUTER_SOLICITATION:
 		case NDISC_ROUTER_ADVERTISEMENT:
@@ -298,7 +301,9 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_tos = RT_TOS(ip4h->tos),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
 				FLOWI_FLAG_SKIP_NH_OIF,
+		.flowi4_proto = ip4h->protocol,
 		.daddr = ip4h->daddr,
+		.saddr = ip4h->saddr,
 	};
 
 	if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
@@ -340,6 +345,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -347,7 +353,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);
@@ -407,6 +413,8 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 	struct in6_addr *nexthop;
 	int ret;
 
+	nf_reset(skb);
+
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
 
@@ -518,6 +526,8 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	u32 nexthop;
 	int ret = -EINVAL;
 
+	nf_reset(skb);
+
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
 		struct sk_buff *skb2;
@@ -723,15 +733,15 @@ static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 static void vrf_dev_uninit(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct slave_queue *queue = &vrf->queue;
-	struct list_head *head = &queue->all_slaves;
-	struct slave *slave, *next;
+//	struct slave_queue *queue = &vrf->queue;
+//	struct list_head *head = &queue->all_slaves;
+//	struct slave *slave, *next;
 
 	vrf_rtable_destroy(vrf);
 	vrf_rt6_destroy(vrf);
 
-	list_for_each_entry_safe(slave, next, head, list)
-		vrf_del_slave(dev, slave->dev);
+//	list_for_each_entry_safe(slave, next, head, list)
+//		vrf_del_slave(dev, slave->dev);
 
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
@@ -904,6 +914,14 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
 
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct slave_queue *queue = &vrf->queue;
+	struct list_head *all_slaves = &queue->all_slaves;
+	struct slave *slave, *next;
+
+	list_for_each_entry_safe(slave, next, all_slaves, list)
+		vrf_del_slave(dev, slave->dev);
+
 	unregister_netdevice_queue(dev, head);
 }
 
@@ -916,6 +934,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
+	if (vrf->tb_id == RT_TABLE_UNSPEC)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e0fcda4ddd55..dab3bf6649e6 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -77,6 +77,8 @@ static const u8 all_zeros_mac[ETH_ALEN];
 
 static int vxlan_sock_add(struct vxlan_dev *vxlan);
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);
+
 /* per-network namespace private data for this module */
 struct vxlan_net {
 	struct list_head  vxlan_list;
@@ -593,7 +595,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 		}
 	}
 
-	pp = eth_gro_receive(head, skb);
+	pp = call_gro_receive(eth_gro_receive, head, skb);
 
 out:
 	skb_gro_remcsum_cleanup(skb, &grc);
@@ -1052,6 +1054,8 @@ static void __vxlan_sock_release(struct vxlan_sock *vs)
 
 static void vxlan_sock_release(struct vxlan_dev *vxlan)
 {
+	vxlan_vs_del_dev(vxlan);
+
 	__vxlan_sock_release(vxlan->vn4_sock);
 #if IS_ENABLED(CONFIG_IPV6)
 	__vxlan_sock_release(vxlan->vn6_sock);
@@ -1254,7 +1258,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
-		goto error;
+		goto drop;
 
 	vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
 	flags = ntohl(vxh->vx_flags);
@@ -1306,8 +1310,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		gbp = (struct vxlanhdr_gbp *)vxh;
 		md->gbp = ntohs(gbp->policy_id);
 
-		if (tun_dst)
+		if (tun_dst) {
 			tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
+			tun_dst->u.tun_info.options_len = sizeof(*md);
+		}
 
 		if (gbp->dont_learn)
 			md->gbp |= VXLAN_GBP_DONT_LEARN;
@@ -1342,13 +1348,7 @@ drop:
 bad_flags:
 	netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
 		   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
-
-error:
-	if (tun_dst)
-		dst_release((struct dst_entry *)tun_dst);
-
-	/* Return non vxlan pkt */
-	return 1;
+	goto drop;
 }
 
 static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
@@ -2240,7 +2240,7 @@ static void vxlan_cleanup(unsigned long arg)
 				= container_of(p, struct vxlan_fdb, hlist);
 			unsigned long timeout;
 
-			if (f->state & NUD_PERMANENT)
+			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
 			timeout = f->used + vxlan->cfg.age_interval * HZ;
@@ -2259,6 +2259,15 @@ static void vxlan_cleanup(unsigned long arg)
 	mod_timer(&vxlan->age_timer, next_timer);
 }
 
+static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
+{
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+
+	spin_lock(&vn->sock_lock);
+	hlist_del_init_rcu(&vxlan->hlist);
+	spin_unlock(&vn->sock_lock);
+}
+
 static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
@@ -2368,29 +2377,43 @@ static void vxlan_set_multicast_list(struct net_device *dev)
 {
 }
 
-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+static int __vxlan_change_mtu(struct net_device *dev,
+			      struct net_device *lowerdev,
+			      struct vxlan_rdst *dst, int new_mtu, bool strict)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct net_device *lowerdev;
-	int max_mtu;
+	int max_mtu = IP_MAX_MTU;
 
-	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
-	if (lowerdev == NULL)
-		return eth_change_mtu(dev, new_mtu);
+	if (lowerdev)
+		max_mtu = lowerdev->mtu;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6)
-		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+		max_mtu -= VXLAN6_HEADROOM;
 	else
-		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+		max_mtu -= VXLAN_HEADROOM;
 
-	if (new_mtu < 68 || new_mtu > max_mtu)
+	if (new_mtu < 68)
 		return -EINVAL;
 
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
 
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *dst = &vxlan->default_dst;
+	struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+							 dst->remote_ifindex);
+	return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
+}
+
 static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
 				struct ip_tunnel_info *info,
 				__be16 sport, __be16 dport)
@@ -2590,7 +2613,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
 
 	if (data[IFLA_VXLAN_ID]) {
 		__u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
-		if (id >= VXLAN_VID_MASK)
+		if (id >= VXLAN_N_VID)
 			return -ERANGE;
 	}
 
@@ -2766,6 +2789,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
+	struct net_device *lowerdev = NULL;
 
 	vxlan->net = src_net;
 
@@ -2786,9 +2810,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	}
 
 	if (conf->remote_ifindex) {
-		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
@@ -2812,6 +2834,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (conf->mtu) {
+		err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+		if (err)
+			return err;
+	}
+
 	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
 		needed_headroom += VXLAN6_HEADROOM;
 	else
@@ -2989,6 +3017,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
+	if (tb[IFLA_MTU])
+		conf.mtu = nla_get_u32(tb[IFLA_MTU]);
+
 	err = vxlan_dev_configure(src_net, dev, &conf);
 	switch (err) {
 	case -ENODEV:
@@ -3010,12 +3041,6 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
-
-	spin_lock(&vn->sock_lock);
-	if (!hlist_unhashed(&vxlan->hlist))
-		hlist_del_rcu(&vxlan->hlist);
-	spin_unlock(&vn->sock_lock);
 
 	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 44541dbc5c28..69b994f3b8c5 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                 dev->mem_start   = card->phys_mem
                                  + BUF_OFFSET ( txBuffer[i][0][0]);
                 dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
+                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
                 dev->base_addr   = card->pci_conf;
                 dev->irq         = card->irq;
 
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 0947cc271e69..05de75360fa4 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -1607,6 +1607,12 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode)
 		goto err_wmi_detach;
 	}
 
+	/* If firmware indicates Full Rx Reorder support it must be used in a
+	 * slightly different manner. Let HTT code know.
+	 */
+	ar->htt.rx_ring.in_ord_rx = !!(test_bit(WMI_SERVICE_RX_FULL_REORDER,
+						ar->wmi.svc_map));
+
 	status = ath10k_htt_rx_alloc(&ar->htt);
 	if (status) {
 		ath10k_err(ar, "failed to alloc htt rx: %d\n", status);
@@ -1669,18 +1675,16 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode)
 		goto err_hif_stop;
 	}
 
-	/* If firmware indicates Full Rx Reorder support it must be used in a
-	 * slightly different manner. Let HTT code know.
-	 */
-	ar->htt.rx_ring.in_ord_rx = !!(test_bit(WMI_SERVICE_RX_FULL_REORDER,
-						ar->wmi.svc_map));
-
 	status = ath10k_htt_rx_ring_refill(ar);
 	if (status) {
 		ath10k_err(ar, "failed to refill htt rx ring: %d\n", status);
 		goto err_hif_stop;
 	}
 
+	ar->free_vdev_map = (1LL << ar->max_num_vdevs) - 1;
+
+	INIT_LIST_HEAD(&ar->arvifs);
+
 	/* we don't care about HTT in UTF mode */
 	if (mode == ATH10K_FIRMWARE_MODE_NORMAL) {
 		status = ath10k_htt_setup(&ar->htt);
@@ -1694,10 +1698,6 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode)
 	if (status)
 		goto err_hif_stop;
 
-	ar->free_vdev_map = (1LL << ar->max_num_vdevs) - 1;
-
-	INIT_LIST_HEAD(&ar->arvifs);
-
 	return 0;
 
 err_hif_stop:
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 6cc1aa3449c8..1a88a24ffeac 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -1986,7 +1986,12 @@ static ssize_t ath10k_write_pktlog_filter(struct file *file,
 		goto out;
 	}
 
-	if (filter && (filter != ar->debug.pktlog_filter)) {
+	if (filter == ar->debug.pktlog_filter) {
+		ret = count;
+		goto out;
+	}
+
+	if (filter) {
 		ret = ath10k_wmi_pdev_pktlog_enable(ar, filter);
 		if (ret) {
 			ath10k_warn(ar, "failed to enable pktlog filter %x: %d\n",
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 95a55405ebf0..6decf4a95ce1 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4456,7 +4456,10 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		goto err_vdev_delete;
 	}
 
-	if (ar->cfg_tx_chainmask) {
+	/* Configuring number of spatial stream for monitor interface is causing
+	 * target assert in qca9888 and qca6174.
+	 */
+	if (ar->cfg_tx_chainmask && (vif->type != NL80211_IFTYPE_MONITOR)) {
 		u16 nss = get_nss_from_chainmask(ar->cfg_tx_chainmask);
 
 		vdev_param = ar->wmi.vdev_param->nss;
@@ -6348,12 +6351,13 @@ static u64 ath10k_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 static int ath10k_ampdu_action(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
-			       enum ieee80211_ampdu_mlme_action action,
-			       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			       u8 buf_size, bool amsdu)
+			       struct ieee80211_ampdu_params *params)
 {
 	struct ath10k *ar = hw->priv;
 	struct ath10k_vif *arvif = ath10k_vif_to_arvif(vif);
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
 
 	ath10k_dbg(ar, ATH10K_DBG_MAC, "mac ampdu vdev_id %i sta %pM tid %hu action %d\n",
 		   arvif->vdev_id, sta->addr, tid, action);
@@ -6416,7 +6420,13 @@ ath10k_mac_update_rx_channel(struct ath10k *ar,
 			def = &vifs[0].new_ctx->def;
 
 		ar->rx_channel = def->chan;
-	} else if (ctx && ath10k_mac_num_chanctxs(ar) == 0) {
+	} else if ((ctx && ath10k_mac_num_chanctxs(ar) == 0) ||
+		   (ctx && (ar->state == ATH10K_STATE_RESTARTED))) {
+		/* During driver restart due to firmware assert, since mac80211
+		 * already has valid channel context for given radio, channel
+		 * context iteration return num_chanctx > 0. So fix rx_channel
+		 * when restart is in progress.
+		 */
 		ar->rx_channel = ctx->def.chan;
 	} else {
 		ar->rx_channel = NULL;
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 930785a724e1..907fd60c4241 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -3050,7 +3050,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 		goto err_core_destroy;
 	}
 
-	if (QCA_REV_6174(ar))
+	if (QCA_REV_6174(ar) || QCA_REV_9377(ar))
 		ath10k_pci_override_ce_config(ar);
 
 	ret = ath10k_pci_alloc_pipes(ar);
diff --git a/drivers/net/wireless/ath/ath10k/spectral.c b/drivers/net/wireless/ath/ath10k/spectral.c
index 4671cfbcd8f7..a0e7eebc206a 100644
--- a/drivers/net/wireless/ath/ath10k/spectral.c
+++ b/drivers/net/wireless/ath/ath10k/spectral.c
@@ -338,7 +338,7 @@ static ssize_t write_file_spec_scan_ctl(struct file *file,
 		} else {
 			res = -EINVAL;
 		}
-	} else if (strncmp("background", buf, 9) == 0) {
+	} else if (strncmp("background", buf, 10) == 0) {
 		res = ath10k_spectral_scan_config(ar, SPECTRAL_BACKGROUND);
 	} else if (strncmp("manual", buf, 6) == 0) {
 		res = ath10k_spectral_scan_config(ar, SPECTRAL_MANUAL);
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index 8f4f6a892581..cfed5808bc4e 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -639,6 +639,9 @@ ath10k_wmi_vdev_spectral_conf(struct ath10k *ar,
 	struct sk_buff *skb;
 	u32 cmd_id;
 
+	if (!ar->wmi.ops->gen_vdev_spectral_conf)
+		return -EOPNOTSUPP;
+
 	skb = ar->wmi.ops->gen_vdev_spectral_conf(ar, arg);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -654,6 +657,9 @@ ath10k_wmi_vdev_spectral_enable(struct ath10k *ar, u32 vdev_id, u32 trigger,
 	struct sk_buff *skb;
 	u32 cmd_id;
 
+	if (!ar->wmi.ops->gen_vdev_spectral_enable)
+		return -EOPNOTSUPP;
+
 	skb = ar->wmi.ops->gen_vdev_spectral_enable(ar, vdev_id, trigger,
 						    enable);
 	if (IS_ERR(skb))
diff --git a/drivers/net/wireless/ath/ath5k/led.c b/drivers/net/wireless/ath/ath5k/led.c
index 803030fd17d3..6a2a16856763 100644
--- a/drivers/net/wireless/ath/ath5k/led.c
+++ b/drivers/net/wireless/ath/ath5k/led.c
@@ -77,7 +77,7 @@ static const struct pci_device_id ath5k_led_devices[] = {
 	/* HP Compaq CQ60-206US (ddreggors@jumptv.com) */
 	{ ATH_SDEVICE(PCI_VENDOR_ID_HP, 0x0137a), ATH_LED(3, 1) },
 	/* HP Compaq C700 (nitrousnrg@gmail.com) */
-	{ ATH_SDEVICE(PCI_VENDOR_ID_HP, 0x0137b), ATH_LED(3, 1) },
+	{ ATH_SDEVICE(PCI_VENDOR_ID_HP, 0x0137b), ATH_LED(3, 0) },
 	/* LiteOn AR5BXB63 (magooz@salug.it) */
 	{ ATH_SDEVICE(PCI_VENDOR_ID_ATHEROS, 0x3067), ATH_LED(3, 0) },
 	/* IBM-specific AR5212 (all others) */
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index dc44cfef7517..16e052d02c94 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -502,8 +502,7 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			break;
 		return -EOPNOTSUPP;
 	default:
-		WARN_ON(1);
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	mutex_lock(&ah->lock);
diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
index 8f8793004b9f..1b271b99c49e 100644
--- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
@@ -274,6 +274,9 @@ void ar5008_hw_cmn_spur_mitigate(struct ath_hw *ah,
 	};
 	static const int inc[4] = { 0, 100, 0, 0 };
 
+	memset(&mask_m, 0, sizeof(int8_t) * 123);
+	memset(&mask_p, 0, sizeof(int8_t) * 123);
+
 	cur_bin = -6000;
 	upper = bin + 100;
 	lower = bin - 100;
@@ -424,14 +427,9 @@ static void ar5008_hw_spur_mitigate(struct ath_hw *ah,
 	int tmp, new;
 	int i;
 
-	int8_t mask_m[123];
-	int8_t mask_p[123];
 	int cur_bb_spur;
 	bool is2GHz = IS_CHAN_2GHZ(chan);
 
-	memset(&mask_m, 0, sizeof(int8_t) * 123);
-	memset(&mask_p, 0, sizeof(int8_t) * 123);
-
 	for (i = 0; i < AR_EEPROM_MODAL_SPURS; i++) {
 		cur_bb_spur = ah->eep_ops->get_spur_channel(ah, i, is2GHz);
 		if (AR_NO_SPUR == cur_bb_spur)
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
index db6624527d99..53d7445a5d12 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
@@ -178,14 +178,9 @@ static void ar9002_hw_spur_mitigate(struct ath_hw *ah,
 	int i;
 	struct chan_centers centers;
 
-	int8_t mask_m[123];
-	int8_t mask_p[123];
 	int cur_bb_spur;
 	bool is2GHz = IS_CHAN_2GHZ(chan);
 
-	memset(&mask_m, 0, sizeof(int8_t) * 123);
-	memset(&mask_p, 0, sizeof(int8_t) * 123);
-
 	ath9k_hw_get_channel_centers(ah, chan, &centers);
 	freq = centers.synth_center;
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 8b4561e8ce1a..ef493271c712 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -4176,7 +4176,7 @@ static void ath9k_hw_ar9300_set_board_values(struct ath_hw *ah,
 	if (!AR_SREV_9330(ah) && !AR_SREV_9340(ah) && !AR_SREV_9531(ah))
 		ar9003_hw_internal_regulator_apply(ah);
 	ar9003_hw_apply_tuning_caps(ah);
-	ar9003_hw_apply_minccapwr_thresh(ah, chan);
+	ar9003_hw_apply_minccapwr_thresh(ah, is2ghz);
 	ar9003_hw_txend_to_xpa_off_apply(ah, is2ghz);
 	ar9003_hw_thermometer_apply(ah);
 	ar9003_hw_thermo_cal_apply(ah);
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h
index 694ca2e680e5..74670e08e6da 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.h
@@ -73,13 +73,13 @@
 #define AR9300_OTP_BASE \
 		((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x30000 : 0x14000)
 #define AR9300_OTP_STATUS \
-		((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x30018 : 0x15f18)
+		((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x31018 : 0x15f18)
 #define AR9300_OTP_STATUS_TYPE		0x7
 #define AR9300_OTP_STATUS_VALID		0x4
 #define AR9300_OTP_STATUS_ACCESS_BUSY	0x2
 #define AR9300_OTP_STATUS_SM_BUSY	0x1
 #define AR9300_OTP_READ_DATA \
-		((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x3001c : 0x15f1c)
+		((AR_SREV_9340(ah) || AR_SREV_9550(ah)) ? 0x3101c : 0x15f1c)
 
 enum targetPowerHTRates {
 	HT_TARGET_RATE_0_8_16,
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index 201425e7f9cb..fbc8c9a9014b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1815,8 +1815,6 @@ static void ar9003_hw_spectral_scan_wait(struct ath_hw *ah)
 static void ar9003_hw_tx99_start(struct ath_hw *ah, u32 qnum)
 {
 	REG_SET_BIT(ah, AR_PHY_TEST, PHY_AGC_CLR);
-	REG_SET_BIT(ah, 0x9864, 0x7f000);
-	REG_SET_BIT(ah, 0x9924, 0x7f00fe);
 	REG_CLR_BIT(ah, AR_DIAG_SW, AR_DIAG_RX_DIS);
 	REG_WRITE(ah, AR_CR, AR_CR_RXD);
 	REG_WRITE(ah, AR_DLCL_IFS(qnum), 0);
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index b42f4a963ef4..a660e40f2df1 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -959,6 +959,7 @@ struct ath_softc {
 	struct survey_info *cur_survey;
 	struct survey_info survey[ATH9K_NUM_CHANNELS];
 
+	spinlock_t intr_lock;
 	struct tasklet_struct intr_tq;
 	struct tasklet_struct bcon_tasklet;
 	struct ath_hw *sc_ah;
diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c
index a8762711ad74..03945731eb65 100644
--- a/drivers/net/wireless/ath/ath9k/common-spectral.c
+++ b/drivers/net/wireless/ath/ath9k/common-spectral.c
@@ -528,6 +528,9 @@ int ath_cmn_process_fft(struct ath_spec_scan_priv *spec_priv, struct ieee80211_h
 	if (!(radar_info->pulse_bw_info & SPECTRAL_SCAN_BITMASK))
 		return 0;
 
+	if (!spec_priv->rfs_chan_spec_scan)
+		return 1;
+
 	/* Output buffers are full, no need to process anything
 	 * since there is no space to put the result anyway
 	 */
@@ -1072,7 +1075,7 @@ static struct rchan_callbacks rfs_spec_scan_cb = {
 
 void ath9k_cmn_spectral_deinit_debug(struct ath_spec_scan_priv *spec_priv)
 {
-	if (config_enabled(CONFIG_ATH9K_DEBUGFS)) {
+	if (config_enabled(CONFIG_ATH9K_DEBUGFS) && spec_priv->rfs_chan_spec_scan) {
 		relay_close(spec_priv->rfs_chan_spec_scan);
 		spec_priv->rfs_chan_spec_scan = NULL;
 	}
@@ -1086,6 +1089,9 @@ void ath9k_cmn_spectral_init_debug(struct ath_spec_scan_priv *spec_priv,
 					    debugfs_phy,
 					    1024, 256, &rfs_spec_scan_cb,
 					    NULL);
+	if (!spec_priv->rfs_chan_spec_scan)
+		return;
+
 	debugfs_create_file("spectral_scan_ctl",
 			    S_IRUSR | S_IWUSR,
 			    debugfs_phy, spec_priv,
diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index cc81482c934d..113a43fca9cf 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -403,10 +403,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 
 	if (match) {
 		if (AR_SREV_9287(ah)) {
-			/* FIXME: array overrun? */
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_9287[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_9287[idxL].pwrPdg[i],
 						data_9287[idxL].vpdPdg[i],
@@ -416,7 +415,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else if (eeprom_4k) {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_4k[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_4k[idxL].pwrPdg[i],
 						data_4k[idxL].vpdPdg[i],
@@ -426,7 +425,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_def[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_def[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_def[idxL].pwrPdg[i],
 						data_def[idxL].vpdPdg[i],
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 165dd202c365..c92564b3ec85 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -37,6 +37,7 @@ static struct usb_device_id ath9k_hif_usb_ids[] = {
 	{ USB_DEVICE(0x0cf3, 0xb002) }, /* Ubiquiti WifiStation */
 	{ USB_DEVICE(0x057c, 0x8403) }, /* AVM FRITZ!WLAN 11N v2 USB */
 	{ USB_DEVICE(0x0471, 0x209e) }, /* Philips (or NXP) PTA01 */
+	{ USB_DEVICE(0x1eda, 0x2315) }, /* AirTies */
 
 	{ USB_DEVICE(0x0cf3, 0x7015),
 	  .driver_info = AR9287_USB },  /* Atheros */
@@ -1216,6 +1217,9 @@ static int send_eject_command(struct usb_interface *interface)
 	u8 bulk_out_ep;
 	int r;
 
+	if (iface_desc->desc.bNumEndpoints < 2)
+		return -ENODEV;
+
 	/* Find bulk out endpoint */
 	for (r = 1; r >= 0; r--) {
 		endpoint = &iface_desc->endpoint[r].desc;
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index a680a970b7f7..e4281438c04f 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1657,13 +1657,14 @@ static void ath9k_htc_reset_tsf(struct ieee80211_hw *hw,
 
 static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
-				  enum ieee80211_ampdu_mlme_action action,
-				  struct ieee80211_sta *sta,
-				  u16 tid, u16 *ssn, u8 buf_size, bool amsdu)
+				  struct ieee80211_ampdu_params *params)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
 	struct ath9k_htc_sta *ista;
 	int ret = 0;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
 
 	mutex_lock(&priv->mutex);
 	ath9k_htc_ps_wakeup(priv);
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 2e2b92ba96b8..0f5672f5c9ba 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -49,6 +49,10 @@ int ath9k_led_blink;
 module_param_named(blink, ath9k_led_blink, int, 0444);
 MODULE_PARM_DESC(blink, "Enable LED blink on activity");
 
+static int ath9k_led_active_high = -1;
+module_param_named(led_active_high, ath9k_led_active_high, int, 0444);
+MODULE_PARM_DESC(led_active_high, "Invert LED polarity");
+
 static int ath9k_btcoex_enable;
 module_param_named(btcoex_enable, ath9k_btcoex_enable, int, 0444);
 MODULE_PARM_DESC(btcoex_enable, "Enable wifi-BT coexistence");
@@ -600,6 +604,9 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 	if (ret)
 		return ret;
 
+	if (ath9k_led_active_high != -1)
+		ah->config.led_active_high = ath9k_led_active_high == 1;
+
 	/*
 	 * Enable WLAN/BT RX Antenna diversity only when:
 	 *
@@ -612,6 +619,7 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 		common->bt_ant_diversity = 1;
 
 	spin_lock_init(&common->cc_lock);
+	spin_lock_init(&sc->intr_lock);
 	spin_lock_init(&sc->sc_serial_rw);
 	spin_lock_init(&sc->sc_pm_lock);
 	spin_lock_init(&sc->chan_lock);
@@ -862,8 +870,8 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
 			hw->wiphy->interface_modes |=
 					BIT(NL80211_IFTYPE_P2P_DEVICE);
 
-			hw->wiphy->iface_combinations = if_comb;
-			hw->wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+		hw->wiphy->iface_combinations = if_comb;
+		hw->wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
 	}
 
 	hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index bba85d1a6cd1..d937c39b3a0b 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -805,21 +805,12 @@ void ath9k_hw_disable_interrupts(struct ath_hw *ah)
 }
 EXPORT_SYMBOL(ath9k_hw_disable_interrupts);
 
-void ath9k_hw_enable_interrupts(struct ath_hw *ah)
+static void __ath9k_hw_enable_interrupts(struct ath_hw *ah)
 {
 	struct ath_common *common = ath9k_hw_common(ah);
 	u32 sync_default = AR_INTR_SYNC_DEFAULT;
 	u32 async_mask;
 
-	if (!(ah->imask & ATH9K_INT_GLOBAL))
-		return;
-
-	if (!atomic_inc_and_test(&ah->intr_ref_cnt)) {
-		ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n",
-			atomic_read(&ah->intr_ref_cnt));
-		return;
-	}
-
 	if (AR_SREV_9340(ah) || AR_SREV_9550(ah) || AR_SREV_9531(ah) ||
 	    AR_SREV_9561(ah))
 		sync_default &= ~AR_INTR_SYNC_HOST1_FATAL;
@@ -841,6 +832,39 @@ void ath9k_hw_enable_interrupts(struct ath_hw *ah)
 	ath_dbg(common, INTERRUPT, "AR_IMR 0x%x IER 0x%x\n",
 		REG_READ(ah, AR_IMR), REG_READ(ah, AR_IER));
 }
+
+void ath9k_hw_resume_interrupts(struct ath_hw *ah)
+{
+	struct ath_common *common = ath9k_hw_common(ah);
+
+	if (!(ah->imask & ATH9K_INT_GLOBAL))
+		return;
+
+	if (atomic_read(&ah->intr_ref_cnt) != 0) {
+		ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n",
+			atomic_read(&ah->intr_ref_cnt));
+		return;
+	}
+
+	__ath9k_hw_enable_interrupts(ah);
+}
+EXPORT_SYMBOL(ath9k_hw_resume_interrupts);
+
+void ath9k_hw_enable_interrupts(struct ath_hw *ah)
+{
+	struct ath_common *common = ath9k_hw_common(ah);
+
+	if (!(ah->imask & ATH9K_INT_GLOBAL))
+		return;
+
+	if (!atomic_inc_and_test(&ah->intr_ref_cnt)) {
+		ath_dbg(common, INTERRUPT, "Do not enable IER ref count %d\n",
+			atomic_read(&ah->intr_ref_cnt));
+		return;
+	}
+
+	__ath9k_hw_enable_interrupts(ah);
+}
 EXPORT_SYMBOL(ath9k_hw_enable_interrupts);
 
 void ath9k_hw_set_interrupts(struct ath_hw *ah)
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index 7fbf7f965f61..1b63d26f30ce 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -748,6 +748,7 @@ void ath9k_hw_set_interrupts(struct ath_hw *ah);
 void ath9k_hw_enable_interrupts(struct ath_hw *ah);
 void ath9k_hw_disable_interrupts(struct ath_hw *ah);
 void ath9k_hw_kill_interrupts(struct ath_hw *ah);
+void ath9k_hw_resume_interrupts(struct ath_hw *ah);
 
 void ar9002_hw_attach_mac_ops(struct ath_hw *ah);
 
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index d184e682e636..3abc64574116 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -373,21 +373,20 @@ void ath9k_tasklet(unsigned long data)
 	struct ath_common *common = ath9k_hw_common(ah);
 	enum ath_reset_type type;
 	unsigned long flags;
-	u32 status = sc->intrstatus;
+	u32 status;
 	u32 rxmask;
 
+	spin_lock_irqsave(&sc->intr_lock, flags);
+	status = sc->intrstatus;
+	sc->intrstatus = 0;
+	spin_unlock_irqrestore(&sc->intr_lock, flags);
+
 	ath9k_ps_wakeup(sc);
 	spin_lock(&sc->sc_pcu_lock);
 
 	if (status & ATH9K_INT_FATAL) {
 		type = RESET_TYPE_FATAL_INT;
 		ath9k_queue_reset(sc, type);
-
-		/*
-		 * Increment the ref. counter here so that
-		 * interrupts are enabled in the reset routine.
-		 */
-		atomic_inc(&ah->intr_ref_cnt);
 		ath_dbg(common, RESET, "FATAL: Skipping interrupts\n");
 		goto out;
 	}
@@ -403,11 +402,6 @@ void ath9k_tasklet(unsigned long data)
 			type = RESET_TYPE_BB_WATCHDOG;
 			ath9k_queue_reset(sc, type);
 
-			/*
-			 * Increment the ref. counter here so that
-			 * interrupts are enabled in the reset routine.
-			 */
-			atomic_inc(&ah->intr_ref_cnt);
 			ath_dbg(common, RESET,
 				"BB_WATCHDOG: Skipping interrupts\n");
 			goto out;
@@ -420,7 +414,6 @@ void ath9k_tasklet(unsigned long data)
 		if ((sc->gtt_cnt >= MAX_GTT_CNT) && !ath9k_hw_check_alive(ah)) {
 			type = RESET_TYPE_TX_GTT;
 			ath9k_queue_reset(sc, type);
-			atomic_inc(&ah->intr_ref_cnt);
 			ath_dbg(common, RESET,
 				"GTT: Skipping interrupts\n");
 			goto out;
@@ -477,7 +470,7 @@ void ath9k_tasklet(unsigned long data)
 	ath9k_btcoex_handle_interrupt(sc, status);
 
 	/* re-enable hardware interrupt */
-	ath9k_hw_enable_interrupts(ah);
+	ath9k_hw_resume_interrupts(ah);
 out:
 	spin_unlock(&sc->sc_pcu_lock);
 	ath9k_ps_restore(sc);
@@ -541,7 +534,9 @@ irqreturn_t ath_isr(int irq, void *dev)
 		return IRQ_NONE;
 
 	/* Cache the status */
-	sc->intrstatus = status;
+	spin_lock(&sc->intr_lock);
+	sc->intrstatus |= status;
+	spin_unlock(&sc->intr_lock);
 
 	if (status & SCHED_INTR)
 		sched = true;
@@ -587,7 +582,7 @@ chip_reset:
 
 	if (sched) {
 		/* turn off every interrupt */
-		ath9k_hw_disable_interrupts(ah);
+		ath9k_hw_kill_interrupts(ah);
 		tasklet_schedule(&sc->intr_tq);
 	}
 
@@ -1550,13 +1545,13 @@ static int ath9k_sta_state(struct ieee80211_hw *hw,
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	int ret = 0;
 
-	if (old_state == IEEE80211_STA_AUTH &&
-	    new_state == IEEE80211_STA_ASSOC) {
+	if (old_state == IEEE80211_STA_NOTEXIST &&
+	    new_state == IEEE80211_STA_NONE) {
 		ret = ath9k_sta_add(hw, vif, sta);
 		ath_dbg(common, CONFIG,
 			"Add station: %pM\n", sta->addr);
-	} else if (old_state == IEEE80211_STA_ASSOC &&
-		   new_state == IEEE80211_STA_AUTH) {
+	} else if (old_state == IEEE80211_STA_NONE &&
+		   new_state == IEEE80211_STA_NOTEXIST) {
 		ret = ath9k_sta_remove(hw, vif, sta);
 		ath_dbg(common, CONFIG,
 			"Remove station: %pM\n", sta->addr);
@@ -1860,14 +1855,16 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 static int ath9k_ampdu_action(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif,
-			      enum ieee80211_ampdu_mlme_action action,
-			      struct ieee80211_sta *sta,
-			      u16 tid, u16 *ssn, u8 buf_size, bool amsdu)
+			      struct ieee80211_ampdu_params *params)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	bool flush = false;
 	int ret = 0;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 
 	mutex_lock(&sc->mutex);
 
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index e6fef1be9977..ea7b8c25955f 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -27,8 +27,17 @@ static const struct pci_device_id ath_pci_id_table[] = {
 	{ PCI_VDEVICE(ATHEROS, 0x0023) }, /* PCI   */
 	{ PCI_VDEVICE(ATHEROS, 0x0024) }, /* PCI-E */
 	{ PCI_VDEVICE(ATHEROS, 0x0027) }, /* PCI   */
+
+#ifdef CONFIG_ATH9K_PCOEM
+	/* Mini PCI AR9220 MB92 cards: Compex WLM200NX, Wistron DNMA-92 */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+			 0x0029,
+			 PCI_VENDOR_ID_ATHEROS,
+			 0x2096),
+	  .driver_data = ATH9K_PCI_LED_ACT_HI },
+#endif
+
 	{ PCI_VDEVICE(ATHEROS, 0x0029) }, /* PCI   */
-	{ PCI_VDEVICE(ATHEROS, 0x002A) }, /* PCI-E */
 
 #ifdef CONFIG_ATH9K_PCOEM
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
@@ -76,7 +85,11 @@ static const struct pci_device_id ath_pci_id_table[] = {
 			 0x10CF, /* Fujitsu */
 			 0x1536),
 	  .driver_data = ATH9K_PCI_D3_L1_WAR },
+#endif
 
+	{ PCI_VDEVICE(ATHEROS, 0x002A) }, /* PCI-E */
+
+#ifdef CONFIG_ATH9K_PCOEM
 	/* AR9285 card for Asus */
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
 			 0x002B,
diff --git a/drivers/net/wireless/ath/ath9k/tx99.c b/drivers/net/wireless/ath/ath9k/tx99.c
index ac4781f37e78..b4e6304afd40 100644
--- a/drivers/net/wireless/ath/ath9k/tx99.c
+++ b/drivers/net/wireless/ath/ath9k/tx99.c
@@ -190,22 +190,27 @@ static ssize_t write_file_tx99(struct file *file, const char __user *user_buf,
 	if (strtobool(buf, &start))
 		return -EINVAL;
 
+	mutex_lock(&sc->mutex);
+
 	if (start == sc->tx99_state) {
 		if (!start)
-			return count;
+			goto out;
 		ath_dbg(common, XMIT, "Resetting TX99\n");
 		ath9k_tx99_deinit(sc);
 	}
 
 	if (!start) {
 		ath9k_tx99_deinit(sc);
-		return count;
+		goto out;
 	}
 
 	r = ath9k_tx99_init(sc);
-	if (r)
+	if (r) {
+		mutex_unlock(&sc->mutex);
 		return r;
-
+	}
+out:
+	mutex_unlock(&sc->mutex);
 	return count;
 }
 
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index 19d3d64416bf..4d1527a2e292 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1413,10 +1413,12 @@ static void carl9170_ampdu_work(struct work_struct *work)
 
 static int carl9170_op_ampdu_action(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
-				    enum ieee80211_ampdu_mlme_action action,
-				    struct ieee80211_sta *sta,
-				    u16 tid, u16 *ssn, u8 buf_size, bool amsdu)
+				    struct ieee80211_ampdu_params *params)
 {
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 	struct ar9170 *ar = hw->priv;
 	struct carl9170_sta_info *sta_info = (void *) sta->drv_priv;
 	struct carl9170_sta_tid *tid_info;
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 7c169abdbafe..a27279c2c695 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -857,12 +857,14 @@ static int wcn36xx_resume(struct ieee80211_hw *hw)
 
 static int wcn36xx_ampdu_action(struct ieee80211_hw *hw,
 		    struct ieee80211_vif *vif,
-		    enum ieee80211_ampdu_mlme_action action,
-		    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-		    u8 buf_size, bool amsdu)
+		    struct ieee80211_ampdu_params *params)
 {
 	struct wcn36xx *wcn = hw->priv;
 	struct wcn36xx_sta *sta_priv = NULL;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 
 	wcn36xx_dbg(WCN36XX_DBG_MAC, "mac ampdu action action %d tid %d\n",
 		    action, tid);
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index bb69a5949aea..85bca557a339 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -330,18 +330,19 @@ static void wil_fw_error_worker(struct work_struct *work)
 
 	wil->last_fw_recovery = jiffies;
 
+	wil_info(wil, "fw error recovery requested (try %d)...\n",
+		 wil->recovery_count);
+	if (!no_fw_recovery)
+		wil->recovery_state = fw_recovery_running;
+	if (wil_wait_for_recovery(wil) != 0)
+		return;
+
 	mutex_lock(&wil->mutex);
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
-		wil_info(wil, "fw error recovery requested (try %d)...\n",
-			 wil->recovery_count);
-		if (!no_fw_recovery)
-			wil->recovery_state = fw_recovery_running;
-		if (0 != wil_wait_for_recovery(wil))
-			break;
-
+		/* silent recovery, upper layers will see disconnect */
 		__wil_down(wil);
 		__wil_up(wil);
 		break;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
index 410a6645d316..59cef6c69fe8 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
@@ -726,8 +726,10 @@ int brcmf_sdiod_recv_chain(struct brcmf_sdio_dev *sdiodev,
 			return -ENOMEM;
 		err = brcmf_sdiod_buffrw(sdiodev, SDIO_FUNC_2, false, addr,
 					 glom_skb);
-		if (err)
+		if (err) {
+			brcmu_pkt_buf_free_skb(glom_skb);
 			goto done;
+		}
 
 		skb_queue_walk(pktq, skb) {
 			memcpy(skb->data, glom_skb->data, skb->len);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
index deb5f78dcacc..da5826d788d6 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
@@ -2408,7 +2408,7 @@ static void brcmf_fill_bss_param(struct brcmf_if *ifp, struct station_info *si)
 				     WL_BSS_INFO_MAX);
 	if (err) {
 		brcmf_err("Failed to get bss info (%d)\n", err);
-		return;
+		goto out_kfree;
 	}
 	si->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
 	si->bss_param.beacon_interval = le16_to_cpu(buf->bss_le.beacon_period);
@@ -2420,6 +2420,9 @@ static void brcmf_fill_bss_param(struct brcmf_if *ifp, struct station_info *si)
 		si->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_PREAMBLE;
 	if (capability & WLAN_CAPABILITY_SHORT_SLOT_TIME)
 		si->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME;
+
+out_kfree:
+	kfree(buf);
 }
 
 static s32
@@ -4099,7 +4102,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 				(u8 *)&settings->beacon.head[ie_offset],
 				settings->beacon.head_len - ie_offset,
 				WLAN_EID_SSID);
-		if (!ssid_ie)
+		if (!ssid_ie || ssid_ie->len > IEEE80211_MAX_SSID_LEN)
 			return -EINVAL;
 
 		memcpy(ssid_le.SSID, ssid_ie->data, ssid_ie->len);
@@ -4469,6 +4472,11 @@ brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, true,
 					GFP_KERNEL);
 	} else if (ieee80211_is_action(mgmt->frame_control)) {
+		if (len > BRCMF_FIL_ACTION_FRAME_SIZE + DOT11_MGMT_HDR_LEN) {
+			brcmf_err("invalid action frame length\n");
+			err = -EINVAL;
+			goto exit;
+		}
 		af_params = kzalloc(sizeof(*af_params), GFP_KERNEL);
 		if (af_params == NULL) {
 			brcmf_err("unable to allocate frame\n");
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/core.c b/drivers/net/wireless/brcm80211/brcmfmac/core.c
index b5ab98ee1445..82753e7c7e7c 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/core.c
@@ -211,7 +211,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 	int ret;
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = ifp->drvr;
-	struct ethhdr *eh = (struct ethhdr *)(skb->data);
+	struct ethhdr *eh;
 
 	brcmf_dbg(DATA, "Enter, idx=%d\n", ifp->bssidx);
 
@@ -232,22 +232,13 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 		goto done;
 	}
 
-	/* Make sure there's enough room for any header */
-	if (skb_headroom(skb) < drvr->hdrlen) {
-		struct sk_buff *skb2;
-
-		brcmf_dbg(INFO, "%s: insufficient headroom\n",
+	/* Make sure there's enough writable headroom*/
+	ret = skb_cow_head(skb, drvr->hdrlen);
+	if (ret < 0) {
+		brcmf_err("%s: skb_cow_head failed\n",
 			  brcmf_ifname(drvr, ifp->bssidx));
-		drvr->bus_if->tx_realloc++;
-		skb2 = skb_realloc_headroom(skb, drvr->hdrlen);
 		dev_kfree_skb(skb);
-		skb = skb2;
-		if (skb == NULL) {
-			brcmf_err("%s: skb_realloc_headroom failed\n",
-				  brcmf_ifname(drvr, ifp->bssidx));
-			ret = -ENOMEM;
-			goto done;
-		}
+		goto done;
 	}
 
 	/* validate length for ether packet */
@@ -257,6 +248,8 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 		goto done;
 	}
 
+	eh = (struct ethhdr *)(skb->data);
+
 	if (eh->h_proto == htons(ETH_P_PAE))
 		atomic_inc(&ifp->pend_8021x_cnt);
 
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/brcm80211/brcmsmac/dma.c
index 796f5f9d5d5a..b7df576bb84d 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/dma.c
@@ -1079,8 +1079,10 @@ bool dma_rxfill(struct dma_pub *pub)
 
 		pa = dma_map_single(di->dmadev, p->data, di->rxbufsize,
 				    DMA_FROM_DEVICE);
-		if (dma_mapping_error(di->dmadev, pa))
+		if (dma_mapping_error(di->dmadev, pa)) {
+			brcmu_pkt_buf_free_skb(p);
 			return false;
+		}
 
 		/* save the free packet pointer */
 		di->rxp[rxout] = p;
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index bec2dc1ca2e4..61ae2768132a 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -818,13 +818,15 @@ brcms_ops_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static int
 brcms_ops_ampdu_action(struct ieee80211_hw *hw,
 		    struct ieee80211_vif *vif,
-		    enum ieee80211_ampdu_mlme_action action,
-		    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-		    u8 buf_size, bool amsdu)
+		    struct ieee80211_ampdu_params *params)
 {
 	struct brcms_info *wl = hw->priv;
 	struct scb *scb = &wl->wlc->pri_scb;
 	int status;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u8 buf_size = params->buf_size;
 
 	if (WARN_ON(scb->magic != SCB_MAGIC))
 		return -EIDRM;
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/stf.c b/drivers/net/wireless/brcm80211/brcmsmac/stf.c
index dd9162722495..0ab865de1491 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/stf.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/stf.c
@@ -87,7 +87,7 @@ void
 brcms_c_stf_ss_algo_channel_get(struct brcms_c_info *wlc, u16 *ss_algo_channel,
 			    u16 chanspec)
 {
-	struct tx_power power;
+	struct tx_power power = { };
 	u8 siso_mcs_id, cdd_mcs_id, stbc_mcs_id;
 
 	/* Clear previous settings */
diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c
index 95a7fdb3cc1c..c602a1e674ca 100644
--- a/drivers/net/wireless/cw1200/sta.c
+++ b/drivers/net/wireless/cw1200/sta.c
@@ -2135,9 +2135,7 @@ void cw1200_mcast_timeout(unsigned long arg)
 
 int cw1200_ampdu_action(struct ieee80211_hw *hw,
 			struct ieee80211_vif *vif,
-			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			u8 buf_size, bool amsdu)
+			struct ieee80211_ampdu_params *params)
 {
 	/* Aggregation is implemented fully in firmware,
 	 * including block ack negotiation. Do not allow
diff --git a/drivers/net/wireless/cw1200/sta.h b/drivers/net/wireless/cw1200/sta.h
index bebb3379017f..a0bacaa39b31 100644
--- a/drivers/net/wireless/cw1200/sta.h
+++ b/drivers/net/wireless/cw1200/sta.h
@@ -109,9 +109,7 @@ void cw1200_bss_info_changed(struct ieee80211_hw *dev,
 			     u32 changed);
 int cw1200_ampdu_action(struct ieee80211_hw *hw,
 			struct ieee80211_vif *vif,
-			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			u8 buf_size, bool amsdu);
+			struct ieee80211_ampdu_params *params);
 
 void cw1200_suspend_resume(struct cw1200_common *priv,
 			  struct wsm_suspend_resume *arg);
diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c
index 6df3ee561d52..515aa3f993f3 100644
--- a/drivers/net/wireless/hostap/hostap_hw.c
+++ b/drivers/net/wireless/hostap/hostap_hw.c
@@ -836,25 +836,30 @@ static int hfa384x_get_rid(struct net_device *dev, u16 rid, void *buf, int len,
 	spin_lock_bh(&local->baplock);
 
 	res = hfa384x_setup_bap(dev, BAP0, rid, 0);
-	if (!res)
-		res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec));
+	if (res)
+		goto unlock;
+
+	res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec));
+	if (res)
+		goto unlock;
 
 	if (le16_to_cpu(rec.len) == 0) {
 		/* RID not available */
 		res = -ENODATA;
+		goto unlock;
 	}
 
 	rlen = (le16_to_cpu(rec.len) - 1) * 2;
-	if (!res && exact_len && rlen != len) {
+	if (exact_len && rlen != len) {
 		printk(KERN_DEBUG "%s: hfa384x_get_rid - RID len mismatch: "
 		       "rid=0x%04x, len=%d (expected %d)\n",
 		       dev->name, rid, rlen, len);
 		res = -ENODATA;
 	}
 
-	if (!res)
-		res = hfa384x_from_bap(dev, BAP0, buf, len);
+	res = hfa384x_from_bap(dev, BAP0, buf, len);
 
+unlock:
 	spin_unlock_bh(&local->baplock);
 	mutex_unlock(&local->rid_bap_mtx);
 
diff --git a/drivers/net/wireless/iwlegacy/3945.c b/drivers/net/wireless/iwlegacy/3945.c
index 93bdf684babe..ae047ab7a4df 100644
--- a/drivers/net/wireless/iwlegacy/3945.c
+++ b/drivers/net/wireless/iwlegacy/3945.c
@@ -1019,12 +1019,13 @@ il3945_hw_txq_ctx_free(struct il_priv *il)
 	int txq_id;
 
 	/* Tx queues */
-	if (il->txq)
+	if (il->txq) {
 		for (txq_id = 0; txq_id < il->hw_params.max_txq_num; txq_id++)
 			if (txq_id == IL39_CMD_QUEUE_NUM)
 				il_cmd_queue_free(il);
 			else
 				il_tx_queue_free(il, txq_id);
+	}
 
 	/* free tx queue structure */
 	il_free_txq_mem(il);
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 6656215a13a9..04b0349a6ad9 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -5982,12 +5982,14 @@ il4965_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 int
 il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 * ssn,
-			u8 buf_size, bool amsdu)
+			struct ieee80211_ampdu_params *params)
 {
 	struct il_priv *il = hw->priv;
 	int ret = -EINVAL;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 
 	D_HT("A-MPDU action on addr %pM tid %d\n", sta->addr, tid);
 
diff --git a/drivers/net/wireless/iwlegacy/4965.h b/drivers/net/wireless/iwlegacy/4965.h
index 8ab8706f9422..e432715e02d8 100644
--- a/drivers/net/wireless/iwlegacy/4965.h
+++ b/drivers/net/wireless/iwlegacy/4965.h
@@ -182,9 +182,7 @@ void il4965_mac_update_tkip_key(struct ieee80211_hw *hw,
 				struct ieee80211_sta *sta, u32 iv32,
 				u16 *phase1key);
 int il4965_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			    enum ieee80211_ampdu_mlme_action action,
-			    struct ieee80211_sta *sta, u16 tid, u16 * ssn,
-			    u8 buf_size, bool amsdu);
+			    struct ieee80211_ampdu_params *params);
 int il4965_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 void
diff --git a/drivers/net/wireless/iwlwifi/dvm/calib.c b/drivers/net/wireless/iwlwifi/dvm/calib.c
index 20e6aa910700..c148085742a0 100644
--- a/drivers/net/wireless/iwlwifi/dvm/calib.c
+++ b/drivers/net/wireless/iwlwifi/dvm/calib.c
@@ -901,7 +901,7 @@ static void iwlagn_gain_computation(struct iwl_priv *priv,
 		/* bound gain by 2 bits value max, 3rd bit is sign */
 		data->delta_gain_code[i] =
 			min(abs(delta_g),
-			(long) CHAIN_NOISE_MAX_DELTA_GAIN_CODE);
+			(s32) CHAIN_NOISE_MAX_DELTA_GAIN_CODE);
 
 		if (delta_g < 0)
 			/*
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index b3ad34e8bf5a..1eb1a823a111 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -729,12 +729,15 @@ static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
 
 static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
-				   enum ieee80211_ampdu_mlme_action action,
-				   struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-				   u8 buf_size, bool amsdu)
+				   struct ieee80211_ampdu_params *params)
 {
 	struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw);
 	int ret = -EINVAL;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	u8 buf_size = params->buf_size;
 	struct iwl_station_priv *sta_priv = (void *) sta->drv_priv;
 
 	IWL_DEBUG_HT(priv, "A-MPDU action on addr %pM tid %d\n",
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index d906fa13ba97..9584f950fd2f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -106,7 +106,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant)
 				    sizeof(tx_ant_cmd), &tx_ant_cmd);
 }
 
-static void iwl_free_fw_paging(struct iwl_mvm *mvm)
+void iwl_free_fw_paging(struct iwl_mvm *mvm)
 {
 	int i;
 
@@ -126,6 +126,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm)
 			     get_order(mvm->fw_paging_db[i].fw_paging_size));
 	}
 	kfree(mvm->trans->paging_download_buf);
+	mvm->trans->paging_download_buf = NULL;
+
 	memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db));
 }
 
@@ -933,7 +935,8 @@ int iwl_mvm_start_fw_dbg_conf(struct iwl_mvm *mvm, u8 conf_id)
 	}
 
 	mvm->fw_dbg_conf = conf_id;
-	return ret;
+
+	return 0;
 }
 
 static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index e88afac51c5d..1a8ea775de08 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -826,13 +826,16 @@ iwl_mvm_ampdu_check_trigger(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
-				    enum ieee80211_ampdu_mlme_action action,
-				    struct ieee80211_sta *sta, u16 tid,
-				    u16 *ssn, u8 buf_size, bool amsdu)
+				    struct ieee80211_ampdu_params *params)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
 	bool tx_agg_ref = false;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	u8 buf_size = params->buf_size;
 
 	IWL_DEBUG_HT(mvm, "A-MPDU action on addr %pM tid %d: action %d\n",
 		     sta->addr, tid, action);
@@ -1557,6 +1560,8 @@ void __iwl_mvm_mac_stop(struct iwl_mvm *mvm)
 	/* the fw is stopped, the aux sta is dead: clean up driver state */
 	iwl_mvm_del_aux_sta(mvm);
 
+	iwl_free_fw_paging(mvm);
+
 	/*
 	 * Clear IN_HW_RESTART flag when stopping the hw (as restart_complete()
 	 * won't be called in this case).
@@ -3990,8 +3995,8 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 	if (idx != 0)
 		return -ENOENT;
 
-	if (fw_has_capa(&mvm->fw->ucode_capa,
-			IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+	if (!fw_has_capa(&mvm->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
 		return -ENOENT;
 
 	mutex_lock(&mvm->mutex);
@@ -4037,8 +4042,8 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
-	if (fw_has_capa(&mvm->fw->ucode_capa,
-			IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
+	if (!fw_has_capa(&mvm->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_RADIO_BEACON_STATS))
 		return;
 
 	/* if beacon filtering isn't on mac80211 does it anyway */
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index 4bde2d027dcd..244e26c26821 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -1190,6 +1190,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm,
 void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm,
 					      struct iwl_rx_cmd_buffer *rxb);
 
+/* Paging */
+void iwl_free_fw_paging(struct iwl_mvm *mvm);
+
 /* MVM debugfs */
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir);
diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c
index b0f59fdd287c..d7d72adb6343 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sf.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sf.c
@@ -215,7 +215,7 @@ static int iwl_mvm_sf_config(struct iwl_mvm *mvm, u8 sta_id,
 			     enum iwl_sf_state new_state)
 {
 	struct iwl_sf_cfg_cmd sf_cmd = {
-		.state = cpu_to_le32(SF_FULL_ON),
+		.state = cpu_to_le32(new_state),
 	};
 	struct ieee80211_sta *sta;
 	int ret = 0;
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index d58c094f2f04..f7e6a09926dd 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -475,48 +475,64 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
 
 #ifdef CONFIG_ACPI
-#define SPL_METHOD		"SPLC"
-#define SPL_DOMAINTYPE_MODULE	BIT(0)
-#define SPL_DOMAINTYPE_WIFI	BIT(1)
-#define SPL_DOMAINTYPE_WIGIG	BIT(2)
-#define SPL_DOMAINTYPE_RFEM	BIT(3)
+#define ACPI_SPLC_METHOD	"SPLC"
+#define ACPI_SPLC_DOMAIN_WIFI	(0x07)
 
-static u64 splx_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splx)
+static u64 splc_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splc)
 {
-	union acpi_object *limits, *domain_type, *power_limit;
-
-	if (splx->type != ACPI_TYPE_PACKAGE ||
-	    splx->package.count != 2 ||
-	    splx->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    splx->package.elements[0].integer.value != 0) {
-		IWL_ERR(trans, "Unsupported splx structure\n");
+	union acpi_object *data_pkg, *dflt_pwr_limit;
+	int i;
+
+	/* We need at least two elements, one for the revision and one
+	 * for the data itself.  Also check that the revision is
+	 * supported (currently only revision 0).
+	*/
+	if (splc->type != ACPI_TYPE_PACKAGE ||
+	    splc->package.count < 2 ||
+	    splc->package.elements[0].type != ACPI_TYPE_INTEGER ||
+	    splc->package.elements[0].integer.value != 0) {
+		IWL_DEBUG_INFO(trans,
+			       "Unsupported structure returned by the SPLC method.  Ignoring.\n");
 		return 0;
 	}
 
-	limits = &splx->package.elements[1];
-	if (limits->type != ACPI_TYPE_PACKAGE ||
-	    limits->package.count < 2 ||
-	    limits->package.elements[0].type != ACPI_TYPE_INTEGER ||
-	    limits->package.elements[1].type != ACPI_TYPE_INTEGER) {
-		IWL_ERR(trans, "Invalid limits element\n");
-		return 0;
+	/* loop through all the packages to find the one for WiFi */
+	for (i = 1; i < splc->package.count; i++) {
+		union acpi_object *domain;
+
+		data_pkg = &splc->package.elements[i];
+
+		/* Skip anything that is not a package with the right
+		 * amount of elements (i.e. at least 2 integers).
+		 */
+		if (data_pkg->type != ACPI_TYPE_PACKAGE ||
+		    data_pkg->package.count < 2 ||
+		    data_pkg->package.elements[0].type != ACPI_TYPE_INTEGER ||
+		    data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER)
+			continue;
+
+		domain = &data_pkg->package.elements[0];
+		if (domain->integer.value == ACPI_SPLC_DOMAIN_WIFI)
+			break;
+
+		data_pkg = NULL;
 	}
 
-	domain_type = &limits->package.elements[0];
-	power_limit = &limits->package.elements[1];
-	if (!(domain_type->integer.value & SPL_DOMAINTYPE_WIFI)) {
-		IWL_DEBUG_INFO(trans, "WiFi power is not limited\n");
+	if (!data_pkg) {
+		IWL_DEBUG_INFO(trans,
+			       "No element for the WiFi domain returned by the SPLC method.\n");
 		return 0;
 	}
 
-	return power_limit->integer.value;
+	dflt_pwr_limit = &data_pkg->package.elements[1];
+	return dflt_pwr_limit->integer.value;
 }
 
 static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
 {
 	acpi_handle pxsx_handle;
 	acpi_handle handle;
-	struct acpi_buffer splx = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct acpi_buffer splc = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
 
 	pxsx_handle = ACPI_HANDLE(&pdev->dev);
@@ -527,23 +543,24 @@ static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
 	}
 
 	/* Get the method's handle */
-	status = acpi_get_handle(pxsx_handle, (acpi_string)SPL_METHOD, &handle);
+	status = acpi_get_handle(pxsx_handle, (acpi_string)ACPI_SPLC_METHOD,
+				 &handle);
 	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_INFO(trans, "SPL method not found\n");
+		IWL_DEBUG_INFO(trans, "SPLC method not found\n");
 		return;
 	}
 
 	/* Call SPLC with no arguments */
-	status = acpi_evaluate_object(handle, NULL, NULL, &splx);
+	status = acpi_evaluate_object(handle, NULL, NULL, &splc);
 	if (ACPI_FAILURE(status)) {
 		IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status);
 		return;
 	}
 
-	trans->dflt_pwr_limit = splx_get_pwr_limit(trans, splx.pointer);
+	trans->dflt_pwr_limit = splc_get_pwr_limit(trans, splc.pointer);
 	IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n",
 		       trans->dflt_pwr_limit);
-	kfree(splx.pointer);
+	kfree(splc.pointer);
 }
 
 #else /* CONFIG_ACPI */
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 8c7204738aa3..00e0332e2544 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -731,8 +731,8 @@ static int iwl_pcie_rsa_race_bug_wa(struct iwl_trans *trans)
 	 */
 	val = iwl_read_prph(trans, PREG_AUX_BUS_WPROT_0);
 	if (val & (BIT(1) | BIT(17))) {
-		IWL_INFO(trans,
-			 "can't access the RSA semaphore it is write protected\n");
+		IWL_DEBUG_INFO(trans,
+			       "can't access the RSA semaphore it is write protected\n");
 		return 0;
 	}
 
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index a8c8a4a7420b..8dfe6b2bc703 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -1508,9 +1508,9 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 
 	/* start the TFD with the scratchbuf */
 	scratch_size = min_t(int, copy_size, IWL_HCMD_SCRATCHBUF_SIZE);
-	memcpy(&txq->scratchbufs[q->write_ptr], &out_cmd->hdr, scratch_size);
+	memcpy(&txq->scratchbufs[idx], &out_cmd->hdr, scratch_size);
 	iwl_pcie_txq_build_tfd(trans, txq,
-			       iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr),
+			       iwl_pcie_get_scratchbuf_dma(txq, idx),
 			       scratch_size, true);
 
 	/* map first command fragment, if any remains */
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c00a7daaa4bc..019d7165a045 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1817,10 +1817,12 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw,
 
 static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
-				       enum ieee80211_ampdu_mlme_action action,
-				       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-				       u8 buf_size, bool amsdu)
+				       struct ieee80211_ampdu_params *params)
 {
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+
 	switch (action) {
 	case IEEE80211_AMPDU_TX_START:
 		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
@@ -2537,7 +2539,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	tasklet_hrtimer_init(&data->beacon_timer,
 			     mac80211_hwsim_beacon,
-			     CLOCK_MONOTONIC_RAW, HRTIMER_MODE_ABS);
+			     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 
 	spin_lock_bh(&hwsim_radio_lock);
 	list_add_tail(&data->list, &hwsim_radios);
@@ -2723,6 +2725,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
 	if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] ||
 	    !info->attrs[HWSIM_ATTR_FLAGS] ||
 	    !info->attrs[HWSIM_ATTR_COOKIE] ||
+	    !info->attrs[HWSIM_ATTR_SIGNAL] ||
 	    !info->attrs[HWSIM_ATTR_TX_INFO])
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c
index f715eee39851..e70dd9523911 100644
--- a/drivers/net/wireless/mediatek/mt7601u/main.c
+++ b/drivers/net/wireless/mediatek/mt7601u/main.c
@@ -334,11 +334,13 @@ static int mt7601u_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 
 static int
 mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		  enum ieee80211_ampdu_mlme_action action,
-		  struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size,
-		  bool amsdu)
+		  struct ieee80211_ampdu_params *params)
 {
 	struct mt7601u_dev *dev = hw->priv;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
 
 	WARN_ON(msta->wcid.idx > GROUP_WCID(0));
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.c b/drivers/net/wireless/mwifiex/11n_aggr.c
index aa498e0d2204..49f3e17c28ea 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/mwifiex/11n_aggr.c
@@ -101,13 +101,6 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv,
 {
 	struct txpd *local_tx_pd;
 	struct mwifiex_txinfo *tx_info = MWIFIEX_SKB_TXCB(skb);
-	unsigned int pad;
-	int headroom = (priv->adapter->iface_type ==
-			MWIFIEX_USB) ? 0 : INTF_HEADER_LEN;
-
-	pad = ((void *)skb->data - sizeof(*local_tx_pd) -
-		headroom - NULL) & (MWIFIEX_DMA_ALIGN_SZ - 1);
-	skb_push(skb, pad);
 
 	skb_push(skb, sizeof(*local_tx_pd));
 
@@ -121,12 +114,10 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv,
 	local_tx_pd->bss_num = priv->bss_num;
 	local_tx_pd->bss_type = priv->bss_type;
 	/* Always zero as the data is followed by struct txpd */
-	local_tx_pd->tx_pkt_offset = cpu_to_le16(sizeof(struct txpd) +
-						 pad);
+	local_tx_pd->tx_pkt_offset = cpu_to_le16(sizeof(struct txpd));
 	local_tx_pd->tx_pkt_type = cpu_to_le16(PKT_TYPE_AMSDU);
 	local_tx_pd->tx_pkt_length = cpu_to_le16(skb->len -
-						 sizeof(*local_tx_pd) -
-						 pad);
+						 sizeof(*local_tx_pd));
 
 	if (tx_info->flags & MWIFIEX_BUF_FLAG_TDLS_PKT)
 		local_tx_pd->flags |= MWIFIEX_TXPD_FLAGS_TDLS_PACKET;
@@ -190,7 +181,11 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 				       ra_list_flags);
 		return -1;
 	}
-	skb_reserve(skb_aggr, MWIFIEX_MIN_DATA_HEADER_LEN);
+
+	/* skb_aggr->data already 64 byte align, just reserve bus interface
+	 * header and txpd.
+	 */
+	skb_reserve(skb_aggr, headroom + sizeof(struct txpd));
 	tx_info_aggr =  MWIFIEX_SKB_TXCB(skb_aggr);
 
 	memset(tx_info_aggr, 0, sizeof(*tx_info_aggr));
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 4073116e6e9f..9a8982f581c5 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -2144,8 +2144,9 @@ done:
 			is_scanning_required = 1;
 		} else {
 			mwifiex_dbg(priv->adapter, MSG,
-				    "info: trying to associate to '%s' bssid %pM\n",
-				    (char *)req_ssid.ssid, bss->bssid);
+				    "info: trying to associate to '%.*s' bssid %pM\n",
+				    req_ssid.ssid_len, (char *)req_ssid.ssid,
+				    bss->bssid);
 			memcpy(&priv->cfg_bssid, bss->bssid, ETH_ALEN);
 			break;
 		}
@@ -2202,8 +2203,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	mwifiex_dbg(adapter, INFO,
-		    "info: Trying to associate to %s and bssid %pM\n",
-		    (char *)sme->ssid, sme->bssid);
+		    "info: Trying to associate to %.*s and bssid %pM\n",
+		    (int)sme->ssid_len, (char *)sme->ssid, sme->bssid);
 
 	ret = mwifiex_cfg80211_assoc(priv, sme->ssid_len, sme->ssid, sme->bssid,
 				     priv->bss_mode, sme->channel, sme, 0);
@@ -2333,8 +2334,8 @@ mwifiex_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	mwifiex_dbg(priv->adapter, MSG,
-		    "info: trying to join to %s and bssid %pM\n",
-		    (char *)params->ssid, params->bssid);
+		    "info: trying to join to %.*s and bssid %pM\n",
+		    params->ssid_len, (char *)params->ssid, params->bssid);
 
 	mwifiex_set_ibss_params(priv, params);
 
@@ -3739,7 +3740,7 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter)
 	if (adapter->config_bands & BAND_A)
 		n_channels_a = mwifiex_band_5ghz.n_channels;
 
-	adapter->num_in_chan_stats = max_t(u32, n_channels_bg, n_channels_a);
+	adapter->num_in_chan_stats = n_channels_bg + n_channels_a;
 	adapter->chan_stats = vmalloc(sizeof(*adapter->chan_stats) *
 				      adapter->num_in_chan_stats);
 
diff --git a/drivers/net/wireless/mwifiex/debugfs.c b/drivers/net/wireless/mwifiex/debugfs.c
index 9824d8dd2b44..45d97b64ef84 100644
--- a/drivers/net/wireless/mwifiex/debugfs.c
+++ b/drivers/net/wireless/mwifiex/debugfs.c
@@ -115,7 +115,8 @@ mwifiex_info_read(struct file *file, char __user *ubuf,
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) {
 		p += sprintf(p, "multicast_count=\"%d\"\n",
 			     netdev_mc_count(netdev));
-		p += sprintf(p, "essid=\"%s\"\n", info.ssid.ssid);
+		p += sprintf(p, "essid=\"%.*s\"\n", info.ssid.ssid_len,
+			     info.ssid.ssid);
 		p += sprintf(p, "bssid=\"%pM\"\n", info.bssid);
 		p += sprintf(p, "channel=\"%d\"\n", (int) info.bss_chan);
 		p += sprintf(p, "country_code = \"%s\"\n", info.country_code);
diff --git a/drivers/net/wireless/mwifiex/join.c b/drivers/net/wireless/mwifiex/join.c
index 3cda1f956f0b..6378dfd3b4e8 100644
--- a/drivers/net/wireless/mwifiex/join.c
+++ b/drivers/net/wireless/mwifiex/join.c
@@ -661,9 +661,8 @@ int mwifiex_ret_802_11_associate(struct mwifiex_private *priv,
 	priv->assoc_rsp_size = min(le16_to_cpu(resp->size) - S_DS_GEN,
 				   sizeof(priv->assoc_rsp_buf));
 
-	memcpy(priv->assoc_rsp_buf, &resp->params, priv->assoc_rsp_size);
-
 	assoc_rsp->a_id = cpu_to_le16(aid);
+	memcpy(priv->assoc_rsp_buf, &resp->params, priv->assoc_rsp_size);
 
 	if (status_code) {
 		priv->adapter->dbg.num_cmd_assoc_failure++;
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 21192b6f9c64..268e50ba88a5 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -947,6 +947,7 @@ static int mwifiex_pcie_delete_cmdrsp_buf(struct mwifiex_adapter *adapter)
 	if (card && card->cmd_buf) {
 		mwifiex_unmap_pci_memory(adapter, card->cmd_buf,
 					 PCI_DMA_TODEVICE);
+		dev_kfree_skb_any(card->cmd_buf);
 	}
 	return 0;
 }
@@ -1513,6 +1514,11 @@ mwifiex_pcie_send_cmd(struct mwifiex_adapter *adapter, struct sk_buff *skb)
 		return -1;
 
 	card->cmd_buf = skb;
+	/*
+	 * Need to keep a reference, since core driver might free up this
+	 * buffer before we've unmapped it.
+	 */
+	skb_get(skb);
 
 	/* To send a command, the driver will:
 		1. Write the 64bit physical address of the data buffer to
@@ -1610,6 +1616,7 @@ static int mwifiex_pcie_process_cmd_complete(struct mwifiex_adapter *adapter)
 	if (card->cmd_buf) {
 		mwifiex_unmap_pci_memory(adapter, card->cmd_buf,
 					 PCI_DMA_TODEVICE);
+		dev_kfree_skb_any(card->cmd_buf);
 		card->cmd_buf = NULL;
 	}
 
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index c20017ced566..fb98f42cb5e7 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -2170,6 +2170,12 @@ mwifiex_update_chan_statistics(struct mwifiex_private *priv,
 					      sizeof(struct mwifiex_chan_stats);
 
 	for (i = 0 ; i < num_chan; i++) {
+		if (adapter->survey_idx >= adapter->num_in_chan_stats) {
+			mwifiex_dbg(adapter, WARN,
+				    "FW reported too many channel results (max %d)\n",
+				    adapter->num_in_chan_stats);
+			return;
+		}
 		chan_stats.chan_num = fw_chan_stats->chan_num;
 		chan_stats.bandcfg = fw_chan_stats->bandcfg;
 		chan_stats.flags = fw_chan_stats->flags;
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index a6c8a4f7bfe9..6cfa2969b123 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -313,6 +313,7 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss,
 			mwifiex_dbg(adapter, ERROR,
 				    "Attempt to reconnect on csa closed chan(%d)\n",
 				    bss_desc->channel);
+			ret = -1;
 			goto done;
 		}
 
@@ -1097,8 +1098,6 @@ int mwifiex_set_encode(struct mwifiex_private *priv, struct key_params *kp,
 			encrypt_key.is_rx_seq_valid = true;
 		}
 	} else {
-		if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP)
-			return 0;
 		encrypt_key.key_disable = true;
 		if (mac_addr)
 			memcpy(encrypt_key.mac_addr, mac_addr, ETH_ALEN);
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 30e3aaae32e2..088429d0a634 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -5421,11 +5421,13 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx,
 
 static int
 mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		   enum ieee80211_ampdu_mlme_action action,
-		   struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-		   u8 buf_size, bool amsdu)
+		   struct ieee80211_ampdu_params *params)
 {
-
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	u8 buf_size = params->buf_size;
 	int i, rc = 0;
 	struct mwl8k_priv *priv = hw->priv;
 	struct mwl8k_ampdu_stream *stream;
diff --git a/drivers/net/wireless/p54/fwio.c b/drivers/net/wireless/p54/fwio.c
index 257a9eadd595..4ac6764f4897 100644
--- a/drivers/net/wireless/p54/fwio.c
+++ b/drivers/net/wireless/p54/fwio.c
@@ -488,7 +488,7 @@ int p54_scan(struct p54_common *priv, u16 mode, u16 dwell)
 
 			entry += sizeof(__le16);
 			chan->pa_points_per_curve = 8;
-			memset(chan->curve_data, 0, sizeof(*chan->curve_data));
+			memset(chan->curve_data, 0, sizeof(chan->curve_data));
 			memcpy(chan->curve_data, entry,
 			       sizeof(struct p54_pa_curve_data_sample) *
 			       min((u8)8, curve_data->points_per_channel));
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c
index 6aed923a709a..7d820c395375 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.c
@@ -5375,13 +5375,13 @@ static int rtl8xxxu_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 static int
 rtl8xxxu_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      enum ieee80211_ampdu_mlme_action action,
-		      struct ieee80211_sta *sta, u16 tid, u16 *ssn, u8 buf_size,
-		      bool amsdu)
+		      struct ieee80211_ampdu_params *params)
 {
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
 	u8 ampdu_factor, ampdu_density;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
 
 	switch (action) {
 	case IEEE80211_AMPDU_TX_START:
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 0517a4f2d3f2..aab752328c26 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1303,12 +1303,13 @@ EXPORT_SYMBOL_GPL(rtl_action_proc);
 
 static void setup_arp_tx(struct rtl_priv *rtlpriv, struct rtl_ps_ctl *ppsc)
 {
+	struct ieee80211_hw *hw = rtlpriv->hw;
+
 	rtlpriv->ra.is_special_data = true;
 	if (rtlpriv->cfg->ops->get_btc_status())
 		rtlpriv->btcoexist.btc_ops->btc_special_packet_notify(
 					rtlpriv, 1);
-	rtlpriv->enter_ps = false;
-	schedule_work(&rtlpriv->works.lps_change_work);
+	rtl_lps_leave(hw);
 	ppsc->last_delaylps_stamp_jiffies = jiffies;
 }
 
@@ -1381,8 +1382,7 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx,
 
 		if (is_tx) {
 			rtlpriv->ra.is_special_data = true;
-			rtlpriv->enter_ps = false;
-			schedule_work(&rtlpriv->works.lps_change_work);
+			rtl_lps_leave(hw);
 			ppsc->last_delaylps_stamp_jiffies = jiffies;
 		}
 
@@ -1660,9 +1660,9 @@ void rtl_watchdog_wq_callback(void *data)
 		if (((rtlpriv->link_info.num_rx_inperiod +
 		      rtlpriv->link_info.num_tx_inperiod) > 8) ||
 		    (rtlpriv->link_info.num_rx_inperiod > 2))
-			rtl_lps_enter(hw);
-		else
 			rtl_lps_leave(hw);
+		else
+			rtl_lps_enter(hw);
 	}
 
 	rtlpriv->link_info.num_rx_inperiod = 0;
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
index f2b9d11adc9e..e85f1652ce55 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
@@ -1203,7 +1203,6 @@ static void btc8723b2ant_set_ant_path(struct btc_coexist *btcoexist,
 
 		/* Force GNT_BT to low */
 		btcoexist->btc_write_1byte_bitmask(btcoexist, 0x765, 0x18, 0x0);
-		btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
 
 		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT) {
 			/* tell firmware "no antenna inverse" */
@@ -1211,19 +1210,25 @@ static void btc8723b2ant_set_ant_path(struct btc_coexist *btcoexist,
 			h2c_parameter[1] = 1;  /* ext switch type */
 			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 						h2c_parameter);
+			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
 		} else {
 			/* tell firmware "antenna inverse" */
 			h2c_parameter[0] = 1;
 			h2c_parameter[1] = 1;  /* ext switch type */
 			btcoexist->btc_fill_h2c(btcoexist, 0x65, 2,
 						h2c_parameter);
+			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x280);
 		}
 	}
 
 	/* ext switch setting */
 	if (use_ext_switch) {
 		/* fixed internal switch S1->WiFi, S0->BT */
-		btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
+		if (board_info->btdm_ant_pos == BTC_ANTENNA_AT_MAIN_PORT)
+			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x0);
+		else
+			btcoexist->btc_write_2byte(btcoexist, 0x948, 0x280);
+
 		switch (antpos_type) {
 		case BTC_ANT_WIFI_AT_MAIN:
 			/* ext switch main at wifi */
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index b2791c893417..babd1490f20c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -965,13 +965,38 @@ void exhalbtc_set_chip_type(u8 chip_type)
 	}
 }
 
-void exhalbtc_set_ant_num(u8 type, u8 ant_num)
+void exhalbtc_set_ant_num(struct rtl_priv *rtlpriv, u8 type, u8 ant_num)
 {
 	if (BT_COEX_ANT_TYPE_PG == type) {
 		gl_bt_coexist.board_info.pg_ant_num = ant_num;
 		gl_bt_coexist.board_info.btdm_ant_num = ant_num;
+		/* The antenna position:
+		 * Main (default) or Aux for pgAntNum=2 && btdmAntNum =1.
+		 * The antenna position should be determined by
+		 * auto-detect mechanism.
+		 * The following is assumed to main,
+		 * and those must be modified
+		 * if y auto-detect mechanism is ready
+		 */
+		if ((gl_bt_coexist.board_info.pg_ant_num == 2) &&
+		    (gl_bt_coexist.board_info.btdm_ant_num == 1))
+			gl_bt_coexist.board_info.btdm_ant_pos =
+						       BTC_ANTENNA_AT_MAIN_PORT;
+		else
+			gl_bt_coexist.board_info.btdm_ant_pos =
+						       BTC_ANTENNA_AT_MAIN_PORT;
 	} else if (BT_COEX_ANT_TYPE_ANTDIV == type) {
 		gl_bt_coexist.board_info.btdm_ant_num = ant_num;
+		gl_bt_coexist.board_info.btdm_ant_pos =
+						       BTC_ANTENNA_AT_MAIN_PORT;
+	} else if (type == BT_COEX_ANT_TYPE_DETECTED) {
+		gl_bt_coexist.board_info.btdm_ant_num = ant_num;
+		if (rtlpriv->cfg->mod_params->ant_sel == 1)
+			gl_bt_coexist.board_info.btdm_ant_pos =
+				BTC_ANTENNA_AT_AUX_PORT;
+		else
+			gl_bt_coexist.board_info.btdm_ant_pos =
+				BTC_ANTENNA_AT_MAIN_PORT;
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
index 0a903ea179ef..f41ca57dd8a7 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.h
@@ -535,7 +535,7 @@ void exhalbtc_set_bt_patch_version(u16 bt_hci_version, u16 bt_patch_version);
 void exhalbtc_update_min_bt_rssi(char bt_rssi);
 void exhalbtc_set_bt_exist(bool bt_exist);
 void exhalbtc_set_chip_type(u8 chip_type);
-void exhalbtc_set_ant_num(u8 type, u8 ant_num);
+void exhalbtc_set_ant_num(struct rtl_priv *rtlpriv, u8 type, u8 ant_num);
 void exhalbtc_display_bt_coex_info(struct btc_coexist *btcoexist);
 void exhalbtc_signal_compensation(struct btc_coexist *btcoexist,
 				  u8 *rssi_wifi, u8 *rssi_bt);
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/rtl_btc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/rtl_btc.c
index b9b0cb7af8ea..d3fd9211b3a4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/rtl_btc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/rtl_btc.c
@@ -72,7 +72,10 @@ void rtl_btc_init_hal_vars(struct rtl_priv *rtlpriv)
 		 __func__, bt_type);
 	exhalbtc_set_chip_type(bt_type);
 
-	exhalbtc_set_ant_num(BT_COEX_ANT_TYPE_PG, ant_num);
+	if (rtlpriv->cfg->mod_params->ant_sel == 1)
+		exhalbtc_set_ant_num(rtlpriv, BT_COEX_ANT_TYPE_DETECTED, 1);
+	else
+		exhalbtc_set_ant_num(rtlpriv, BT_COEX_ANT_TYPE_PG, ant_num);
 }
 
 void rtl_btc_init_hw_config(struct rtl_priv *rtlpriv)
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index c925a4dff599..8b537a5a4b01 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -1153,10 +1153,8 @@ static void rtl_op_bss_info_changed(struct ieee80211_hw *hw,
 		} else {
 			mstatus = RT_MEDIA_DISCONNECT;
 
-			if (mac->link_state == MAC80211_LINKED) {
-				rtlpriv->enter_ps = false;
-				schedule_work(&rtlpriv->works.lps_change_work);
-			}
+			if (mac->link_state == MAC80211_LINKED)
+				rtl_lps_leave(hw);
 			if (ppsc->p2p_ps_info.p2p_ps_mode > P2P_PS_NONE)
 				rtl_p2p_ps_cmd(hw, P2P_PS_DISABLE);
 			mac->link_state = MAC80211_NOLINK;
@@ -1371,11 +1369,13 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw,
 
 static int rtl_op_ampdu_action(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
-			       enum ieee80211_ampdu_mlme_action action,
-			       struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			       u8 buf_size, bool amsdu)
+			       struct ieee80211_ampdu_params *params)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 
 	switch (action) {
 	case IEEE80211_AMPDU_TX_START:
@@ -1432,8 +1432,7 @@ static void rtl_op_sw_scan_start(struct ieee80211_hw *hw,
 	}
 
 	if (mac->link_state == MAC80211_LINKED) {
-		rtlpriv->enter_ps = false;
-		schedule_work(&rtlpriv->works.lps_change_work);
+		rtl_lps_leave(hw);
 		mac->link_state = MAC80211_LINKED_SCANNING;
 	} else {
 		rtl_ips_nic_on(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 7f471bff435c..c48b7e8ee0d6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -664,11 +664,9 @@ tx_status_ok:
 	}
 
 	if (((rtlpriv->link_info.num_rx_inperiod +
-		rtlpriv->link_info.num_tx_inperiod) > 8) ||
-		(rtlpriv->link_info.num_rx_inperiod > 2)) {
-		rtlpriv->enter_ps = false;
-		schedule_work(&rtlpriv->works.lps_change_work);
-	}
+	      rtlpriv->link_info.num_tx_inperiod) > 8) ||
+	      (rtlpriv->link_info.num_rx_inperiod > 2))
+		rtl_lps_leave(hw);
 }
 
 static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
@@ -919,10 +917,8 @@ new_trx_end:
 		}
 		if (((rtlpriv->link_info.num_rx_inperiod +
 		      rtlpriv->link_info.num_tx_inperiod) > 8) ||
-		      (rtlpriv->link_info.num_rx_inperiod > 2)) {
-			rtlpriv->enter_ps = false;
-			schedule_work(&rtlpriv->works.lps_change_work);
-		}
+		      (rtlpriv->link_info.num_rx_inperiod > 2))
+			rtl_lps_leave(hw);
 		skb = new_skb;
 no_new:
 		if (rtlpriv->use_new_trx_flow) {
@@ -1573,7 +1569,7 @@ int rtl_pci_reset_trx_ring(struct ieee80211_hw *hw)
 							 true,
 							 HW_DESC_TXBUFF_ADDR),
 						 skb->len, PCI_DMA_TODEVICE);
-				kfree_skb(skb);
+				dev_kfree_skb_irq(skb);
 				ring->idx = (ring->idx + 1) % ring->entries;
 			}
 			ring->idx = 0;
@@ -2273,7 +2269,7 @@ int rtl_pci_probe(struct pci_dev *pdev,
 	/* find adapter */
 	if (!_rtl_pci_find_adapter(pdev, hw)) {
 		err = -ENODEV;
-		goto fail3;
+		goto fail2;
 	}
 
 	/* Init IO handler */
@@ -2343,10 +2339,10 @@ fail3:
 	pci_set_drvdata(pdev, NULL);
 	rtl_deinit_core(hw);
 
+fail2:
 	if (rtlpriv->io.pci_mem_start != 0)
 		pci_iounmap(pdev, (void __iomem *)rtlpriv->io.pci_mem_start);
 
-fail2:
 	pci_release_regions(pdev);
 	complete(&rtlpriv->firmware_loading_complete);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h
index 5da6703942d9..672f81ea02d0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.h
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.h
@@ -275,10 +275,10 @@ struct mp_adapter {
 };
 
 struct rtl_pci_priv {
+	struct bt_coexist_info bt_coexist;
+	struct rtl_led_ctl ledctl;
 	struct rtl_pci dev;
 	struct mp_adapter ndis_adapter;
-	struct rtl_led_ctl ledctl;
-	struct bt_coexist_info bt_coexist;
 };
 
 #define rtl_pcipriv(hw)		(((struct rtl_pci_priv *)(rtl_priv(hw))->priv))
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c
index b69321d45f04..626ff300352b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.c
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.c
@@ -414,8 +414,8 @@ void rtl_lps_set_psmode(struct ieee80211_hw *hw, u8 rt_psmode)
 	}
 }
 
-/*Enter the leisure power save mode.*/
-void rtl_lps_enter(struct ieee80211_hw *hw)
+/* Interrupt safe routine to enter the leisure power save mode.*/
+static void rtl_lps_enter_core(struct ieee80211_hw *hw)
 {
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
@@ -455,10 +455,9 @@ void rtl_lps_enter(struct ieee80211_hw *hw)
 
 	spin_unlock_irqrestore(&rtlpriv->locks.lps_lock, flag);
 }
-EXPORT_SYMBOL(rtl_lps_enter);
 
-/*Leave the leisure power save mode.*/
-void rtl_lps_leave(struct ieee80211_hw *hw)
+/* Interrupt safe routine to leave the leisure power save mode.*/
+static void rtl_lps_leave_core(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
@@ -488,7 +487,6 @@ void rtl_lps_leave(struct ieee80211_hw *hw)
 	}
 	spin_unlock_irqrestore(&rtlpriv->locks.lps_lock, flag);
 }
-EXPORT_SYMBOL(rtl_lps_leave);
 
 /* For sw LPS*/
 void rtl_swlps_beacon(struct ieee80211_hw *hw, void *data, unsigned int len)
@@ -681,12 +679,34 @@ void rtl_lps_change_work_callback(struct work_struct *work)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	if (rtlpriv->enter_ps)
-		rtl_lps_enter(hw);
+		rtl_lps_enter_core(hw);
 	else
-		rtl_lps_leave(hw);
+		rtl_lps_leave_core(hw);
 }
 EXPORT_SYMBOL_GPL(rtl_lps_change_work_callback);
 
+void rtl_lps_enter(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	if (!in_interrupt())
+		return rtl_lps_enter_core(hw);
+	rtlpriv->enter_ps = true;
+	schedule_work(&rtlpriv->works.lps_change_work);
+}
+EXPORT_SYMBOL_GPL(rtl_lps_enter);
+
+void rtl_lps_leave(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+	if (!in_interrupt())
+		return rtl_lps_leave_core(hw);
+	rtlpriv->enter_ps = false;
+	schedule_work(&rtlpriv->works.lps_change_work);
+}
+EXPORT_SYMBOL_GPL(rtl_lps_leave);
+
 void rtl_swlps_wq_callback(void *data)
 {
 	struct rtl_works *rtlworks = container_of_dwork_rtl(data,
diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c
index 5be34118e0af..f67e7e5b13e1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/regd.c
+++ b/drivers/net/wireless/realtek/rtlwifi/regd.c
@@ -345,9 +345,9 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select(
 		return &rtl_regdom_no_midband;
 	case COUNTRY_CODE_IC:
 		return &rtl_regdom_11;
-	case COUNTRY_CODE_ETSI:
 	case COUNTRY_CODE_TELEC_NETGEAR:
 		return &rtl_regdom_60_64;
+	case COUNTRY_CODE_ETSI:
 	case COUNTRY_CODE_SPAIN:
 	case COUNTRY_CODE_FRANCE:
 	case COUNTRY_CODE_ISRAEL:
@@ -406,6 +406,8 @@ static u8 channel_plan_to_country_code(u8 channelplan)
 		return COUNTRY_CODE_WORLD_WIDE_13;
 	case 0x22:
 		return COUNTRY_CODE_IC;
+	case 0x25:
+		return COUNTRY_CODE_ETSI;
 	case 0x32:
 		return COUNTRY_CODE_TELEC_NETGEAR;
 	case 0x41:
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index 5f14308e8eb3..b1601441991d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -1003,7 +1003,7 @@ static void _rtl92ee_hw_configure(struct ieee80211_hw *hw)
 	rtl_write_word(rtlpriv, REG_SIFS_TRX, 0x100a);
 
 	/* Note Data sheet don't define */
-	rtl_write_word(rtlpriv, 0x4C7, 0x80);
+	rtl_write_byte(rtlpriv, 0x4C7, 0x80);
 
 	rtl_write_byte(rtlpriv, REG_RX_PKT_LIMIT, 0x20);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index c983d2fe147f..5a3df9198ddf 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -2684,6 +2684,7 @@ void rtl8723be_read_bt_coexist_info_from_hwpg(struct ieee80211_hw *hw,
 					      bool auto_load_fail, u8 *hwinfo)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
 	u8 value;
 	u32 tmpu_32;
 
@@ -2702,6 +2703,10 @@ void rtl8723be_read_bt_coexist_info_from_hwpg(struct ieee80211_hw *hw,
 		rtlpriv->btcoexist.btc_info.ant_num = ANT_X2;
 	}
 
+	/* override ant_num / ant_path */
+	if (mod_params->ant_sel)
+		rtlpriv->btcoexist.btc_info.ant_num =
+			(mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
 }
 
 void rtl8723be_bt_reg_init(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index a78eaeda0008..2101793438ed 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -273,6 +273,7 @@ static struct rtl_mod_params rtl8723be_mod_params = {
 	.msi_support = false,
 	.disable_watchdog = false,
 	.debug = DBG_EMERG,
+	.ant_sel = 0,
 };
 
 static struct rtl_hal_cfg rtl8723be_hal_cfg = {
@@ -394,6 +395,7 @@ module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444);
 module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444);
 module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog,
 		   bool, 0444);
+module_param_named(ant_sel, rtl8723be_mod_params.ant_sel, int, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
 MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
@@ -402,6 +404,7 @@ MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n");
 MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(disable_watchdog,
 		 "Set to 1 to disable the watchdog (default 0)\n");
+MODULE_PARM_DESC(ant_sel, "Set to 1 or 2 to force antenna number (default 0)\n");
 
 static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index bbb789f8990b..c2103e7a8132 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -1127,7 +1127,7 @@ static u8 _rtl8821ae_dbi_read(struct rtl_priv *rtlpriv, u16 addr)
 	}
 	if (0 == tmp) {
 		read_addr = REG_DBI_RDATA + addr % 4;
-		ret = rtl_read_word(rtlpriv, read_addr);
+		ret = rtl_read_byte(rtlpriv, read_addr);
 	}
 	return ret;
 }
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 9b4d8a637915..4b354918e183 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -359,6 +359,107 @@ bool rtl8821ae_phy_rf_config(struct ieee80211_hw *hw)
 	return rtl8821ae_phy_rf6052_config(hw);
 }
 
+static void _rtl8812ae_phy_set_rfe_reg_24g(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u8 tmp;
+
+	switch (rtlhal->rfe_type) {
+	case 3:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337770);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337770);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1);
+		break;
+	case 4:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x001);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x001);
+		break;
+	case 5:
+		rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x77);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3);
+		rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp & ~0x1);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		break;
+	case 1:
+		if (rtlpriv->btcoexist.bt_coexistence) {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x777777);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77777777);
+			rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+			break;
+		}
+	case 0:
+	case 2:
+	default:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77777777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		break;
+	}
+}
+
+static void _rtl8812ae_phy_set_rfe_reg_5g(struct ieee80211_hw *hw)
+{
+	struct rtl_priv *rtlpriv = rtl_priv(hw);
+	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	u8 tmp;
+
+	switch (rtlhal->rfe_type) {
+	case 0:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337717);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337717);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	case 1:
+		if (rtlpriv->btcoexist.bt_coexistence) {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, 0xffffff, 0x337717);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RA_RFE_INV, 0x33f00000, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		} else {
+			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
+				      0x77337717);
+			rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x000);
+			rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x000);
+		}
+		break;
+	case 3:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x54337717);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x54337717);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, 0x900, 0x00000303, 0x1);
+		break;
+	case 5:
+		rtl_write_byte(rtlpriv, RA_RFE_PINMUX + 2, 0x33);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		tmp = rtl_read_byte(rtlpriv, RA_RFE_INV + 3);
+		rtl_write_byte(rtlpriv, RA_RFE_INV + 3, tmp | 0x1);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	case 2:
+	case 4:
+	default:
+		rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD, 0x77337777);
+		rtl_set_bbreg(hw, RA_RFE_INV, BMASKRFEINV, 0x010);
+		rtl_set_bbreg(hw, RB_RFE_INV, BMASKRFEINV, 0x010);
+		break;
+	}
+}
+
 u32 phy_get_tx_swing_8812A(struct ieee80211_hw *hw, u8	band,
 			   u8 rf_path)
 {
@@ -553,14 +654,9 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
 			/* 0x82C[1:0] = 2b'00 */
 			rtl_set_bbreg(hw, 0x82c, 0x3, 0);
 		}
-		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
-				      0x77777777);
-			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
-				      0x77777777);
-			rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x000);
-			rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x000);
-		}
+
+		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE)
+			_rtl8812ae_phy_set_rfe_reg_24g(hw);
 
 		rtl_set_bbreg(hw, RTXPATH, 0xf0, 0x1);
 		rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0x1);
@@ -615,14 +711,8 @@ void rtl8821ae_phy_switch_wirelessband(struct ieee80211_hw *hw, u8 band)
 			/* 0x82C[1:0] = 2'b00 */
 			rtl_set_bbreg(hw, 0x82c, 0x3, 1);
 
-		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-			rtl_set_bbreg(hw, RA_RFE_PINMUX, BMASKDWORD,
-				      0x77337777);
-			rtl_set_bbreg(hw, RB_RFE_PINMUX, BMASKDWORD,
-				      0x77337777);
-			rtl_set_bbreg(hw, RA_RFE_INV, 0x3ff00000, 0x010);
-			rtl_set_bbreg(hw, RB_RFE_INV, 0x3ff00000, 0x010);
-		}
+		if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE)
+			_rtl8812ae_phy_set_rfe_reg_5g(hw);
 
 		rtl_set_bbreg(hw, RTXPATH, 0xf0, 0);
 		rtl_set_bbreg(hw, RCCK_RX, 0x0f000000, 0xf);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
index 1d6110f9c1fb..ed69dbe178ff 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/reg.h
@@ -2424,6 +2424,7 @@
 #define	BMASKH4BITS			0xf0000000
 #define BMASKOFDM_D			0xffc00000
 #define	BMASKCCK			0x3f3f3f3f
+#define BMASKRFEINV			0x3ff00000
 
 #define BRFREGOFFSETMASK		0xfffff
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index aac1ed3f7bb4..ad8390d2997b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -834,12 +834,30 @@ static void rtl_usb_stop(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+	struct urb *urb;
 
 	/* should after adapter start and interrupt enable. */
 	set_hal_stop(rtlhal);
 	cancel_work_sync(&rtlpriv->works.fill_h2c_cmd);
 	/* Enable software */
 	SET_USB_STOP(rtlusb);
+
+	/* free pre-allocated URBs from rtl_usb_start() */
+	usb_kill_anchored_urbs(&rtlusb->rx_submitted);
+
+	tasklet_kill(&rtlusb->rx_work_tasklet);
+	cancel_work_sync(&rtlpriv->works.lps_change_work);
+
+	flush_workqueue(rtlpriv->works.rtl_wq);
+
+	skb_queue_purge(&rtlusb->rx_queue);
+
+	while ((urb = usb_get_from_anchor(&rtlusb->rx_cleanup_urbs))) {
+		usb_free_coherent(urb->dev, urb->transfer_buffer_length,
+				urb->transfer_buffer, urb->transfer_dma);
+		usb_free_urb(urb);
+	}
+
 	rtlpriv->cfg->ops->hw_disable(hw);
 }
 
@@ -1073,6 +1091,7 @@ int rtl_usb_probe(struct usb_interface *intf,
 		return -ENOMEM;
 	}
 	rtlpriv = hw->priv;
+	rtlpriv->hw = hw;
 	rtlpriv->usb_data = kzalloc(RTL_USB_MAX_RX_COUNT * sizeof(u32),
 				    GFP_KERNEL);
 	if (!rtlpriv->usb_data)
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.h b/drivers/net/wireless/realtek/rtlwifi/usb.h
index 685273ca9561..441c4412130c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.h
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.h
@@ -150,8 +150,9 @@ struct rtl_usb {
 };
 
 struct rtl_usb_priv {
-	struct rtl_usb dev;
+	struct bt_coexist_info bt_coexist;
 	struct rtl_led_ctl ledctl;
+	struct rtl_usb dev;
 };
 
 #define rtl_usbpriv(hw)	 (((struct rtl_usb_priv *)(rtl_priv(hw))->priv))
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 4544752a2ba8..b6faf624480e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2252,6 +2252,9 @@ struct rtl_mod_params {
 
 	/* default 0: 1 means do not disable interrupts */
 	bool int_clear;
+
+	/* select antenna */
+	int ant_sel;
 };
 
 struct rtl_hal_usbint_cfg {
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index b5bcc933a2a6..4df992de7d07 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -659,29 +659,24 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw,
  *				 informs the f/w regarding this.
  * @hw: Pointer to the ieee80211_hw structure.
  * @vif: Pointer to the ieee80211_vif structure.
- * @action: ieee80211_ampdu_mlme_action enum.
- * @sta: Pointer to the ieee80211_sta structure.
- * @tid: Traffic identifier.
- * @ssn: Pointer to ssn value.
- * @buf_size: Buffer size (for kernel version > 2.6.38).
- * @amsdu: is AMSDU in AMPDU allowed
+ * @params: Pointer to A-MPDU action parameters
  *
  * Return: status: 0 on success, negative error code on failure.
  */
 static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
-				     enum ieee80211_ampdu_mlme_action action,
-				     struct ieee80211_sta *sta,
-				     unsigned short tid,
-				     unsigned short *ssn,
-				     unsigned char buf_size,
-				     bool amsdu)
+				     struct ieee80211_ampdu_params *params)
 {
 	int status = -EOPNOTSUPP;
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
 	u16 seq_no = 0;
 	u8 ii = 0;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	u8 buf_size = params->buf_size;
 
 	for (ii = 0; ii < RSI_MAX_VIFS; ii++) {
 		if (vif == adapter->vifs[ii])
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 9733b31a780d..69c1c09687a3 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -7935,10 +7935,11 @@ u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 EXPORT_SYMBOL_GPL(rt2800_get_tsf);
 
 int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			u8 buf_size, bool amsdu)
+			struct ieee80211_ampdu_params *params)
 {
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
 	struct rt2x00_sta *sta_priv = (struct rt2x00_sta *)sta->drv_priv;
 	int ret = 0;
 
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h
index 440790b92b19..83f1a44fb9b4 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.h
+++ b/drivers/net/wireless/rt2x00/rt2800lib.h
@@ -218,9 +218,7 @@ int rt2800_conf_tx(struct ieee80211_hw *hw,
 		   const struct ieee80211_tx_queue_params *params);
 u64 rt2800_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			enum ieee80211_ampdu_mlme_action action,
-			struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			u8 buf_size, bool amsdu);
+			struct ieee80211_ampdu_params *params);
 int rt2800_get_survey(struct ieee80211_hw *hw, int idx,
 		      struct survey_info *survey);
 void rt2800_disable_wpdma(struct rt2x00_dev *rt2x00dev);
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index cd4777954f87..9bee3f11898a 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -1567,6 +1567,7 @@ struct ieee80211_hw *wl1251_alloc_hw(void)
 
 	wl->state = WL1251_STATE_OFF;
 	mutex_init(&wl->mutex);
+	spin_lock_init(&wl->wl_lock);
 
 	wl->tx_mgmt_frm_rate = DEFAULT_HW_GEN_TX_RATE;
 	wl->tx_mgmt_frm_mod = DEFAULT_HW_GEN_MODULATION_TYPE;
diff --git a/drivers/net/wireless/ti/wl18xx/event.c b/drivers/net/wireless/ti/wl18xx/event.c
index 09c7e098f460..085ef5c87262 100644
--- a/drivers/net/wireless/ti/wl18xx/event.c
+++ b/drivers/net/wireless/ti/wl18xx/event.c
@@ -206,5 +206,33 @@ int wl18xx_process_mailbox_events(struct wl1271 *wl)
 						 mbox->sc_pwd_len,
 						 mbox->sc_pwd);
 
+	if (vector & RX_BA_WIN_SIZE_CHANGE_EVENT_ID) {
+		struct wl12xx_vif *wlvif;
+		struct ieee80211_vif *vif;
+		struct ieee80211_sta *sta;
+		u8 link_id = mbox->rx_ba_link_id;
+		u8 win_size = mbox->rx_ba_win_size;
+		const u8 *addr;
+
+		wlvif = wl->links[link_id].wlvif;
+		vif = wl12xx_wlvif_to_vif(wlvif);
+
+		/* Update RX aggregation window size and call
+		 * MAC routine to stop active RX aggregations for this link
+		 */
+		if (wlvif->bss_type != BSS_TYPE_AP_BSS)
+			addr = vif->bss_conf.bssid;
+		else
+			addr = wl->links[link_id].addr;
+
+		sta = ieee80211_find_sta(vif, addr);
+		if (sta) {
+			sta->max_rx_aggregation_subframes = win_size;
+			ieee80211_stop_rx_ba_session(vif,
+						wl->links[link_id].ba_bitmap,
+						addr);
+		}
+	}
+
 	return 0;
 }
diff --git a/drivers/net/wireless/ti/wl18xx/event.h b/drivers/net/wireless/ti/wl18xx/event.h
index f3d4f13379cb..9495fadc8093 100644
--- a/drivers/net/wireless/ti/wl18xx/event.h
+++ b/drivers/net/wireless/ti/wl18xx/event.h
@@ -38,6 +38,7 @@ enum {
 	REMAIN_ON_CHANNEL_COMPLETE_EVENT_ID      = BIT(18),
 	DFS_CHANNELS_CONFIG_COMPLETE_EVENT       = BIT(19),
 	PERIODIC_SCAN_REPORT_EVENT_ID            = BIT(20),
+	RX_BA_WIN_SIZE_CHANGE_EVENT_ID           = BIT(21),
 	SMART_CONFIG_SYNC_EVENT_ID               = BIT(22),
 	SMART_CONFIG_DECODE_EVENT_ID             = BIT(23),
 	TIME_SYNC_EVENT_ID                       = BIT(24),
diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c
index 50cce42089a5..47f355e92193 100644
--- a/drivers/net/wireless/ti/wl18xx/main.c
+++ b/drivers/net/wireless/ti/wl18xx/main.c
@@ -1029,7 +1029,8 @@ static int wl18xx_boot(struct wl1271 *wl)
 		DFS_CHANNELS_CONFIG_COMPLETE_EVENT |
 		SMART_CONFIG_SYNC_EVENT_ID |
 		SMART_CONFIG_DECODE_EVENT_ID |
-		TIME_SYNC_EVENT_ID;
+		TIME_SYNC_EVENT_ID |
+		RX_BA_WIN_SIZE_CHANGE_EVENT_ID;
 
 	wl->ap_event_mask = MAX_TX_FAILURE_EVENT_ID;
 
diff --git a/drivers/net/wireless/ti/wlcore/acx.c b/drivers/net/wireless/ti/wlcore/acx.c
index f28fa3b5029d..0646c9b6f8d7 100644
--- a/drivers/net/wireless/ti/wlcore/acx.c
+++ b/drivers/net/wireless/ti/wlcore/acx.c
@@ -1419,7 +1419,8 @@ out:
 
 /* setup BA session receiver setting in the FW. */
 int wl12xx_acx_set_ba_receiver_session(struct wl1271 *wl, u8 tid_index,
-				       u16 ssn, bool enable, u8 peer_hlid)
+				       u16 ssn, bool enable, u8 peer_hlid,
+				       u8 win_size)
 {
 	struct wl1271_acx_ba_receiver_setup *acx;
 	int ret;
@@ -1435,7 +1436,7 @@ int wl12xx_acx_set_ba_receiver_session(struct wl1271 *wl, u8 tid_index,
 	acx->hlid = peer_hlid;
 	acx->tid = tid_index;
 	acx->enable = enable;
-	acx->win_size = wl->conf.ht.rx_ba_win_size;
+	acx->win_size =	win_size;
 	acx->ssn = ssn;
 
 	ret = wlcore_cmd_configure_failsafe(wl, ACX_BA_SESSION_RX_SETUP, acx,
diff --git a/drivers/net/wireless/ti/wlcore/acx.h b/drivers/net/wireless/ti/wlcore/acx.h
index 954d57ec98f4..524aea495dff 100644
--- a/drivers/net/wireless/ti/wlcore/acx.h
+++ b/drivers/net/wireless/ti/wlcore/acx.h
@@ -1112,7 +1112,8 @@ int wl1271_acx_set_ht_information(struct wl1271 *wl,
 int wl12xx_acx_set_ba_initiator_policy(struct wl1271 *wl,
 				       struct wl12xx_vif *wlvif);
 int wl12xx_acx_set_ba_receiver_session(struct wl1271 *wl, u8 tid_index,
-				       u16 ssn, bool enable, u8 peer_hlid);
+				       u16 ssn, bool enable, u8 peer_hlid,
+				       u8 win_size);
 int wl12xx_acx_tsf_info(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 			u64 *mactime);
 int wl1271_acx_ps_rx_streaming(struct wl1271 *wl, struct wl12xx_vif *wlvif,
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index ec7f6af3fab2..7b27c7e23af2 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -5261,14 +5261,16 @@ out:
 
 static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
-				  enum ieee80211_ampdu_mlme_action action,
-				  struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-				  u8 buf_size, bool amsdu)
+				  struct ieee80211_ampdu_params *params)
 {
 	struct wl1271 *wl = hw->priv;
 	struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif);
 	int ret;
 	u8 hlid, *ba_bitmap;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 ampdu action %d tid %d", action,
 		     tid);
@@ -5326,7 +5328,9 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 		}
 
 		ret = wl12xx_acx_set_ba_receiver_session(wl, tid, *ssn, true,
-							 hlid);
+				hlid,
+				params->buf_size);
+
 		if (!ret) {
 			*ba_bitmap |= BIT(tid);
 			wl->ba_rx_session_count++;
@@ -5347,7 +5351,7 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 		}
 
 		ret = wl12xx_acx_set_ba_receiver_session(wl, tid, 0, false,
-							 hlid);
+							 hlid, 0);
 		if (!ret) {
 			*ba_bitmap &= ~BIT(tid);
 			wl->ba_rx_session_count--;
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 44f059f7f34e..9ebe00ea8f81 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -71,7 +71,7 @@
  * only support SPI for 12xx - this code should be reworked when 18xx
  * support is introduced
  */
-#define SPI_AGGR_BUFFER_SIZE (4 * PAGE_SIZE)
+#define SPI_AGGR_BUFFER_SIZE (4 * SZ_4K)
 
 /* Maximum number of SPI write chunks */
 #define WSPI_MAX_NUM_OF_CHUNKS \
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 0333ab0fd926..34173b5e886f 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -201,6 +201,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */
 	unsigned long   remaining_credit;
 	struct timer_list credit_timeout;
 	u64 credit_window_start;
+	bool rate_limited;
 
 	/* Statistics */
 	struct xenvif_stats stats;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index e7bd63eb2876..60b26f32d31d 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -105,7 +105,11 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete(napi);
-		xenvif_napi_schedule_or_enable_events(queue);
+		/* If the queue is rate-limited, it shall be
+		 * rescheduled in the timer callback.
+		 */
+		if (likely(!queue->rate_limited))
+			xenvif_napi_schedule_or_enable_events(queue);
 	}
 
 	return work_done;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 1049c34e7d43..72ee1c305cc4 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -687,6 +687,7 @@ static void tx_add_credit(struct xenvif_queue *queue)
 		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */
 
 	queue->remaining_credit = min(max_credit, max_burst);
+	queue->rate_limited = false;
 }
 
 void xenvif_tx_credit_callback(unsigned long data)
@@ -1184,8 +1185,10 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 		msecs_to_jiffies(queue->credit_usec / 1000);
 
 	/* Timer could already be pending in rare cases. */
-	if (timer_pending(&queue->credit_timeout))
+	if (timer_pending(&queue->credit_timeout)) {
+		queue->rate_limited = true;
 		return true;
+	}
 
 	/* Passed the point where we can replenish credit? */
 	if (time_after_eq64(now, next_credit)) {
@@ -1200,6 +1203,7 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 		mod_timer(&queue->credit_timeout,
 			  next_credit);
 		queue->credit_window_start = next_credit;
+		queue->rate_limited = true;
 
 		return true;
 	}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d6abf191122a..34a062ccb11d 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -304,7 +304,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 		queue->rx_skbs[id] = skb;
 
 		ref = gnttab_claim_grant_reference(&queue->gref_rx_head);
-		BUG_ON((signed short)ref < 0);
+		WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
 		queue->grant_rx_ref[id] = ref;
 
 		page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
@@ -321,7 +321,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 	queue->rx.req_prod_pvt = req_prod;
 
 	/* Not enough requests? Try again later. */
-	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+	if (req_prod - queue->rx.sring->req_prod < NET_RX_SLOTS_MIN) {
 		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
 		return;
 	}
@@ -437,7 +437,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
 	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
 	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
-	BUG_ON((signed short)ref < 0);
+	WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
 
 	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 					gfn, GNTMAP_readonly);
@@ -1391,6 +1391,8 @@ static void xennet_disconnect_backend(struct netfront_info *info)
 	for (i = 0; i < num_queues && info->queues; ++i) {
 		struct netfront_queue *queue = &info->queues[i];
 
+		del_timer_sync(&queue->rx_refill_timer);
+
 		if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
 			unbind_from_irqhandler(queue->tx_irq, queue);
 		if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
@@ -1745,7 +1747,6 @@ static void xennet_destroy_queues(struct netfront_info *info)
 
 		if (netif_running(info->netdev))
 			napi_disable(&queue->napi);
-		del_timer_sync(&queue->rx_refill_timer);
 		netif_napi_del(&queue->napi);
 	}
 
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index ccb07a1b153d..23e53780728b 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -352,7 +352,7 @@ static int fdp_nci_patch_otp(struct nci_dev *ndev)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
 	struct device *dev = &info->phy->i2c_dev->dev;
-	u8 conn_id;
+	int conn_id;
 	int r = 0;
 
 	if (info->otp_version >= info->otp_patch_version)
@@ -423,7 +423,7 @@ static int fdp_nci_patch_ram(struct nci_dev *ndev)
 {
 	struct fdp_nci_info *info = nci_get_drvdata(ndev);
 	struct device *dev = &info->phy->i2c_dev->dev;
-	u8 conn_id;
+	int conn_id;
 	int r = 0;
 
 	if (info->ram_version >= info->ram_patch_version)
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 532db28145c7..a5d7332dfce5 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -210,14 +210,14 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id)
 	struct sk_buff *skb;
 	int r;
 
-	client = phy->i2c_dev;
-	dev_dbg(&client->dev, "%s\n", __func__);
-
 	if (!phy || irq != phy->i2c_dev->irq) {
 		WARN_ON_ONCE(1);
 		return IRQ_NONE;
 	}
 
+	client = phy->i2c_dev;
+	dev_dbg(&client->dev, "%s\n", __func__);
+
 	r = fdp_nci_i2c_read(phy, &skb);
 
 	if (r == -EREMOTEIO)
diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c
index 83deda4bb4d6..6f9563a96488 100644
--- a/drivers/nfc/mei_phy.c
+++ b/drivers/nfc/mei_phy.c
@@ -133,7 +133,7 @@ static int mei_nfc_if_version(struct nfc_mei_phy *phy)
 		return -ENOMEM;
 
 	bytes_recv = mei_cldev_recv(phy->cldev, (u8 *)reply, if_version_length);
-	if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) {
+	if (bytes_recv < 0 || bytes_recv < if_version_length) {
 		pr_err("Could not read IF version\n");
 		r = -EIO;
 		goto err;
diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c
index f8dcdf4b24f6..af62c4c854f3 100644
--- a/drivers/nfc/nfcmrvl/fw_dnld.c
+++ b/drivers/nfc/nfcmrvl/fw_dnld.c
@@ -459,7 +459,7 @@ int	nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv)
 
 	INIT_WORK(&priv->fw_dnld.rx_work, fw_dnld_rx_work);
 	snprintf(name, sizeof(name), "%s_nfcmrvl_fw_dnld_rx_wq",
-		 dev_name(priv->dev));
+		 dev_name(&priv->ndev->nfc_dev->dev));
 	priv->fw_dnld.rx_wq = create_singlethread_workqueue(name);
 	if (!priv->fw_dnld.rx_wq)
 		return -ENOMEM;
@@ -496,6 +496,7 @@ int nfcmrvl_fw_dnld_start(struct nci_dev *ndev, const char *firmware_name)
 {
 	struct nfcmrvl_private *priv = nci_get_drvdata(ndev);
 	struct nfcmrvl_fw_dnld *fw_dnld = &priv->fw_dnld;
+	int res;
 
 	if (!priv->support_fw_dnld)
 		return -ENOTSUPP;
@@ -511,7 +512,9 @@ int nfcmrvl_fw_dnld_start(struct nci_dev *ndev, const char *firmware_name)
 	 */
 
 	/* Retrieve FW binary */
-	if (request_firmware(&fw_dnld->fw, firmware_name, priv->dev) < 0) {
+	res = request_firmware(&fw_dnld->fw, firmware_name,
+			       &ndev->nfc_dev->dev);
+	if (res < 0) {
 		nfc_err(priv->dev, "failed to retrieve FW %s", firmware_name);
 		return -ENOENT;
 	}
diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c
index 51c8240a1672..a446590a71ca 100644
--- a/drivers/nfc/nfcmrvl/main.c
+++ b/drivers/nfc/nfcmrvl/main.c
@@ -124,12 +124,13 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy,
 	memcpy(&priv->config, pdata, sizeof(*pdata));
 
 	if (priv->config.reset_n_io) {
-		rc = devm_gpio_request_one(dev,
-					   priv->config.reset_n_io,
-					   GPIOF_OUT_INIT_LOW,
-					   "nfcmrvl_reset_n");
-		if (rc < 0)
+		rc = gpio_request_one(priv->config.reset_n_io,
+				      GPIOF_OUT_INIT_LOW,
+				      "nfcmrvl_reset_n");
+		if (rc < 0) {
+			priv->config.reset_n_io = 0;
 			nfc_err(dev, "failed to request reset_n io\n");
+		}
 	}
 
 	if (phy == NFCMRVL_PHY_SPI) {
@@ -154,7 +155,13 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy,
 	if (!priv->ndev) {
 		nfc_err(dev, "nci_allocate_device failed\n");
 		rc = -ENOMEM;
-		goto error;
+		goto error_free_gpio;
+	}
+
+	rc = nfcmrvl_fw_dnld_init(priv);
+	if (rc) {
+		nfc_err(dev, "failed to initialize FW download %d\n", rc);
+		goto error_free_dev;
 	}
 
 	nci_set_drvdata(priv->ndev, priv);
@@ -162,24 +169,22 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy,
 	rc = nci_register_device(priv->ndev);
 	if (rc) {
 		nfc_err(dev, "nci_register_device failed %d\n", rc);
-		goto error_free_dev;
+		goto error_fw_dnld_deinit;
 	}
 
 	/* Ensure that controller is powered off */
 	nfcmrvl_chip_halt(priv);
 
-	rc = nfcmrvl_fw_dnld_init(priv);
-	if (rc) {
-		nfc_err(dev, "failed to initialize FW download %d\n", rc);
-		goto error_free_dev;
-	}
-
 	nfc_info(dev, "registered with nci successfully\n");
 	return priv;
 
+error_fw_dnld_deinit:
+	nfcmrvl_fw_dnld_deinit(priv);
 error_free_dev:
 	nci_free_device(priv->ndev);
-error:
+error_free_gpio:
+	if (priv->config.reset_n_io)
+		gpio_free(priv->config.reset_n_io);
 	kfree(priv);
 	return ERR_PTR(rc);
 }
@@ -195,7 +200,7 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv)
 	nfcmrvl_fw_dnld_deinit(priv);
 
 	if (priv->config.reset_n_io)
-		devm_gpio_free(priv->dev, priv->config.reset_n_io);
+		gpio_free(priv->config.reset_n_io);
 
 	nci_unregister_device(ndev);
 	nci_free_device(ndev);
diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c
index 83a99e38e7bd..6c0c301611c4 100644
--- a/drivers/nfc/nfcmrvl/uart.c
+++ b/drivers/nfc/nfcmrvl/uart.c
@@ -109,6 +109,7 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu)
 	struct nfcmrvl_private *priv;
 	struct nfcmrvl_platform_data *pdata = NULL;
 	struct nfcmrvl_platform_data config;
+	struct device *dev = nu->tty->dev;
 
 	/*
 	 * Platform data cannot be used here since usually it is already used
@@ -116,9 +117,8 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu)
 	 * and check if DT entries were added.
 	 */
 
-	if (nu->tty->dev->parent && nu->tty->dev->parent->of_node)
-		if (nfcmrvl_uart_parse_dt(nu->tty->dev->parent->of_node,
-					  &config) == 0)
+	if (dev && dev->parent && dev->parent->of_node)
+		if (nfcmrvl_uart_parse_dt(dev->parent->of_node, &config) == 0)
 			pdata = &config;
 
 	if (!pdata) {
@@ -131,7 +131,7 @@ static int nfcmrvl_nci_uart_open(struct nci_uart *nu)
 	}
 
 	priv = nfcmrvl_nci_register_dev(NFCMRVL_PHY_UART, nu, &uart_ops,
-					nu->tty->dev, pdata);
+					dev, pdata);
 	if (IS_ERR(priv))
 		return PTR_ERR(priv);
 
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 60654d524858..3bbdf60f8908 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -599,7 +599,7 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
 	if (!mw->virt_addr)
 		return -ENOMEM;
 
-	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+	if (mw_num < qp_count % mw_count)
 		num_qps_mw = qp_count / mw_count + 1;
 	else
 		num_qps_mw = qp_count / mw_count;
@@ -947,7 +947,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
 	qp->event_handler = NULL;
 	ntb_qp_link_down_reset(qp);
 
-	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+	if (mw_num < qp_count % mw_count)
 		num_qps_mw = qp_count / mw_count + 1;
 	else
 		num_qps_mw = qp_count / mw_count;
@@ -1065,8 +1065,8 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 	qp_count = ilog2(qp_bitmap);
 	if (max_num_clients && max_num_clients < qp_count)
 		qp_count = max_num_clients;
-	else if (mw_count < qp_count)
-		qp_count = mw_count;
+	else if (nt->mw_count < qp_count)
+		qp_count = nt->mw_count;
 
 	qp_bitmap &= BIT_ULL(qp_count) - 1;
 
@@ -1623,7 +1623,7 @@ ntb_transport_create_queue(void *data, struct device *client_dev,
 
 	node = dev_to_node(&ndev->dev);
 
-	free_queue = ffs(nt->qp_bitmap);
+	free_queue = ffs(nt->qp_bitmap_free);
 	if (!free_queue)
 		goto err;
 
@@ -2082,9 +2082,8 @@ module_init(ntb_transport_init);
 
 static void __exit ntb_transport_exit(void)
 {
-	debugfs_remove_recursive(nt_debugfs_dir);
-
 	ntb_unregister_client(&ntb_transport_client);
 	bus_unregister(&ntb_transport_bus);
+	debugfs_remove_recursive(nt_debugfs_dir);
 }
 module_exit(ntb_transport_exit);
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index efb2c1ceef98..957234272ef7 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1205,10 +1205,13 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector,
 		struct page *page, int rw)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
+	int rc;
 
-	btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector);
-	page_endio(page, rw & WRITE, 0);
-	return 0;
+	rc = btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	if (rc == 0)
+		page_endio(page, rw & WRITE, 0);
+
+	return rc;
 }
 
 
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 7e2c43f701bc..254b0ee37039 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -335,7 +335,7 @@ static const struct nd_cmd_desc __nd_cmd_dimm_descs[] = {
 	[ND_CMD_IMPLEMENTED] = { },
 	[ND_CMD_SMART] = {
 		.out_num = 2,
-		.out_sizes = { 4, 8, },
+		.out_sizes = { 4, 128, },
 	},
 	[ND_CMD_SMART_THRESHOLD] = {
 		.out_num = 2,
@@ -513,10 +513,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 
 	/* fail write commands (when read-only) */
 	if (read_only)
-		switch (ioctl_cmd) {
-		case ND_IOCTL_VENDOR:
-		case ND_IOCTL_SET_CONFIG_DATA:
-		case ND_IOCTL_ARS_START:
+		switch (cmd) {
+		case ND_CMD_VENDOR:
+		case ND_CMD_SET_CONFIG_DATA:
+		case ND_CMD_ARS_START:
 			dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
 					nvdimm ? nvdimm_cmd_name(cmd)
 					: nvdimm_bus_cmd_name(cmd));
@@ -590,8 +590,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len);
 	if (rc < 0)
 		goto out_unlock;
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+
 	if (copy_to_user(p, buf, buf_len))
 		rc = -EFAULT;
+
+	vfree(buf);
+	return rc;
+
  out_unlock:
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
  out:
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 62120c38d56b..aae7379af4e4 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1534,6 +1534,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id)
 static int find_pmem_label_set(struct nd_region *nd_region,
 		struct nd_namespace_pmem *nspm)
 {
+	u64 altcookie = nd_region_interleave_set_altcookie(nd_region);
 	u64 cookie = nd_region_interleave_set_cookie(nd_region);
 	struct nd_namespace_label *nd_label;
 	u8 select_id[NSLABEL_UUID_LEN];
@@ -1542,8 +1543,10 @@ static int find_pmem_label_set(struct nd_region *nd_region,
 	int rc = -ENODEV, l;
 	u16 i;
 
-	if (cookie == 0)
+	if (cookie == 0) {
+		dev_dbg(&nd_region->dev, "invalid interleave-set-cookie\n");
 		return -ENXIO;
+	}
 
 	/*
 	 * Find a complete set of labels by uuid.  By definition we can start
@@ -1552,13 +1555,24 @@ static int find_pmem_label_set(struct nd_region *nd_region,
 	for_each_label(l, nd_label, nd_region->mapping[0].labels) {
 		u64 isetcookie = __le64_to_cpu(nd_label->isetcookie);
 
-		if (isetcookie != cookie)
-			continue;
+		if (isetcookie != cookie) {
+			dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n",
+					nd_label->uuid);
+			if (isetcookie != altcookie)
+				continue;
+
+			dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n",
+					nd_label->uuid);
+		}
+
+		for (i = 0; nd_region->ndr_mappings; i++) {
+			if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i))
+				continue;
+			if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i))
+				continue;
+			break;
+		}
 
-		for (i = 0; nd_region->ndr_mappings; i++)
-			if (!has_uuid_at_pos(nd_region, nd_label->uuid,
-						cookie, i))
-				break;
 		if (i < nd_region->ndr_mappings) {
 			/*
 			 * Give up if we don't find an instance of a
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 417e521d299c..fc870e55bb66 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -245,6 +245,7 @@ struct nd_region *to_nd_region(struct device *dev);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
 u64 nd_region_interleave_set_cookie(struct nd_region *nd_region);
+u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region);
 void nvdimm_bus_lock(struct device *dev);
 void nvdimm_bus_unlock(struct device *dev);
 bool is_nvdimm_bus_locked(struct device *dev);
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 71805a1aa0f3..9d3974591cd6 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -275,7 +275,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	} else {
 		/* from init we validate */
 		if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
-			return -EINVAL;
+			return -ENODEV;
 	}
 
 	/*
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 9521696c9385..dc2e919daa39 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -379,6 +379,15 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
 	return 0;
 }
 
+u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region)
+{
+	struct nd_interleave_set *nd_set = nd_region->nd_set;
+
+	if (nd_set)
+		return nd_set->altcookie;
+	return 0;
+}
+
 /*
  * Upon successful probe/remove, take/release a reference on the
  * associated interleave set (if present), and plant new btt + namespace
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 044253dca30a..b8a5a8e8f57d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -27,6 +27,13 @@ enum {
 	NVME_NS_LIGHTNVM	= 1,
 };
 
+/* The below value is the specific amount of delay needed before checking
+ * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
+ * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
+ * found empirically.
+ */
+#define NVME_QUIRK_DELAY_AMOUNT		2000
+
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
  */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0c67b57be83c..4c673d45f1bd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1633,10 +1633,15 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
  */
 static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
 {
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
 	dev->ctrl_config &= ~NVME_CC_SHN_MASK;
 	dev->ctrl_config &= ~NVME_CC_ENABLE;
 	writel(dev->ctrl_config, &dev->bar->cc);
 
+	if (pdev->vendor == 0x1c58 && pdev->device == 0x0003)
+		msleep(NVME_QUIRK_DELAY_AMOUNT);
+
 	return nvme_wait_ready(dev, cap, false);
 }
 
@@ -2672,10 +2677,10 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	return 0;
 }
 
-static int nvme_dev_map(struct nvme_dev *dev)
+static int nvme_pci_enable(struct nvme_dev *dev)
 {
 	u64 cap;
-	int bars, result = -ENOMEM;
+	int result = -ENOMEM;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pci_enable_device_mem(pdev))
@@ -2683,24 +2688,14 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
 	dev->entry[0].vector = pdev->irq;
 	pci_set_master(pdev);
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	if (!bars)
-		goto disable_pci;
-
-	if (pci_request_selected_regions(pdev, bars, "nvme"))
-		goto disable_pci;
 
 	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
 	    dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
 		goto disable;
 
-	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
-	if (!dev->bar)
-		goto disable;
-
 	if (readl(&dev->bar->csts) == -1) {
 		result = -ENODEV;
-		goto unmap;
+		goto disable;
 	}
 
 	/*
@@ -2710,7 +2705,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	if (!pdev->irq) {
 		result = pci_enable_msix(pdev, dev->entry, 1);
 		if (result < 0)
-			goto unmap;
+			goto disable;
 	}
 
 	cap = lo_hi_readq(&dev->bar->cap);
@@ -2734,18 +2729,21 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
 	return 0;
 
- unmap:
-	iounmap(dev->bar);
-	dev->bar = NULL;
  disable:
-	pci_release_regions(pdev);
- disable_pci:
 	pci_disable_device(pdev);
+
 	return result;
 }
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
+	if (dev->bar)
+		iounmap(dev->bar);
+	pci_release_regions(to_pci_dev(dev->dev));
+}
+
+static void nvme_pci_disable(struct nvme_dev *dev)
+{
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pdev->msi_enabled)
@@ -2753,12 +2751,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev)
 	else if (pdev->msix_enabled)
 		pci_disable_msix(pdev);
 
-	if (dev->bar) {
-		iounmap(dev->bar);
-		dev->bar = NULL;
-		pci_release_regions(pdev);
-	}
-
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 }
@@ -2962,7 +2954,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 
 	nvme_dev_list_remove(dev);
 
-	if (dev->bar) {
+	if (pci_is_enabled(to_pci_dev(dev->dev))) {
 		nvme_freeze_queues(dev);
 		csts = readl(&dev->bar->csts);
 	}
@@ -2976,7 +2968,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 		nvme_shutdown_ctrl(dev);
 		nvme_disable_queue(dev, 0);
 	}
-	nvme_dev_unmap(dev);
+	nvme_pci_disable(dev);
 
 	for (i = dev->queue_count - 1; i >= 0; i--)
 		nvme_clear_queue(dev->queues[i]);
@@ -3136,7 +3128,7 @@ static void nvme_probe_work(struct work_struct *work)
 	bool start_thread = false;
 	int result;
 
-	result = nvme_dev_map(dev);
+	result = nvme_pci_enable(dev);
 	if (result)
 		goto out;
 
@@ -3292,6 +3284,27 @@ static ssize_t nvme_sysfs_reset(struct device *dev,
 }
 static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
 
+static int nvme_dev_map(struct nvme_dev *dev)
+{
+	int bars;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	if (!bars)
+		return -ENODEV;
+	if (pci_request_selected_regions(pdev, bars, "nvme"))
+		return -ENODEV;
+
+	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+	if (!dev->bar)
+		goto release;
+
+	return 0;
+release:
+	pci_release_regions(pdev);
+	return -ENODEV;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -3317,6 +3330,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_WORK(&dev->reset_work, nvme_reset_work);
 	dev->dev = get_device(&pdev->dev);
 	pci_set_drvdata(pdev, dev);
+
+	result = nvme_dev_map(dev);
+	if (result)
+		goto free;
+
 	result = nvme_set_instance(dev);
 	if (result)
 		goto put_pci;
@@ -3355,6 +3373,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_release_instance(dev);
  put_pci:
 	put_device(dev->dev);
+	nvme_dev_unmap(dev);
  free:
 	kfree(dev->queues);
 	kfree(dev->entry);
@@ -3398,6 +3417,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_free_queues(dev, 0);
 	nvme_release_cmb(dev);
 	nvme_release_prp_pools(dev);
+	nvme_dev_unmap(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }
 
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index b7971d410b60..74e5360c53f0 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -88,7 +88,7 @@ static struct nvmem_config imx_ocotp_nvmem_config = {
 
 static const struct of_device_id imx_ocotp_dt_ids[] = {
 	{ .compatible = "fsl,imx6q-ocotp",  (void *)128 },
-	{ .compatible = "fsl,imx6sl-ocotp", (void *)32 },
+	{ .compatible = "fsl,imx6sl-ocotp", (void *)64 },
 	{ .compatible = "fsl,imx6sx-ocotp", (void *)128 },
 	{ },
 };
diff --git a/drivers/nvmem/mxs-ocotp.c b/drivers/nvmem/mxs-ocotp.c
index 8ba19bba3156..2bb3c5799ac4 100644
--- a/drivers/nvmem/mxs-ocotp.c
+++ b/drivers/nvmem/mxs-ocotp.c
@@ -94,7 +94,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size,
 	if (ret)
 		goto close_banks;
 
-	while (val_size) {
+	while (val_size >= reg_size) {
 		if ((offset < OCOTP_DATA_OFFSET) || (offset % 16)) {
 			/* fill up non-data register */
 			*buf = 0;
@@ -103,7 +103,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size,
 		}
 
 		buf++;
-		val_size--;
+		val_size -= reg_size;
 		offset += reg_size;
 	}
 
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 9582c5703b3c..4fe5fe21cd49 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -260,7 +260,7 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 	if (!parser->range || parser->range + parser->np > parser->end)
 		return NULL;
 
-	range->pci_space = parser->range[0];
+	range->pci_space = be32_to_cpup(parser->range);
 	range->flags = of_bus_pci_get_flags(parser->range);
 	range->pci_addr = of_read_number(parser->range + 1, ns);
 	range->cpu_addr = of_translate_address(parser->node,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 017dd94f16ea..31341290cd91 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -112,6 +112,7 @@ static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
 	return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
 }
 
+/* always return newly allocated name, caller must free after use */
 static const char *safe_name(struct kobject *kobj, const char *orig_name)
 {
 	const char *name = orig_name;
@@ -126,9 +127,12 @@ static const char *safe_name(struct kobject *kobj, const char *orig_name)
 		name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
 	}
 
-	if (name != orig_name)
+	if (name == orig_name) {
+		name = kstrdup(orig_name, GFP_KERNEL);
+	} else {
 		pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
 			kobject_name(kobj), name);
+	}
 	return name;
 }
 
@@ -159,6 +163,7 @@ int __of_add_property_sysfs(struct device_node *np, struct property *pp)
 int __of_attach_node_sysfs(struct device_node *np)
 {
 	const char *name;
+	struct kobject *parent;
 	struct property *pp;
 	int rc;
 
@@ -171,15 +176,16 @@ int __of_attach_node_sysfs(struct device_node *np)
 	np->kobj.kset = of_kset;
 	if (!np->parent) {
 		/* Nodes without parents are new top level trees */
-		rc = kobject_add(&np->kobj, NULL, "%s",
-				 safe_name(&of_kset->kobj, "base"));
+		name = safe_name(&of_kset->kobj, "base");
+		parent = NULL;
 	} else {
 		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
-		if (!name || !name[0])
-			return -EINVAL;
-
-		rc = kobject_add(&np->kobj, &np->parent->kobj, "%s", name);
+		parent = &np->parent->kobj;
 	}
+	if (!name)
+		return -ENOMEM;
+	rc = kobject_add(&np->kobj, parent, "%s", name);
+	kfree(name);
 	if (rc)
 		return rc;
 
@@ -1753,6 +1759,12 @@ int __of_remove_property(struct device_node *np, struct property *prop)
 	return 0;
 }
 
+void __of_sysfs_remove_bin_file(struct device_node *np, struct property *prop)
+{
+	sysfs_remove_bin_file(&np->kobj, &prop->attr);
+	kfree(prop->attr.attr.name);
+}
+
 void __of_remove_property_sysfs(struct device_node *np, struct property *prop)
 {
 	if (!IS_ENABLED(CONFIG_SYSFS))
@@ -1760,7 +1772,7 @@ void __of_remove_property_sysfs(struct device_node *np, struct property *prop)
 
 	/* at early boot, bail here and defer setup to of_init() */
 	if (of_kset && of_node_is_attached(np))
-		sysfs_remove_bin_file(&np->kobj, &prop->attr);
+		__of_sysfs_remove_bin_file(np, prop);
 }
 
 /**
@@ -1830,7 +1842,7 @@ void __of_update_property_sysfs(struct device_node *np, struct property *newprop
 		return;
 
 	if (oldprop)
-		sysfs_remove_bin_file(&np->kobj, &oldprop->attr);
+		__of_sysfs_remove_bin_file(np, oldprop);
 	__of_add_property_sysfs(np, newprop);
 }
 
@@ -2241,20 +2253,13 @@ struct device_node *of_graph_get_endpoint_by_regs(
 	const struct device_node *parent, int port_reg, int reg)
 {
 	struct of_endpoint endpoint;
-	struct device_node *node, *prev_node = NULL;
-
-	while (1) {
-		node = of_graph_get_next_endpoint(parent, prev_node);
-		of_node_put(prev_node);
-		if (!node)
-			break;
+	struct device_node *node = NULL;
 
+	for_each_endpoint_of_node(parent, node) {
 		of_graph_parse_endpoint(node, &endpoint);
 		if (((port_reg == -1) || (endpoint.port == port_reg)) &&
 			((reg == -1) || (endpoint.id == reg)))
 			return node;
-
-		prev_node = node;
 	}
 
 	return NULL;
diff --git a/drivers/of/device.c b/drivers/of/device.c
index e5f47cec75f3..97a280d50d6d 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -225,6 +225,7 @@ ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len)
 
 	return tsize;
 }
+EXPORT_SYMBOL_GPL(of_device_get_modalias);
 
 /**
  * of_device_uevent - Display OF related uevent information
@@ -287,3 +288,4 @@ int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(of_device_uevent_modalias);
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 53826b84e0ec..2d72ddcf534f 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -55,7 +55,7 @@ void __of_detach_node_sysfs(struct device_node *np)
 	/* only remove properties if on sysfs */
 	if (of_node_is_attached(np)) {
 		for_each_property_of_node(np, pp)
-			sysfs_remove_bin_file(&np->kobj, &pp->attr);
+			__of_sysfs_remove_bin_file(np, pp);
 		kobject_del(&np->kobj);
 	}
 
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 655f79db7899..58048dd5fcd0 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -632,9 +632,12 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 	const char *pathp;
 	int offset, rc = 0, depth = -1;
 
-        for (offset = fdt_next_node(blob, -1, &depth);
-             offset >= 0 && depth >= 0 && !rc;
-             offset = fdt_next_node(blob, offset, &depth)) {
+	if (!blob)
+		return 0;
+
+	for (offset = fdt_next_node(blob, -1, &depth);
+	     offset >= 0 && depth >= 0 && !rc;
+	     offset = fdt_next_node(blob, offset, &depth)) {
 
 		pathp = fdt_get_name(blob, offset, NULL);
 		if (*pathp == '/')
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 72a2c1969646..28da6242eb84 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -386,13 +386,13 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
 EXPORT_SYMBOL_GPL(of_irq_to_resource);
 
 /**
- * of_irq_get - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get - Decode a node's IRQ and return it as a Linux IRQ number
  * @dev: pointer to device tree node
- * @index: zero-based index of the irq
- *
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created.
+ * @index: zero-based index of the IRQ
  *
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
  */
 int of_irq_get(struct device_node *dev, int index)
 {
@@ -413,12 +413,13 @@ int of_irq_get(struct device_node *dev, int index)
 EXPORT_SYMBOL_GPL(of_irq_get);
 
 /**
- * of_irq_get_byname - Decode a node's IRQ and return it as a Linux irq number
+ * of_irq_get_byname - Decode a node's IRQ and return it as a Linux IRQ number
  * @dev: pointer to device tree node
- * @name: irq name
+ * @name: IRQ name
  *
- * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
- * is not yet created, or error code in case of any other failure.
+ * Returns Linux IRQ number on success, or 0 on the IRQ mapping failure, or
+ * -EPROBE_DEFER if the IRQ domain is not yet created, or error code in case
+ * of any other failure.
  */
 int of_irq_get_byname(struct device_node *dev, const char *name)
 {
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 8e882e706cd8..46ddbee22ce3 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -81,6 +81,9 @@ extern int __of_attach_node_sysfs(struct device_node *np);
 extern void __of_detach_node(struct device_node *np);
 extern void __of_detach_node_sysfs(struct device_node *np);
 
+extern void __of_sysfs_remove_bin_file(struct device_node *np,
+				       struct property *prop);
+
 /* iterators for transactions, used for overlays */
 /* forward iterator */
 #define for_each_transaction_entry(_oft, _te) \
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 1a3556a9e9ea..07dd81586c52 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -32,11 +32,13 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
 	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
 	phys_addr_t *res_base)
 {
+	phys_addr_t base;
 	/*
 	 * We use __memblock_alloc_base() because memblock_alloc_base()
 	 * panic()s on allocation failure.
 	 */
-	phys_addr_t base = __memblock_alloc_base(size, align, end);
+	end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end;
+	base = __memblock_alloc_base(size, align, end);
 	if (!base)
 		return -ENOMEM;
 
@@ -125,8 +127,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 	}
 
 	/* Need adjust the alignment to satisfy the CMA requirement */
-	if (IS_ENABLED(CONFIG_CMA) && of_flat_dt_is_compatible(node, "shared-dma-pool"))
-		align = max(align, (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+	if (IS_ENABLED(CONFIG_CMA) && of_flat_dt_is_compatible(node, "shared-dma-pool")) {
+		unsigned long order =
+			max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
+
+		align = max(align, (phys_addr_t)PAGE_SIZE << order);
+	}
 
 	prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
 	if (prop) {
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 8e11fb2831cd..34f1d6b41fb9 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -741,6 +741,8 @@ ccio_map_single(struct device *dev, void *addr, size_t size,
 
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return DMA_ERROR_CODE;
 
 	BUG_ON(size <= 0);
 
@@ -805,6 +807,10 @@ ccio_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
 	
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 	DBG_RUN("%s() iovp 0x%lx/%x\n",
 		__func__, (long)iova, size);
@@ -908,6 +914,8 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 	
 	DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
 
@@ -980,6 +988,10 @@ ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 	DBG_RUN_SG("%s() START %d entries, %p,%x\n",
 		__func__, nents, sg_virt(sglist), sglist->length);
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index a0580afe1713..005ea632ba53 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -154,7 +154,10 @@ struct dino_device
 };
 
 /* Looks nice and keeps the compiler happy */
-#define DINO_DEV(d) ((struct dino_device *) d)
+#define DINO_DEV(d) ({				\
+	void *__pdata = d;			\
+	BUG_ON(!__pdata);			\
+	(struct dino_device *)__pdata; })
 
 
 /*
@@ -951,7 +954,7 @@ static int __init dino_probe(struct parisc_device *dev)
 
 	dino_dev->hba.dev = dev;
 	dino_dev->hba.base_addr = ioremap_nocache(hpa, 4096);
-	dino_dev->hba.lmmio_space_offset = 0;	/* CPU addrs == bus addrs */
+	dino_dev->hba.lmmio_space_offset = PCI_F_EXTEND;
 	spin_lock_init(&dino_dev->dinosaur_pen);
 	dino_dev->hba.iommu = ccio_get_iommu(dev);
 
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 42844c2bc065..d0c2759076a2 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -111,8 +111,10 @@ static u32 lba_t32;
 
 
 /* Looks nice and keeps the compiler happy */
-#define LBA_DEV(d) ((struct lba_device *) (d))
-
+#define LBA_DEV(d) ({				\
+	void *__pdata = d;			\
+	BUG_ON(!__pdata);			\
+	(struct lba_device *)__pdata; })
 
 /*
 ** Only allow 8 subsidiary busses per LBA
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 225049b492e5..d6326144ce01 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -691,6 +691,8 @@ static int sba_dma_supported( struct device *dev, u64 mask)
 		return 0;
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 
 	/*
 	 * check if mask is >= than the current max IO Virt Address
@@ -722,6 +724,8 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 	int pide;
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return DMA_ERROR_CODE;
 
 	/* save offset bits */
 	offset = ((dma_addr_t) (long) addr) & ~IOVP_MASK;
@@ -803,6 +807,10 @@ sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
 	DBG_RUN("%s() iovp 0x%lx/%x\n", __func__, (long) iova, size);
 
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 	offset = iova & ~IOVP_MASK;
 	iova ^= offset;        /* clear offset bits */
 	size += offset;
@@ -942,6 +950,8 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
 
 	ioc = GET_IOC(dev);
+	if (!ioc)
+		return 0;
 
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
@@ -1027,6 +1037,10 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 		__func__, nents, sg_virt(sglist), sglist->length);
 
 	ioc = GET_IOC(dev);
+	if (!ioc) {
+		WARN_ON(!ioc);
+		return;
+	}
 
 #ifdef SBA_COLLECT_STATS
 	ioc->usg_calls++;
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index 6e3a60c78873..50f3bb0dd1f1 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -293,7 +293,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
 		p->irq = PARPORT_IRQ_NONE;
 	}
 	if (p->irq != PARPORT_IRQ_NONE) {
-		printk(", irq %d", p->irq);
+		pr_cont(", irq %d", p->irq);
 
 		if (p->dma == PARPORT_DMA_AUTO) {
 			p->dma = PARPORT_DMA_NONE;
@@ -303,8 +303,8 @@ struct parport *parport_gsc_probe_port(unsigned long base,
                                            is mandatory (see above) */
 		p->dma = PARPORT_DMA_NONE;
 
-	printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+	pr_cont(" [");
+#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}}
 	{
 		int f = 0;
 		printmode(PCSPP);
@@ -315,7 +315,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
 //		printmode(DMA);
 	}
 #undef printmode
-	printk("]\n");
+	pr_cont("]\n");
 
 	if (p->irq != PARPORT_IRQ_NONE) {
 		if (request_irq (p->irq, parport_irq_handler,
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 5ce5ef211bdb..754f21fd9768 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -936,8 +936,10 @@ parport_register_dev_model(struct parport *port, const char *name,
 	 * pardevice fields. -arca
 	 */
 	port->ops->init_state(par_dev, par_dev->state);
-	port->proc_device = par_dev;
-	parport_device_proc_register(par_dev);
+	if (!test_and_set_bit(PARPORT_DEVPROC_REGISTERED, &port->devflags)) {
+		port->proc_device = par_dev;
+		parport_device_proc_register(par_dev);
+	}
 
 	return par_dev;
 
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index e12bafdc42e0..f2fcbe944d94 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -258,8 +258,13 @@ static int dlpar_add_phb(char *drc_name, struct device_node *dn)
 
 static int dlpar_add_vio_slot(char *drc_name, struct device_node *dn)
 {
-	if (vio_find_node(dn))
+	struct vio_dev *vio_dev;
+
+	vio_dev = vio_find_node(dn);
+	if (vio_dev) {
+		put_device(&vio_dev->dev);
 		return -EINVAL;
+	}
 
 	if (!vio_register_device_node(dn)) {
 		printk(KERN_ERR
@@ -335,6 +340,9 @@ static int dlpar_remove_vio_slot(char *drc_name, struct device_node *dn)
 		return -EINVAL;
 
 	vio_unregister_device(vio_dev);
+
+	put_device(&vio_dev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 31f31d460fc9..357527712539 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -303,13 +303,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 			return rc;
 	}
 
-	pci_iov_set_numvfs(dev, nr_virtfn);
-	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
-	pci_cfg_access_lock(dev);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
-	msleep(100);
-	pci_cfg_access_unlock(dev);
-
 	iov->initial_VFs = initial;
 	if (nr_virtfn < initial)
 		initial = nr_virtfn;
@@ -320,6 +313,13 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 		goto err_pcibios;
 	}
 
+	pci_iov_set_numvfs(dev, nr_virtfn);
+	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
+	pci_cfg_access_lock(dev);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	msleep(100);
+	pci_cfg_access_unlock(dev);
+
 	for (i = 0; i < initial; i++) {
 		rc = virtfn_add(dev, i, 0);
 		if (rc)
@@ -555,21 +555,61 @@ void pci_iov_release(struct pci_dev *dev)
 }
 
 /**
- * pci_iov_resource_bar - get position of the SR-IOV BAR
+ * pci_iov_update_resource - update a VF BAR
  * @dev: the PCI device
  * @resno: the resource number
  *
- * Returns position of the BAR encapsulated in the SR-IOV capability.
+ * Update a VF BAR in the SR-IOV capability of a PF.
  */
-int pci_iov_resource_bar(struct pci_dev *dev, int resno)
+void pci_iov_update_resource(struct pci_dev *dev, int resno)
 {
-	if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END)
-		return 0;
+	struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL;
+	struct resource *res = dev->resource + resno;
+	int vf_bar = resno - PCI_IOV_RESOURCES;
+	struct pci_bus_region region;
+	u16 cmd;
+	u32 new;
+	int reg;
+
+	/*
+	 * The generic pci_restore_bars() path calls this for all devices,
+	 * including VFs and non-SR-IOV devices.  If this is not a PF, we
+	 * have nothing to do.
+	 */
+	if (!iov)
+		return;
+
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &cmd);
+	if ((cmd & PCI_SRIOV_CTRL_VFE) && (cmd & PCI_SRIOV_CTRL_MSE)) {
+		dev_WARN(&dev->dev, "can't update enabled VF BAR%d %pR\n",
+			 vf_bar, res);
+		return;
+	}
+
+	/*
+	 * Ignore unimplemented BARs, unused resource slots for 64-bit
+	 * BARs, and non-movable resources, e.g., those described via
+	 * Enhanced Allocation.
+	 */
+	if (!res->flags)
+		return;
+
+	if (res->flags & IORESOURCE_UNSET)
+		return;
+
+	if (res->flags & IORESOURCE_PCI_FIXED)
+		return;
 
-	BUG_ON(!dev->is_physfn);
+	pcibios_resource_to_bus(dev->bus, &region, res);
+	new = region.start;
+	new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK;
 
-	return dev->sriov->pos + PCI_SRIOV_BAR +
-		4 * (resno - PCI_IOV_RESOURCES);
+	reg = iov->pos + PCI_SRIOV_BAR + 4 * vf_bar;
+	pci_write_config_dword(dev, reg, new);
+	if (res->flags & IORESOURCE_MEM_64) {
+		new = region.start >> 16 >> 16;
+		pci_write_config_dword(dev, reg + 4, new);
+	}
 }
 
 resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev,
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 7eaa4c87fec7..10a6a8e5db88 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1278,6 +1278,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		pci_msi_domain_update_chip_ops(info);
 
+	info->flags |= MSI_FLAG_ACTIVATE_EARLY;
+
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (!domain)
 		return NULL;
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index d7ffd66814bb..fca925543fae 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -945,6 +945,7 @@ static int pci_pm_thaw_noirq(struct device *dev)
 		return pci_legacy_resume_early(dev);
 
 	pci_update_current_state(pci_dev, PCI_D0);
+	pci_restore_state(pci_dev);
 
 	if (drv && drv->pm && drv->pm->thaw_noirq)
 		error = drv->pm->thaw_noirq(dev);
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index eead54cd01b2..f8b2b5987ea9 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -973,15 +973,19 @@ void pci_remove_legacy_files(struct pci_bus *b)
 int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
 		  enum pci_mmap_api mmap_api)
 {
-	unsigned long nr, start, size, pci_start;
+	unsigned long nr, start, size;
+	resource_size_t pci_start = 0, pci_end;
 
 	if (pci_resource_len(pdev, resno) == 0)
 		return 0;
 	nr = vma_pages(vma);
 	start = vma->vm_pgoff;
 	size = ((pci_resource_len(pdev, resno) - 1) >> PAGE_SHIFT) + 1;
-	pci_start = (mmap_api == PCI_MMAP_PROCFS) ?
-			pci_resource_start(pdev, resno) >> PAGE_SHIFT : 0;
+	if (mmap_api == PCI_MMAP_PROCFS) {
+		pci_resource_to_user(pdev, resno, &pdev->resource[resno],
+				     &pci_start, &pci_end);
+		pci_start >>= PAGE_SHIFT;
+	}
 	if (start >= pci_start && start < pci_start + size &&
 			start + nr <= pci_start + size)
 		return 1;
@@ -1372,10 +1376,10 @@ int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 	if (!sysfs_initialized)
 		return -EACCES;
 
-	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
-		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pci_config_attr);
-	else
+	if (pdev->cfg_size > PCI_CFG_SPACE_SIZE)
 		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+	else
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pci_config_attr);
 	if (retval)
 		goto err;
 
@@ -1427,10 +1431,10 @@ err_rom_file:
 err_resource_files:
 	pci_remove_resource_files(pdev);
 err_config_file:
-	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
-		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
-	else
+	if (pdev->cfg_size > PCI_CFG_SPACE_SIZE)
 		sysfs_remove_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+	else
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
 err:
 	return retval;
 }
@@ -1464,10 +1468,10 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 
 	pci_remove_capabilities_sysfs(pdev);
 
-	if (pdev->cfg_size < PCI_CFG_SPACE_EXP_SIZE)
-		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
-	else
+	if (pdev->cfg_size > PCI_CFG_SPACE_SIZE)
 		sysfs_remove_bin_file(&pdev->dev.kobj, &pcie_config_attr);
+	else
+		sysfs_remove_bin_file(&pdev->dev.kobj, &pci_config_attr);
 
 	pci_remove_resource_files(pdev);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 42d8617352ae..1a14ca8965e6 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -519,10 +519,6 @@ static void pci_restore_bars(struct pci_dev *dev)
 {
 	int i;
 
-	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
-	if (dev->is_virtfn)
-		return;
-
 	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++)
 		pci_update_resource(dev, i);
 }
@@ -1736,8 +1732,8 @@ static void pci_pme_list_scan(struct work_struct *work)
 		}
 	}
 	if (!list_empty(&pci_pme_list))
-		schedule_delayed_work(&pci_pme_work,
-				      msecs_to_jiffies(PME_TIMEOUT));
+		queue_delayed_work(system_freezable_wq, &pci_pme_work,
+				   msecs_to_jiffies(PME_TIMEOUT));
 	mutex_unlock(&pci_pme_list_mutex);
 }
 
@@ -1802,8 +1798,9 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
 			mutex_lock(&pci_pme_list_mutex);
 			list_add(&pme_dev->list, &pci_pme_list);
 			if (list_is_singular(&pci_pme_list))
-				schedule_delayed_work(&pci_pme_work,
-						      msecs_to_jiffies(PME_TIMEOUT));
+				queue_delayed_work(system_freezable_wq,
+						   &pci_pme_work,
+						   msecs_to_jiffies(PME_TIMEOUT));
 			mutex_unlock(&pci_pme_list_mutex);
 		} else {
 			mutex_lock(&pci_pme_list_mutex);
@@ -2043,6 +2040,10 @@ bool pci_dev_run_wake(struct pci_dev *dev)
 	if (!dev->pme_support)
 		return false;
 
+	/* PME-capable in principle, but not from the intended sleep state */
+	if (!pci_pme_capable(dev, pci_target_state(dev)))
+		return false;
+
 	while (bus->parent) {
 		struct pci_dev *bridge = bus->self;
 
@@ -4468,36 +4469,6 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags)
 }
 EXPORT_SYMBOL(pci_select_bars);
 
-/**
- * pci_resource_bar - get position of the BAR associated with a resource
- * @dev: the PCI device
- * @resno: the resource number
- * @type: the BAR type to be filled in
- *
- * Returns BAR position in config space, or 0 if the BAR is invalid.
- */
-int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
-{
-	int reg;
-
-	if (resno < PCI_ROM_RESOURCE) {
-		*type = pci_bar_unknown;
-		return PCI_BASE_ADDRESS_0 + 4 * resno;
-	} else if (resno == PCI_ROM_RESOURCE) {
-		*type = pci_bar_mem32;
-		return dev->rom_base_reg;
-	} else if (resno < PCI_BRIDGE_RESOURCES) {
-		/* device specific resource */
-		*type = pci_bar_unknown;
-		reg = pci_iov_resource_bar(dev, resno);
-		if (reg)
-			return reg;
-	}
-
-	dev_err(&dev->dev, "BAR %d: invalid resource\n", resno);
-	return 0;
-}
-
 /* Some architectures require additional programming to enable VGA */
 static arch_set_vga_state_t arch_set_vga_state;
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d390fc1475ec..c43e448873ca 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -232,7 +232,6 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 int pci_setup_device(struct pci_dev *dev);
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		    struct resource *res, unsigned int reg);
-int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type);
 void pci_configure_ari(struct pci_dev *dev);
 void __pci_bus_size_bridges(struct pci_bus *bus,
 			struct list_head *realloc_head);
@@ -276,7 +275,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
-int pci_iov_resource_bar(struct pci_dev *dev, int resno);
+void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
 int pci_iov_bus_range(struct pci_bus *bus);
@@ -290,10 +289,6 @@ static inline void pci_iov_release(struct pci_dev *dev)
 
 {
 }
-static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno)
-{
-	return 0;
-}
 static inline void pci_restore_iov_state(struct pci_dev *dev)
 {
 }
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
index 182224acedbe..58f1419a68ae 100644
--- a/drivers/pci/pcie/aer/aer_inject.c
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -283,20 +283,6 @@ out:
 	return 0;
 }
 
-static struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
-{
-	while (1) {
-		if (!pci_is_pcie(dev))
-			break;
-		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
-			return dev;
-		if (!dev->bus->self)
-			break;
-		dev = dev->bus->self;
-	}
-	return NULL;
-}
-
 static int find_aer_device_iter(struct device *device, void *data)
 {
 	struct pcie_device **result = data;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 317e3558a35e..c6a012b5ba39 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -518,25 +518,32 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link)
 		return NULL;
+
 	INIT_LIST_HEAD(&link->sibling);
 	INIT_LIST_HEAD(&link->children);
 	INIT_LIST_HEAD(&link->link);
 	link->pdev = pdev;
-	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) {
+
+	/*
+	 * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
+	 * hierarchies.
+	 */
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
+	    pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) {
+		link->root = link;
+	} else {
 		struct pcie_link_state *parent;
+
 		parent = pdev->bus->parent->self->link_state;
 		if (!parent) {
 			kfree(link);
 			return NULL;
 		}
+
 		link->parent = parent;
+		link->root = link->parent->root;
 		list_add(&link->link, &parent->children);
 	}
-	/* Setup a pointer to the root port link */
-	if (!link->parent)
-		link->root = link;
-	else
-		link->root = link->parent->root;
 
 	list_add(&link->sibling, &link_list);
 	pdev->link_state = link;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index edb1984201e9..b83df942794f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -226,7 +226,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			mask64 = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
-		res->flags |= (l & IORESOURCE_ROM_ENABLE);
+		if (l & PCI_ROM_ADDRESS_ENABLE)
+			res->flags |= IORESOURCE_ROM_ENABLE;
 		l64 = l & PCI_ROM_ADDRESS_MASK;
 		sz64 = sz & PCI_ROM_ADDRESS_MASK;
 		mask64 = (u32)PCI_ROM_ADDRESS_MASK;
@@ -319,6 +320,9 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 {
 	unsigned int pos, reg;
 
+	if (dev->non_compliant_bars)
+		return;
+
 	for (pos = 0; pos < howmany; pos++) {
 		struct resource *res = &dev->resource[pos];
 		reg = PCI_BASE_ADDRESS_0 + (pos << 2);
@@ -1016,6 +1020,7 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
 	if (!pos)
 		return;
+
 	pdev->pcie_cap = pos;
 	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
 	pdev->pcie_flags_reg = reg16;
@@ -1023,13 +1028,14 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
 
 	/*
-	 * A Root Port is always the upstream end of a Link.  No PCIe
-	 * component has two Links.  Two Links are connected by a Switch
-	 * that has a Port on each Link and internal logic to connect the
-	 * two Ports.
+	 * A Root Port or a PCI-to-PCIe bridge is always the upstream end
+	 * of a Link.  No PCIe component has two Links.  Two Links are
+	 * connected by a Switch that has a Port on each Link and internal
+	 * logic to connect the two Ports.
 	 */
 	type = pci_pcie_type(pdev);
-	if (type == PCI_EXP_TYPE_ROOT_PORT)
+	if (type == PCI_EXP_TYPE_ROOT_PORT ||
+	    type == PCI_EXP_TYPE_PCIE_BRIDGE)
 		pdev->has_secondary_link = 1;
 	else if (type == PCI_EXP_TYPE_UPSTREAM ||
 		 type == PCI_EXP_TYPE_DOWNSTREAM) {
@@ -1174,6 +1180,7 @@ void pci_msi_setup_pci_dev(struct pci_dev *dev)
 int pci_setup_device(struct pci_dev *dev)
 {
 	u32 class;
+	u16 cmd;
 	u8 hdr_type;
 	int pos = 0;
 	struct pci_bus_region region;
@@ -1219,6 +1226,16 @@ int pci_setup_device(struct pci_dev *dev)
 	/* device class may be changed after fixup */
 	class = dev->class >> 8;
 
+	if (dev->non_compliant_bars) {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
+			dev_info(&dev->dev, "device has non-compliant BARs; disabling IO/MEM decoding\n");
+			cmd &= ~PCI_COMMAND_IO;
+			cmd &= ~PCI_COMMAND_MEMORY;
+			pci_write_config_word(dev, PCI_COMMAND, cmd);
+		}
+	}
+
 	switch (dev->hdr_type) {		    /* header type */
 	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
 		if (class == PCI_CLASS_BRIDGE_PCI)
@@ -1401,6 +1418,21 @@ static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp)
 		dev_warn(&dev->dev, "PCI-X settings not supported\n");
 }
 
+static bool pcie_root_rcb_set(struct pci_dev *dev)
+{
+	struct pci_dev *rp = pcie_find_root_port(dev);
+	u16 lnkctl;
+
+	if (!rp)
+		return false;
+
+	pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl);
+	if (lnkctl & PCI_EXP_LNKCTL_RCB)
+		return true;
+
+	return false;
+}
+
 static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
 {
 	int pos;
@@ -1430,9 +1462,20 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
 			~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or);
 
 	/* Initialize Link Control Register */
-	if (pcie_cap_has_lnkctl(dev))
+	if (pcie_cap_has_lnkctl(dev)) {
+
+		/*
+		 * If the Root Port supports Read Completion Boundary of
+		 * 128, set RCB to 128.  Otherwise, clear it.
+		 */
+		hpp->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB;
+		hpp->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB;
+		if (pcie_root_rcb_set(dev))
+			hpp->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB;
+
 		pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL,
 			~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or);
+	}
 
 	/* Find Advanced Error Reporting Enhanced Capability */
 	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 7e327309cf69..254192b5dad1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -287,6 +287,18 @@ static void quirk_citrine(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
 
+/*
+ * This chip can cause bus lockups if config addresses above 0x600
+ * are read or written.
+ */
+static void quirk_nfp6000(struct pci_dev *dev)
+{
+	dev->cfg_size = 0x600;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP4000,	quirk_nfp6000);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000,	quirk_nfp6000);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000_VF,	quirk_nfp6000);
+
 /*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
 static void quirk_extend_bar_to_page(struct pci_dev *dev)
 {
@@ -3115,13 +3127,16 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
 }
 
 /*
- * Atheros AR93xx chips do not behave after a bus reset.  The device will
- * throw a Link Down error on AER-capable systems and regardless of AER,
- * config space of the device is never accessible again and typically
- * causes the system to hang or reset when access is attempted.
+ * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
+ * The device will throw a Link Down error on AER-capable systems and
+ * regardless of AER, config space of the device is never accessible again
+ * and typically causes the system to hang or reset when access is attempted.
  * http://www.spinics.net/lists/linux-pci/msg34797.html
  */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0032, quirk_no_bus_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x003c, quirk_no_bus_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0033, quirk_no_bus_reset);
 
 static void quirk_no_pm_reset(struct pci_dev *dev)
 {
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index eb0ad530dc43..3eea7fc5e1a2 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -31,6 +31,11 @@ int pci_enable_rom(struct pci_dev *pdev)
 	if (!res->flags)
 		return -1;
 
+	/*
+	 * Ideally pci_update_resource() would update the ROM BAR address,
+	 * and we would only set the enable bit here.  But apparently some
+	 * devices have buggy ROM BARs that read as zero when disabled.
+	 */
 	pcibios_resource_to_bus(pdev->bus, &region, res);
 	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
 	rom_addr &= ~PCI_ROM_ADDRESS_MASK;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 604011e047d6..25062966cbfa 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -25,21 +25,18 @@
 #include <linux/slab.h>
 #include "pci.h"
 
-
-void pci_update_resource(struct pci_dev *dev, int resno)
+static void pci_std_update_resource(struct pci_dev *dev, int resno)
 {
 	struct pci_bus_region region;
 	bool disable;
 	u16 cmd;
 	u32 new, check, mask;
 	int reg;
-	enum pci_bar_type type;
 	struct resource *res = dev->resource + resno;
 
-	if (dev->is_virtfn) {
-		dev_warn(&dev->dev, "can't update VF BAR%d\n", resno);
+	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
+	if (dev->is_virtfn)
 		return;
-	}
 
 	/*
 	 * Ignore resources for unimplemented BARs and unused resource slots
@@ -60,21 +57,34 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 		return;
 
 	pcibios_resource_to_bus(dev->bus, &region, res);
+	new = region.start;
 
-	new = region.start | (res->flags & PCI_REGION_FLAG_MASK);
-	if (res->flags & IORESOURCE_IO)
+	if (res->flags & IORESOURCE_IO) {
 		mask = (u32)PCI_BASE_ADDRESS_IO_MASK;
-	else
+		new |= res->flags & ~PCI_BASE_ADDRESS_IO_MASK;
+	} else if (resno == PCI_ROM_RESOURCE) {
+		mask = (u32)PCI_ROM_ADDRESS_MASK;
+	} else {
 		mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+		new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK;
+	}
 
-	reg = pci_resource_bar(dev, resno, &type);
-	if (!reg)
-		return;
-	if (type != pci_bar_unknown) {
+	if (resno < PCI_ROM_RESOURCE) {
+		reg = PCI_BASE_ADDRESS_0 + 4 * resno;
+	} else if (resno == PCI_ROM_RESOURCE) {
+
+		/*
+		 * Apparently some Matrox devices have ROM BARs that read
+		 * as zero when disabled, so don't update ROM BARs unless
+		 * they're enabled.  See https://lkml.org/lkml/2005/8/30/138.
+		 */
 		if (!(res->flags & IORESOURCE_ROM_ENABLE))
 			return;
+
+		reg = dev->rom_base_reg;
 		new |= PCI_ROM_ADDRESS_ENABLE;
-	}
+	} else
+		return;
 
 	/*
 	 * We can't update a 64-bit BAR atomically, so when possible,
@@ -110,6 +120,16 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 }
 
+void pci_update_resource(struct pci_dev *dev, int resno)
+{
+	if (resno <= PCI_ROM_RESOURCE)
+		pci_std_update_resource(dev, resno);
+#ifdef CONFIG_PCI_IOV
+	else if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
+		pci_iov_update_resource(dev, resno);
+#endif
+}
+
 int pci_claim_resource(struct pci_dev *dev, int resource)
 {
 	struct resource *res = &dev->resource[resource];
diff --git a/drivers/pcmcia/db1xxx_ss.c b/drivers/pcmcia/db1xxx_ss.c
index 4c2fa05b4589..944674ee3464 100644
--- a/drivers/pcmcia/db1xxx_ss.c
+++ b/drivers/pcmcia/db1xxx_ss.c
@@ -56,6 +56,7 @@ struct db1x_pcmcia_sock {
 	int	stschg_irq;	/* card-status-change irq */
 	int	card_irq;	/* card irq */
 	int	eject_irq;	/* db1200/pb1200 have these */
+	int	insert_gpio;	/* db1000 carddetect gpio */
 
 #define BOARD_TYPE_DEFAULT	0	/* most boards */
 #define BOARD_TYPE_DB1200	1	/* IRQs aren't gpios */
@@ -83,7 +84,7 @@ static int db1200_card_inserted(struct db1x_pcmcia_sock *sock)
 /* carddetect gpio: low-active */
 static int db1000_card_inserted(struct db1x_pcmcia_sock *sock)
 {
-	return !gpio_get_value(irq_to_gpio(sock->insert_irq));
+	return !gpio_get_value(sock->insert_gpio);
 }
 
 static int db1x_card_inserted(struct db1x_pcmcia_sock *sock)
@@ -457,9 +458,15 @@ static int db1x_pcmcia_socket_probe(struct platform_device *pdev)
 	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "card");
 	sock->card_irq = r ? r->start : 0;
 
-	/* insert: irq which triggers on card insertion/ejection */
+	/* insert: irq which triggers on card insertion/ejection
+	 * BIG FAT NOTE: on DB1000/1100/1500/1550 we pass a GPIO here!
+	 */
 	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "insert");
 	sock->insert_irq = r ? r->start : -1;
+	if (sock->board_type == BOARD_TYPE_DEFAULT) {
+		sock->insert_gpio = r ? r->start : -1;
+		sock->insert_irq = r ? gpio_to_irq(r->start) : -1;
+	}
 
 	/* stschg: irq which trigger on card status change (optional) */
 	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "stschg");
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index be3755c973e9..8af1f900ea65 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -815,6 +815,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 			if (i > 0 && spi != using_spi) {
 				pr_err("PPI/SPI IRQ type mismatch for %s!\n",
 					dn->name);
+				of_node_put(dn);
 				kfree(irqs);
 				return -EINVAL;
 			}
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 03cb3ea2d2c0..b5679fb67591 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -368,6 +368,7 @@ config PHY_QCOM_UFS
 config PHY_TUSB1210
 	tristate "TI TUSB1210 ULPI PHY module"
 	depends on USB_ULPI_BUS
+	depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in
 	select GENERIC_PHY
 	help
 	  Support for TI TUSB1210 USB ULPI PHY.
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 2e6ca69635aa..17dd8fe12b54 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -779,7 +779,7 @@ static int bcm2835_pctl_dt_node_to_map(struct pinctrl_dev *pctldev,
 		}
 		if (num_pulls) {
 			err = of_property_read_u32_index(np, "brcm,pull",
-					(num_funcs > 1) ? i : 0, &pull);
+					(num_pulls > 1) ? i : 0, &pull);
 			if (err)
 				goto out;
 			err = bcm2835_pctl_dt_node_to_map_pull(pc, np, pin,
diff --git a/drivers/pinctrl/berlin/berlin-bg4ct.c b/drivers/pinctrl/berlin/berlin-bg4ct.c
index 09172043d589..c617ec49e9ed 100644
--- a/drivers/pinctrl/berlin/berlin-bg4ct.c
+++ b/drivers/pinctrl/berlin/berlin-bg4ct.c
@@ -217,7 +217,7 @@ static const struct berlin_desc_group berlin4ct_soc_pinctrl_groups[] = {
 	BERLIN_PINCTRL_GROUP("SCRD0_CRD_PRES", 0xc, 0x3, 0x15,
 			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO20 */
 			BERLIN_PINCTRL_FUNCTION(0x1, "scrd0"), /* crd pres */
-			BERLIN_PINCTRL_FUNCTION(0x1, "sd1a")), /* DAT3 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "sd1a")), /* DAT3 */
 	BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x18,
 			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
 			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index a5bb93987378..398ec45aadef 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -207,9 +207,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
 		pin_reg = &info->pin_regs[pin_id];
 
 		if (pin_reg->mux_reg == -1) {
-			dev_err(ipctl->dev, "Pin(%s) does not support mux function\n",
+			dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n",
 				info->pins[pin_id].name);
-			return -EINVAL;
+			continue;
 		}
 
 		if (info->flags & SHARE_MUX_CONF_REG) {
@@ -726,19 +726,18 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 
 	if (of_property_read_bool(dev_np, "fsl,input-sel")) {
 		np = of_parse_phandle(dev_np, "fsl,input-sel", 0);
-		if (np) {
-			ipctl->input_sel_base = of_iomap(np, 0);
-			if (IS_ERR(ipctl->input_sel_base)) {
-				of_node_put(np);
-				dev_err(&pdev->dev,
-					"iomuxc input select base address not found\n");
-				return PTR_ERR(ipctl->input_sel_base);
-			}
-		} else {
+		if (!np) {
 			dev_err(&pdev->dev, "iomuxc fsl,input-sel property not found\n");
 			return -EINVAL;
 		}
+
+		ipctl->input_sel_base = of_iomap(np, 0);
 		of_node_put(np);
+		if (!ipctl->input_sel_base) {
+			dev_err(&pdev->dev,
+				"iomuxc input select base address not found\n");
+			return -ENOMEM;
+		}
 	}
 
 	imx_pinctrl_desc.name = dev_name(&pdev->dev);
diff --git a/drivers/pinctrl/freescale/pinctrl-mxs.c b/drivers/pinctrl/freescale/pinctrl-mxs.c
index 6bbda6b4ab50..5da9c95dccb7 100644
--- a/drivers/pinctrl/freescale/pinctrl-mxs.c
+++ b/drivers/pinctrl/freescale/pinctrl-mxs.c
@@ -195,6 +195,16 @@ static int mxs_pinctrl_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
+static void mxs_pinctrl_rmwl(u32 value, u32 mask, u8 shift, void __iomem *reg)
+{
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp &= ~(mask << shift);
+	tmp |= value << shift;
+	writel(tmp, reg);
+}
+
 static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
 			       unsigned group)
 {
@@ -212,8 +222,7 @@ static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
 		reg += bank * 0x20 + pin / 16 * 0x10;
 		shift = pin % 16 * 2;
 
-		writel(0x3 << shift, reg + CLR);
-		writel(g->muxsel[i] << shift, reg + SET);
+		mxs_pinctrl_rmwl(g->muxsel[i], 0x3, shift, reg);
 	}
 
 	return 0;
@@ -280,8 +289,7 @@ static int mxs_pinconf_group_set(struct pinctrl_dev *pctldev,
 			/* mA */
 			if (config & MA_PRESENT) {
 				shift = pin % 8 * 4;
-				writel(0x3 << shift, reg + CLR);
-				writel(ma << shift, reg + SET);
+				mxs_pinctrl_rmwl(ma, 0x3, shift, reg);
 			}
 
 			/* vol */
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index 5979d38c46b2..7329500943a3 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -19,7 +19,7 @@
 
 #define BXT_PAD_OWN	0x020
 #define BXT_HOSTSW_OWN	0x080
-#define BXT_PADCFGLOCK	0x090
+#define BXT_PADCFGLOCK	0x060
 #define BXT_GPI_IE	0x110
 
 #define BXT_COMMUNITY(s, e)				\
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 84936bae6e5e..930f0f25c1ce 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -160,7 +160,6 @@ struct chv_pin_context {
  * @pctldev: Pointer to the pin controller device
  * @chip: GPIO chip in this pin controller
  * @regs: MMIO registers
- * @lock: Lock to serialize register accesses
  * @intr_lines: Stores mapping between 16 HW interrupt wires and GPIO
  *		offset (in GPIO number space)
  * @community: Community this pinctrl instance represents
@@ -174,7 +173,6 @@ struct chv_pinctrl {
 	struct pinctrl_dev *pctldev;
 	struct gpio_chip chip;
 	void __iomem *regs;
-	raw_spinlock_t lock;
 	unsigned intr_lines[16];
 	const struct chv_community *community;
 	u32 saved_intmask;
@@ -659,6 +657,17 @@ static const struct chv_community *chv_communities[] = {
 	&southeast_community,
 };
 
+/*
+ * Lock to serialize register accesses
+ *
+ * Due to a silicon issue, a shared lock must be used to prevent
+ * concurrent accesses across the 4 GPIO controllers.
+ *
+ * See Intel Atom Z8000 Processor Series Specification Update (Rev. 005),
+ * errata #CHT34, for further information.
+ */
+static DEFINE_RAW_SPINLOCK(chv_lock);
+
 static void __iomem *chv_padreg(struct chv_pinctrl *pctrl, unsigned offset,
 				unsigned reg)
 {
@@ -720,13 +729,13 @@ static void chv_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s,
 	u32 ctrl0, ctrl1;
 	bool locked;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	ctrl0 = readl(chv_padreg(pctrl, offset, CHV_PADCTRL0));
 	ctrl1 = readl(chv_padreg(pctrl, offset, CHV_PADCTRL1));
 	locked = chv_pad_locked(pctrl, offset);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	if (ctrl0 & CHV_PADCTRL0_GPIOEN) {
 		seq_puts(s, "GPIO ");
@@ -789,14 +798,14 @@ static int chv_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned function,
 
 	grp = &pctrl->community->groups[group];
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	/* Check first that the pad is not locked */
 	for (i = 0; i < grp->npins; i++) {
 		if (chv_pad_locked(pctrl, grp->pins[i])) {
 			dev_warn(pctrl->dev, "unable to set mode for locked pin %u\n",
 				 grp->pins[i]);
-			raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+			raw_spin_unlock_irqrestore(&chv_lock, flags);
 			return -EBUSY;
 		}
 	}
@@ -839,7 +848,7 @@ static int chv_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned function,
 			pin, altfunc->mode, altfunc->invert_oe ? "" : "not ");
 	}
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	return 0;
 }
@@ -853,13 +862,13 @@ static int chv_gpio_request_enable(struct pinctrl_dev *pctldev,
 	void __iomem *reg;
 	u32 value;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	if (chv_pad_locked(pctrl, offset)) {
 		value = readl(chv_padreg(pctrl, offset, CHV_PADCTRL0));
 		if (!(value & CHV_PADCTRL0_GPIOEN)) {
 			/* Locked so cannot enable */
-			raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+			raw_spin_unlock_irqrestore(&chv_lock, flags);
 			return -EBUSY;
 		}
 	} else {
@@ -899,7 +908,7 @@ static int chv_gpio_request_enable(struct pinctrl_dev *pctldev,
 		chv_writel(value, reg);
 	}
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	return 0;
 }
@@ -913,13 +922,13 @@ static void chv_gpio_disable_free(struct pinctrl_dev *pctldev,
 	void __iomem *reg;
 	u32 value;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	reg = chv_padreg(pctrl, offset, CHV_PADCTRL0);
 	value = readl(reg) & ~CHV_PADCTRL0_GPIOEN;
 	chv_writel(value, reg);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 }
 
 static int chv_gpio_set_direction(struct pinctrl_dev *pctldev,
@@ -931,7 +940,7 @@ static int chv_gpio_set_direction(struct pinctrl_dev *pctldev,
 	unsigned long flags;
 	u32 ctrl0;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	ctrl0 = readl(reg) & ~CHV_PADCTRL0_GPIOCFG_MASK;
 	if (input)
@@ -940,7 +949,7 @@ static int chv_gpio_set_direction(struct pinctrl_dev *pctldev,
 		ctrl0 |= CHV_PADCTRL0_GPIOCFG_GPO << CHV_PADCTRL0_GPIOCFG_SHIFT;
 	chv_writel(ctrl0, reg);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	return 0;
 }
@@ -965,10 +974,10 @@ static int chv_config_get(struct pinctrl_dev *pctldev, unsigned pin,
 	u16 arg = 0;
 	u32 term;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	ctrl0 = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
 	ctrl1 = readl(chv_padreg(pctrl, pin, CHV_PADCTRL1));
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	term = (ctrl0 & CHV_PADCTRL0_TERM_MASK) >> CHV_PADCTRL0_TERM_SHIFT;
 
@@ -1042,7 +1051,7 @@ static int chv_config_set_pull(struct chv_pinctrl *pctrl, unsigned pin,
 	unsigned long flags;
 	u32 ctrl0, pull;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	ctrl0 = readl(reg);
 
 	switch (param) {
@@ -1065,7 +1074,7 @@ static int chv_config_set_pull(struct chv_pinctrl *pctrl, unsigned pin,
 			pull = CHV_PADCTRL0_TERM_20K << CHV_PADCTRL0_TERM_SHIFT;
 			break;
 		default:
-			raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+			raw_spin_unlock_irqrestore(&chv_lock, flags);
 			return -EINVAL;
 		}
 
@@ -1083,7 +1092,7 @@ static int chv_config_set_pull(struct chv_pinctrl *pctrl, unsigned pin,
 			pull = CHV_PADCTRL0_TERM_20K << CHV_PADCTRL0_TERM_SHIFT;
 			break;
 		default:
-			raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+			raw_spin_unlock_irqrestore(&chv_lock, flags);
 			return -EINVAL;
 		}
 
@@ -1091,12 +1100,12 @@ static int chv_config_set_pull(struct chv_pinctrl *pctrl, unsigned pin,
 		break;
 
 	default:
-		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+		raw_spin_unlock_irqrestore(&chv_lock, flags);
 		return -EINVAL;
 	}
 
 	chv_writel(ctrl0, reg);
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	return 0;
 }
@@ -1162,9 +1171,9 @@ static int chv_gpio_get(struct gpio_chip *chip, unsigned offset)
 	unsigned long flags;
 	u32 ctrl0, cfg;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	ctrl0 = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	cfg = ctrl0 & CHV_PADCTRL0_GPIOCFG_MASK;
 	cfg >>= CHV_PADCTRL0_GPIOCFG_SHIFT;
@@ -1182,7 +1191,7 @@ static void chv_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	void __iomem *reg;
 	u32 ctrl0;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	reg = chv_padreg(pctrl, pin, CHV_PADCTRL0);
 	ctrl0 = readl(reg);
@@ -1194,7 +1203,7 @@ static void chv_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 
 	chv_writel(ctrl0, reg);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 }
 
 static int chv_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
@@ -1204,9 +1213,9 @@ static int chv_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 	u32 ctrl0, direction;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	ctrl0 = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	direction = ctrl0 & CHV_PADCTRL0_GPIOCFG_MASK;
 	direction >>= CHV_PADCTRL0_GPIOCFG_SHIFT;
@@ -1244,14 +1253,14 @@ static void chv_gpio_irq_ack(struct irq_data *d)
 	int pin = chv_gpio_offset_to_pin(pctrl, irqd_to_hwirq(d));
 	u32 intr_line;
 
-	raw_spin_lock(&pctrl->lock);
+	raw_spin_lock(&chv_lock);
 
 	intr_line = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
 	intr_line &= CHV_PADCTRL0_INTSEL_MASK;
 	intr_line >>= CHV_PADCTRL0_INTSEL_SHIFT;
 	chv_writel(BIT(intr_line), pctrl->regs + CHV_INTSTAT);
 
-	raw_spin_unlock(&pctrl->lock);
+	raw_spin_unlock(&chv_lock);
 }
 
 static void chv_gpio_irq_mask_unmask(struct irq_data *d, bool mask)
@@ -1262,7 +1271,7 @@ static void chv_gpio_irq_mask_unmask(struct irq_data *d, bool mask)
 	u32 value, intr_line;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	intr_line = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
 	intr_line &= CHV_PADCTRL0_INTSEL_MASK;
@@ -1275,7 +1284,7 @@ static void chv_gpio_irq_mask_unmask(struct irq_data *d, bool mask)
 		value |= BIT(intr_line);
 	chv_writel(value, pctrl->regs + CHV_INTMASK);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 }
 
 static void chv_gpio_irq_mask(struct irq_data *d)
@@ -1309,7 +1318,7 @@ static unsigned chv_gpio_irq_startup(struct irq_data *d)
 		unsigned long flags;
 		u32 intsel, value;
 
-		raw_spin_lock_irqsave(&pctrl->lock, flags);
+		raw_spin_lock_irqsave(&chv_lock, flags);
 		intsel = readl(chv_padreg(pctrl, pin, CHV_PADCTRL0));
 		intsel &= CHV_PADCTRL0_INTSEL_MASK;
 		intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
@@ -1324,7 +1333,7 @@ static unsigned chv_gpio_irq_startup(struct irq_data *d)
 			irq_set_handler_locked(d, handler);
 			pctrl->intr_lines[intsel] = offset;
 		}
-		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+		raw_spin_unlock_irqrestore(&chv_lock, flags);
 	}
 
 	chv_gpio_irq_unmask(d);
@@ -1340,7 +1349,7 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned type)
 	unsigned long flags;
 	u32 value;
 
-	raw_spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&chv_lock, flags);
 
 	/*
 	 * Pins which can be used as shared interrupt are configured in
@@ -1389,7 +1398,7 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned type)
 	else if (type & IRQ_TYPE_LEVEL_MASK)
 		irq_set_handler_locked(d, handle_level_irq);
 
-	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
 
 	return 0;
 }
@@ -1457,12 +1466,11 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 		offset += range->npins;
 	}
 
-	/* Mask and clear all interrupts */
-	chv_writel(0, pctrl->regs + CHV_INTMASK);
+	/* Clear all interrupts */
 	chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
 
 	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
-				   handle_simple_irq, IRQ_TYPE_NONE);
+				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add IRQ chip\n");
 		goto fail;
@@ -1501,7 +1509,6 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
 	if (i == ARRAY_SIZE(chv_communities))
 		return -ENODEV;
 
-	raw_spin_lock_init(&pctrl->lock);
 	pctrl->dev = &pdev->dev;
 
 #ifdef CONFIG_PM_SLEEP
@@ -1556,12 +1563,15 @@ static int chv_pinctrl_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int chv_pinctrl_suspend(struct device *dev)
+static int chv_pinctrl_suspend_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct chv_pinctrl *pctrl = platform_get_drvdata(pdev);
+	unsigned long flags;
 	int i;
 
+	raw_spin_lock_irqsave(&chv_lock, flags);
+
 	pctrl->saved_intmask = readl(pctrl->regs + CHV_INTMASK);
 
 	for (i = 0; i < pctrl->community->npins; i++) {
@@ -1582,15 +1592,20 @@ static int chv_pinctrl_suspend(struct device *dev)
 		ctx->padctrl1 = readl(reg);
 	}
 
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
+
 	return 0;
 }
 
-static int chv_pinctrl_resume(struct device *dev)
+static int chv_pinctrl_resume_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct chv_pinctrl *pctrl = platform_get_drvdata(pdev);
+	unsigned long flags;
 	int i;
 
+	raw_spin_lock_irqsave(&chv_lock, flags);
+
 	/*
 	 * Mask all interrupts before restoring per-pin configuration
 	 * registers because we don't know in which state BIOS left them
@@ -1635,12 +1650,15 @@ static int chv_pinctrl_resume(struct device *dev)
 	chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
 	chv_writel(pctrl->saved_intmask, pctrl->regs + CHV_INTMASK);
 
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
+
 	return 0;
 }
 #endif
 
 static const struct dev_pm_ops chv_pinctrl_pm_ops = {
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend, chv_pinctrl_resume)
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend_noirq,
+				      chv_pinctrl_resume_noirq)
 };
 
 static const struct acpi_device_id chv_pinctrl_acpi_match[] = {
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 5c717275a7fa..181b35879ebd 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -939,7 +939,8 @@ static int mtk_gpio_set_debounce(struct gpio_chip *chip, unsigned offset,
 	struct mtk_pinctrl *pctl = dev_get_drvdata(chip->dev);
 	int eint_num, virq, eint_offset;
 	unsigned int set_offset, bit, clr_bit, clr_offset, rst, i, unmask, dbnc;
-	static const unsigned int dbnc_arr[] = {0 , 1, 16, 32, 64, 128, 256};
+	static const unsigned int debounce_time[] = {500, 1000, 16000, 32000, 64000,
+						128000, 256000};
 	const struct mtk_desc_pin *pin;
 	struct irq_data *d;
 
@@ -957,9 +958,9 @@ static int mtk_gpio_set_debounce(struct gpio_chip *chip, unsigned offset,
 	if (!mtk_eint_can_en_debounce(pctl, eint_num))
 		return -ENOSYS;
 
-	dbnc = ARRAY_SIZE(dbnc_arr);
-	for (i = 0; i < ARRAY_SIZE(dbnc_arr); i++) {
-		if (debounce <= dbnc_arr[i]) {
+	dbnc = ARRAY_SIZE(debounce_time);
+	for (i = 0; i < ARRAY_SIZE(debounce_time); i++) {
+		if (debounce <= debounce_time[i]) {
 			dbnc = i;
 			break;
 		}
@@ -1190,9 +1191,10 @@ static void mtk_eint_irq_handler(struct irq_desc *desc)
 	const struct mtk_desc_pin *pin;
 
 	chained_irq_enter(chip, desc);
-	for (eint_num = 0; eint_num < pctl->devdata->ap_num; eint_num += 32) {
+	for (eint_num = 0;
+	     eint_num < pctl->devdata->ap_num;
+	     eint_num += 32, reg += 4) {
 		status = readl(reg);
-		reg += 4;
 		while (status) {
 			offset = __ffs(status);
 			index = eint_num + offset;
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 84943e4cff09..13730ca151ad 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -246,7 +246,7 @@ static int meson_pmx_request_gpio(struct pinctrl_dev *pcdev,
 {
 	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
 
-	meson_pmx_disable_other_groups(pc, range->pin_base + offset, -1);
+	meson_pmx_disable_other_groups(pc, offset, -1);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c
index 9677807db364..b505b87661f8 100644
--- a/drivers/pinctrl/meson/pinctrl-meson8b.c
+++ b/drivers/pinctrl/meson/pinctrl-meson8b.c
@@ -732,8 +732,8 @@ static const char * const sdxc_c_groups[] = {
 static const char * const nand_groups[] = {
 	"nand_io", "nand_io_ce0", "nand_io_ce1",
 	"nand_io_rb0", "nand_ale", "nand_cle",
-	"nand_wen_clk", "nand_ren_clk", "nand_dqs0",
-	"nand_dqs1"
+	"nand_wen_clk", "nand_ren_clk", "nand_dqs_0",
+	"nand_dqs_1"
 };
 
 static const char * const nor_groups[] = {
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index eebfae0c9b7c..f844b4ae7f79 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -995,7 +995,7 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 		int val;
 
 		if (pull)
-			pullidx = data_out ? 1 : 2;
+			pullidx = data_out ? 2 : 1;
 
 		seq_printf(s, " gpio-%-3d (%-20.20s) in  %s %s",
 			   gpio,
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 3318f1d6193c..7340ff78839a 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -48,17 +48,6 @@ static int amd_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
 
 	spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + offset * 4);
-	/*
-	 * Suppose BIOS or Bootloader sets specific debounce for the
-	 * GPIO. if not, set debounce to be  2.75ms and remove glitch.
-	*/
-	if ((pin_reg & DB_TMR_OUT_MASK) == 0) {
-		pin_reg |= 0xf;
-		pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
-		pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF;
-		pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
-	}
-
 	pin_reg &= ~BIT(OUTPUT_ENABLE_OFF);
 	writel(pin_reg, gpio_dev->base + offset * 4);
 	spin_unlock_irqrestore(&gpio_dev->lock, flags);
@@ -331,15 +320,6 @@ static void amd_gpio_irq_enable(struct irq_data *d)
 
 	spin_lock_irqsave(&gpio_dev->lock, flags);
 	pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
-	/*
-		Suppose BIOS or Bootloader sets specific debounce for the
-		GPIO. if not, set debounce to be  2.75ms.
-	*/
-	if ((pin_reg & DB_TMR_OUT_MASK) == 0) {
-		pin_reg |= 0xf;
-		pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
-		pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
-	}
 	pin_reg |= BIT(INTERRUPT_ENABLE_OFF);
 	pin_reg |= BIT(INTERRUPT_MASK_OFF);
 	writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 33edd07d9149..271cca63e9bd 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -717,9 +717,11 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev,
 			break;
 		case PIN_CONFIG_BIAS_PULL_UP:
 			conf |= ATMEL_PIO_PUEN_MASK;
+			conf &= (~ATMEL_PIO_PDEN_MASK);
 			break;
 		case PIN_CONFIG_BIAS_PULL_DOWN:
 			conf |= ATMEL_PIO_PDEN_MASK;
+			conf &= (~ATMEL_PIO_PUEN_MASK);
 			break;
 		case PIN_CONFIG_DRIVE_OPEN_DRAIN:
 			if (arg == 0)
@@ -1000,7 +1002,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		atmel_pioctrl->irqs[i] = res->start;
 		irq_set_chained_handler(res->start, atmel_gpio_irq_handler);
 		irq_set_handler_data(res->start, atmel_pioctrl);
-		dev_dbg(dev, "bank %i: hwirq=%u\n", i, res->start);
+		dev_dbg(dev, "bank %i: irq=%pr\n", i, res);
 	}
 
 	atmel_pioctrl->irq_domain = irq_domain_add_linear(dev->of_node,
diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c
index 85c9046c690e..98a459b1c095 100644
--- a/drivers/pinctrl/pinctrl-pistachio.c
+++ b/drivers/pinctrl/pinctrl-pistachio.c
@@ -469,27 +469,27 @@ static const char * const pistachio_mips_pll_lock_groups[] = {
 	"mfio83",
 };
 
-static const char * const pistachio_sys_pll_lock_groups[] = {
+static const char * const pistachio_audio_pll_lock_groups[] = {
 	"mfio84",
 };
 
-static const char * const pistachio_wifi_pll_lock_groups[] = {
+static const char * const pistachio_rpu_v_pll_lock_groups[] = {
 	"mfio85",
 };
 
-static const char * const pistachio_bt_pll_lock_groups[] = {
+static const char * const pistachio_rpu_l_pll_lock_groups[] = {
 	"mfio86",
 };
 
-static const char * const pistachio_rpu_v_pll_lock_groups[] = {
+static const char * const pistachio_sys_pll_lock_groups[] = {
 	"mfio87",
 };
 
-static const char * const pistachio_rpu_l_pll_lock_groups[] = {
+static const char * const pistachio_wifi_pll_lock_groups[] = {
 	"mfio88",
 };
 
-static const char * const pistachio_audio_pll_lock_groups[] = {
+static const char * const pistachio_bt_pll_lock_groups[] = {
 	"mfio89",
 };
 
@@ -559,12 +559,12 @@ enum pistachio_mux_option {
 	PISTACHIO_FUNCTION_DREQ4,
 	PISTACHIO_FUNCTION_DREQ5,
 	PISTACHIO_FUNCTION_MIPS_PLL_LOCK,
+	PISTACHIO_FUNCTION_AUDIO_PLL_LOCK,
+	PISTACHIO_FUNCTION_RPU_V_PLL_LOCK,
+	PISTACHIO_FUNCTION_RPU_L_PLL_LOCK,
 	PISTACHIO_FUNCTION_SYS_PLL_LOCK,
 	PISTACHIO_FUNCTION_WIFI_PLL_LOCK,
 	PISTACHIO_FUNCTION_BT_PLL_LOCK,
-	PISTACHIO_FUNCTION_RPU_V_PLL_LOCK,
-	PISTACHIO_FUNCTION_RPU_L_PLL_LOCK,
-	PISTACHIO_FUNCTION_AUDIO_PLL_LOCK,
 	PISTACHIO_FUNCTION_DEBUG_RAW_CCA_IND,
 	PISTACHIO_FUNCTION_DEBUG_ED_SEC20_CCA_IND,
 	PISTACHIO_FUNCTION_DEBUG_ED_SEC40_CCA_IND,
@@ -620,12 +620,12 @@ static const struct pistachio_function pistachio_functions[] = {
 	FUNCTION(dreq4),
 	FUNCTION(dreq5),
 	FUNCTION(mips_pll_lock),
+	FUNCTION(audio_pll_lock),
+	FUNCTION(rpu_v_pll_lock),
+	FUNCTION(rpu_l_pll_lock),
 	FUNCTION(sys_pll_lock),
 	FUNCTION(wifi_pll_lock),
 	FUNCTION(bt_pll_lock),
-	FUNCTION(rpu_v_pll_lock),
-	FUNCTION(rpu_l_pll_lock),
-	FUNCTION(audio_pll_lock),
 	FUNCTION(debug_raw_cca_ind),
 	FUNCTION(debug_ed_sec20_cca_ind),
 	FUNCTION(debug_ed_sec40_cca_ind),
@@ -809,17 +809,17 @@ static const struct pistachio_pin_group pistachio_groups[] = {
 			   PADS_FUNCTION_SELECT2, 12, 0x3),
 	MFIO_MUX_PIN_GROUP(83, MIPS_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
 			   PADS_FUNCTION_SELECT2, 14, 0x3),
-	MFIO_MUX_PIN_GROUP(84, SYS_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
+	MFIO_MUX_PIN_GROUP(84, AUDIO_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
 			   PADS_FUNCTION_SELECT2, 16, 0x3),
-	MFIO_MUX_PIN_GROUP(85, WIFI_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
+	MFIO_MUX_PIN_GROUP(85, RPU_V_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
 			   PADS_FUNCTION_SELECT2, 18, 0x3),
-	MFIO_MUX_PIN_GROUP(86, BT_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
+	MFIO_MUX_PIN_GROUP(86, RPU_L_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
 			   PADS_FUNCTION_SELECT2, 20, 0x3),
-	MFIO_MUX_PIN_GROUP(87, RPU_V_PLL_LOCK, DREQ2, SOCIF_DEBUG,
+	MFIO_MUX_PIN_GROUP(87, SYS_PLL_LOCK, DREQ2, SOCIF_DEBUG,
 			   PADS_FUNCTION_SELECT2, 22, 0x3),
-	MFIO_MUX_PIN_GROUP(88, RPU_L_PLL_LOCK, DREQ3, SOCIF_DEBUG,
+	MFIO_MUX_PIN_GROUP(88, WIFI_PLL_LOCK, DREQ3, SOCIF_DEBUG,
 			   PADS_FUNCTION_SELECT2, 24, 0x3),
-	MFIO_MUX_PIN_GROUP(89, AUDIO_PLL_LOCK, DREQ4, DREQ5,
+	MFIO_MUX_PIN_GROUP(89, BT_PLL_LOCK, DREQ4, DREQ5,
 			   PADS_FUNCTION_SELECT2, 26, 0x3),
 	PIN_GROUP(TCK, "tck"),
 	PIN_GROUP(TRSTN, "trstn"),
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index ef04b962c3d5..73d8d47ea465 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1273,9 +1273,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 
 		/* Parse pins in each row from LSB */
 		while (mask) {
-			bit_pos = ffs(mask);
+			bit_pos = __ffs(mask);
 			pin_num_from_lsb = bit_pos / pcs->bits_per_pin;
-			mask_pos = ((pcs->fmask) << (bit_pos - 1));
+			mask_pos = ((pcs->fmask) << bit_pos);
 			val_pos = val & mask_pos;
 			submask = mask & mask_pos;
 
@@ -1576,6 +1576,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc,
 		else
 			mask &= ~soc_mask;
 		pcs->write(mask, pcswi->reg);
+
+		/* flush posted write */
+		mask = pcs->read(pcswi->reg);
 		raw_spin_unlock(&pcs->lock);
 	}
 
@@ -1847,7 +1850,7 @@ static int pcs_probe(struct platform_device *pdev)
 	ret = of_property_read_u32(np, "pinctrl-single,function-mask",
 				   &pcs->fmask);
 	if (!ret) {
-		pcs->fshift = ffs(pcs->fmask) - 1;
+		pcs->fshift = __ffs(pcs->fmask);
 		pcs->fmax = pcs->fmask >> pcs->fshift;
 	} else {
 		/* If mask property doesn't exist, function mux is invalid. */
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 146264a41ec8..9736f9be5447 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -597,10 +597,6 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
 
 	spin_lock_irqsave(&pctrl->lock, flags);
 
-	val = readl(pctrl->regs + g->intr_status_reg);
-	val &= ~BIT(g->intr_status_bit);
-	writel(val, pctrl->regs + g->intr_status_reg);
-
 	val = readl(pctrl->regs + g->intr_cfg_reg);
 	val |= BIT(g->intr_enable_bit);
 	writel(val, pctrl->regs + g->intr_cfg_reg);
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 71ccf6a90b22..2551e4adb33f 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -194,8 +194,6 @@ static int exynos_irq_request_resources(struct irq_data *irqd)
 
 	spin_unlock_irqrestore(&bank->slock, flags);
 
-	exynos_irq_unmask(irqd);
-
 	return 0;
 }
 
@@ -216,8 +214,6 @@ static void exynos_irq_release_resources(struct irq_data *irqd)
 	shift = irqd->hwirq * bank_type->fld_width[PINCFG_TYPE_FUNC];
 	mask = (1 << bank_type->fld_width[PINCFG_TYPE_FUNC]) - 1;
 
-	exynos_irq_mask(irqd);
-
 	spin_lock_irqsave(&bank->slock, flags);
 
 	con = readl(d->virt_base + reg_con);
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos5440.c b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
index 82dc109f7ed4..3149a877c51f 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos5440.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
@@ -107,6 +107,7 @@ struct exynos5440_pmx_func {
  * @nr_groups: number of pin groups available.
  * @pmx_functions: list of pin functions parsed from device tree.
  * @nr_functions: number of pin functions available.
+ * @range: gpio range to register with pinctrl
  */
 struct exynos5440_pinctrl_priv_data {
 	void __iomem			*reg_base;
@@ -117,6 +118,7 @@ struct exynos5440_pinctrl_priv_data {
 	unsigned int			nr_groups;
 	const struct exynos5440_pmx_func	*pmx_functions;
 	unsigned int			nr_functions;
+	struct pinctrl_gpio_range	range;
 };
 
 /**
@@ -742,7 +744,6 @@ static int exynos5440_pinctrl_register(struct platform_device *pdev,
 	struct pinctrl_desc *ctrldesc;
 	struct pinctrl_dev *pctl_dev;
 	struct pinctrl_pin_desc *pindesc, *pdesc;
-	struct pinctrl_gpio_range grange;
 	char *pin_names;
 	int pin, ret;
 
@@ -794,12 +795,12 @@ static int exynos5440_pinctrl_register(struct platform_device *pdev,
 		return PTR_ERR(pctl_dev);
 	}
 
-	grange.name = "exynos5440-pctrl-gpio-range";
-	grange.id = 0;
-	grange.base = 0;
-	grange.npins = EXYNOS5440_MAX_PINS;
-	grange.gc = priv->gc;
-	pinctrl_add_gpio_range(pctl_dev, &grange);
+	priv->range.name = "exynos5440-pctrl-gpio-range";
+	priv->range.id = 0;
+	priv->range.base = 0;
+	priv->range.npins = EXYNOS5440_MAX_PINS;
+	priv->range.gc = priv->gc;
+	pinctrl_add_gpio_range(pctl_dev, &priv->range);
 	return 0;
 }
 
diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c
index 181ea98a63b7..699efb1a8c45 100644
--- a/drivers/pinctrl/sh-pfc/core.c
+++ b/drivers/pinctrl/sh-pfc/core.c
@@ -543,9 +543,14 @@ static int sh_pfc_probe(struct platform_device *pdev)
 		ret = info->ops->init(pfc);
 		if (ret < 0)
 			return ret;
+
+		/* .init() may have overridden pfc->info */
+		info = pfc->info;
 	}
 
-	pinctrl_provide_dummies();
+	/* Enable dummy states for those platforms without pinctrl support */
+	if (!of_have_populated_dt())
+		pinctrl_provide_dummies();
 
 	ret = sh_pfc_init_ranges(pfc);
 	if (ret < 0)
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 87a4f44147c1..42ffa8708abc 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -1102,7 +1102,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP6_5_3, FMIN_E, SEL_FM_4),
 	PINMUX_IPSR_DATA(IP6_7_6, AUDIO_CLKOUT),
 	PINMUX_IPSR_MSEL(IP6_7_6, MSIOF1_SS1_B, SEL_SOF1_1),
-	PINMUX_IPSR_MSEL(IP6_5_3, TX2, SEL_SCIF2_0),
+	PINMUX_IPSR_MSEL(IP6_7_6, TX2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP6_7_6, SCIFA2_TXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_DATA(IP6_9_8, IRQ0),
 	PINMUX_IPSR_MSEL(IP6_9_8, SCIFB1_RXD_D, SEL_SCIFB1_3),
diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c
index 863c3e30ce05..50f2014fed55 100644
--- a/drivers/pinctrl/sh-pfc/pinctrl.c
+++ b/drivers/pinctrl/sh-pfc/pinctrl.c
@@ -483,7 +483,8 @@ static bool sh_pfc_pinconf_validate(struct sh_pfc *pfc, unsigned int _pin,
 
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
-		return true;
+		return pin->configs &
+			(SH_PFC_PIN_CFG_PULL_UP | SH_PFC_PIN_CFG_PULL_DOWN);
 
 	case PIN_CONFIG_BIAS_PULL_UP:
 		return pin->configs & SH_PFC_PIN_CFG_PULL_UP;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
index 862a096c5dba..be5c71df148d 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
@@ -811,6 +811,7 @@ static const struct sunxi_desc_pin sun4i_a10_pins[] = {
 		  SUNXI_FUNCTION(0x2, "lcd1"),		/* D16 */
 		  SUNXI_FUNCTION(0x3, "pata"),		/* ATAD12 */
 		  SUNXI_FUNCTION(0x4, "keypad"),	/* IN6 */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* DET */
 		  SUNXI_FUNCTION_IRQ(0x6, 16),		/* EINT16 */
 		  SUNXI_FUNCTION(0x7, "csi1")),		/* D16 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 17),
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a23.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a23.c
index 55083d278bb1..51fbf85301be 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a23.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a23.c
@@ -485,12 +485,12 @@ static const struct sunxi_desc_pin sun8i_a23_pins[] = {
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "uart2"),		/* RTS */
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RTS */
 		  SUNXI_FUNCTION_IRQ_BANK(0x4, 2, 8)),	/* PG_EINT8 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "uart2"),		/* CTS */
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* CTS */
 		  SUNXI_FUNCTION_IRQ_BANK(0x4, 2, 9)),	/* PG_EINT9 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c
index 00265f0435a7..584cdedea7a4 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a33.c
@@ -407,12 +407,12 @@ static const struct sunxi_desc_pin sun8i_a33_pins[] = {
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "uart2"),		/* RTS */
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RTS */
 		  SUNXI_FUNCTION_IRQ_BANK(0x4, 1, 8)),	/* PG_EINT8 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x2, "uart2"),		/* CTS */
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* CTS */
 		  SUNXI_FUNCTION_IRQ_BANK(0x4, 1, 9)),	/* PG_EINT9 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
@@ -485,6 +485,7 @@ static const struct sunxi_pinctrl_desc sun8i_a33_pinctrl_data = {
 	.pins = sun8i_a33_pins,
 	.npins = ARRAY_SIZE(sun8i_a33_pins),
 	.irq_banks = 2,
+	.irq_bank_base = 1,
 };
 
 static int sun8i_a33_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
index 90b973e15982..a7c81e988656 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c
@@ -394,7 +394,7 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = {
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 18),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
-		  SUNXI_FUNCTION(0x3, "owa")),		/* DOUT */
+		  SUNXI_FUNCTION(0x3, "spdif")),	/* DOUT */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 19),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out")),
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index dead97daca35..a4a5b504c532 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -578,7 +578,7 @@ static void sunxi_pinctrl_irq_release_resources(struct irq_data *d)
 static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
-	u32 reg = sunxi_irq_cfg_reg(d->hwirq);
+	u32 reg = sunxi_irq_cfg_reg(d->hwirq, pctl->desc->irq_bank_base);
 	u8 index = sunxi_irq_cfg_offset(d->hwirq);
 	unsigned long flags;
 	u32 regval;
@@ -625,7 +625,8 @@ static int sunxi_pinctrl_irq_set_type(struct irq_data *d, unsigned int type)
 static void sunxi_pinctrl_irq_ack(struct irq_data *d)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
-	u32 status_reg = sunxi_irq_status_reg(d->hwirq);
+	u32 status_reg = sunxi_irq_status_reg(d->hwirq,
+					      pctl->desc->irq_bank_base);
 	u8 status_idx = sunxi_irq_status_offset(d->hwirq);
 
 	/* Clear the IRQ */
@@ -635,7 +636,7 @@ static void sunxi_pinctrl_irq_ack(struct irq_data *d)
 static void sunxi_pinctrl_irq_mask(struct irq_data *d)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
-	u32 reg = sunxi_irq_ctrl_reg(d->hwirq);
+	u32 reg = sunxi_irq_ctrl_reg(d->hwirq, pctl->desc->irq_bank_base);
 	u8 idx = sunxi_irq_ctrl_offset(d->hwirq);
 	unsigned long flags;
 	u32 val;
@@ -652,7 +653,7 @@ static void sunxi_pinctrl_irq_mask(struct irq_data *d)
 static void sunxi_pinctrl_irq_unmask(struct irq_data *d)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
-	u32 reg = sunxi_irq_ctrl_reg(d->hwirq);
+	u32 reg = sunxi_irq_ctrl_reg(d->hwirq, pctl->desc->irq_bank_base);
 	u8 idx = sunxi_irq_ctrl_offset(d->hwirq);
 	unsigned long flags;
 	u32 val;
@@ -744,7 +745,7 @@ static void sunxi_pinctrl_irq_handler(struct irq_desc *desc)
 	if (bank == pctl->desc->irq_banks)
 		return;
 
-	reg = sunxi_irq_status_reg_from_bank(bank);
+	reg = sunxi_irq_status_reg_from_bank(bank, pctl->desc->irq_bank_base);
 	val = readl(pctl->membase + reg);
 
 	if (val) {
@@ -1023,9 +1024,11 @@ int sunxi_pinctrl_init(struct platform_device *pdev,
 
 	for (i = 0; i < pctl->desc->irq_banks; i++) {
 		/* Mask and clear all IRQs before registering a handler */
-		writel(0, pctl->membase + sunxi_irq_ctrl_reg_from_bank(i));
+		writel(0, pctl->membase + sunxi_irq_ctrl_reg_from_bank(i,
+						pctl->desc->irq_bank_base));
 		writel(0xffffffff,
-			pctl->membase + sunxi_irq_status_reg_from_bank(i));
+		       pctl->membase + sunxi_irq_status_reg_from_bank(i,
+						pctl->desc->irq_bank_base));
 
 		irq_set_chained_handler_and_data(pctl->irq[i],
 						 sunxi_pinctrl_irq_handler,
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index e248e81a0f9e..0afce1ab12d0 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -97,6 +97,7 @@ struct sunxi_pinctrl_desc {
 	int				npins;
 	unsigned			pin_base;
 	unsigned			irq_banks;
+	unsigned			irq_bank_base;
 	bool				irq_read_needs_mux;
 };
 
@@ -233,12 +234,12 @@ static inline u32 sunxi_pull_offset(u16 pin)
 	return pin_num * PULL_PINS_BITS;
 }
 
-static inline u32 sunxi_irq_cfg_reg(u16 irq)
+static inline u32 sunxi_irq_cfg_reg(u16 irq, unsigned bank_base)
 {
 	u8 bank = irq / IRQ_PER_BANK;
 	u8 reg = (irq % IRQ_PER_BANK) / IRQ_CFG_IRQ_PER_REG * 0x04;
 
-	return IRQ_CFG_REG + bank * IRQ_MEM_SIZE + reg;
+	return IRQ_CFG_REG + (bank_base + bank) * IRQ_MEM_SIZE + reg;
 }
 
 static inline u32 sunxi_irq_cfg_offset(u16 irq)
@@ -247,16 +248,16 @@ static inline u32 sunxi_irq_cfg_offset(u16 irq)
 	return irq_num * IRQ_CFG_IRQ_BITS;
 }
 
-static inline u32 sunxi_irq_ctrl_reg_from_bank(u8 bank)
+static inline u32 sunxi_irq_ctrl_reg_from_bank(u8 bank, unsigned bank_base)
 {
-	return IRQ_CTRL_REG + bank * IRQ_MEM_SIZE;
+	return IRQ_CTRL_REG + (bank_base + bank) * IRQ_MEM_SIZE;
 }
 
-static inline u32 sunxi_irq_ctrl_reg(u16 irq)
+static inline u32 sunxi_irq_ctrl_reg(u16 irq, unsigned bank_base)
 {
 	u8 bank = irq / IRQ_PER_BANK;
 
-	return sunxi_irq_ctrl_reg_from_bank(bank);
+	return sunxi_irq_ctrl_reg_from_bank(bank, bank_base);
 }
 
 static inline u32 sunxi_irq_ctrl_offset(u16 irq)
@@ -265,16 +266,16 @@ static inline u32 sunxi_irq_ctrl_offset(u16 irq)
 	return irq_num * IRQ_CTRL_IRQ_BITS;
 }
 
-static inline u32 sunxi_irq_status_reg_from_bank(u8 bank)
+static inline u32 sunxi_irq_status_reg_from_bank(u8 bank, unsigned bank_base)
 {
-	return IRQ_STATUS_REG + bank * IRQ_MEM_SIZE;
+	return IRQ_STATUS_REG + (bank_base + bank) * IRQ_MEM_SIZE;
 }
 
-static inline u32 sunxi_irq_status_reg(u16 irq)
+static inline u32 sunxi_irq_status_reg(u16 irq, unsigned bank_base)
 {
 	u8 bank = irq / IRQ_PER_BANK;
 
-	return sunxi_irq_status_reg_from_bank(bank);
+	return sunxi_irq_status_reg_from_bank(bank, bank_base);
 }
 
 static inline u32 sunxi_irq_status_offset(u16 irq)
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
index 589872cc8adb..a19c29c79b0a 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-core.c
@@ -73,6 +73,12 @@ static void uniphier_pctl_pin_dbg_show(struct pinctrl_dev *pctldev,
 	case UNIPHIER_PIN_PULL_DOWN:
 		pull_dir = "DOWN";
 		break;
+	case UNIPHIER_PIN_PULL_UP_FIXED:
+		pull_dir = "UP(FIXED)";
+		break;
+	case UNIPHIER_PIN_PULL_DOWN_FIXED:
+		pull_dir = "DOWN(FIXED)";
+		break;
 	case UNIPHIER_PIN_PULL_NONE:
 		pull_dir = "NONE";
 		break;
diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c
index d45cd254ed1c..2b331d5b9e79 100644
--- a/drivers/platform/chrome/cros_ec_dev.c
+++ b/drivers/platform/chrome/cros_ec_dev.c
@@ -147,13 +147,19 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg)
 		goto exit;
 	}
 
+	if (u_cmd.outsize != s_cmd->outsize ||
+	    u_cmd.insize != s_cmd->insize) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
 	s_cmd->command += ec->cmd_offset;
 	ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd);
 	/* Only copy data to userland if data was received. */
 	if (ret < 0)
 		goto exit;
 
-	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + u_cmd.insize))
+	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + s_cmd->insize))
 		ret = -EFAULT;
 exit:
 	kfree(s_cmd);
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index 990308ca384f..92430f781eb7 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -380,3 +380,20 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
 	return ret;
 }
 EXPORT_SYMBOL(cros_ec_cmd_xfer);
+
+int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
+			    struct cros_ec_command *msg)
+{
+	int ret;
+
+	ret = cros_ec_cmd_xfer(ec_dev, msg);
+	if (ret < 0) {
+		dev_err(ec_dev->dev, "Command xfer error (err:%d)\n", ret);
+	} else if (msg->result != EC_RES_SUCCESS) {
+		dev_dbg(ec_dev->dev, "Command result (err: %d)\n", msg->result);
+		return -EPROTO;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(cros_ec_cmd_xfer_status);
diff --git a/drivers/platform/goldfish/pdev_bus.c b/drivers/platform/goldfish/pdev_bus.c
index 1f52462f4cdd..dd9ea463c2a4 100644
--- a/drivers/platform/goldfish/pdev_bus.c
+++ b/drivers/platform/goldfish/pdev_bus.c
@@ -157,23 +157,26 @@ static int goldfish_new_pdev(void)
 static irqreturn_t goldfish_pdev_bus_interrupt(int irq, void *dev_id)
 {
 	irqreturn_t ret = IRQ_NONE;
+
 	while (1) {
 		u32 op = readl(pdev_bus_base + PDEV_BUS_OP);
-		switch (op) {
-		case PDEV_BUS_OP_DONE:
-			return IRQ_NONE;
 
+		switch (op) {
 		case PDEV_BUS_OP_REMOVE_DEV:
 			goldfish_pdev_remove();
+			ret = IRQ_HANDLED;
 			break;
 
 		case PDEV_BUS_OP_ADD_DEV:
 			goldfish_new_pdev();
+			ret = IRQ_HANDLED;
 			break;
+
+		case PDEV_BUS_OP_DONE:
+		default:
+			return ret;
 		}
-		ret = IRQ_HANDLED;
 	}
-	return ret;
 }
 
 static int goldfish_pdev_bus_probe(struct platform_device *pdev)
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 1062fa42ff26..b2cdc1a1ad4f 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -1816,11 +1816,24 @@ static int __init acer_wmi_enable_lm(void)
 	return status;
 }
 
+#define ACER_WMID_ACCEL_HID	"BST0001"
+
 static acpi_status __init acer_wmi_get_handle_cb(acpi_handle ah, u32 level,
 						void *ctx, void **retval)
 {
+	struct acpi_device *dev;
+
+	if (!strcmp(ctx, "SENR")) {
+		if (acpi_bus_get_device(ah, &dev))
+			return AE_OK;
+		if (!strcmp(ACER_WMID_ACCEL_HID, acpi_device_hid(dev)))
+			return AE_OK;
+	} else
+		return AE_OK;
+
 	*(acpi_handle *)retval = ah;
-	return AE_OK;
+
+	return AE_CTRL_TERMINATE;
 }
 
 static int __init acer_wmi_get_handle(const char *name, const char *prop,
@@ -1847,7 +1860,7 @@ static int __init acer_wmi_accel_setup(void)
 {
 	int err;
 
-	err = acer_wmi_get_handle("SENR", "BST0001", &gsensor_handle);
+	err = acer_wmi_get_handle("SENR", ACER_WMID_ACCEL_HID, &gsensor_handle);
 	if (err)
 		return err;
 
@@ -2185,10 +2198,11 @@ static int __init acer_wmi_init(void)
 		err = acer_wmi_input_setup();
 		if (err)
 			return err;
+		err = acer_wmi_accel_setup();
+		if (err)
+			return err;
 	}
 
-	acer_wmi_accel_setup();
-
 	err = platform_driver_register(&acer_platform_driver);
 	if (err) {
 		pr_err("Unable to register platform driver\n");
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 131fee2b093e..a3661cc44f86 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -128,6 +128,15 @@ static const struct dmi_system_id asus_quirks[] = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X45U",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X45U"),
+		},
+		.driver_data = &quirk_asus_wapf4,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "ASUSTeK COMPUTER INC. X456UA",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/dell-rbtn.c b/drivers/platform/x86/dell-rbtn.c
index cd410e392550..d33e9ad3218f 100644
--- a/drivers/platform/x86/dell-rbtn.c
+++ b/drivers/platform/x86/dell-rbtn.c
@@ -28,6 +28,7 @@ struct rbtn_data {
 	enum rbtn_type type;
 	struct rfkill *rfkill;
 	struct input_dev *input_dev;
+	bool suspended;
 };
 
 
@@ -220,9 +221,55 @@ static const struct acpi_device_id rbtn_ids[] = {
 	{ "", 0 },
 };
 
+#ifdef CONFIG_PM_SLEEP
+static void ACPI_SYSTEM_XFACE rbtn_clear_suspended_flag(void *context)
+{
+	struct rbtn_data *rbtn_data = context;
+
+	rbtn_data->suspended = false;
+}
+
+static int rbtn_suspend(struct device *dev)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct rbtn_data *rbtn_data = acpi_driver_data(device);
+
+	rbtn_data->suspended = true;
+
+	return 0;
+}
+
+static int rbtn_resume(struct device *dev)
+{
+	struct acpi_device *device = to_acpi_device(dev);
+	struct rbtn_data *rbtn_data = acpi_driver_data(device);
+	acpi_status status;
+
+	/*
+	 * Upon resume, some BIOSes send an ACPI notification thet triggers
+	 * an unwanted input event. In order to ignore it, we use a flag
+	 * that we set at suspend and clear once we have received the extra
+	 * ACPI notification. Since ACPI notifications are delivered
+	 * asynchronously to drivers, we clear the flag from the workqueue
+	 * used to deliver the notifications. This should be enough
+	 * to have the flag cleared only after we received the extra
+	 * notification, if any.
+	 */
+	status = acpi_os_execute(OSL_NOTIFY_HANDLER,
+			 rbtn_clear_suspended_flag, rbtn_data);
+	if (ACPI_FAILURE(status))
+		rbtn_clear_suspended_flag(rbtn_data);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(rbtn_pm_ops, rbtn_suspend, rbtn_resume);
+
 static struct acpi_driver rbtn_driver = {
 	.name = "dell-rbtn",
 	.ids = rbtn_ids,
+	.drv.pm = &rbtn_pm_ops,
 	.ops = {
 		.add = rbtn_add,
 		.remove = rbtn_remove,
@@ -384,6 +431,15 @@ static void rbtn_notify(struct acpi_device *device, u32 event)
 {
 	struct rbtn_data *rbtn_data = device->driver_data;
 
+	/*
+	 * Some BIOSes send a notification at resume.
+	 * Ignore it to prevent unwanted input events.
+	 */
+	if (rbtn_data->suspended) {
+		dev_dbg(&device->dev, "ACPI notification ignored\n");
+		return;
+	}
+
 	if (event != 0x80) {
 		dev_info(&device->dev, "Received unknown event (0x%x)\n",
 			 event);
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index fb4dd7b3ee71..af2046c87806 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -723,6 +723,11 @@ static int __init hp_wmi_rfkill_setup(struct platform_device *device)
 	if (err)
 		return err;
 
+	err = hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 1, &wireless,
+				   sizeof(wireless), 0);
+	if (err)
+		return err;
+
 	if (wireless & 0x1) {
 		wifi_rfkill = rfkill_alloc("hp-wifi", &device->dev,
 					   RFKILL_TYPE_WLAN,
@@ -910,7 +915,7 @@ static int __init hp_wmi_bios_setup(struct platform_device *device)
 	gps_rfkill = NULL;
 	rfkill2_count = 0;
 
-	if (hp_wmi_bios_2009_later() || hp_wmi_rfkill_setup(device))
+	if (hp_wmi_rfkill_setup(device))
 		hp_wmi_rfkill2_setup(device);
 
 	err = device_create_file(&device->dev, &dev_attr_display);
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index d78ee151c9e4..09cc64b3b695 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -807,6 +807,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
 			case 11:
 			case 7:
 			case 6:
+			case 1:
 				ideapad_input_report(priv, vpc_bit);
 				break;
 			case 5:
@@ -865,6 +866,20 @@ static const struct dmi_system_id no_hw_rfkill_list[] = {
 		},
 	},
 	{
+		.ident = "Lenovo ideapad Y700-15ISK",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700-15ISK"),
+		},
+	},
+	{
+		.ident = "Lenovo ideapad Y700 Touch-15ISK",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700 Touch-15ISK"),
+		},
+	},
+	{
 		.ident = "Lenovo ideapad Y700-17ISK",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 1fc0de870ff8..361770568ad0 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -77,7 +77,7 @@ static int mfld_pb_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0,
+	error = request_threaded_irq(irq, NULL, mfld_pb_isr, IRQF_ONESHOT,
 				     DRIVER_NAME, input);
 	if (error) {
 		dev_err(&pdev->dev, "Unable to request irq %d for mfld power"
diff --git a/drivers/platform/x86/toshiba-wmi.c b/drivers/platform/x86/toshiba-wmi.c
index feac4576b837..2df07ee8f3c3 100644
--- a/drivers/platform/x86/toshiba-wmi.c
+++ b/drivers/platform/x86/toshiba-wmi.c
@@ -24,14 +24,15 @@
 #include <linux/acpi.h>
 #include <linux/input.h>
 #include <linux/input/sparse-keymap.h>
+#include <linux/dmi.h>
 
 MODULE_AUTHOR("Azael Avalos");
 MODULE_DESCRIPTION("Toshiba WMI Hotkey Driver");
 MODULE_LICENSE("GPL");
 
-#define TOSHIBA_WMI_EVENT_GUID	"59142400-C6A3-40FA-BADB-8A2652834100"
+#define WMI_EVENT_GUID	"59142400-C6A3-40FA-BADB-8A2652834100"
 
-MODULE_ALIAS("wmi:"TOSHIBA_WMI_EVENT_GUID);
+MODULE_ALIAS("wmi:"WMI_EVENT_GUID);
 
 static struct input_dev *toshiba_wmi_input_dev;
 
@@ -63,6 +64,16 @@ static void toshiba_wmi_notify(u32 value, void *context)
 	kfree(response.pointer);
 }
 
+static struct dmi_system_id toshiba_wmi_dmi_table[] __initdata = {
+	{
+		.ident = "Toshiba laptop",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		},
+	},
+	{}
+};
+
 static int __init toshiba_wmi_input_setup(void)
 {
 	acpi_status status;
@@ -81,7 +92,7 @@ static int __init toshiba_wmi_input_setup(void)
 	if (err)
 		goto err_free_dev;
 
-	status = wmi_install_notify_handler(TOSHIBA_WMI_EVENT_GUID,
+	status = wmi_install_notify_handler(WMI_EVENT_GUID,
 					    toshiba_wmi_notify, NULL);
 	if (ACPI_FAILURE(status)) {
 		err = -EIO;
@@ -95,7 +106,7 @@ static int __init toshiba_wmi_input_setup(void)
 	return 0;
 
  err_remove_notifier:
-	wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID);
+	wmi_remove_notify_handler(WMI_EVENT_GUID);
  err_free_keymap:
 	sparse_keymap_free(toshiba_wmi_input_dev);
  err_free_dev:
@@ -105,7 +116,7 @@ static int __init toshiba_wmi_input_setup(void)
 
 static void toshiba_wmi_input_destroy(void)
 {
-	wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID);
+	wmi_remove_notify_handler(WMI_EVENT_GUID);
 	sparse_keymap_free(toshiba_wmi_input_dev);
 	input_unregister_device(toshiba_wmi_input_dev);
 }
@@ -114,7 +125,8 @@ static int __init toshiba_wmi_init(void)
 {
 	int ret;
 
-	if (!wmi_has_guid(TOSHIBA_WMI_EVENT_GUID))
+	if (!wmi_has_guid(WMI_EVENT_GUID) ||
+	    !dmi_check_system(toshiba_wmi_dmi_table))
 		return -ENODEV;
 
 	ret = toshiba_wmi_input_setup();
@@ -130,7 +142,7 @@ static int __init toshiba_wmi_init(void)
 
 static void __exit toshiba_wmi_exit(void)
 {
-	if (wmi_has_guid(TOSHIBA_WMI_EVENT_GUID))
+	if (wmi_has_guid(WMI_EVENT_GUID))
 		toshiba_wmi_input_destroy();
 }
 
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index b0f62141ea4d..f774cb576ffa 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -131,7 +131,7 @@ MODULE_LICENSE("GPL");
 /* Field definitions */
 #define HCI_ACCEL_MASK			0x7fff
 #define HCI_HOTKEY_DISABLE		0x0b
-#define HCI_HOTKEY_ENABLE		0x01
+#define HCI_HOTKEY_ENABLE		0x09
 #define HCI_HOTKEY_SPECIAL_FUNCTIONS	0x10
 #define HCI_LCD_BRIGHTNESS_BITS		3
 #define HCI_LCD_BRIGHTNESS_SHIFT	(16-HCI_LCD_BRIGHTNESS_BITS)
diff --git a/drivers/pnp/quirks.c b/drivers/pnp/quirks.c
index 943c1cb9566c..d28e3ab9479c 100644
--- a/drivers/pnp/quirks.c
+++ b/drivers/pnp/quirks.c
@@ -342,7 +342,9 @@ static void quirk_amd_mmconfig_area(struct pnp_dev *dev)
 /* Device IDs of parts that have 32KB MCH space */
 static const unsigned int mch_quirk_devices[] = {
 	0x0154,	/* Ivy Bridge */
+	0x0a04, /* Haswell-ULT */
 	0x0c00,	/* Haswell */
+	0x1604, /* Broadwell */
 };
 
 static struct pci_dev *get_intel_host(void)
diff --git a/drivers/power/bq24190_charger.c b/drivers/power/bq24190_charger.c
index f5746b9f4e83..f05d2773fe00 100644
--- a/drivers/power/bq24190_charger.c
+++ b/drivers/power/bq24190_charger.c
@@ -144,10 +144,7 @@
  * so the first read after a fault returns the latched value and subsequent
  * reads return the current value.  In order to return the fault status
  * to the user, have the interrupt handler save the reg's value and retrieve
- * it in the appropriate health/status routine.  Each routine has its own
- * flag indicating whether it should use the value stored by the last run
- * of the interrupt handler or do an actual reg read.  That way each routine
- * can report back whatever fault may have occured.
+ * it in the appropriate health/status routine.
  */
 struct bq24190_dev_info {
 	struct i2c_client		*client;
@@ -159,10 +156,6 @@ struct bq24190_dev_info {
 	unsigned int			gpio_int;
 	unsigned int			irq;
 	struct mutex			f_reg_lock;
-	bool				first_time;
-	bool				charger_health_valid;
-	bool				battery_health_valid;
-	bool				battery_status_valid;
 	u8				f_reg;
 	u8				ss_reg;
 	u8				watchdog;
@@ -636,21 +629,11 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
 		union power_supply_propval *val)
 {
 	u8 v;
-	int health, ret;
+	int health;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->charger_health_valid) {
-		v = bdi->f_reg;
-		bdi->charger_health_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &v);
-		if (ret < 0)
-			return ret;
-	}
+	v = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	if (v & BQ24190_REG_F_BOOST_FAULT_MASK) {
 		/*
@@ -937,18 +920,8 @@ static int bq24190_battery_get_status(struct bq24190_dev_info *bdi,
 	int status, ret;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->battery_status_valid) {
-		chrg_fault = bdi->f_reg;
-		bdi->battery_status_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &chrg_fault);
-		if (ret < 0)
-			return ret;
-	}
+	chrg_fault = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	chrg_fault &= BQ24190_REG_F_CHRG_FAULT_MASK;
 	chrg_fault >>= BQ24190_REG_F_CHRG_FAULT_SHIFT;
@@ -996,21 +969,11 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi,
 		union power_supply_propval *val)
 {
 	u8 v;
-	int health, ret;
+	int health;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->battery_health_valid) {
-		v = bdi->f_reg;
-		bdi->battery_health_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &v);
-		if (ret < 0)
-			return ret;
-	}
+	v = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
@@ -1197,9 +1160,12 @@ static const struct power_supply_desc bq24190_battery_desc = {
 static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 {
 	struct bq24190_dev_info *bdi = data;
-	bool alert_userspace = false;
+	const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
+	const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
+				| BQ24190_REG_F_NTC_FAULT_MASK;
+	bool alert_charger = false, alert_battery = false;
 	u8 ss_reg = 0, f_reg = 0;
-	int ret;
+	int i, ret;
 
 	pm_runtime_get_sync(bdi->dev);
 
@@ -1209,6 +1175,32 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 		goto out;
 	}
 
+	i = 0;
+	do {
+		ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
+		if (ret < 0) {
+			dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
+			goto out;
+		}
+	} while (f_reg && ++i < 2);
+
+	if (f_reg != bdi->f_reg) {
+		dev_info(bdi->dev,
+			"Fault: boost %d, charge %d, battery %d, ntc %d\n",
+			!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK));
+
+		mutex_lock(&bdi->f_reg_lock);
+		if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f))
+			alert_battery = true;
+		if ((bdi->f_reg & ~battery_mask_f) != (f_reg & ~battery_mask_f))
+			alert_charger = true;
+		bdi->f_reg = f_reg;
+		mutex_unlock(&bdi->f_reg_lock);
+	}
+
 	if (ss_reg != bdi->ss_reg) {
 		/*
 		 * The device is in host mode so when PG_STAT goes from 1->0
@@ -1225,47 +1217,17 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 					ret);
 		}
 
+		if ((bdi->ss_reg & battery_mask_ss) != (ss_reg & battery_mask_ss))
+			alert_battery = true;
+		if ((bdi->ss_reg & ~battery_mask_ss) != (ss_reg & ~battery_mask_ss))
+			alert_charger = true;
 		bdi->ss_reg = ss_reg;
-		alert_userspace = true;
-	}
-
-	mutex_lock(&bdi->f_reg_lock);
-
-	ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
-	if (ret < 0) {
-		mutex_unlock(&bdi->f_reg_lock);
-		dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
-		goto out;
 	}
 
-	if (f_reg != bdi->f_reg) {
-		bdi->f_reg = f_reg;
-		bdi->charger_health_valid = true;
-		bdi->battery_health_valid = true;
-		bdi->battery_status_valid = true;
-
-		alert_userspace = true;
-	}
-
-	mutex_unlock(&bdi->f_reg_lock);
-
-	/*
-	 * Sometimes bq24190 gives a steady trickle of interrupts even
-	 * though the watchdog timer is turned off and neither the STATUS
-	 * nor FAULT registers have changed.  Weed out these sprurious
-	 * interrupts so userspace isn't alerted for no reason.
-	 * In addition, the chip always generates an interrupt after
-	 * register reset so we should ignore that one (the very first
-	 * interrupt received).
-	 */
-	if (alert_userspace) {
-		if (!bdi->first_time) {
-			power_supply_changed(bdi->charger);
-			power_supply_changed(bdi->battery);
-		} else {
-			bdi->first_time = false;
-		}
-	}
+	if (alert_charger)
+		power_supply_changed(bdi->charger);
+	if (alert_battery)
+		power_supply_changed(bdi->battery);
 
 out:
 	pm_runtime_put_sync(bdi->dev);
@@ -1300,6 +1262,10 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi)
 		goto out;
 
 	ret = bq24190_set_mode_host(bdi);
+	if (ret < 0)
+		goto out;
+
+	ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
 out:
 	pm_runtime_put_sync(bdi->dev);
 	return ret;
@@ -1375,10 +1341,8 @@ static int bq24190_probe(struct i2c_client *client,
 	bdi->model = id->driver_data;
 	strncpy(bdi->model_name, id->name, I2C_NAME_SIZE);
 	mutex_init(&bdi->f_reg_lock);
-	bdi->first_time = true;
-	bdi->charger_health_valid = false;
-	bdi->battery_health_valid = false;
-	bdi->battery_status_valid = false;
+	bdi->f_reg = 0;
+	bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
 
 	i2c_set_clientdata(client, bdi);
 
@@ -1392,22 +1356,13 @@ static int bq24190_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
-	ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
-			bq24190_irq_handler_thread,
-			IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-			"bq24190-charger", bdi);
-	if (ret < 0) {
-		dev_err(dev, "Can't set up irq handler\n");
-		goto out1;
-	}
-
 	pm_runtime_enable(dev);
 	pm_runtime_resume(dev);
 
 	ret = bq24190_hw_init(bdi);
 	if (ret < 0) {
 		dev_err(dev, "Hardware init failed\n");
-		goto out2;
+		goto out1;
 	}
 
 	charger_cfg.drv_data = bdi;
@@ -1418,7 +1373,7 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->charger)) {
 		dev_err(dev, "Can't register charger\n");
 		ret = PTR_ERR(bdi->charger);
-		goto out2;
+		goto out1;
 	}
 
 	battery_cfg.drv_data = bdi;
@@ -1427,24 +1382,34 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->battery)) {
 		dev_err(dev, "Can't register battery\n");
 		ret = PTR_ERR(bdi->battery);
-		goto out3;
+		goto out2;
 	}
 
 	ret = bq24190_sysfs_create_group(bdi);
 	if (ret) {
 		dev_err(dev, "Can't create sysfs entries\n");
+		goto out3;
+	}
+
+	ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
+			bq24190_irq_handler_thread,
+			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+			"bq24190-charger", bdi);
+	if (ret < 0) {
+		dev_err(dev, "Can't set up irq handler\n");
 		goto out4;
 	}
 
 	return 0;
 
 out4:
-	power_supply_unregister(bdi->battery);
+	bq24190_sysfs_remove_group(bdi);
 out3:
-	power_supply_unregister(bdi->charger);
+	power_supply_unregister(bdi->battery);
 out2:
-	pm_runtime_disable(dev);
+	power_supply_unregister(bdi->charger);
 out1:
+	pm_runtime_disable(dev);
 	if (bdi->gpio_int)
 		gpio_free(bdi->gpio_int);
 
@@ -1488,12 +1453,13 @@ static int bq24190_pm_resume(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
 
-	bdi->charger_health_valid = false;
-	bdi->battery_health_valid = false;
-	bdi->battery_status_valid = false;
+	bdi->f_reg = 0;
+	bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
 
 	pm_runtime_get_sync(bdi->dev);
 	bq24190_register_reset(bdi);
+	bq24190_set_mode_host(bdi);
+	bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
 	pm_runtime_put_sync(bdi->dev);
 
 	/* Things may have changed while suspended so alert upper layer */
diff --git a/drivers/power/bq24257_charger.c b/drivers/power/bq24257_charger.c
index 1fea2c7ef97f..6fc31bdc639b 100644
--- a/drivers/power/bq24257_charger.c
+++ b/drivers/power/bq24257_charger.c
@@ -1068,6 +1068,12 @@ static int bq24257_probe(struct i2c_client *client,
 		return ret;
 	}
 
+	ret = bq24257_power_supply_init(bq);
+	if (ret < 0) {
+		dev_err(dev, "Failed to register power supply\n");
+		return ret;
+	}
+
 	ret = devm_request_threaded_irq(dev, client->irq, NULL,
 					bq24257_irq_handler_thread,
 					IRQF_TRIGGER_FALLING |
@@ -1078,12 +1084,6 @@ static int bq24257_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	ret = bq24257_power_supply_init(bq);
-	if (ret < 0) {
-		dev_err(dev, "Failed to register power supply\n");
-		return ret;
-	}
-
 	ret = sysfs_create_group(&bq->charger->dev.kobj, &bq24257_attr_group);
 	if (ret < 0) {
 		dev_err(dev, "Can't create sysfs entries\n");
diff --git a/drivers/power/max17042_battery.c b/drivers/power/max17042_battery.c
index 9c65f134d447..da7a75f82489 100644
--- a/drivers/power/max17042_battery.c
+++ b/drivers/power/max17042_battery.c
@@ -457,13 +457,16 @@ static inline void max17042_write_model_data(struct max17042_chip *chip,
 }
 
 static inline void max17042_read_model_data(struct max17042_chip *chip,
-					u8 addr, u32 *data, int size)
+					u8 addr, u16 *data, int size)
 {
 	struct regmap *map = chip->regmap;
 	int i;
+	u32 tmp;
 
-	for (i = 0; i < size; i++)
-		regmap_read(map, addr + i, &data[i]);
+	for (i = 0; i < size; i++) {
+		regmap_read(map, addr + i, &tmp);
+		data[i] = (u16)tmp;
+	}
 }
 
 static inline int max17042_model_data_compare(struct max17042_chip *chip,
@@ -486,7 +489,7 @@ static int max17042_init_model(struct max17042_chip *chip)
 {
 	int ret;
 	int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl);
-	u32 *temp_data;
+	u16 *temp_data;
 
 	temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL);
 	if (!temp_data)
@@ -501,7 +504,7 @@ static int max17042_init_model(struct max17042_chip *chip)
 	ret = max17042_model_data_compare(
 		chip,
 		chip->pdata->config_data->cell_char_tbl,
-		(u16 *)temp_data,
+		temp_data,
 		table_size);
 
 	max10742_lock_model(chip);
@@ -514,7 +517,7 @@ static int max17042_verify_model_lock(struct max17042_chip *chip)
 {
 	int i;
 	int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl);
-	u32 *temp_data;
+	u16 *temp_data;
 	int ret = 0;
 
 	temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL);
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 456987c88baa..b13cd074c52a 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -565,11 +565,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd,
 
 	WARN_ON(tzd == NULL);
 	psy = tzd->devdata;
-	ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val);
+	if (ret)
+		return ret;
 
 	/* Convert tenths of degree Celsius to milli degree Celsius. */
-	if (!ret)
-		*temp = val.intval * 100;
+	*temp = val.intval * 100;
 
 	return ret;
 }
@@ -612,10 +613,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
@@ -628,10 +631,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd,
 	int ret;
 
 	psy = tcd->devdata;
-	ret = psy->desc->get_property(psy,
-		POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
-	if (!ret)
-		*state = val.intval;
+	ret = power_supply_get_property(psy,
+			POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val);
+	if (ret)
+		return ret;
+
+	*state = val.intval;
 
 	return ret;
 }
diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index e9e24df35f26..2579f025b90b 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -14,9 +14,12 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 
+#include <soc/at91/at91sam9_ddrsdr.h>
+
 #define AT91_SHDW_CR	0x00		/* Shut Down Control Register */
 #define AT91_SHDW_SHDW		BIT(0)			/* Shut Down command */
 #define AT91_SHDW_KEY		(0xa5 << 24)		/* KEY Password */
@@ -50,6 +53,7 @@ static const char *shdwc_wakeup_modes[] = {
 
 static void __iomem *at91_shdwc_base;
 static struct clk *sclk;
+static void __iomem *mpddrc_base;
 
 static void __init at91_wakeup_status(void)
 {
@@ -73,6 +77,29 @@ static void at91_poweroff(void)
 	writel(AT91_SHDW_KEY | AT91_SHDW_SHDW, at91_shdwc_base + AT91_SHDW_CR);
 }
 
+static void at91_lpddr_poweroff(void)
+{
+	asm volatile(
+		/* Align to cache lines */
+		".balign 32\n\t"
+
+		/* Ensure AT91_SHDW_CR is in the TLB by reading it */
+		"	ldr	r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		/* Power down SDRAM0 */
+		"	str	%1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
+		/* Shutdown CPU */
+		"	str	%3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		"	b	.\n\t"
+		:
+		: "r" (mpddrc_base),
+		  "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
+		  "r" (at91_shdwc_base),
+		  "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW)
+		: "r0");
+}
+
 static int at91_poweroff_get_wakeup_mode(struct device_node *np)
 {
 	const char *pm;
@@ -124,6 +151,8 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev)
 static int __init at91_poweroff_probe(struct platform_device *pdev)
 {
 	struct resource *res;
+	struct device_node *np;
+	u32 ddr_type;
 	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -150,12 +179,30 @@ static int __init at91_poweroff_probe(struct platform_device *pdev)
 
 	pm_power_off = at91_poweroff;
 
+	np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc");
+	if (!np)
+		return 0;
+
+	mpddrc_base = of_iomap(np, 0);
+	of_node_put(np);
+
+	if (!mpddrc_base)
+		return 0;
+
+	ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD;
+	if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) ||
+	    (ddr_type == AT91_DDRSDRC_MD_LPDDR3))
+		pm_power_off = at91_lpddr_poweroff;
+	else
+		iounmap(mpddrc_base);
+
 	return 0;
 }
 
 static int __exit at91_poweroff_remove(struct platform_device *pdev)
 {
-	if (pm_power_off == at91_poweroff)
+	if (pm_power_off == at91_poweroff ||
+	    pm_power_off == at91_lpddr_poweroff)
 		pm_power_off = NULL;
 
 	clk_disable_unprepare(sclk);
@@ -163,6 +210,11 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id at91_ramc_of_match[] = {
+	{ .compatible = "atmel,sama5d3-ddramc", },
+	{ /* sentinel */ }
+};
+
 static const struct of_device_id at91_poweroff_of_match[] = {
 	{ .compatible = "atmel,at91sam9260-shdwc", },
 	{ .compatible = "atmel,at91sam9rl-shdwc", },
diff --git a/drivers/power/reset/hisi-reboot.c b/drivers/power/reset/hisi-reboot.c
index 9ab7f562a83b..f69387e12c1e 100644
--- a/drivers/power/reset/hisi-reboot.c
+++ b/drivers/power/reset/hisi-reboot.c
@@ -53,13 +53,16 @@ static int hisi_reboot_probe(struct platform_device *pdev)
 
 	if (of_property_read_u32(np, "reboot-offset", &reboot_offset) < 0) {
 		pr_err("failed to find reboot-offset property\n");
+		iounmap(base);
 		return -EINVAL;
 	}
 
 	err = register_restart_handler(&hisi_restart_nb);
-	if (err)
+	if (err) {
 		dev_err(&pdev->dev, "cannot register restart handler (err=%d)\n",
 			err);
+		iounmap(base);
+	}
 
 	return err;
 }
diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c
index d9f56730c735..040a40b4b173 100644
--- a/drivers/power/tps65217_charger.c
+++ b/drivers/power/tps65217_charger.c
@@ -205,6 +205,7 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	if (!charger)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, charger);
 	charger->tps = tps;
 	charger->dev = &pdev->dev;
 
diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
index 38a8bbe74810..83797d89c30f 100644
--- a/drivers/pps/clients/pps_parport.c
+++ b/drivers/pps/clients/pps_parport.c
@@ -195,7 +195,7 @@ static void parport_detach(struct parport *port)
 	struct pps_client_pp *device;
 
 	/* FIXME: oooh, this is ugly! */
-	if (strcmp(pardev->name, KBUILD_MODNAME))
+	if (!pardev || strcmp(pardev->name, KBUILD_MODNAME))
 		/* not our port */
 		return;
 
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index d24ca5f281b4..ec84ff8ad1b4 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -321,6 +321,8 @@ int pwmchip_remove(struct pwm_chip *chip)
 	unsigned int i;
 	int ret = 0;
 
+	pwmchip_sysfs_unexport_children(chip);
+
 	mutex_lock(&pwm_lock);
 
 	for (i = 0; i < chip->npwm; i++) {
@@ -889,7 +891,7 @@ EXPORT_SYMBOL_GPL(devm_pwm_put);
   */
 bool pwm_can_sleep(struct pwm_device *pwm)
 {
-	return pwm->chip->can_sleep;
+	return true;
 }
 EXPORT_SYMBOL_GPL(pwm_can_sleep);
 
diff --git a/drivers/pwm/pwm-brcmstb.c b/drivers/pwm/pwm-brcmstb.c
index 423ce087cd9c..5d5adee16886 100644
--- a/drivers/pwm/pwm-brcmstb.c
+++ b/drivers/pwm/pwm-brcmstb.c
@@ -274,8 +274,8 @@ static int brcmstb_pwm_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	p->base = devm_ioremap_resource(&pdev->dev, res);
-	if (!p->base) {
-		ret = -ENOMEM;
+	if (IS_ERR(p->base)) {
+		ret = PTR_ERR(p->base);
 		goto out_clk;
 	}
 
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index f9dfc8b6407a..7225ac6b3df5 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -80,7 +80,6 @@ struct fsl_pwm_chip {
 
 	struct mutex lock;
 
-	unsigned int use_count;
 	unsigned int cnt_select;
 	unsigned int clk_ps;
 
@@ -300,9 +299,6 @@ static int fsl_counter_clock_enable(struct fsl_pwm_chip *fpc)
 {
 	int ret;
 
-	if (fpc->use_count++ != 0)
-		return 0;
-
 	/* select counter clock source */
 	regmap_update_bits(fpc->regmap, FTM_SC, FTM_SC_CLK_MASK,
 			   FTM_SC_CLK(fpc->cnt_select));
@@ -334,25 +330,6 @@ static int fsl_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	return ret;
 }
 
-static void fsl_counter_clock_disable(struct fsl_pwm_chip *fpc)
-{
-	/*
-	 * already disabled, do nothing
-	 */
-	if (fpc->use_count == 0)
-		return;
-
-	/* there are still users, so can't disable yet */
-	if (--fpc->use_count > 0)
-		return;
-
-	/* no users left, disable PWM counter clock */
-	regmap_update_bits(fpc->regmap, FTM_SC, FTM_SC_CLK_MASK, 0);
-
-	clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
-	clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
-}
-
 static void fsl_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct fsl_pwm_chip *fpc = to_fsl_chip(chip);
@@ -362,7 +339,8 @@ static void fsl_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	regmap_update_bits(fpc->regmap, FTM_OUTMASK, BIT(pwm->hwpwm),
 			   BIT(pwm->hwpwm));
 
-	fsl_counter_clock_disable(fpc);
+	clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
+	clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
 
 	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
 	if ((val & 0xFF) == 0xFF)
@@ -492,17 +470,24 @@ static int fsl_pwm_remove(struct platform_device *pdev)
 static int fsl_pwm_suspend(struct device *dev)
 {
 	struct fsl_pwm_chip *fpc = dev_get_drvdata(dev);
-	u32 val;
+	int i;
 
 	regcache_cache_only(fpc->regmap, true);
 	regcache_mark_dirty(fpc->regmap);
 
-	/* read from cache */
-	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
-	if ((val & 0xFF) != 0xFF) {
+	for (i = 0; i < fpc->chip.npwm; i++) {
+		struct pwm_device *pwm = &fpc->chip.pwms[i];
+
+		if (!test_bit(PWMF_REQUESTED, &pwm->flags))
+			continue;
+
+		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_SYS]);
+
+		if (!pwm_is_enabled(pwm))
+			continue;
+
 		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
 		clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
-		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_SYS]);
 	}
 
 	return 0;
@@ -511,12 +496,19 @@ static int fsl_pwm_suspend(struct device *dev)
 static int fsl_pwm_resume(struct device *dev)
 {
 	struct fsl_pwm_chip *fpc = dev_get_drvdata(dev);
-	u32 val;
+	int i;
+
+	for (i = 0; i < fpc->chip.npwm; i++) {
+		struct pwm_device *pwm = &fpc->chip.pwms[i];
+
+		if (!test_bit(PWMF_REQUESTED, &pwm->flags))
+			continue;
 
-	/* read from cache */
-	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
-	if ((val & 0xFF) != 0xFF) {
 		clk_prepare_enable(fpc->clk[FSL_PWM_CLK_SYS]);
+
+		if (!pwm_is_enabled(pwm))
+			continue;
+
 		clk_prepare_enable(fpc->clk[fpc->cnt_select]);
 		clk_prepare_enable(fpc->clk[FSL_PWM_CLK_CNTEN]);
 	}
diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 9fde60ce8e7b..6e203a65effb 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -24,9 +24,7 @@ struct lpc32xx_pwm_chip {
 	void __iomem *base;
 };
 
-#define PWM_ENABLE	(1 << 31)
-#define PWM_RELOADV(x)	(((x) & 0xFF) << 8)
-#define PWM_DUTY(x)	((x) & 0xFF)
+#define PWM_ENABLE	BIT(31)
 
 #define to_lpc32xx_pwm_chip(_chip) \
 	container_of(_chip, struct lpc32xx_pwm_chip, chip)
@@ -38,40 +36,27 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	unsigned long long c;
 	int period_cycles, duty_cycles;
 	u32 val;
-
-	c = clk_get_rate(lpc32xx->clk) / 256;
-	c = c * period_ns;
-	do_div(c, NSEC_PER_SEC);
-
-	/* Handle high and low extremes */
-	if (c == 0)
-		c = 1;
-	if (c > 255)
-		c = 0; /* 0 set division by 256 */
-	period_cycles = c;
-
-	/* The duty-cycle value is as follows:
-	 *
-	 *  DUTY-CYCLE     HIGH LEVEL
-	 *      1            99.9%
-	 *      25           90.0%
-	 *      128          50.0%
-	 *      220          10.0%
-	 *      255           0.1%
-	 *      0             0.0%
-	 *
-	 * In other words, the register value is duty-cycle % 256 with
-	 * duty-cycle in the range 1-256.
-	 */
-	c = 256 * duty_ns;
-	do_div(c, period_ns);
-	if (c > 255)
-		c = 255;
-	duty_cycles = 256 - c;
+	c = clk_get_rate(lpc32xx->clk);
+
+	/* The highest acceptable divisor is 256, which is represented by 0 */
+	period_cycles = div64_u64(c * period_ns,
+			       (unsigned long long)NSEC_PER_SEC * 256);
+	if (!period_cycles)
+		period_cycles = 1;
+	if (period_cycles > 255)
+		period_cycles = 0;
+
+	/* Compute 256 x #duty/period value and care for corner cases */
+	duty_cycles = div64_u64((unsigned long long)(period_ns - duty_ns) * 256,
+				period_ns);
+	if (!duty_cycles)
+		duty_cycles = 1;
+	if (duty_cycles > 255)
+		duty_cycles = 255;
 
 	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
 	val &= ~0xFFFF;
-	val |= PWM_RELOADV(period_cycles) | PWM_DUTY(duty_cycles);
+	val |= (period_cycles << 8) | duty_cycles;
 	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
 
 	return 0;
@@ -134,7 +119,7 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev)
 
 	lpc32xx->chip.dev = &pdev->dev;
 	lpc32xx->chip.ops = &lpc32xx_pwm_ops;
-	lpc32xx->chip.npwm = 2;
+	lpc32xx->chip.npwm = 1;
 	lpc32xx->chip.base = -1;
 
 	ret = pwmchip_add(&lpc32xx->chip);
diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c
index 117fccf7934a..01a6a83f625d 100644
--- a/drivers/pwm/pwm-pca9685.c
+++ b/drivers/pwm/pwm-pca9685.c
@@ -65,7 +65,6 @@
 #define PCA9685_MAXCHAN		0x10
 
 #define LED_FULL		(1 << 4)
-#define MODE1_RESTART		(1 << 7)
 #define MODE1_SLEEP		(1 << 4)
 #define MODE2_INVRT		(1 << 4)
 #define MODE2_OUTDRV		(1 << 2)
@@ -117,16 +116,6 @@ static int pca9685_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 			udelay(500);
 
 			pca->period_ns = period_ns;
-
-			/*
-			 * If the duty cycle did not change, restart PWM with
-			 * the same duty cycle to period ratio and return.
-			 */
-			if (duty_ns == pca->duty_ns) {
-				regmap_update_bits(pca->regmap, PCA9685_MODE1,
-						   MODE1_RESTART, 0x1);
-				return 0;
-			}
 		} else {
 			dev_err(chip->dev,
 				"prescaler not set: period out of bounds!\n");
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 9c90886f4123..375008e2be20 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -350,6 +350,26 @@ void pwmchip_sysfs_unexport(struct pwm_chip *chip)
 	}
 }
 
+void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
+{
+	struct device *parent;
+	unsigned int i;
+
+	parent = class_find_device(&pwm_class, NULL, chip,
+				   pwmchip_sysfs_match);
+	if (!parent)
+		return;
+
+	for (i = 0; i < chip->npwm; i++) {
+		struct pwm_device *pwm = &chip->pwms[i];
+
+		if (test_bit(PWMF_EXPORTED, &pwm->flags))
+			pwm_unexport_child(parent, pwm);
+	}
+
+	put_device(parent);
+}
+
 static int __init pwm_sysfs_init(void)
 {
 	return class_register(&pwm_class);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 63cd5e68c864..3a6d0290c54c 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -296,7 +296,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 		if (!sreg->sel && !strcmp(sreg->name, "vddpu"))
 			sreg->sel = 22;
 
-		if (!sreg->sel) {
+		if (!sreg->bypass && !sreg->sel) {
 			dev_err(&pdev->dev, "Failed to read a valid default voltage selector.\n");
 			return -EINVAL;
 		}
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index f2e1a39ce0f3..5cf4a97e0304 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -221,10 +221,10 @@ static const struct regulator_desc axp22x_regulators[] = {
 		 AXP22X_ELDO2_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(1)),
 	AXP_DESC(AXP22X, ELDO3, "eldo3", "eldoin", 700, 3300, 100,
 		 AXP22X_ELDO3_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(2)),
-	AXP_DESC_IO(AXP22X, LDO_IO0, "ldo_io0", "ips", 1800, 3300, 100,
+	AXP_DESC_IO(AXP22X, LDO_IO0, "ldo_io0", "ips", 700, 3300, 100,
 		    AXP22X_LDO_IO0_V_OUT, 0x1f, AXP20X_GPIO0_CTRL, 0x07,
 		    AXP22X_IO_ENABLED, AXP22X_IO_DISABLED),
-	AXP_DESC_IO(AXP22X, LDO_IO1, "ldo_io1", "ips", 1800, 3300, 100,
+	AXP_DESC_IO(AXP22X, LDO_IO1, "ldo_io1", "ips", 700, 3300, 100,
 		    AXP22X_LDO_IO1_V_OUT, 0x1f, AXP20X_GPIO1_CTRL, 0x07,
 		    AXP22X_IO_ENABLED, AXP22X_IO_DISABLED),
 	AXP_DESC_FIXED(AXP22X, RTC_LDO, "rtc_ldo", "ips", 3000),
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 73b7683355cd..f9b8c44677eb 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -132,24 +132,24 @@ static bool have_full_constraints(void)
 	return has_full_constraints || of_have_populated_dt();
 }
 
+static inline struct regulator_dev *rdev_get_supply(struct regulator_dev *rdev)
+{
+	if (rdev && rdev->supply)
+		return rdev->supply->rdev;
+
+	return NULL;
+}
+
 /**
  * regulator_lock_supply - lock a regulator and its supplies
  * @rdev:         regulator source
  */
 static void regulator_lock_supply(struct regulator_dev *rdev)
 {
-	struct regulator *supply;
-	int i = 0;
-
-	while (1) {
-		mutex_lock_nested(&rdev->mutex, i++);
-		supply = rdev->supply;
-
-		if (!rdev->supply)
-			return;
+	int i;
 
-		rdev = supply->rdev;
-	}
+	for (i = 0; rdev; rdev = rdev_get_supply(rdev), i++)
+		mutex_lock_nested(&rdev->mutex, i);
 }
 
 /**
@@ -1519,6 +1519,7 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		ret = regulator_enable(rdev->supply);
 		if (ret < 0) {
 			_regulator_put(rdev->supply);
+			rdev->supply = NULL;
 			return ret;
 		}
 	}
@@ -4273,12 +4274,13 @@ static void regulator_summary_show_subtree(struct seq_file *s,
 	seq_puts(s, "\n");
 
 	list_for_each_entry(consumer, &rdev->consumer_list, list) {
-		if (consumer->dev->class == &regulator_class)
+		if (consumer->dev && consumer->dev->class == &regulator_class)
 			continue;
 
 		seq_printf(s, "%*s%-*s ",
 			   (level + 1) * 3 + 1, "",
-			   30 - (level + 1) * 3, dev_name(consumer->dev));
+			   30 - (level + 1) * 3,
+			   consumer->dev ? dev_name(consumer->dev) : "deviceless");
 
 		switch (rdev->desc->type) {
 		case REGULATOR_VOLTAGE:
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index 6fa0c7d13290..4bda998afdef 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -166,29 +166,30 @@ static const struct regulator_desc pm8x41_hfsmps = {
 static const struct regulator_desc pm8841_ftsmps = {
 	.linear_ranges = (struct regulator_linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0, 184, 5000),
-		REGULATOR_LINEAR_RANGE(700000, 185, 339, 10000),
+		REGULATOR_LINEAR_RANGE(1280000, 185, 261, 10000),
 	},
 	.n_linear_ranges = 2,
-	.n_voltages = 340,
+	.n_voltages = 262,
 	.ops = &rpm_smps_ldo_ops,
 };
 
 static const struct regulator_desc pm8941_boost = {
 	.linear_ranges = (struct regulator_linear_range[]) {
-		REGULATOR_LINEAR_RANGE(4000000, 0, 15, 100000),
+		REGULATOR_LINEAR_RANGE(4000000, 0, 30, 50000),
 	},
 	.n_linear_ranges = 1,
-	.n_voltages = 16,
+	.n_voltages = 31,
 	.ops = &rpm_smps_ldo_ops,
 };
 
 static const struct regulator_desc pm8941_pldo = {
 	.linear_ranges = (struct regulator_linear_range[]) {
-		REGULATOR_LINEAR_RANGE( 750000,  0,  30, 25000),
-		REGULATOR_LINEAR_RANGE(1500000, 31, 99, 50000),
+		REGULATOR_LINEAR_RANGE( 750000,  0,  63, 12500),
+		REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
+		REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
 	},
-	.n_linear_ranges = 2,
-	.n_voltages = 100,
+	.n_linear_ranges = 3,
+	.n_voltages = 164,
 	.ops = &rpm_smps_ldo_ops,
 };
 
diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 88a5dc88badc..fee6457e3111 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1050,6 +1050,8 @@ static struct regulator_ops spmi_vs_ops = {
 	.set_pull_down		= spmi_regulator_common_set_pull_down,
 	.set_soft_start		= spmi_regulator_common_set_soft_start,
 	.set_over_current_protection = spmi_regulator_vs_ocp,
+	.set_mode		= spmi_regulator_common_set_mode,
+	.get_mode		= spmi_regulator_common_get_mode,
 };
 
 static struct regulator_ops spmi_boost_ops = {
@@ -1440,6 +1442,7 @@ static const struct spmi_regulator_data pm8941_regulators[] = {
 	{ "s1", 0x1400, "vdd_s1", },
 	{ "s2", 0x1700, "vdd_s2", },
 	{ "s3", 0x1a00, "vdd_s3", },
+	{ "s4", 0xa000, },
 	{ "l1", 0x4000, "vdd_l1_l3", },
 	{ "l2", 0x4100, "vdd_l2_lvs_1_2_3", },
 	{ "l3", 0x4200, "vdd_l1_l3", },
@@ -1467,8 +1470,8 @@ static const struct spmi_regulator_data pm8941_regulators[] = {
 	{ "lvs1", 0x8000, "vdd_l2_lvs_1_2_3", },
 	{ "lvs2", 0x8100, "vdd_l2_lvs_1_2_3", },
 	{ "lvs3", 0x8200, "vdd_l2_lvs_1_2_3", },
-	{ "mvs1", 0x8300, "vin_5vs", },
-	{ "mvs2", 0x8400, "vin_5vs", },
+	{ "5vs1", 0x8300, "vin_5vs", "ocp-5vs1", },
+	{ "5vs2", 0x8400, "vin_5vs", "ocp-5vs2", },
 	{ }
 };
 
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 72fc3c32db49..b6d831b84e1d 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -305,7 +305,7 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.enable_mask	= S2MPS11_ENABLE_MASK			\
 }
 
-#define regulator_desc_s2mps11_buck6_10(num, min, step) {	\
+#define regulator_desc_s2mps11_buck67810(num, min, step) {	\
 	.name		= "BUCK"#num,				\
 	.id		= S2MPS11_BUCK##num,			\
 	.ops		= &s2mps11_buck_ops,			\
@@ -321,6 +321,22 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.enable_mask	= S2MPS11_ENABLE_MASK			\
 }
 
+#define regulator_desc_s2mps11_buck9 {				\
+	.name		= "BUCK9",				\
+	.id		= S2MPS11_BUCK9,			\
+	.ops		= &s2mps11_buck_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= MIN_3000_MV,				\
+	.uV_step	= STEP_25_MV,				\
+	.n_voltages	= S2MPS11_BUCK9_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
+	.vsel_reg	= S2MPS11_REG_B9CTRL2,			\
+	.vsel_mask	= S2MPS11_BUCK9_VSEL_MASK,		\
+	.enable_reg	= S2MPS11_REG_B9CTRL1,			\
+	.enable_mask	= S2MPS11_ENABLE_MASK			\
+}
+
 static const struct regulator_desc s2mps11_regulators[] = {
 	regulator_desc_s2mps11_ldo(1, STEP_25_MV),
 	regulator_desc_s2mps11_ldo(2, STEP_50_MV),
@@ -365,11 +381,11 @@ static const struct regulator_desc s2mps11_regulators[] = {
 	regulator_desc_s2mps11_buck1_4(3),
 	regulator_desc_s2mps11_buck1_4(4),
 	regulator_desc_s2mps11_buck5,
-	regulator_desc_s2mps11_buck6_10(6, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps11_buck6_10(7, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps11_buck6_10(8, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps11_buck6_10(9, MIN_3000_MV, STEP_25_MV),
-	regulator_desc_s2mps11_buck6_10(10, MIN_750_MV, STEP_12_5_MV),
+	regulator_desc_s2mps11_buck67810(6, MIN_600_MV, STEP_6_25_MV),
+	regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_6_25_MV),
+	regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_6_25_MV),
+	regulator_desc_s2mps11_buck9,
+	regulator_desc_s2mps11_buck67810(10, MIN_750_MV, STEP_12_5_MV),
 };
 
 static struct regulator_ops s2mps14_reg_ops;
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 58f5d3b8e981..27343e1c43ef 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -202,9 +202,10 @@ static int s5m8767_get_register(struct s5m8767_info *s5m8767, int reg_id,
 		}
 	}
 
-	if (i < s5m8767->num_regulators)
-		*enable_ctrl =
-		s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
+	if (i >= s5m8767->num_regulators)
+		return -EINVAL;
+
+	*enable_ctrl = s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
 
 	return 0;
 }
@@ -937,8 +938,12 @@ static int s5m8767_pmic_probe(struct platform_device *pdev)
 			else
 				regulators[id].vsel_mask = 0xff;
 
-			s5m8767_get_register(s5m8767, id, &enable_reg,
+			ret = s5m8767_get_register(s5m8767, id, &enable_reg,
 					     &enable_val);
+			if (ret) {
+				dev_err(s5m8767->dev, "error reading registers\n");
+				return ret;
+			}
 			regulators[id].enable_reg = enable_reg;
 			regulators[id].enable_mask = S5M8767_ENCTRL_MASK;
 			regulators[id].enable_val = enable_val;
diff --git a/drivers/regulator/stw481x-vmmc.c b/drivers/regulator/stw481x-vmmc.c
index 7d2ae3e9e942..342f5da79975 100644
--- a/drivers/regulator/stw481x-vmmc.c
+++ b/drivers/regulator/stw481x-vmmc.c
@@ -47,7 +47,8 @@ static struct regulator_desc vmmc_regulator = {
 	.volt_table = stw481x_vmmc_voltages,
 	.enable_time = 200, /* FIXME: look this up */
 	.enable_reg = STW_CONF1,
-	.enable_mask = STW_CONF1_PDN_VMMC,
+	.enable_mask = STW_CONF1_PDN_VMMC | STW_CONF1_MMC_LS_STATUS,
+	.enable_val = STW_CONF1_PDN_VMMC,
 	.vsel_reg = STW_CONF1,
 	.vsel_mask = STW_CONF1_VMMC_MASK,
 };
diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c
index d2c3d7cc35f5..5ca6d2130593 100644
--- a/drivers/regulator/tps65023-regulator.c
+++ b/drivers/regulator/tps65023-regulator.c
@@ -311,8 +311,7 @@ static int tps_65023_probe(struct i2c_client *client,
 
 	/* Enable setting output voltage by I2C */
 	regmap_update_bits(tps->regmap, TPS65023_REG_CON_CTRL2,
-					TPS65023_REG_CTRL2_CORE_ADJ,
-					TPS65023_REG_CTRL2_CORE_ADJ);
+			   TPS65023_REG_CTRL2_CORE_ADJ, 0);
 
 	return 0;
 }
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index fb991ec76423..696116ebdf50 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -1111,6 +1111,12 @@ static int tps65910_probe(struct platform_device *pdev)
 		pmic->num_regulators = ARRAY_SIZE(tps65910_regs);
 		pmic->ext_sleep_control = tps65910_ext_sleep_control;
 		info = tps65910_regs;
+		/* Work around silicon erratum SWCZ010: output programmed
+		 * voltage level can go higher than expected or crash
+		 * Workaround: use no synchronization of DCDC clocks
+		 */
+		tps65910_reg_clear_bits(pmic->mfd, TPS65910_DCDCCTRL,
+					DCDCCTRL_DCDCCKSYNC_MASK);
 		break;
 	case TPS65911:
 		pmic->get_ctrl_reg = &tps65911_get_ctrl_register;
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 9e03d158f411..4f7ce0097191 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1239,11 +1239,6 @@ int rproc_add(struct rproc *rproc)
 	if (ret < 0)
 		return ret;
 
-	/* expose to rproc_get_by_phandle users */
-	mutex_lock(&rproc_list_mutex);
-	list_add(&rproc->node, &rproc_list);
-	mutex_unlock(&rproc_list_mutex);
-
 	dev_info(dev, "%s is available\n", rproc->name);
 
 	dev_info(dev, "Note: remoteproc is still under development and considered experimental.\n");
@@ -1251,8 +1246,16 @@ int rproc_add(struct rproc *rproc)
 
 	/* create debugfs entries */
 	rproc_create_debug_dir(rproc);
+	ret = rproc_add_virtio_devices(rproc);
+	if (ret < 0)
+		return ret;
 
-	return rproc_add_virtio_devices(rproc);
+	/* expose to rproc_get_by_phandle users */
+	mutex_lock(&rproc_list_mutex);
+	list_add(&rproc->node, &rproc_list);
+	mutex_unlock(&rproc_list_mutex);
+
+	return 0;
 }
 EXPORT_SYMBOL(rproc_add);
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 5836751b8203..9bb934ed2a7a 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -748,9 +748,23 @@ EXPORT_SYMBOL_GPL(rtc_irq_set_freq);
  */
 static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer)
 {
+	struct timerqueue_node *next = timerqueue_getnext(&rtc->timerqueue);
+	struct rtc_time tm;
+	ktime_t now;
+
 	timer->enabled = 1;
+	__rtc_read_time(rtc, &tm);
+	now = rtc_tm_to_ktime(tm);
+
+	/* Skip over expired timers */
+	while (next) {
+		if (next->expires.tv64 >= now.tv64)
+			break;
+		next = timerqueue_iterate_next(next);
+	}
+
 	timerqueue_add(&rtc->timerqueue, &timer->node);
-	if (&timer->node == timerqueue_getnext(&rtc->timerqueue)) {
+	if (!next) {
 		struct rtc_wkalrm alarm;
 		int err;
 		alarm.time = rtc_ktime_to_tm(timer->node.expires);
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index 05a51ef52703..d5c1b057a739 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -187,9 +187,9 @@ ds1685_rtc_end_data_access(struct ds1685_priv *rtc)
  * Only use this where you are certain another lock will not be held.
  */
 static inline void
-ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long flags)
+ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long *flags)
 {
-	spin_lock_irqsave(&rtc->lock, flags);
+	spin_lock_irqsave(&rtc->lock, *flags);
 	ds1685_rtc_switch_to_bank1(rtc);
 }
 
@@ -1304,7 +1304,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 {
 	struct ds1685_priv *rtc = dev_get_drvdata(dev);
 	u8 reg = 0, bit = 0, tmp;
-	unsigned long flags = 0;
+	unsigned long flags;
 	long int val = 0;
 	const struct ds1685_rtc_ctrl_regs *reg_info =
 		ds1685_rtc_sysfs_ctrl_regs_lookup(attr->attr.name);
@@ -1325,7 +1325,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 	bit = reg_info->bit;
 
 	/* Safe to spinlock during a write. */
-	ds1685_rtc_begin_ctrl_access(rtc, flags);
+	ds1685_rtc_begin_ctrl_access(rtc, &flags);
 	tmp = rtc->read(rtc, reg);
 	rtc->write(rtc, reg, (val ? (tmp | bit) : (tmp & ~(bit))));
 	ds1685_rtc_end_ctrl_access(rtc, flags);
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 097325d96db5..b1b4746a0eab 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -144,7 +144,7 @@ static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	 * it does not seem to carry it over a subsequent write/read.
 	 * So we'll limit ourself to 100 years, starting at 2000 for now.
 	 */
-	buf[6] = tm->tm_year - 100;
+	buf[6] = bin2bcd(tm->tm_year - 100);
 
 	/*
 	 * CTL1 only contains TEST-mode bits apart from stop,
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 7184a0eda793..725dccae24e7 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -465,7 +465,7 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 
 	info->virq = regmap_irq_get_virq(max77686->rtc_irq_data,
 					 MAX77686_RTCIRQ_RTCA1);
-	if (!info->virq) {
+	if (info->virq <= 0) {
 		ret = -ENXIO;
 		goto err_rtc;
 	}
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index ec2e9c5fb993..22394fe30579 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -109,6 +109,7 @@
 /* OMAP_RTC_OSC_REG bit fields: */
 #define OMAP_RTC_OSC_32KCLK_EN		BIT(6)
 #define OMAP_RTC_OSC_SEL_32KCLK_SRC	BIT(3)
+#define OMAP_RTC_OSC_OSC32K_GZ_DISABLE	BIT(4)
 
 /* OMAP_RTC_IRQWAKEEN bit fields: */
 #define OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN	BIT(1)
@@ -646,8 +647,9 @@ static int omap_rtc_probe(struct platform_device *pdev)
 	 */
 	if (rtc->has_ext_clk) {
 		reg = rtc_read(rtc, OMAP_RTC_OSC_REG);
-		rtc_write(rtc, OMAP_RTC_OSC_REG,
-			  reg | OMAP_RTC_OSC_SEL_32KCLK_SRC);
+		reg &= ~OMAP_RTC_OSC_OSC32K_GZ_DISABLE;
+		reg |= OMAP_RTC_OSC_32KCLK_EN | OMAP_RTC_OSC_SEL_32KCLK_SRC;
+		rtc_writel(rtc, OMAP_RTC_OSC_REG, reg);
 	}
 
 	rtc->type->lock(rtc);
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index bd911bafb809..17341feadad1 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -65,7 +65,6 @@
 
 static const struct i2c_device_id rx8025_id[] = {
 	{ "rx8025", 0 },
-	{ "rv8803", 1 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, rx8025_id);
diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c
index f40afdd0e5f5..00662dd28d66 100644
--- a/drivers/rtc/rtc-s35390a.c
+++ b/drivers/rtc/rtc-s35390a.c
@@ -15,6 +15,7 @@
 #include <linux/bitrev.h>
 #include <linux/bcd.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #define S35390A_CMD_STATUS1	0
 #define S35390A_CMD_STATUS2	1
@@ -34,10 +35,14 @@
 #define S35390A_ALRM_BYTE_HOURS	1
 #define S35390A_ALRM_BYTE_MINS	2
 
+/* flags for STATUS1 */
 #define S35390A_FLAG_POC	0x01
 #define S35390A_FLAG_BLD	0x02
+#define S35390A_FLAG_INT2	0x04
 #define S35390A_FLAG_24H	0x40
 #define S35390A_FLAG_RESET	0x80
+
+/* flag for STATUS2 */
 #define S35390A_FLAG_TEST	0x01
 
 #define S35390A_INT2_MODE_MASK		0xF0
@@ -94,19 +99,63 @@ static int s35390a_get_reg(struct s35390a *s35390a, int reg, char *buf, int len)
 	return 0;
 }
 
-static int s35390a_reset(struct s35390a *s35390a)
+/*
+ * Returns <0 on error, 0 if rtc is setup fine and 1 if the chip was reset.
+ * To keep the information if an irq is pending, pass the value read from
+ * STATUS1 to the caller.
+ */
+static int s35390a_reset(struct s35390a *s35390a, char *status1)
 {
-	char buf[1];
-
-	if (s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf)) < 0)
-		return -EIO;
-
-	if (!(buf[0] & (S35390A_FLAG_POC | S35390A_FLAG_BLD)))
+	char buf;
+	int ret;
+	unsigned initcount = 0;
+
+	ret = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, status1, 1);
+	if (ret < 0)
+		return ret;
+
+	if (*status1 & S35390A_FLAG_POC)
+		/*
+		 * Do not communicate for 0.5 seconds since the power-on
+		 * detection circuit is in operation.
+		 */
+		msleep(500);
+	else if (!(*status1 & S35390A_FLAG_BLD))
+		/*
+		 * If both POC and BLD are unset everything is fine.
+		 */
 		return 0;
 
-	buf[0] |= (S35390A_FLAG_RESET | S35390A_FLAG_24H);
-	buf[0] &= 0xf0;
-	return s35390a_set_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf));
+	/*
+	 * At least one of POC and BLD are set, so reinitialise chip. Keeping
+	 * this information in the hardware to know later that the time isn't
+	 * valid is unfortunately not possible because POC and BLD are cleared
+	 * on read. So the reset is best done now.
+	 *
+	 * The 24H bit is kept over reset, so set it already here.
+	 */
+initialize:
+	*status1 = S35390A_FLAG_24H;
+	buf = S35390A_FLAG_RESET | S35390A_FLAG_24H;
+	ret = s35390a_set_reg(s35390a, S35390A_CMD_STATUS1, &buf, 1);
+
+	if (ret < 0)
+		return ret;
+
+	ret = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, &buf, 1);
+	if (ret < 0)
+		return ret;
+
+	if (buf & (S35390A_FLAG_POC | S35390A_FLAG_BLD)) {
+		/* Try up to five times to reset the chip */
+		if (initcount < 5) {
+			++initcount;
+			goto initialize;
+		} else
+			return -EIO;
+	}
+
+	return 1;
 }
 
 static int s35390a_disable_test_mode(struct s35390a *s35390a)
@@ -242,6 +291,8 @@ static int s35390a_set_alarm(struct i2c_client *client, struct rtc_wkalrm *alm)
 
 	if (alm->time.tm_wday != -1)
 		buf[S35390A_ALRM_BYTE_WDAY] = bin2bcd(alm->time.tm_wday) | 0x80;
+	else
+		buf[S35390A_ALRM_BYTE_WDAY] = 0;
 
 	buf[S35390A_ALRM_BYTE_HOURS] = s35390a_hr2reg(s35390a,
 			alm->time.tm_hour) | 0x80;
@@ -265,27 +316,61 @@ static int s35390a_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alm)
 	char buf[3], sts;
 	int i, err;
 
+	/*
+	 * initialize all members to -1 to signal the core that they are not
+	 * defined by the hardware.
+	 */
+	alm->time.tm_sec = -1;
+	alm->time.tm_min = -1;
+	alm->time.tm_hour = -1;
+	alm->time.tm_mday = -1;
+	alm->time.tm_mon = -1;
+	alm->time.tm_year = -1;
+	alm->time.tm_wday = -1;
+	alm->time.tm_yday = -1;
+	alm->time.tm_isdst = -1;
+
 	err = s35390a_get_reg(s35390a, S35390A_CMD_STATUS2, &sts, sizeof(sts));
 	if (err < 0)
 		return err;
 
-	if (bitrev8(sts) != S35390A_INT2_MODE_ALARM)
-		return -EINVAL;
+	if ((bitrev8(sts) & S35390A_INT2_MODE_MASK) != S35390A_INT2_MODE_ALARM) {
+		/*
+		 * When the alarm isn't enabled, the register to configure
+		 * the alarm time isn't accessible.
+		 */
+		alm->enabled = 0;
+		return 0;
+	} else {
+		alm->enabled = 1;
+	}
 
 	err = s35390a_get_reg(s35390a, S35390A_CMD_INT2_REG1, buf, sizeof(buf));
 	if (err < 0)
 		return err;
 
 	/* This chip returns the bits of each byte in reverse order */
-	for (i = 0; i < 3; ++i) {
+	for (i = 0; i < 3; ++i)
 		buf[i] = bitrev8(buf[i]);
-		buf[i] &= ~0x80;
-	}
 
-	alm->time.tm_wday = bcd2bin(buf[S35390A_ALRM_BYTE_WDAY]);
-	alm->time.tm_hour = s35390a_reg2hr(s35390a,
-						buf[S35390A_ALRM_BYTE_HOURS]);
-	alm->time.tm_min = bcd2bin(buf[S35390A_ALRM_BYTE_MINS]);
+	/*
+	 * B0 of the three matching registers is an enable flag. Iff it is set
+	 * the configured value is used for matching.
+	 */
+	if (buf[S35390A_ALRM_BYTE_WDAY] & 0x80)
+		alm->time.tm_wday =
+			bcd2bin(buf[S35390A_ALRM_BYTE_WDAY] & ~0x80);
+
+	if (buf[S35390A_ALRM_BYTE_HOURS] & 0x80)
+		alm->time.tm_hour =
+			s35390a_reg2hr(s35390a,
+				       buf[S35390A_ALRM_BYTE_HOURS] & ~0x80);
+
+	if (buf[S35390A_ALRM_BYTE_MINS] & 0x80)
+		alm->time.tm_min = bcd2bin(buf[S35390A_ALRM_BYTE_MINS] & ~0x80);
+
+	/* alarm triggers always at s=0 */
+	alm->time.tm_sec = 0;
 
 	dev_dbg(&client->dev, "%s: alm is mins=%d, hours=%d, wday=%d\n",
 			__func__, alm->time.tm_min, alm->time.tm_hour,
@@ -327,11 +412,11 @@ static struct i2c_driver s35390a_driver;
 static int s35390a_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
-	int err;
+	int err, err_reset;
 	unsigned int i;
 	struct s35390a *s35390a;
 	struct rtc_time tm;
-	char buf[1];
+	char buf, status1;
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		err = -ENODEV;
@@ -360,29 +445,35 @@ static int s35390a_probe(struct i2c_client *client,
 		}
 	}
 
-	err = s35390a_reset(s35390a);
-	if (err < 0) {
+	err_reset = s35390a_reset(s35390a, &status1);
+	if (err_reset < 0) {
+		err = err_reset;
 		dev_err(&client->dev, "error resetting chip\n");
 		goto exit_dummy;
 	}
 
-	err = s35390a_disable_test_mode(s35390a);
-	if (err < 0) {
-		dev_err(&client->dev, "error disabling test mode\n");
-		goto exit_dummy;
-	}
-
-	err = s35390a_get_reg(s35390a, S35390A_CMD_STATUS1, buf, sizeof(buf));
-	if (err < 0) {
-		dev_err(&client->dev, "error checking 12/24 hour mode\n");
-		goto exit_dummy;
-	}
-	if (buf[0] & S35390A_FLAG_24H)
+	if (status1 & S35390A_FLAG_24H)
 		s35390a->twentyfourhour = 1;
 	else
 		s35390a->twentyfourhour = 0;
 
-	if (s35390a_get_datetime(client, &tm) < 0)
+	if (status1 & S35390A_FLAG_INT2) {
+		/* disable alarm (and maybe test mode) */
+		buf = 0;
+		err = s35390a_set_reg(s35390a, S35390A_CMD_STATUS2, &buf, 1);
+		if (err < 0) {
+			dev_err(&client->dev, "error disabling alarm");
+			goto exit_dummy;
+		}
+	} else {
+		err = s35390a_disable_test_mode(s35390a);
+		if (err < 0) {
+			dev_err(&client->dev, "error disabling test mode\n");
+			goto exit_dummy;
+		}
+	}
+
+	if (err_reset > 0 || s35390a_get_datetime(client, &tm) < 0)
 		dev_warn(&client->dev, "clock needs to be set\n");
 
 	device_set_wakeup_capable(&client->dev, 1);
@@ -395,6 +486,10 @@ static int s35390a_probe(struct i2c_client *client,
 		err = PTR_ERR(s35390a->rtc);
 		goto exit_dummy;
 	}
+
+	if (status1 & S35390A_FLAG_INT2)
+		rtc_update_irq(s35390a->rtc, 1, RTC_AF);
+
 	return 0;
 
 exit_dummy:
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index ffb860d18701..f92528822f06 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -149,12 +149,14 @@ static int s3c_rtc_setfreq(struct s3c_rtc *info, int freq)
 	if (!is_power_of_2(freq))
 		return -EINVAL;
 
+	s3c_rtc_enable_clk(info);
 	spin_lock_irq(&info->pie_lock);
 
 	if (info->data->set_freq)
 		info->data->set_freq(info, freq);
 
 	spin_unlock_irq(&info->pie_lock);
+	s3c_rtc_disable_clk(info);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index c169a2cd4727..e29cc9fca0bf 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -37,9 +37,11 @@
 
 /* Control register */
 #define SUN6I_LOSC_CTRL				0x0000
+#define SUN6I_LOSC_CTRL_KEY			(0x16aa << 16)
 #define SUN6I_LOSC_CTRL_ALM_DHMS_ACC		BIT(9)
 #define SUN6I_LOSC_CTRL_RTC_HMS_ACC		BIT(8)
 #define SUN6I_LOSC_CTRL_RTC_YMD_ACC		BIT(7)
+#define SUN6I_LOSC_CTRL_EXT_OSC			BIT(0)
 #define SUN6I_LOSC_CTRL_ACC_MASK		GENMASK(9, 7)
 
 /* RTC */
@@ -114,13 +116,17 @@ struct sun6i_rtc_dev {
 	void __iomem *base;
 	int irq;
 	unsigned long alarm;
+
+	spinlock_t lock;
 };
 
 static irqreturn_t sun6i_rtc_alarmirq(int irq, void *id)
 {
 	struct sun6i_rtc_dev *chip = (struct sun6i_rtc_dev *) id;
+	irqreturn_t ret = IRQ_NONE;
 	u32 val;
 
+	spin_lock(&chip->lock);
 	val = readl(chip->base + SUN6I_ALRM_IRQ_STA);
 
 	if (val & SUN6I_ALRM_IRQ_STA_CNT_IRQ_PEND) {
@@ -129,10 +135,11 @@ static irqreturn_t sun6i_rtc_alarmirq(int irq, void *id)
 
 		rtc_update_irq(chip->rtc, 1, RTC_AF | RTC_IRQF);
 
-		return IRQ_HANDLED;
+		ret = IRQ_HANDLED;
 	}
+	spin_unlock(&chip->lock);
 
-	return IRQ_NONE;
+	return ret;
 }
 
 static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip)
@@ -140,6 +147,7 @@ static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip)
 	u32 alrm_val = 0;
 	u32 alrm_irq_val = 0;
 	u32 alrm_wake_val = 0;
+	unsigned long flags;
 
 	if (to) {
 		alrm_val = SUN6I_ALRM_EN_CNT_EN;
@@ -150,9 +158,11 @@ static void sun6i_rtc_setaie(int to, struct sun6i_rtc_dev *chip)
 		       chip->base + SUN6I_ALRM_IRQ_STA);
 	}
 
+	spin_lock_irqsave(&chip->lock, flags);
 	writel(alrm_val, chip->base + SUN6I_ALRM_EN);
 	writel(alrm_irq_val, chip->base + SUN6I_ALRM_IRQ_EN);
 	writel(alrm_wake_val, chip->base + SUN6I_ALARM_CONFIG);
+	spin_unlock_irqrestore(&chip->lock, flags);
 }
 
 static int sun6i_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
@@ -191,11 +201,15 @@ static int sun6i_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 static int sun6i_rtc_getalarm(struct device *dev, struct rtc_wkalrm *wkalrm)
 {
 	struct sun6i_rtc_dev *chip = dev_get_drvdata(dev);
+	unsigned long flags;
 	u32 alrm_st;
 	u32 alrm_en;
 
+	spin_lock_irqsave(&chip->lock, flags);
 	alrm_en = readl(chip->base + SUN6I_ALRM_IRQ_EN);
 	alrm_st = readl(chip->base + SUN6I_ALRM_IRQ_STA);
+	spin_unlock_irqrestore(&chip->lock, flags);
+
 	wkalrm->enabled = !!(alrm_en & SUN6I_ALRM_EN_CNT_EN);
 	wkalrm->pending = !!(alrm_st & SUN6I_ALRM_EN_CNT_EN);
 	rtc_time_to_tm(chip->alarm, &wkalrm->time);
@@ -356,6 +370,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
+	spin_lock_init(&chip->lock);
 
 	platform_set_drvdata(pdev, chip);
 	chip->dev = &pdev->dev;
@@ -404,6 +419,10 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 	/* disable alarm wakeup */
 	writel(0, chip->base + SUN6I_ALARM_CONFIG);
 
+	/* switch to the external, more precise, oscillator */
+	writel(SUN6I_LOSC_CTRL_KEY | SUN6I_LOSC_CTRL_EXT_OSC,
+	       chip->base + SUN6I_LOSC_CTRL);
+
 	chip->rtc = rtc_device_register("rtc-sun6i", &pdev->dev,
 					&sun6i_rtc_ops, THIS_MODULE);
 	if (IS_ERR(chip->rtc)) {
diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c
index 60232bd366ef..71216aa68905 100644
--- a/drivers/rtc/rtc-tegra.c
+++ b/drivers/rtc/rtc-tegra.c
@@ -18,6 +18,7 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 #include <linux/kernel.h>
+#include <linux/clk.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -59,6 +60,7 @@ struct tegra_rtc_info {
 	struct platform_device	*pdev;
 	struct rtc_device	*rtc_dev;
 	void __iomem		*rtc_base; /* NULL if not initialized. */
+	struct clk		*clk;
 	int			tegra_rtc_irq; /* alarm and periodic irq */
 	spinlock_t		tegra_rtc_lock;
 };
@@ -332,6 +334,14 @@ static int __init tegra_rtc_probe(struct platform_device *pdev)
 	if (info->tegra_rtc_irq <= 0)
 		return -EBUSY;
 
+	info->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(info->clk))
+		return PTR_ERR(info->clk);
+
+	ret = clk_prepare_enable(info->clk);
+	if (ret < 0)
+		return ret;
+
 	/* set context info. */
 	info->pdev = pdev;
 	spin_lock_init(&info->tegra_rtc_lock);
@@ -352,7 +362,7 @@ static int __init tegra_rtc_probe(struct platform_device *pdev)
 		ret = PTR_ERR(info->rtc_dev);
 		dev_err(&pdev->dev, "Unable to register device (err=%d).\n",
 			ret);
-		return ret;
+		goto disable_clk;
 	}
 
 	ret = devm_request_irq(&pdev->dev, info->tegra_rtc_irq,
@@ -362,12 +372,25 @@ static int __init tegra_rtc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Unable to request interrupt for device (err=%d).\n",
 			ret);
-		return ret;
+		goto disable_clk;
 	}
 
 	dev_notice(&pdev->dev, "Tegra internal Real Time Clock\n");
 
 	return 0;
+
+disable_clk:
+	clk_disable_unprepare(info->clk);
+	return ret;
+}
+
+static int tegra_rtc_remove(struct platform_device *pdev)
+{
+	struct tegra_rtc_info *info = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(info->clk);
+
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -419,6 +442,7 @@ static void tegra_rtc_shutdown(struct platform_device *pdev)
 
 MODULE_ALIAS("platform:tegra_rtc");
 static struct platform_driver tegra_rtc_driver = {
+	.remove		= tegra_rtc_remove,
 	.shutdown	= tegra_rtc_shutdown,
 	.driver		= {
 		.name	= "tegra_rtc",
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index f64c282275b3..e1b86bb01062 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -272,12 +272,13 @@ static irqreturn_t rtclong1_interrupt(int irq, void *dev_id)
 }
 
 static const struct rtc_class_ops vr41xx_rtc_ops = {
-	.release	= vr41xx_rtc_release,
-	.ioctl		= vr41xx_rtc_ioctl,
-	.read_time	= vr41xx_rtc_read_time,
-	.set_time	= vr41xx_rtc_set_time,
-	.read_alarm	= vr41xx_rtc_read_alarm,
-	.set_alarm	= vr41xx_rtc_set_alarm,
+	.release		= vr41xx_rtc_release,
+	.ioctl			= vr41xx_rtc_ioctl,
+	.read_time		= vr41xx_rtc_read_time,
+	.set_time		= vr41xx_rtc_set_time,
+	.read_alarm		= vr41xx_rtc_read_alarm,
+	.set_alarm		= vr41xx_rtc_set_alarm,
+	.alarm_irq_enable	= vr41xx_rtc_alarm_irq_enable,
 };
 
 static int rtc_probe(struct platform_device *pdev)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 4abfbdb285ec..84c13dffa3a8 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1584,9 +1584,18 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
 	unsigned long long now;
 	int expires;
 
+	cqr = (struct dasd_ccw_req *) intparm;
 	if (IS_ERR(irb)) {
 		switch (PTR_ERR(irb)) {
 		case -EIO:
+			if (cqr && cqr->status == DASD_CQR_CLEAR_PENDING) {
+				device = (struct dasd_device *) cqr->startdev;
+				cqr->status = DASD_CQR_CLEARED;
+				dasd_device_clear_timer(device);
+				wake_up(&dasd_flush_wq);
+				dasd_schedule_device_bh(device);
+				return;
+			}
 			break;
 		case -ETIMEDOUT:
 			DBF_EVENT_DEVID(DBF_WARNING, cdev, "%s: "
@@ -1602,7 +1611,6 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
 	}
 
 	now = get_tod_clock();
-	cqr = (struct dasd_ccw_req *) intparm;
 	/* check for conditions that should be handled immediately */
 	if (!cqr ||
 	    !(scsw_dstat(&irb->scsw) == (DEV_STAT_CHN_END | DEV_STAT_DEV_END) &&
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 94a8f4ab57bc..ae1dc37e4068 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -892,7 +892,7 @@ dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
-	dev_sz = dev_info->end - dev_info->start;
+	dev_sz = dev_info->end - dev_info->start + 1;
 	offset = secnum * 512;
 	addr = (void *) (dev_info->start + offset);
 	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 7c511add5aa7..bae98521c808 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -124,7 +124,12 @@ con3270_create_status(struct con3270 *cp)
 static void
 con3270_update_string(struct con3270 *cp, struct string *s, int nr)
 {
-	if (s->len >= cp->view.cols - 5)
+	if (s->len < 4) {
+		/* This indicates a bug, but printing a warning would
+		 * cause a deadlock. */
+		return;
+	}
+	if (s->string[s->len - 4] != TO_RA)
 		return;
 	raw3270_buffer_address(cp->view.dev, s->string + s->len - 3,
 			       cp->view.cols * (nr + 1));
@@ -461,11 +466,11 @@ con3270_cline_end(struct con3270 *cp)
 		cp->cline->len + 4 : cp->view.cols;
 	s = con3270_alloc_string(cp, size);
 	memcpy(s->string, cp->cline->string, cp->cline->len);
-	if (s->len < cp->view.cols - 5) {
+	if (cp->cline->len < cp->view.cols - 5) {
 		s->string[s->len - 4] = TO_RA;
 		s->string[s->len - 1] = 0;
 	} else {
-		while (--size > cp->cline->len)
+		while (--size >= cp->cline->len)
 			s->string[size] = cp->view.ascebc[' '];
 	}
 	/* Replace cline with allocated line s and reset cline. */
diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c
index 648cb86afd42..ea607a4a1bdd 100644
--- a/drivers/s390/char/sclp_ctl.c
+++ b/drivers/s390/char/sclp_ctl.c
@@ -56,6 +56,7 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area)
 {
 	struct sclp_ctl_sccb ctl_sccb;
 	struct sccb_header *sccb;
+	unsigned long copied;
 	int rc;
 
 	if (copy_from_user(&ctl_sccb, user_area, sizeof(ctl_sccb)))
@@ -65,14 +66,15 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area)
 	sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!sccb)
 		return -ENOMEM;
-	if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sizeof(*sccb))) {
+	copied = PAGE_SIZE -
+		copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), PAGE_SIZE);
+	if (offsetof(struct sccb_header, length) +
+	    sizeof(sccb->length) > copied || sccb->length > copied) {
 		rc = -EFAULT;
 		goto out_free;
 	}
-	if (sccb->length > PAGE_SIZE || sccb->length < 8)
-		return -EINVAL;
-	if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sccb->length)) {
-		rc = -EFAULT;
+	if (sccb->length < 8) {
+		rc = -EINVAL;
 		goto out_free;
 	}
 	rc = sclp_sync_request(ctl_sccb.cmdw, sccb);
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 799c1524c779..4b8de3e70cf2 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -872,7 +872,7 @@ static int __init vmlogrdr_init(void)
 		goto cleanup;
 
 	for (i=0; i < MAXMINOR; ++i ) {
-		sys_ser[i].buffer = (char *) get_zeroed_page(GFP_KERNEL);
+		sys_ser[i].buffer = (char *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 		if (!sys_ser[i].buffer) {
 			rc = -ENOMEM;
 			break;
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index c692dfebd0ba..50597f9522fe 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -139,11 +139,11 @@ static ssize_t chp_measurement_chars_read(struct file *filp,
 
 	device = container_of(kobj, struct device, kobj);
 	chp = to_channelpath(device);
-	if (!chp->cmg_chars)
+	if (chp->cmg == -1)
 		return 0;
 
-	return memory_read_from_buffer(buf, count, &off,
-				chp->cmg_chars, sizeof(struct cmg_chars));
+	return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars,
+				       sizeof(chp->cmg_chars));
 }
 
 static struct bin_attribute chp_measurement_chars_attr = {
@@ -416,7 +416,8 @@ static void chp_release(struct device *dev)
  * chp_update_desc - update channel-path description
  * @chp - channel-path
  *
- * Update the channel-path description of the specified channel-path.
+ * Update the channel-path description of the specified channel-path
+ * including channel measurement related information.
  * Return zero on success, non-zero otherwise.
  */
 int chp_update_desc(struct channel_path *chp)
@@ -428,8 +429,10 @@ int chp_update_desc(struct channel_path *chp)
 		return rc;
 
 	rc = chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1);
+	if (rc)
+		return rc;
 
-	return rc;
+	return chsc_get_channel_measurement_chars(chp);
 }
 
 /**
@@ -466,14 +469,6 @@ int chp_new(struct chp_id chpid)
 		ret = -ENODEV;
 		goto out_free;
 	}
-	/* Get channel-measurement characteristics. */
-	if (css_chsc_characteristics.scmc && css_chsc_characteristics.secm) {
-		ret = chsc_get_channel_measurement_chars(chp);
-		if (ret)
-			goto out_free;
-	} else {
-		chp->cmg = -1;
-	}
 	dev_set_name(&chp->dev, "chp%x.%02x", chpid.cssid, chpid.id);
 
 	/* make it known to the system */
diff --git a/drivers/s390/cio/chp.h b/drivers/s390/cio/chp.h
index 4efd5b867cc3..af0232290dc4 100644
--- a/drivers/s390/cio/chp.h
+++ b/drivers/s390/cio/chp.h
@@ -48,7 +48,7 @@ struct channel_path {
 	/* Channel-measurement related stuff: */
 	int cmg;
 	int shared;
-	void *cmg_chars;
+	struct cmg_chars cmg_chars;
 };
 
 /* Return channel_path struct for given chpid. */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index a831d18596a5..1e16331891a9 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 
 #include <asm/cio.h>
@@ -94,12 +95,13 @@ struct chsc_ssd_area {
 int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 {
 	struct chsc_ssd_area *ssd_area;
+	unsigned long flags;
 	int ccode;
 	int ret;
 	int i;
 	int mask;
 
-	spin_lock_irq(&chsc_page_lock);
+	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
 	ssd_area = chsc_page;
 	ssd_area->request.length = 0x0010;
@@ -143,7 +145,7 @@ int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 			ssd->fla[i] = ssd_area->fla[i];
 	}
 out:
-	spin_unlock_irq(&chsc_page_lock);
+	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
 }
 
@@ -224,8 +226,9 @@ out_unreg:
 
 void chsc_chp_offline(struct chp_id chpid)
 {
-	char dbf_txt[15];
+	struct channel_path *chp = chpid_to_chp(chpid);
 	struct chp_link link;
+	char dbf_txt[15];
 
 	sprintf(dbf_txt, "chpr%x.%02x", chpid.cssid, chpid.id);
 	CIO_TRACE_EVENT(2, dbf_txt);
@@ -236,6 +239,11 @@ void chsc_chp_offline(struct chp_id chpid)
 	link.chpid = chpid;
 	/* Wait until previous actions have settled. */
 	css_wait_for_slow_path();
+
+	mutex_lock(&chp->lock);
+	chp_update_desc(chp);
+	mutex_unlock(&chp->lock);
+
 	for_each_subchannel_staged(s390_subchannel_remove_chpid, NULL, &link);
 }
 
@@ -690,8 +698,9 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow)
 
 void chsc_chp_online(struct chp_id chpid)
 {
-	char dbf_txt[15];
+	struct channel_path *chp = chpid_to_chp(chpid);
 	struct chp_link link;
+	char dbf_txt[15];
 
 	sprintf(dbf_txt, "cadd%x.%02x", chpid.cssid, chpid.id);
 	CIO_TRACE_EVENT(2, dbf_txt);
@@ -701,6 +710,11 @@ void chsc_chp_online(struct chp_id chpid)
 		link.chpid = chpid;
 		/* Wait until previous actions have settled. */
 		css_wait_for_slow_path();
+
+		mutex_lock(&chp->lock);
+		chp_update_desc(chp);
+		mutex_unlock(&chp->lock);
+
 		for_each_subchannel_staged(__s390_process_res_acc, NULL,
 					   &link);
 		css_schedule_reprobe();
@@ -819,9 +833,10 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		u32 fmt : 4;
 		u32 : 16;
 	} __attribute__ ((packed)) *secm_area;
+	unsigned long flags;
 	int ret, ccode;
 
-	spin_lock_irq(&chsc_page_lock);
+	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
 	secm_area = chsc_page;
 	secm_area->request.length = 0x0050;
@@ -851,7 +866,7 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		CIO_CRW_EVENT(2, "chsc: secm failed (rc=%04x)\n",
 			      secm_area->response.code);
 out:
-	spin_unlock_irq(&chsc_page_lock);
+	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
 }
 
@@ -967,22 +982,20 @@ static void
 chsc_initialize_cmg_chars(struct channel_path *chp, u8 cmcv,
 			  struct cmg_chars *chars)
 {
-	struct cmg_chars *cmg_chars;
 	int i, mask;
 
-	cmg_chars = chp->cmg_chars;
 	for (i = 0; i < NR_MEASUREMENT_CHARS; i++) {
 		mask = 0x80 >> (i + 3);
 		if (cmcv & mask)
-			cmg_chars->values[i] = chars->values[i];
+			chp->cmg_chars.values[i] = chars->values[i];
 		else
-			cmg_chars->values[i] = 0;
+			chp->cmg_chars.values[i] = 0;
 	}
 }
 
 int chsc_get_channel_measurement_chars(struct channel_path *chp)
 {
-	struct cmg_chars *cmg_chars;
+	unsigned long flags;
 	int ccode, ret;
 
 	struct {
@@ -1006,12 +1019,13 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 data[NR_MEASUREMENT_CHARS];
 	} __attribute__ ((packed)) *scmc_area;
 
-	chp->cmg_chars = NULL;
-	cmg_chars = kmalloc(sizeof(*cmg_chars), GFP_KERNEL);
-	if (!cmg_chars)
-		return -ENOMEM;
+	chp->shared = -1;
+	chp->cmg = -1;
+
+	if (!css_chsc_characteristics.scmc || !css_chsc_characteristics.secm)
+		return 0;
 
-	spin_lock_irq(&chsc_page_lock);
+	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
 	scmc_area = chsc_page;
 	scmc_area->request.length = 0x0010;
@@ -1031,25 +1045,19 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 			      scmc_area->response.code);
 		goto out;
 	}
-	if (scmc_area->not_valid) {
-		chp->cmg = -1;
-		chp->shared = -1;
+	if (scmc_area->not_valid)
 		goto out;
-	}
+
 	chp->cmg = scmc_area->cmg;
 	chp->shared = scmc_area->shared;
 	if (chp->cmg != 2 && chp->cmg != 3) {
 		/* No cmg-dependent data. */
 		goto out;
 	}
-	chp->cmg_chars = cmg_chars;
 	chsc_initialize_cmg_chars(chp, scmc_area->cmcv,
 				  (struct cmg_chars *) &scmc_area->data);
 out:
-	spin_unlock_irq(&chsc_page_lock);
-	if (!chp->cmg_chars)
-		kfree(cmg_chars);
-
+	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
 }
 
@@ -1130,6 +1138,7 @@ struct css_chsc_char css_chsc_characteristics;
 int __init
 chsc_determine_css_characteristics(void)
 {
+	unsigned long flags;
 	int result;
 	struct {
 		struct chsc_header request;
@@ -1142,7 +1151,7 @@ chsc_determine_css_characteristics(void)
 		u32 chsc_char[508];
 	} __attribute__ ((packed)) *scsc_area;
 
-	spin_lock_irq(&chsc_page_lock);
+	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
 	scsc_area = chsc_page;
 	scsc_area->request.length = 0x0010;
@@ -1164,7 +1173,7 @@ chsc_determine_css_characteristics(void)
 		CIO_CRW_EVENT(2, "chsc: scsc failed (rc=%04x)\n",
 			      scsc_area->response.code);
 exit:
-	spin_unlock_irq(&chsc_page_lock);
+	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return result;
 }
 
diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c
index b2afad5a5682..2a34eb5f6161 100644
--- a/drivers/s390/cio/cmf.c
+++ b/drivers/s390/cio/cmf.c
@@ -753,6 +753,17 @@ static void reset_cmb(struct ccw_device *cdev)
 	cmf_generic_reset(cdev);
 }
 
+static int cmf_enabled(struct ccw_device *cdev)
+{
+	int enabled;
+
+	spin_lock_irq(cdev->ccwlock);
+	enabled = !!cdev->private->cmb;
+	spin_unlock_irq(cdev->ccwlock);
+
+	return enabled;
+}
+
 static struct attribute_group cmf_attr_group;
 
 static struct cmb_operations cmbops_basic = {
@@ -1153,13 +1164,8 @@ static ssize_t cmb_enable_show(struct device *dev,
 			       char *buf)
 {
 	struct ccw_device *cdev = to_ccwdev(dev);
-	int enabled;
 
-	spin_lock_irq(cdev->ccwlock);
-	enabled = !!cdev->private->cmb;
-	spin_unlock_irq(cdev->ccwlock);
-
-	return sprintf(buf, "%d\n", enabled);
+	return sprintf(buf, "%d\n", cmf_enabled(cdev));
 }
 
 static ssize_t cmb_enable_store(struct device *dev,
@@ -1199,15 +1205,20 @@ int ccw_set_cmf(struct ccw_device *cdev, int enable)
  *  @cdev:	The ccw device to be enabled
  *
  *  Returns %0 for success or a negative error value.
- *
+ *  Note: If this is called on a device for which channel measurement is already
+ *	  enabled a reset of the measurement data is triggered.
  *  Context:
  *    non-atomic
  */
 int enable_cmf(struct ccw_device *cdev)
 {
-	int ret;
+	int ret = 0;
 
 	device_lock(&cdev->dev);
+	if (cmf_enabled(cdev)) {
+		cmbops->reset(cdev);
+		goto out_unlock;
+	}
 	get_device(&cdev->dev);
 	ret = cmbops->alloc(cdev);
 	if (ret)
@@ -1226,7 +1237,7 @@ int enable_cmf(struct ccw_device *cdev)
 out:
 	if (ret)
 		put_device(&cdev->dev);
-
+out_unlock:
 	device_unlock(&cdev->dev);
 	return ret;
 }
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 5d06253c2a7a..30e9fbbff051 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -147,11 +147,11 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
 	struct qdio_q *q;
 	int i;
 
-	for_each_input_queue(irq, q, i) {
-		if (!references_shared_dsci(irq) &&
-		    has_multiple_inq_on_dsci(irq))
-			xchg(q->irq_ptr->dsci, 0);
+	if (!references_shared_dsci(irq) &&
+	    has_multiple_inq_on_dsci(irq))
+		xchg(irq->dsci, 0);
 
+	for_each_input_queue(irq, q, i) {
 		if (q->u.in.queue_start_poll) {
 			/* skip if polling is enabled or already in work */
 			if (test_and_set_bit(QDIO_QUEUE_IRQS_DISABLED,
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 24ec282e15d8..7c3b8d3516e3 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1651,6 +1651,9 @@ static void ap_scan_bus(struct work_struct *unused)
 		ap_dev->queue_depth = queue_depth;
 		ap_dev->raw_hwtype = device_type;
 		ap_dev->device_type = device_type;
+		/* CEX6 toleration: map to CEX5 */
+		if (device_type == AP_DEVICE_TYPE_CEX6)
+			ap_dev->device_type = AP_DEVICE_TYPE_CEX5;
 		ap_dev->functions = device_functions;
 		spin_lock_init(&ap_dev->lock);
 		INIT_LIST_HEAD(&ap_dev->pendingq);
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6adcbdf225d1..cc741e948170 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -105,6 +105,7 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr)
 #define AP_DEVICE_TYPE_CEX3C	9
 #define AP_DEVICE_TYPE_CEX4	10
 #define AP_DEVICE_TYPE_CEX5	11
+#define AP_DEVICE_TYPE_CEX6	12
 
 /*
  * Known function facilities
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 1766a20ebcb1..741f3ee81cfe 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -717,6 +717,7 @@ enum qeth_discipline_id {
 };
 
 struct qeth_discipline {
+	const struct device_type *devtype;
 	void (*start_poll)(struct ccw_device *, int, unsigned long);
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
@@ -881,6 +882,9 @@ extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
 extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
 extern struct workqueue_struct *qeth_wq;
 
 int qeth_card_hw_is_reachable(struct qeth_card *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 31ac53fa5cee..d10bf3da8e5f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5449,10 +5449,12 @@ void qeth_core_free_discipline(struct qeth_card *card)
 	card->discipline = NULL;
 }
 
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
 	.name = "qeth_generic",
 	.groups = qeth_generic_attr_groups,
 };
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
 static const struct device_type qeth_osn_devtype = {
 	.name = "qeth_osn",
 	.groups = qeth_osn_attr_groups,
@@ -5578,23 +5580,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		goto err_card;
 	}
 
-	if (card->info.type == QETH_CARD_TYPE_OSN)
-		gdev->dev.type = &qeth_osn_devtype;
-	else
-		gdev->dev.type = &qeth_generic_devtype;
-
 	switch (card->info.type) {
 	case QETH_CARD_TYPE_OSN:
 	case QETH_CARD_TYPE_OSM:
 		rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
 		if (rc)
 			goto err_card;
+
+		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+					? card->discipline->devtype
+					: &qeth_osn_devtype;
 		rc = card->discipline->setup(card->gdev);
 		if (rc)
 			goto err_disc;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
+		break;
 	default:
+		gdev->dev.type = &qeth_generic_devtype;
 		break;
 	}
 
@@ -5650,8 +5651,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		if (rc)
 			goto err;
 		rc = card->discipline->setup(card->gdev);
-		if (rc)
+		if (rc) {
+			qeth_core_free_discipline(card);
 			goto err;
+		}
 	}
 	rc = card->discipline->set_online(gdev);
 err:
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index e6e5b9671bf2..fa844b0ff847 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -409,12 +409,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	if (card->options.layer2 == newdis)
 		goto out;
-	else {
-		card->info.mac_bits  = 0;
-		if (card->discipline) {
-			card->discipline->remove(card->gdev);
-			qeth_core_free_discipline(card);
-		}
+	if (card->info.type == QETH_CARD_TYPE_OSM) {
+		/* fixed layer, can't switch */
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	card->info.mac_bits = 0;
+	if (card->discipline) {
+		card->discipline->remove(card->gdev);
+		qeth_core_free_discipline(card);
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
@@ -422,6 +426,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		goto out;
 
 	rc = card->discipline->setup(card->gdev);
+	if (rc)
+		qeth_core_free_discipline(card);
 out:
 	mutex_unlock(&card->discipline_mutex);
 	return rc ? rc : count;
@@ -699,10 +705,11 @@ static struct attribute *qeth_blkt_device_attrs[] = {
 	&dev_attr_inter_jumbo.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
 	.name = "blkt",
 	.attrs = qeth_blkt_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
 
 static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_state.attr,
@@ -722,9 +729,10 @@ static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_switch_attrs.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
 	.attrs = qeth_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
 
 const struct attribute_group *qeth_generic_attr_groups[] = {
 	&qeth_device_attr_group,
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 0767556404bd..eb87bf97d38a 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -8,6 +8,8 @@
 
 #include "qeth_core.h"
 
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8f1b091e1732..bf1e0e39334d 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1027,11 +1027,21 @@ static int qeth_l2_stop(struct net_device *dev)
 	return 0;
 }
 
+static const struct device_type qeth_l2_devtype = {
+	.name = "qeth_layer2",
+	.groups = qeth_l2_attr_groups,
+};
+
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l2_create_device_attributes(&gdev->dev);
+	if (gdev->dev.type == &qeth_generic_devtype) {
+		rc = qeth_l2_create_device_attributes(&gdev->dev);
+		if (rc)
+			return rc;
+	}
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
@@ -1043,7 +1053,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
 
-	qeth_l2_remove_device_attributes(&cgdev->dev);
+	if (cgdev->dev.type == &qeth_generic_devtype)
+		qeth_l2_remove_device_attributes(&cgdev->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
@@ -1051,6 +1062,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
@@ -1100,7 +1112,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	case QETH_CARD_TYPE_OSN:
 		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
 					 ether_setup);
-		card->dev->flags |= IFF_NOARP;
 		break;
 	default:
 		card->dev = alloc_etherdev(0);
@@ -1113,9 +1124,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
-	card->dev->ethtool_ops =
-		(card->info.type != QETH_CARD_TYPE_OSN) ?
-		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+	if (card->info.type == QETH_CARD_TYPE_OSN) {
+		card->dev->ethtool_ops = &qeth_l2_osn_ops;
+		card->dev->flags |= IFF_NOARP;
+	} else {
+		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+	}
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
@@ -1126,6 +1140,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	qeth_l2_request_initial_mac(card);
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
+	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
 
@@ -1427,6 +1442,7 @@ static int qeth_l2_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l2_discipline = {
+	.devtype = &qeth_l2_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 692db49e3d2a..a48ed9e7e168 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 	} else
 		qeth_bridgeport_an_set(card, 0);
 }
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+	&qeth_device_attr_group,
+	&qeth_device_blkt_group,
+	/* l2 specific, see l2_{create,remove}_device_attributes(): */
+	&qeth_l2_bridgeport_attr_group,
+	NULL,
+};
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 543960e96b42..285fe0b2c753 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3220,14 +3220,18 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
+	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
 
 static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l3_create_device_attributes(&gdev->dev);
+	rc = qeth_l3_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
@@ -3246,6 +3250,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
@@ -3517,6 +3522,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l3_discipline = {
+	.devtype = &qeth_generic_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 5d7fbe4e907e..d5bf36ec8a75 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -3,7 +3,7 @@
  *
  * Debug traces for zfcp.
  *
- * Copyright IBM Corp. 2002, 2013
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -65,7 +65,7 @@ void zfcp_dbf_pl_write(struct zfcp_dbf *dbf, void *data, u16 length, char *area,
  * @tag: tag indicating which kind of unsolicited status has been received
  * @req: request for which a response was received
  */
-void zfcp_dbf_hba_fsf_res(char *tag, struct zfcp_fsf_req *req)
+void zfcp_dbf_hba_fsf_res(char *tag, int level, struct zfcp_fsf_req *req)
 {
 	struct zfcp_dbf *dbf = req->adapter->dbf;
 	struct fsf_qtcb_prefix *q_pref = &req->qtcb->prefix;
@@ -85,6 +85,8 @@ void zfcp_dbf_hba_fsf_res(char *tag, struct zfcp_fsf_req *req)
 	rec->u.res.req_issued = req->issued;
 	rec->u.res.prot_status = q_pref->prot_status;
 	rec->u.res.fsf_status = q_head->fsf_status;
+	rec->u.res.port_handle = q_head->port_handle;
+	rec->u.res.lun_handle = q_head->lun_handle;
 
 	memcpy(rec->u.res.prot_status_qual, &q_pref->prot_status_qual,
 	       FSF_PROT_STATUS_QUAL_SIZE);
@@ -97,7 +99,7 @@ void zfcp_dbf_hba_fsf_res(char *tag, struct zfcp_fsf_req *req)
 				  rec->pl_len, "fsf_res", req->req_id);
 	}
 
-	debug_event(dbf->hba, 1, rec, sizeof(*rec));
+	debug_event(dbf->hba, level, rec, sizeof(*rec));
 	spin_unlock_irqrestore(&dbf->hba_lock, flags);
 }
 
@@ -241,7 +243,8 @@ static void zfcp_dbf_set_common(struct zfcp_dbf_rec *rec,
 	if (sdev) {
 		rec->lun_status = atomic_read(&sdev_to_zfcp(sdev)->status);
 		rec->lun = zfcp_scsi_dev_lun(sdev);
-	}
+	} else
+		rec->lun = ZFCP_DBF_INVALID_LUN;
 }
 
 /**
@@ -286,11 +289,12 @@ void zfcp_dbf_rec_trig(char *tag, struct zfcp_adapter *adapter,
 
 
 /**
- * zfcp_dbf_rec_run - trace event related to running recovery
+ * zfcp_dbf_rec_run_lvl - trace event related to running recovery
+ * @level: trace level to be used for event
  * @tag: identifier for event
  * @erp: erp_action running
  */
-void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
+void zfcp_dbf_rec_run_lvl(int level, char *tag, struct zfcp_erp_action *erp)
 {
 	struct zfcp_dbf *dbf = erp->adapter->dbf;
 	struct zfcp_dbf_rec *rec = &dbf->rec_buf;
@@ -316,17 +320,62 @@ void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
 	else
 		rec->u.run.rec_count = atomic_read(&erp->adapter->erp_counter);
 
+	debug_event(dbf->rec, level, rec, sizeof(*rec));
+	spin_unlock_irqrestore(&dbf->rec_lock, flags);
+}
+
+/**
+ * zfcp_dbf_rec_run - trace event related to running recovery
+ * @tag: identifier for event
+ * @erp: erp_action running
+ */
+void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
+{
+	zfcp_dbf_rec_run_lvl(1, tag, erp);
+}
+
+/**
+ * zfcp_dbf_rec_run_wka - trace wka port event with info like running recovery
+ * @tag: identifier for event
+ * @wka_port: well known address port
+ * @req_id: request ID to correlate with potential HBA trace record
+ */
+void zfcp_dbf_rec_run_wka(char *tag, struct zfcp_fc_wka_port *wka_port,
+			  u64 req_id)
+{
+	struct zfcp_dbf *dbf = wka_port->adapter->dbf;
+	struct zfcp_dbf_rec *rec = &dbf->rec_buf;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dbf->rec_lock, flags);
+	memset(rec, 0, sizeof(*rec));
+
+	rec->id = ZFCP_DBF_REC_RUN;
+	memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
+	rec->port_status = wka_port->status;
+	rec->d_id = wka_port->d_id;
+	rec->lun = ZFCP_DBF_INVALID_LUN;
+
+	rec->u.run.fsf_req_id = req_id;
+	rec->u.run.rec_status = ~0;
+	rec->u.run.rec_step = ~0;
+	rec->u.run.rec_action = ~0;
+	rec->u.run.rec_count = ~0;
+
 	debug_event(dbf->rec, 1, rec, sizeof(*rec));
 	spin_unlock_irqrestore(&dbf->rec_lock, flags);
 }
 
 static inline
-void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf, void *data, u8 id, u16 len,
-		  u64 req_id, u32 d_id)
+void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf,
+		  char *paytag, struct scatterlist *sg, u8 id, u16 len,
+		  u64 req_id, u32 d_id, u16 cap_len)
 {
 	struct zfcp_dbf_san *rec = &dbf->san_buf;
 	u16 rec_len;
 	unsigned long flags;
+	struct zfcp_dbf_pay *payload = &dbf->pay_buf;
+	u16 pay_sum = 0;
 
 	spin_lock_irqsave(&dbf->san_lock, flags);
 	memset(rec, 0, sizeof(*rec));
@@ -334,10 +383,41 @@ void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf, void *data, u8 id, u16 len,
 	rec->id = id;
 	rec->fsf_req_id = req_id;
 	rec->d_id = d_id;
-	rec_len = min(len, (u16)ZFCP_DBF_SAN_MAX_PAYLOAD);
-	memcpy(rec->payload, data, rec_len);
 	memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
+	rec->pl_len = len; /* full length even if we cap pay below */
+	if (!sg)
+		goto out;
+	rec_len = min_t(unsigned int, sg->length, ZFCP_DBF_SAN_MAX_PAYLOAD);
+	memcpy(rec->payload, sg_virt(sg), rec_len); /* part of 1st sg entry */
+	if (len <= rec_len)
+		goto out; /* skip pay record if full content in rec->payload */
+
+	/* if (len > rec_len):
+	 * dump data up to cap_len ignoring small duplicate in rec->payload
+	 */
+	spin_lock(&dbf->pay_lock);
+	memset(payload, 0, sizeof(*payload));
+	memcpy(payload->area, paytag, ZFCP_DBF_TAG_LEN);
+	payload->fsf_req_id = req_id;
+	payload->counter = 0;
+	for (; sg && pay_sum < cap_len; sg = sg_next(sg)) {
+		u16 pay_len, offset = 0;
+
+		while (offset < sg->length && pay_sum < cap_len) {
+			pay_len = min((u16)ZFCP_DBF_PAY_MAX_REC,
+				      (u16)(sg->length - offset));
+			/* cap_len <= pay_sum < cap_len+ZFCP_DBF_PAY_MAX_REC */
+			memcpy(payload->data, sg_virt(sg) + offset, pay_len);
+			debug_event(dbf->pay, 1, payload,
+				    zfcp_dbf_plen(pay_len));
+			payload->counter++;
+			offset += pay_len;
+			pay_sum += pay_len;
+		}
+	}
+	spin_unlock(&dbf->pay_lock);
 
+out:
 	debug_event(dbf->san, 1, rec, sizeof(*rec));
 	spin_unlock_irqrestore(&dbf->san_lock, flags);
 }
@@ -354,9 +434,62 @@ void zfcp_dbf_san_req(char *tag, struct zfcp_fsf_req *fsf, u32 d_id)
 	struct zfcp_fsf_ct_els *ct_els = fsf->data;
 	u16 length;
 
-	length = (u16)(ct_els->req->length + FC_CT_HDR_LEN);
-	zfcp_dbf_san(tag, dbf, sg_virt(ct_els->req), ZFCP_DBF_SAN_REQ, length,
-		     fsf->req_id, d_id);
+	length = (u16)zfcp_qdio_real_bytes(ct_els->req);
+	zfcp_dbf_san(tag, dbf, "san_req", ct_els->req, ZFCP_DBF_SAN_REQ,
+		     length, fsf->req_id, d_id, length);
+}
+
+static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag,
+					      struct zfcp_fsf_req *fsf,
+					      u16 len)
+{
+	struct zfcp_fsf_ct_els *ct_els = fsf->data;
+	struct fc_ct_hdr *reqh = sg_virt(ct_els->req);
+	struct fc_ns_gid_ft *reqn = (struct fc_ns_gid_ft *)(reqh + 1);
+	struct scatterlist *resp_entry = ct_els->resp;
+	struct fc_gpn_ft_resp *acc;
+	int max_entries, x, last = 0;
+
+	if (!(memcmp(tag, "fsscth2", 7) == 0
+	      && ct_els->d_id == FC_FID_DIR_SERV
+	      && reqh->ct_rev == FC_CT_REV
+	      && reqh->ct_in_id[0] == 0
+	      && reqh->ct_in_id[1] == 0
+	      && reqh->ct_in_id[2] == 0
+	      && reqh->ct_fs_type == FC_FST_DIR
+	      && reqh->ct_fs_subtype == FC_NS_SUBTYPE
+	      && reqh->ct_options == 0
+	      && reqh->_ct_resvd1 == 0
+	      && reqh->ct_cmd == FC_NS_GPN_FT
+	      /* reqh->ct_mr_size can vary so do not match but read below */
+	      && reqh->_ct_resvd2 == 0
+	      && reqh->ct_reason == 0
+	      && reqh->ct_explan == 0
+	      && reqh->ct_vendor == 0
+	      && reqn->fn_resvd == 0
+	      && reqn->fn_domain_id_scope == 0
+	      && reqn->fn_area_id_scope == 0
+	      && reqn->fn_fc4_type == FC_TYPE_FCP))
+		return len; /* not GPN_FT response so do not cap */
+
+	acc = sg_virt(resp_entry);
+	max_entries = (reqh->ct_mr_size * 4 / sizeof(struct fc_gpn_ft_resp))
+		+ 1 /* zfcp_fc_scan_ports: bytes correct, entries off-by-one
+		     * to account for header as 1st pseudo "entry" */;
+
+	/* the basic CT_IU preamble is the same size as one entry in the GPN_FT
+	 * response, allowing us to skip special handling for it - just skip it
+	 */
+	for (x = 1; x < max_entries && !last; x++) {
+		if (x % (ZFCP_FC_GPN_FT_ENT_PAGE + 1))
+			acc++;
+		else
+			acc = sg_virt(++resp_entry);
+
+		last = acc->fp_flags & FC_NS_FID_LAST;
+	}
+	len = min(len, (u16)(x * sizeof(struct fc_gpn_ft_resp)));
+	return len; /* cap after last entry */
 }
 
 /**
@@ -370,9 +503,10 @@ void zfcp_dbf_san_res(char *tag, struct zfcp_fsf_req *fsf)
 	struct zfcp_fsf_ct_els *ct_els = fsf->data;
 	u16 length;
 
-	length = (u16)(ct_els->resp->length + FC_CT_HDR_LEN);
-	zfcp_dbf_san(tag, dbf, sg_virt(ct_els->resp), ZFCP_DBF_SAN_RES, length,
-		     fsf->req_id, 0);
+	length = (u16)zfcp_qdio_real_bytes(ct_els->resp);
+	zfcp_dbf_san(tag, dbf, "san_res", ct_els->resp, ZFCP_DBF_SAN_RES,
+		     length, fsf->req_id, ct_els->d_id,
+		     zfcp_dbf_san_res_cap_len_if_gpn_ft(tag, fsf, length));
 }
 
 /**
@@ -386,11 +520,13 @@ void zfcp_dbf_san_in_els(char *tag, struct zfcp_fsf_req *fsf)
 	struct fsf_status_read_buffer *srb =
 		(struct fsf_status_read_buffer *) fsf->data;
 	u16 length;
+	struct scatterlist sg;
 
 	length = (u16)(srb->length -
 			offsetof(struct fsf_status_read_buffer, payload));
-	zfcp_dbf_san(tag, dbf, srb->payload.data, ZFCP_DBF_SAN_ELS, length,
-		     fsf->req_id, ntoh24(srb->d_id));
+	sg_init_one(&sg, srb->payload.data, length);
+	zfcp_dbf_san(tag, dbf, "san_els", &sg, ZFCP_DBF_SAN_ELS, length,
+		     fsf->req_id, ntoh24(srb->d_id), length);
 }
 
 /**
@@ -399,7 +535,8 @@ void zfcp_dbf_san_in_els(char *tag, struct zfcp_fsf_req *fsf)
  * @sc: pointer to struct scsi_cmnd
  * @fsf: pointer to struct zfcp_fsf_req
  */
-void zfcp_dbf_scsi(char *tag, struct scsi_cmnd *sc, struct zfcp_fsf_req *fsf)
+void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc,
+		   struct zfcp_fsf_req *fsf)
 {
 	struct zfcp_adapter *adapter =
 		(struct zfcp_adapter *) sc->device->host->hostdata[0];
@@ -442,7 +579,7 @@ void zfcp_dbf_scsi(char *tag, struct scsi_cmnd *sc, struct zfcp_fsf_req *fsf)
 		}
 	}
 
-	debug_event(dbf->scsi, 1, rec, sizeof(*rec));
+	debug_event(dbf->scsi, level, rec, sizeof(*rec));
 	spin_unlock_irqrestore(&dbf->scsi_lock, flags);
 }
 
diff --git a/drivers/s390/scsi/zfcp_dbf.h b/drivers/s390/scsi/zfcp_dbf.h
index 0be3d48681ae..db186d44cfaf 100644
--- a/drivers/s390/scsi/zfcp_dbf.h
+++ b/drivers/s390/scsi/zfcp_dbf.h
@@ -2,7 +2,7 @@
  * zfcp device driver
  * debug feature declarations
  *
- * Copyright IBM Corp. 2008, 2010
+ * Copyright IBM Corp. 2008, 2016
  */
 
 #ifndef ZFCP_DBF_H
@@ -17,6 +17,11 @@
 
 #define ZFCP_DBF_INVALID_LUN	0xFFFFFFFFFFFFFFFFull
 
+enum zfcp_dbf_pseudo_erp_act_type {
+	ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD = 0xff,
+	ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL = 0xfe,
+};
+
 /**
  * struct zfcp_dbf_rec_trigger - trace record for triggered recovery action
  * @ready: number of ready recovery actions
@@ -110,6 +115,7 @@ struct zfcp_dbf_san {
 	u32 d_id;
 #define ZFCP_DBF_SAN_MAX_PAYLOAD (FC_CT_HDR_LEN + 32)
 	char payload[ZFCP_DBF_SAN_MAX_PAYLOAD];
+	u16 pl_len;
 } __packed;
 
 /**
@@ -126,6 +132,8 @@ struct zfcp_dbf_hba_res {
 	u8  prot_status_qual[FSF_PROT_STATUS_QUAL_SIZE];
 	u32 fsf_status;
 	u8  fsf_status_qual[FSF_STATUS_QUALIFIER_SIZE];
+	u32 port_handle;
+	u32 lun_handle;
 } __packed;
 
 /**
@@ -275,11 +283,35 @@ struct zfcp_dbf {
 	struct zfcp_dbf_scsi		scsi_buf;
 };
 
+/**
+ * zfcp_dbf_hba_fsf_resp_suppress - true if we should not trace by default
+ * @req: request that has been completed
+ *
+ * Returns true if FCP response with only benign residual under count.
+ */
+static inline
+bool zfcp_dbf_hba_fsf_resp_suppress(struct zfcp_fsf_req *req)
+{
+	struct fsf_qtcb *qtcb = req->qtcb;
+	u32 fsf_stat = qtcb->header.fsf_status;
+	struct fcp_resp *fcp_rsp;
+	u8 rsp_flags, fr_status;
+
+	if (qtcb->prefix.qtcb_type != FSF_IO_COMMAND)
+		return false; /* not an FCP response */
+	fcp_rsp = (struct fcp_resp *)&qtcb->bottom.io.fcp_rsp;
+	rsp_flags = fcp_rsp->fr_flags;
+	fr_status = fcp_rsp->fr_status;
+	return (fsf_stat == FSF_FCP_RSP_AVAILABLE) &&
+		(rsp_flags == FCP_RESID_UNDER) &&
+		(fr_status == SAM_STAT_GOOD);
+}
+
 static inline
 void zfcp_dbf_hba_fsf_resp(char *tag, int level, struct zfcp_fsf_req *req)
 {
 	if (debug_level_enabled(req->adapter->dbf->hba, level))
-		zfcp_dbf_hba_fsf_res(tag, req);
+		zfcp_dbf_hba_fsf_res(tag, level, req);
 }
 
 /**
@@ -296,7 +328,9 @@ void zfcp_dbf_hba_fsf_response(struct zfcp_fsf_req *req)
 		zfcp_dbf_hba_fsf_resp("fs_perr", 1, req);
 
 	} else if (qtcb->header.fsf_status != FSF_GOOD) {
-		zfcp_dbf_hba_fsf_resp("fs_ferr", 1, req);
+		zfcp_dbf_hba_fsf_resp("fs_ferr",
+				      zfcp_dbf_hba_fsf_resp_suppress(req)
+				      ? 5 : 1, req);
 
 	} else if ((req->fsf_command == FSF_QTCB_OPEN_PORT_WITH_DID) ||
 		   (req->fsf_command == FSF_QTCB_OPEN_LUN)) {
@@ -318,7 +352,7 @@ void _zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *scmd,
 					scmd->device->host->hostdata[0];
 
 	if (debug_level_enabled(adapter->dbf->scsi, level))
-		zfcp_dbf_scsi(tag, scmd, req);
+		zfcp_dbf_scsi(tag, level, scmd, req);
 }
 
 /**
@@ -380,4 +414,15 @@ void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
 	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, NULL);
 }
 
+/**
+ * zfcp_dbf_scsi_nullcmnd() - trace NULLify of SCSI command in dev/tgt-reset.
+ * @scmnd: SCSI command that was NULLified.
+ * @fsf_req: request that owned @scmnd.
+ */
+static inline void zfcp_dbf_scsi_nullcmnd(struct scsi_cmnd *scmnd,
+					  struct zfcp_fsf_req *fsf_req)
+{
+	_zfcp_dbf_scsi("scfc__1", 3, scmnd, fsf_req);
+}
+
 #endif /* ZFCP_DBF_H */
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index 3fb410977014..7ccfce559034 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -3,7 +3,7 @@
  *
  * Error Recovery Procedures (ERP).
  *
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -1204,6 +1204,62 @@ static void zfcp_erp_action_dequeue(struct zfcp_erp_action *erp_action)
 	}
 }
 
+/**
+ * zfcp_erp_try_rport_unblock - unblock rport if no more/new recovery
+ * @port: zfcp_port whose fc_rport we should try to unblock
+ */
+static void zfcp_erp_try_rport_unblock(struct zfcp_port *port)
+{
+	unsigned long flags;
+	struct zfcp_adapter *adapter = port->adapter;
+	int port_status;
+	struct Scsi_Host *shost = adapter->scsi_host;
+	struct scsi_device *sdev;
+
+	write_lock_irqsave(&adapter->erp_lock, flags);
+	port_status = atomic_read(&port->status);
+	if ((port_status & ZFCP_STATUS_COMMON_UNBLOCKED)    == 0 ||
+	    (port_status & (ZFCP_STATUS_COMMON_ERP_INUSE |
+			    ZFCP_STATUS_COMMON_ERP_FAILED)) != 0) {
+		/* new ERP of severity >= port triggered elsewhere meanwhile or
+		 * local link down (adapter erp_failed but not clear unblock)
+		 */
+		zfcp_dbf_rec_run_lvl(4, "ertru_p", &port->erp_action);
+		write_unlock_irqrestore(&adapter->erp_lock, flags);
+		return;
+	}
+	spin_lock(shost->host_lock);
+	__shost_for_each_device(sdev, shost) {
+		struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev);
+		int lun_status;
+
+		if (zsdev->port != port)
+			continue;
+		/* LUN under port of interest */
+		lun_status = atomic_read(&zsdev->status);
+		if ((lun_status & ZFCP_STATUS_COMMON_ERP_FAILED) != 0)
+			continue; /* unblock rport despite failed LUNs */
+		/* LUN recovery not given up yet [maybe follow-up pending] */
+		if ((lun_status & ZFCP_STATUS_COMMON_UNBLOCKED) == 0 ||
+		    (lun_status & ZFCP_STATUS_COMMON_ERP_INUSE) != 0) {
+			/* LUN blocked:
+			 * not yet unblocked [LUN recovery pending]
+			 * or meanwhile blocked [new LUN recovery triggered]
+			 */
+			zfcp_dbf_rec_run_lvl(4, "ertru_l", &zsdev->erp_action);
+			spin_unlock(shost->host_lock);
+			write_unlock_irqrestore(&adapter->erp_lock, flags);
+			return;
+		}
+	}
+	/* now port has no child or all children have completed recovery,
+	 * and no ERP of severity >= port was meanwhile triggered elsewhere
+	 */
+	zfcp_scsi_schedule_rport_register(port);
+	spin_unlock(shost->host_lock);
+	write_unlock_irqrestore(&adapter->erp_lock, flags);
+}
+
 static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 {
 	struct zfcp_adapter *adapter = act->adapter;
@@ -1214,11 +1270,18 @@ static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 	case ZFCP_ERP_ACTION_REOPEN_LUN:
 		if (!(act->status & ZFCP_STATUS_ERP_NO_REF))
 			scsi_device_put(sdev);
+		zfcp_erp_try_rport_unblock(port);
 		break;
 
 	case ZFCP_ERP_ACTION_REOPEN_PORT:
-		if (result == ZFCP_ERP_SUCCEEDED)
-			zfcp_scsi_schedule_rport_register(port);
+		/* This switch case might also happen after a forced reopen
+		 * was successfully done and thus overwritten with a new
+		 * non-forced reopen at `ersfs_2'. In this case, we must not
+		 * do the clean-up of the non-forced version.
+		 */
+		if (act->step != ZFCP_ERP_STEP_UNINITIALIZED)
+			if (result == ZFCP_ERP_SUCCEEDED)
+				zfcp_erp_try_rport_unblock(port);
 		/* fall through */
 	case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED:
 		put_device(&port->dev);
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index 5b500652572b..21c8c689b02b 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -3,7 +3,7 @@
  *
  * External function declarations.
  *
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #ifndef ZFCP_EXT_H
@@ -35,8 +35,11 @@ extern void zfcp_dbf_adapter_unregister(struct zfcp_adapter *);
 extern void zfcp_dbf_rec_trig(char *, struct zfcp_adapter *,
 			      struct zfcp_port *, struct scsi_device *, u8, u8);
 extern void zfcp_dbf_rec_run(char *, struct zfcp_erp_action *);
+extern void zfcp_dbf_rec_run_lvl(int level, char *tag,
+				 struct zfcp_erp_action *erp);
+extern void zfcp_dbf_rec_run_wka(char *, struct zfcp_fc_wka_port *, u64);
 extern void zfcp_dbf_hba_fsf_uss(char *, struct zfcp_fsf_req *);
-extern void zfcp_dbf_hba_fsf_res(char *, struct zfcp_fsf_req *);
+extern void zfcp_dbf_hba_fsf_res(char *, int, struct zfcp_fsf_req *);
 extern void zfcp_dbf_hba_bit_err(char *, struct zfcp_fsf_req *);
 extern void zfcp_dbf_hba_berr(struct zfcp_dbf *, struct zfcp_fsf_req *);
 extern void zfcp_dbf_hba_def_err(struct zfcp_adapter *, u64, u16, void **);
@@ -44,7 +47,8 @@ extern void zfcp_dbf_hba_basic(char *, struct zfcp_adapter *);
 extern void zfcp_dbf_san_req(char *, struct zfcp_fsf_req *, u32);
 extern void zfcp_dbf_san_res(char *, struct zfcp_fsf_req *);
 extern void zfcp_dbf_san_in_els(char *, struct zfcp_fsf_req *);
-extern void zfcp_dbf_scsi(char *, struct scsi_cmnd *, struct zfcp_fsf_req *);
+extern void zfcp_dbf_scsi(char *, int, struct scsi_cmnd *,
+			  struct zfcp_fsf_req *);
 
 /* zfcp_erp.c */
 extern void zfcp_erp_set_adapter_status(struct zfcp_adapter *, u32);
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 522a633c866a..27ff38f839fc 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -3,7 +3,7 @@
  *
  * Implementation of FSF commands.
  *
- * Copyright IBM Corp. 2002, 2013
+ * Copyright IBM Corp. 2002, 2015
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -508,7 +508,10 @@ static int zfcp_fsf_exchange_config_evaluate(struct zfcp_fsf_req *req)
 		fc_host_port_type(shost) = FC_PORTTYPE_PTP;
 		break;
 	case FSF_TOPO_FABRIC:
-		fc_host_port_type(shost) = FC_PORTTYPE_NPORT;
+		if (bottom->connection_features & FSF_FEATURE_NPIV_MODE)
+			fc_host_port_type(shost) = FC_PORTTYPE_NPIV;
+		else
+			fc_host_port_type(shost) = FC_PORTTYPE_NPORT;
 		break;
 	case FSF_TOPO_AL:
 		fc_host_port_type(shost) = FC_PORTTYPE_NLPORT;
@@ -613,7 +616,6 @@ static void zfcp_fsf_exchange_port_evaluate(struct zfcp_fsf_req *req)
 
 	if (adapter->connection_features & FSF_FEATURE_NPIV_MODE) {
 		fc_host_permanent_port_name(shost) = bottom->wwpn;
-		fc_host_port_type(shost) = FC_PORTTYPE_NPIV;
 	} else
 		fc_host_permanent_port_name(shost) = fc_host_port_name(shost);
 	fc_host_maxframe_size(shost) = bottom->maximum_frame_size;
@@ -982,8 +984,12 @@ static int zfcp_fsf_setup_ct_els_sbals(struct zfcp_fsf_req *req,
 	if (zfcp_adapter_multi_buffer_active(adapter)) {
 		if (zfcp_qdio_sbals_from_sg(qdio, &req->qdio_req, sg_req))
 			return -EIO;
+		qtcb->bottom.support.req_buf_length =
+			zfcp_qdio_real_bytes(sg_req);
 		if (zfcp_qdio_sbals_from_sg(qdio, &req->qdio_req, sg_resp))
 			return -EIO;
+		qtcb->bottom.support.resp_buf_length =
+			zfcp_qdio_real_bytes(sg_resp);
 
 		zfcp_qdio_set_data_div(qdio, &req->qdio_req,
 					zfcp_qdio_sbale_count(sg_req));
@@ -1073,6 +1079,7 @@ int zfcp_fsf_send_ct(struct zfcp_fc_wka_port *wka_port,
 
 	req->handler = zfcp_fsf_send_ct_handler;
 	req->qtcb->header.port_handle = wka_port->handle;
+	ct->d_id = wka_port->d_id;
 	req->data = ct;
 
 	zfcp_dbf_san_req("fssct_1", req, wka_port->d_id);
@@ -1169,6 +1176,7 @@ int zfcp_fsf_send_els(struct zfcp_adapter *adapter, u32 d_id,
 
 	hton24(req->qtcb->bottom.support.d_id, d_id);
 	req->handler = zfcp_fsf_send_els_handler;
+	els->d_id = d_id;
 	req->data = els;
 
 	zfcp_dbf_san_req("fssels1", req, d_id);
@@ -1604,6 +1612,8 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
+	if (!retval)
+		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
 	return retval;
 }
 
@@ -1657,6 +1667,8 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
+	if (!retval)
+		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
 	return retval;
 }
 
diff --git a/drivers/s390/scsi/zfcp_fsf.h b/drivers/s390/scsi/zfcp_fsf.h
index 57ae3ae1046d..ea3c76ac0de1 100644
--- a/drivers/s390/scsi/zfcp_fsf.h
+++ b/drivers/s390/scsi/zfcp_fsf.h
@@ -3,7 +3,7 @@
  *
  * Interface to the FSF support functions.
  *
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #ifndef FSF_H
@@ -78,6 +78,7 @@
 #define FSF_APP_TAG_CHECK_FAILURE		0x00000082
 #define FSF_REF_TAG_CHECK_FAILURE		0x00000083
 #define FSF_ADAPTER_STATUS_AVAILABLE		0x000000AD
+#define FSF_FCP_RSP_AVAILABLE			0x000000AF
 #define FSF_UNKNOWN_COMMAND			0x000000E2
 #define FSF_UNKNOWN_OP_SUBTYPE                  0x000000E3
 #define FSF_INVALID_COMMAND_OPTION              0x000000E5
@@ -436,6 +437,7 @@ struct zfcp_blk_drv_data {
  * @handler_data: data passed to handler function
  * @port: Optional pointer to port for zfcp internal ELS (only test link ADISC)
  * @status: used to pass error status to calling function
+ * @d_id: Destination ID of either open WKA port for CT or of D_ID for ELS
  */
 struct zfcp_fsf_ct_els {
 	struct scatterlist *req;
@@ -444,6 +446,7 @@ struct zfcp_fsf_ct_els {
 	void *handler_data;
 	struct zfcp_port *port;
 	int status;
+	u32 d_id;
 };
 
 #endif				/* FSF_H */
diff --git a/drivers/s390/scsi/zfcp_reqlist.h b/drivers/s390/scsi/zfcp_reqlist.h
index 7c2c6194dfca..703fce59befe 100644
--- a/drivers/s390/scsi/zfcp_reqlist.h
+++ b/drivers/s390/scsi/zfcp_reqlist.h
@@ -4,7 +4,7 @@
  * Data structure and helper functions for tracking pending FSF
  * requests.
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009, 2016
  */
 
 #ifndef ZFCP_REQLIST_H
@@ -180,4 +180,32 @@ static inline void zfcp_reqlist_move(struct zfcp_reqlist *rl,
 	spin_unlock_irqrestore(&rl->lock, flags);
 }
 
+/**
+ * zfcp_reqlist_apply_for_all() - apply a function to every request.
+ * @rl: the requestlist that contains the target requests.
+ * @f: the function to apply to each request; the first parameter of the
+ *     function will be the target-request; the second parameter is the same
+ *     pointer as given with the argument @data.
+ * @data: freely chosen argument; passed through to @f as second parameter.
+ *
+ * Uses :c:macro:`list_for_each_entry` to iterate over the lists in the hash-
+ * table (not a 'safe' variant, so don't modify the list).
+ *
+ * Holds @rl->lock over the entire request-iteration.
+ */
+static inline void
+zfcp_reqlist_apply_for_all(struct zfcp_reqlist *rl,
+			   void (*f)(struct zfcp_fsf_req *, void *), void *data)
+{
+	struct zfcp_fsf_req *req;
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&rl->lock, flags);
+	for (i = 0; i < ZFCP_REQ_LIST_BUCKETS; i++)
+		list_for_each_entry(req, &rl->buckets[i], list)
+			f(req, data);
+	spin_unlock_irqrestore(&rl->lock, flags);
+}
+
 #endif /* ZFCP_REQLIST_H */
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index b3c6ff49103b..07ffdbb5107f 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -3,7 +3,7 @@
  *
  * Interface to Linux SCSI midlayer.
  *
- * Copyright IBM Corp. 2002, 2013
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -88,9 +88,7 @@ int zfcp_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scpnt)
 	}
 
 	if (unlikely(!(status & ZFCP_STATUS_COMMON_UNBLOCKED))) {
-		/* This could be either
-		 * open LUN pending: this is temporary, will result in
-		 *	open LUN or ERP_FAILED, so retry command
+		/* This could be
 		 * call to rport_delete pending: mimic retry from
 		 * 	fc_remote_port_chkready until rport is BLOCKED
 		 */
@@ -209,6 +207,57 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt)
 	return retval;
 }
 
+struct zfcp_scsi_req_filter {
+	u8 tmf_scope;
+	u32 lun_handle;
+	u32 port_handle;
+};
+
+static void zfcp_scsi_forget_cmnd(struct zfcp_fsf_req *old_req, void *data)
+{
+	struct zfcp_scsi_req_filter *filter =
+		(struct zfcp_scsi_req_filter *)data;
+
+	/* already aborted - prevent side-effects - or not a SCSI command */
+	if (old_req->data == NULL || old_req->fsf_command != FSF_QTCB_FCP_CMND)
+		return;
+
+	/* (tmf_scope == FCP_TMF_TGT_RESET || tmf_scope == FCP_TMF_LUN_RESET) */
+	if (old_req->qtcb->header.port_handle != filter->port_handle)
+		return;
+
+	if (filter->tmf_scope == FCP_TMF_LUN_RESET &&
+	    old_req->qtcb->header.lun_handle != filter->lun_handle)
+		return;
+
+	zfcp_dbf_scsi_nullcmnd((struct scsi_cmnd *)old_req->data, old_req);
+	old_req->data = NULL;
+}
+
+static void zfcp_scsi_forget_cmnds(struct zfcp_scsi_dev *zsdev, u8 tm_flags)
+{
+	struct zfcp_adapter *adapter = zsdev->port->adapter;
+	struct zfcp_scsi_req_filter filter = {
+		.tmf_scope = FCP_TMF_TGT_RESET,
+		.port_handle = zsdev->port->handle,
+	};
+	unsigned long flags;
+
+	if (tm_flags == FCP_TMF_LUN_RESET) {
+		filter.tmf_scope = FCP_TMF_LUN_RESET;
+		filter.lun_handle = zsdev->lun_handle;
+	}
+
+	/*
+	 * abort_lock secures against other processings - in the abort-function
+	 * and normal cmnd-handler - of (struct zfcp_fsf_req *)->data
+	 */
+	write_lock_irqsave(&adapter->abort_lock, flags);
+	zfcp_reqlist_apply_for_all(adapter->req_list, zfcp_scsi_forget_cmnd,
+				   &filter);
+	write_unlock_irqrestore(&adapter->abort_lock, flags);
+}
+
 static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 {
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(scpnt->device);
@@ -241,8 +290,10 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 	if (fsf_req->status & ZFCP_STATUS_FSFREQ_TMFUNCFAILED) {
 		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags);
 		retval = FAILED;
-	} else
+	} else {
 		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags);
+		zfcp_scsi_forget_cmnds(zfcp_sdev, tm_flags);
+	}
 
 	zfcp_fsf_req_free(fsf_req);
 	return retval;
@@ -556,6 +607,9 @@ static void zfcp_scsi_rport_register(struct zfcp_port *port)
 	ids.port_id = port->d_id;
 	ids.roles = FC_RPORT_ROLE_FCP_TARGET;
 
+	zfcp_dbf_rec_trig("scpaddy", port->adapter, port, NULL,
+			  ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD,
+			  ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD);
 	rport = fc_remote_port_add(port->adapter->scsi_host, 0, &ids);
 	if (!rport) {
 		dev_err(&port->adapter->ccw_device->dev,
@@ -577,6 +631,9 @@ static void zfcp_scsi_rport_block(struct zfcp_port *port)
 	struct fc_rport *rport = port->rport;
 
 	if (rport) {
+		zfcp_dbf_rec_trig("scpdely", port->adapter, port, NULL,
+				  ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL,
+				  ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL);
 		fc_remote_port_delete(rport);
 		port->rport = NULL;
 	}
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index d4c285688ce9..3ddc85e6efd6 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -1122,7 +1122,7 @@ process_script_interrupt(__u32 dsps, __u32 dsp, struct scsi_cmnd *SCp,
 		} else {
 			struct scsi_cmnd *SCp;
 
-			SCp = scsi_host_find_tag(SDp->host, SCSI_NO_TAG);
+			SCp = SDp->current_cmnd;
 			if(unlikely(SCp == NULL)) {
 				sdev_printk(KERN_ERR, SDp,
 					"no saved request for untagged cmd\n");
@@ -1826,7 +1826,7 @@ NCR_700_queuecommand_lck(struct scsi_cmnd *SCp, void (*done)(struct scsi_cmnd *)
 		       slot->tag, slot);
 	} else {
 		slot->tag = SCSI_NO_TAG;
-		/* must populate current_cmnd for scsi_host_find_tag to work */
+		/* save current command for reselection */
 		SCp->device->current_cmnd = SCp;
 	}
 	/* sanity check: some of the commands generated by the mid-layer
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 64eed87d34a8..433c5e3d5733 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1637,7 +1637,7 @@ config ATARI_SCSI_RESET_BOOT
 
 config MAC_SCSI
 	tristate "Macintosh NCR5380 SCSI"
-	depends on MAC && SCSI=y
+	depends on MAC && SCSI
 	select SCSI_SPI_ATTRS
 	help
 	  This is the NCR 5380 SCSI controller included on most of the 68030
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 074878b55a0b..467773033a20 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -29,6 +29,7 @@ enum {
 #define AAC_INT_MODE_MSI		(1<<1)
 #define AAC_INT_MODE_AIF		(1<<2)
 #define AAC_INT_MODE_SYNC		(1<<3)
+#define AAC_INT_MODE_MSIX		(1<<16)
 
 #define AAC_INT_ENABLE_TYPE1_INTX	0xfffffffb
 #define AAC_INT_ENABLE_TYPE1_MSIX	0xfffffffa
@@ -944,6 +945,7 @@ struct fib {
 	 */
 	struct list_head	fiblink;
 	void			*data;
+	u32			vector_no;
 	struct hw_fib		*hw_fib_va;		/* Actual shared object */
 	dma_addr_t		hw_fib_pa;		/* physical address of hw_fib*/
 };
@@ -2113,6 +2115,7 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor)
 int aac_acquire_irq(struct aac_dev *dev);
 void aac_free_irq(struct aac_dev *dev);
 const char *aac_driverinfo(struct Scsi_Host *);
+void aac_fib_vector_assign(struct aac_dev *dev);
 struct fib *aac_fib_alloc(struct aac_dev *dev);
 int aac_fib_setup(struct aac_dev *dev);
 void aac_fib_map_free(struct aac_dev *dev);
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 54195a117f72..f78cc943d230 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -63,7 +63,7 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg)
 	struct fib *fibptr;
 	struct hw_fib * hw_fib = (struct hw_fib *)0;
 	dma_addr_t hw_fib_pa = (dma_addr_t)0LL;
-	unsigned size;
+	unsigned int size, osize;
 	int retval;
 
 	if (dev->in_reset) {
@@ -87,7 +87,8 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg)
 	 *	will not overrun the buffer when we copy the memory. Return
 	 *	an error if we would.
 	 */
-	size = le16_to_cpu(kfib->header.Size) + sizeof(struct aac_fibhdr);
+	osize = size = le16_to_cpu(kfib->header.Size) +
+		sizeof(struct aac_fibhdr);
 	if (size < le16_to_cpu(kfib->header.SenderSize))
 		size = le16_to_cpu(kfib->header.SenderSize);
 	if (size > dev->max_fib_size) {
@@ -118,6 +119,14 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg)
 		goto cleanup;
 	}
 
+	/* Sanity check the second copy */
+	if ((osize != le16_to_cpu(kfib->header.Size) +
+		sizeof(struct aac_fibhdr))
+		|| (size < le16_to_cpu(kfib->header.SenderSize))) {
+		retval = -EINVAL;
+		goto cleanup;
+	}
+
 	if (kfib->header.Command == cpu_to_le16(TakeABreakPt)) {
 		aac_adapter_interrupt(dev);
 		/*
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 0e954e37f0b5..26d38b1a45ab 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -37,6 +37,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/completion.h>
 #include <linux/mm.h>
 #include <scsi/scsi_host.h>
@@ -47,6 +48,24 @@ struct aac_common aac_config = {
 	.irq_mod = 1
 };
 
+static inline int aac_is_msix_mode(struct aac_dev *dev)
+{
+	u32 status = 0;
+
+	if (dev->pdev->device == PMC_DEVICE_S6 ||
+		dev->pdev->device == PMC_DEVICE_S7 ||
+		dev->pdev->device == PMC_DEVICE_S8) {
+		status = src_readl(dev, MUnit.OMR);
+	}
+	return (status & AAC_INT_MODE_MSIX);
+}
+
+static inline void aac_change_to_intx(struct aac_dev *dev)
+{
+	aac_src_access_devreg(dev, AAC_DISABLE_MSIX);
+	aac_src_access_devreg(dev, AAC_ENABLE_INTX);
+}
+
 static int aac_alloc_comm(struct aac_dev *dev, void **commaddr, unsigned long commsize, unsigned long commalign)
 {
 	unsigned char *base;
@@ -425,6 +444,15 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 	dev->comm_interface = AAC_COMM_PRODUCER;
 	dev->raw_io_interface = dev->raw_io_64 = 0;
 
+
+	/*
+	 * Enable INTX mode, if not done already Enabled
+	 */
+	if (aac_is_msix_mode(dev)) {
+		aac_change_to_intx(dev);
+		dev_info(&dev->pdev->dev, "Changed firmware to INTX mode");
+	}
+
 	if ((!aac_adapter_sync_cmd(dev, GET_ADAPTER_PROPERTIES,
 		0, 0, 0, 0, 0, 0,
 		status+0, status+1, status+2, status+3, NULL)) &&
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a1f90fe849c9..8c758c36fc70 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -83,13 +83,38 @@ static int fib_map_alloc(struct aac_dev *dev)
 
 void aac_fib_map_free(struct aac_dev *dev)
 {
-	pci_free_consistent(dev->pdev,
-	  dev->max_fib_size * (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB),
-	  dev->hw_fib_va, dev->hw_fib_pa);
+	if (dev->hw_fib_va && dev->max_fib_size) {
+		pci_free_consistent(dev->pdev,
+		(dev->max_fib_size *
+		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)),
+		dev->hw_fib_va, dev->hw_fib_pa);
+	}
 	dev->hw_fib_va = NULL;
 	dev->hw_fib_pa = 0;
 }
 
+void aac_fib_vector_assign(struct aac_dev *dev)
+{
+	u32 i = 0;
+	u32 vector = 1;
+	struct fib *fibptr = NULL;
+
+	for (i = 0, fibptr = &dev->fibs[i];
+		i < (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB);
+		i++, fibptr++) {
+		if ((dev->max_msix == 1) ||
+		  (i > ((dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB - 1)
+			- dev->vector_cap))) {
+			fibptr->vector_no = 0;
+		} else {
+			fibptr->vector_no = vector;
+			vector++;
+			if (vector == dev->max_msix)
+				vector = 1;
+		}
+	}
+}
+
 /**
  *	aac_fib_setup	-	setup the fibs
  *	@dev: Adapter to set up
@@ -151,6 +176,12 @@ int aac_fib_setup(struct aac_dev * dev)
 		hw_fib_pa = hw_fib_pa +
 			dev->max_fib_size + sizeof(struct aac_fib_xporthdr);
 	}
+
+	/*
+	 *Assign vector numbers to fibs
+	 */
+	aac_fib_vector_assign(dev);
+
 	/*
 	 *	Add the fib chain to the free list
 	 */
@@ -580,10 +611,10 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 					}
 					return -EFAULT;
 				}
-				/* We used to udelay() here but that absorbed
-				 * a CPU when a timeout occured. Not very
-				 * useful. */
-				cpu_relax();
+				/*
+				 * Allow other processes / CPUS to use core
+				 */
+				schedule();
 			}
 		} else if (down_interruptible(&fibptr->event_wait)) {
 			/* Do nothing ... satisfy
@@ -1939,6 +1970,10 @@ int aac_command_thread(void *data)
 		if (difference <= 0)
 			difference = 1;
 		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (kthread_should_stop())
+			break;
+
 		schedule_timeout(difference);
 
 		if (kthread_should_stop())
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 3b6e5c67e853..aa6eccb8940b 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1404,8 +1404,18 @@ static int aac_acquire_resources(struct aac_dev *dev)
 
 	aac_adapter_enable_int(dev);
 
-	if (!dev->sync_mode)
+	/*max msix may change  after EEH
+	 * Re-assign vectors to fibs
+	 */
+	aac_fib_vector_assign(dev);
+
+	if (!dev->sync_mode) {
+		/* After EEH recovery or suspend resume, max_msix count
+		 * may change, therfore updating in init as well.
+		 */
 		aac_adapter_start(dev);
+		dev->init->Sa_MSIXVectors = cpu_to_le32(dev->max_msix);
+	}
 	return 0;
 
 error_iounmap:
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 2aa34ea8ceb1..e415e1c58eb5 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -156,8 +156,8 @@ static irqreturn_t aac_src_intr_message(int irq, void *dev_id)
 				break;
 			if (dev->msi_enabled && dev->max_msix > 1)
 				atomic_dec(&dev->rrq_outstanding[vector_no]);
-			aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL);
 			dev->host_rrq[index++] = 0;
+			aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL);
 			if (index == (vector_no + 1) * dev->vector_cap)
 				index = vector_no * dev->vector_cap;
 			dev->host_rrq_idx[vector_no] = index;
@@ -413,16 +413,23 @@ static int aac_src_check_health(struct aac_dev *dev)
 	u32 status = src_readl(dev, MUnit.OMR);
 
 	/*
+	 *	Check to see if the board panic'd.
+	 */
+	if (unlikely(status & KERNEL_PANIC))
+		goto err_blink;
+
+	/*
 	 *	Check to see if the board failed any self tests.
 	 */
 	if (unlikely(status & SELF_TEST_FAILED))
-		return -1;
+		goto err_out;
 
 	/*
-	 *	Check to see if the board panic'd.
+	 *	Check to see if the board failed any self tests.
 	 */
-	if (unlikely(status & KERNEL_PANIC))
-		return (status >> 16) & 0xFF;
+	if (unlikely(status & MONITOR_PANIC))
+		goto err_out;
+
 	/*
 	 *	Wait for the adapter to be up and running.
 	 */
@@ -432,6 +439,12 @@ static int aac_src_check_health(struct aac_dev *dev)
 	 *	Everything is OK
 	 */
 	return 0;
+
+err_out:
+	return -1;
+
+err_blink:
+	return (status > 16) & 0xFF;
 }
 
 /**
@@ -452,36 +465,20 @@ static int aac_src_deliver_message(struct fib *fib)
 #endif
 
 	u16 hdr_size = le16_to_cpu(fib->hw_fib_va->header.Size);
+	u16 vector_no;
 
 	atomic_inc(&q->numpending);
 
 	if (dev->msi_enabled && fib->hw_fib_va->header.Command != AifRequest &&
 	    dev->max_msix > 1) {
-		u_int16_t vector_no, first_choice = 0xffff;
-
-		vector_no = dev->fibs_pushed_no % dev->max_msix;
-		do {
-			vector_no += 1;
-			if (vector_no == dev->max_msix)
-				vector_no = 1;
-			if (atomic_read(&dev->rrq_outstanding[vector_no]) <
-			    dev->vector_cap)
-				break;
-			if (0xffff == first_choice)
-				first_choice = vector_no;
-			else if (vector_no == first_choice)
-				break;
-		} while (1);
-		if (vector_no == first_choice)
-			vector_no = 0;
-		atomic_inc(&dev->rrq_outstanding[vector_no]);
-		if (dev->fibs_pushed_no == 0xffffffff)
-			dev->fibs_pushed_no = 0;
-		else
-			dev->fibs_pushed_no++;
+		vector_no = fib->vector_no;
 		fib->hw_fib_va->header.Handle += (vector_no << 16);
+	} else {
+		vector_no = 0;
 	}
 
+	atomic_inc(&dev->rrq_outstanding[vector_no]);
+
 	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
 		/* Calculate the amount to the fibsize bits */
 		fibsize = (hdr_size + 127) / 128 - 1;
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index b846a4683562..fc6a83188c1e 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1336,6 +1336,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 	case AHC_DEV_Q_TAGGED:
 		scsi_change_queue_depth(sdev,
 				dev->openings + dev->active);
+		break;
 	default:
 		/*
 		 * We allow the OS to queue 2 untagged transactions to
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 333db5953607..7aa01c1960ea 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -2297,15 +2297,23 @@ static int arcmsr_iop_message_xfer(struct AdapterControlBlock *acb,
 	}
 	case ARCMSR_MESSAGE_WRITE_WQBUFFER: {
 		unsigned char *ver_addr;
-		int32_t user_len, cnt2end;
+		uint32_t user_len;
+		int32_t cnt2end;
 		uint8_t *pQbuffer, *ptmpuserbuffer;
+
+		user_len = pcmdmessagefld->cmdmessage.Length;
+		if (user_len > ARCMSR_API_DATA_BUFLEN) {
+			retvalue = ARCMSR_MESSAGE_FAIL;
+			goto message_out;
+		}
+
 		ver_addr = kmalloc(ARCMSR_API_DATA_BUFLEN, GFP_ATOMIC);
 		if (!ver_addr) {
 			retvalue = ARCMSR_MESSAGE_FAIL;
 			goto message_out;
 		}
 		ptmpuserbuffer = ver_addr;
-		user_len = pcmdmessagefld->cmdmessage.Length;
+
 		memcpy(ptmpuserbuffer,
 			pcmdmessagefld->messagedatabuffer, user_len);
 		spin_lock_irqsave(&acb->wqbuffer_lock, flags);
@@ -2537,18 +2545,9 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd,
 	struct AdapterControlBlock *acb = (struct AdapterControlBlock *) host->hostdata;
 	struct CommandControlBlock *ccb;
 	int target = cmd->device->id;
-	int lun = cmd->device->lun;
-	uint8_t scsicmd = cmd->cmnd[0];
 	cmd->scsi_done = done;
 	cmd->host_scribble = NULL;
 	cmd->result = 0;
-	if ((scsicmd == SYNCHRONIZE_CACHE) ||(scsicmd == SEND_DIAGNOSTIC)){
-		if(acb->devstate[target][lun] == ARECA_RAID_GONE) {
-    			cmd->result = (DID_NO_CONNECT << 16);
-		}
-		cmd->scsi_done(cmd);
-		return 0;
-	}
 	if (target == 16) {
 		/* virtual device for iop message transfer */
 		arcmsr_handle_virtual_command(acb, cmd);
@@ -2664,7 +2663,7 @@ static bool arcmsr_hbaB_get_config(struct AdapterControlBlock *acb)
 	if (!arcmsr_hbaB_wait_msgint_ready(acb)) {
 		printk(KERN_NOTICE "arcmsr%d: wait 'get adapter firmware \
 			miscellaneous data' timeout \n", acb->host->host_no);
-		return false;
+		goto err_free_dma;
 	}
 	count = 8;
 	while (count){
@@ -2694,19 +2693,23 @@ static bool arcmsr_hbaB_get_config(struct AdapterControlBlock *acb)
 		acb->firm_model,
 		acb->firm_version);
 
-	acb->signature = readl(&reg->message_rwbuffer[1]);
+	acb->signature = readl(&reg->message_rwbuffer[0]);
 	/*firm_signature,1,00-03*/
-	acb->firm_request_len = readl(&reg->message_rwbuffer[2]);
+	acb->firm_request_len = readl(&reg->message_rwbuffer[1]);
 	/*firm_request_len,1,04-07*/
-	acb->firm_numbers_queue = readl(&reg->message_rwbuffer[3]);
+	acb->firm_numbers_queue = readl(&reg->message_rwbuffer[2]);
 	/*firm_numbers_queue,2,08-11*/
-	acb->firm_sdram_size = readl(&reg->message_rwbuffer[4]);
+	acb->firm_sdram_size = readl(&reg->message_rwbuffer[3]);
 	/*firm_sdram_size,3,12-15*/
-	acb->firm_hd_channels = readl(&reg->message_rwbuffer[5]);
+	acb->firm_hd_channels = readl(&reg->message_rwbuffer[4]);
 	/*firm_ide_channels,4,16-19*/
 	acb->firm_cfg_version = readl(&reg->message_rwbuffer[25]);  /*firm_cfg_version,25,100-103*/
 	/*firm_ide_channels,4,16-19*/
 	return true;
+err_free_dma:
+	dma_free_coherent(&acb->pdev->dev, acb->roundup_ccbsize,
+			acb->dma_coherent2, acb->dma_coherent_handle2);
+	return false;
 }
 
 static bool arcmsr_hbaC_get_config(struct AdapterControlBlock *pACB)
@@ -2880,15 +2883,15 @@ static bool arcmsr_hbaD_get_config(struct AdapterControlBlock *acb)
 		iop_device_map++;
 		count--;
 	}
-	acb->signature = readl(&reg->msgcode_rwbuffer[1]);
+	acb->signature = readl(&reg->msgcode_rwbuffer[0]);
 	/*firm_signature,1,00-03*/
-	acb->firm_request_len = readl(&reg->msgcode_rwbuffer[2]);
+	acb->firm_request_len = readl(&reg->msgcode_rwbuffer[1]);
 	/*firm_request_len,1,04-07*/
-	acb->firm_numbers_queue = readl(&reg->msgcode_rwbuffer[3]);
+	acb->firm_numbers_queue = readl(&reg->msgcode_rwbuffer[2]);
 	/*firm_numbers_queue,2,08-11*/
-	acb->firm_sdram_size = readl(&reg->msgcode_rwbuffer[4]);
+	acb->firm_sdram_size = readl(&reg->msgcode_rwbuffer[3]);
 	/*firm_sdram_size,3,12-15*/
-	acb->firm_hd_channels = readl(&reg->msgcode_rwbuffer[5]);
+	acb->firm_hd_channels = readl(&reg->msgcode_rwbuffer[4]);
 	/*firm_hd_channels,4,16-19*/
 	acb->firm_cfg_version = readl(&reg->msgcode_rwbuffer[25]);
 	pr_notice("Areca RAID Controller%d: Model %s, F/W %s\n",
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index fe0c5143f8e6..758f76e88704 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -4470,6 +4470,7 @@ put_shost:
 	scsi_host_put(phba->shost);
 free_kset:
 	iscsi_boot_destroy_kset(phba->boot_kset);
+	phba->boot_kset = NULL;
 	return -ENOMEM;
 }
 
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index fa09d4be2b53..2b456ca69d5c 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1181,8 +1181,9 @@ static const char * const snstext[] = {
 
 /* Get sense key string or NULL if not available */
 const char *
-scsi_sense_key_string(unsigned char key) {
-	if (key <= 0xE)
+scsi_sense_key_string(unsigned char key)
+{
+	if (key < ARRAY_SIZE(snstext))
 		return snstext[key];
 	return NULL;
 }
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index c11cd193f896..a8ac4c0a1493 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -34,7 +34,6 @@ extern const struct file_operations cxlflash_cxl_fops;
 								   sectors
 								*/
 
-#define NUM_RRQ_ENTRY    16     /* for master issued cmds */
 #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
 
 /* AFU command retry limit */
@@ -48,9 +47,12 @@ extern const struct file_operations cxlflash_cxl_fops;
 							   index derivation
 							 */
 
-#define CXLFLASH_MAX_CMDS               16
+#define CXLFLASH_MAX_CMDS               256
 #define CXLFLASH_MAX_CMDS_PER_LUN       CXLFLASH_MAX_CMDS
 
+/* RRQ for master issued cmds */
+#define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -149,7 +151,7 @@ struct afu_cmd {
 struct afu {
 	/* Stuff requiring alignment go first. */
 
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 128B RRQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
 	/*
 	 * Command & data for AFU commands.
 	 */
@@ -165,6 +167,8 @@ struct afu {
 	struct sisl_host_map __iomem *host_map;		/* MC host map */
 	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */
 
+	struct kref mapcount;
+
 	ctx_hndl_t ctx_hndl;	/* master's context handle */
 	u64 *hrrq_start;
 	u64 *hrrq_end;
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 1e5bf0ca81da..0b096730c72a 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -289,7 +289,7 @@ static void context_reset(struct afu_cmd *cmd)
 		atomic64_set(&afu->room, room);
 		if (room)
 			goto write_rrin;
-		udelay(nretry);
+		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 
 	pr_err("%s: no cmd_room to send reset\n", __func__);
@@ -303,7 +303,7 @@ write_rrin:
 		if (rrin != 0x1)
 			break;
 		/* Double delay each time */
-		udelay(2 << nretry);
+		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 }
 
@@ -338,7 +338,7 @@ retry:
 			atomic64_set(&afu->room, room);
 			if (room)
 				goto write_ioarrin;
-			udelay(nretry);
+			udelay(1 << nretry);
 		} while (nretry++ < MC_ROOM_RETRY_CNT);
 
 		dev_err(dev, "%s: no cmd_room to send 0x%X\n",
@@ -352,7 +352,7 @@ retry:
 		 * afu->room.
 		 */
 		if (nretry++ < MC_ROOM_RETRY_CNT) {
-			udelay(nretry);
+			udelay(1 << nretry);
 			goto retry;
 		}
 
@@ -368,6 +368,7 @@ out:
 
 no_room:
 	afu->read_room = true;
+	kref_get(&cfg->afu->mapcount);
 	schedule_work(&cfg->work_q);
 	rc = SCSI_MLQUEUE_HOST_BUSY;
 	goto out;
@@ -473,6 +474,16 @@ out:
 	return rc;
 }
 
+static void afu_unmap(struct kref *ref)
+{
+	struct afu *afu = container_of(ref, struct afu, mapcount);
+
+	if (likely(afu->afu_map)) {
+		cxl_psa_unmap((void __iomem *)afu->afu_map);
+		afu->afu_map = NULL;
+	}
+}
+
 /**
  * cxlflash_driver_info() - information handler for this host driver
  * @host:	SCSI host associated with device.
@@ -503,6 +514,7 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	ulong lock_flags;
 	short lflag = 0;
 	int rc = 0;
+	int kref_got = 0;
 
 	dev_dbg_ratelimited(dev, "%s: (scp=%p) %d/%d/%d/%llu "
 			    "cdb=(%08X-%08X-%08X-%08X)\n",
@@ -547,6 +559,9 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 		goto out;
 	}
 
+	kref_get(&cfg->afu->mapcount);
+	kref_got = 1;
+
 	cmd->rcb.ctx_id = afu->ctx_hndl;
 	cmd->rcb.port_sel = port_sel;
 	cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
@@ -587,6 +602,8 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	}
 
 out:
+	if (kref_got)
+		kref_put(&afu->mapcount, afu_unmap);
 	pr_devel("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
@@ -632,20 +649,36 @@ static void free_mem(struct cxlflash_cfg *cfg)
  * @cfg:	Internal structure associated with the host.
  *
  * Safe to call with AFU in a partially allocated/initialized state.
+ *
+ * Cleans up all state associated with the command queue, and unmaps
+ * the MMIO space.
+ *
+ *  - complete() will take care of commands we initiated (they'll be checked
+ *  in as part of the cleanup that occurs after the completion)
+ *
+ *  - cmd_checkin() will take care of entries that we did not initiate and that
+ *  have not (and will not) complete because they are sitting on a [now stale]
+ *  hardware queue
  */
 static void stop_afu(struct cxlflash_cfg *cfg)
 {
 	int i;
 	struct afu *afu = cfg->afu;
+	struct afu_cmd *cmd;
 
 	if (likely(afu)) {
-		for (i = 0; i < CXLFLASH_NUM_CMDS; i++)
-			complete(&afu->cmd[i].cevent);
+		for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+			cmd = &afu->cmd[i];
+			complete(&cmd->cevent);
+			if (!atomic_read(&cmd->free))
+				cmd_checkin(cmd);
+		}
 
 		if (likely(afu->afu_map)) {
 			cxl_psa_unmap((void __iomem *)afu->afu_map);
 			afu->afu_map = NULL;
 		}
+		kref_put(&afu->mapcount, afu_unmap);
 	}
 }
 
@@ -731,8 +764,8 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		scsi_remove_host(cfg->host);
 		/* fall through */
 	case INIT_STATE_AFU:
-		term_afu(cfg);
 		cancel_work_sync(&cfg->work_q);
+		term_afu(cfg);
 	case INIT_STATE_PCI:
 		pci_release_regions(cfg->dev);
 		pci_disable_device(pdev);
@@ -963,6 +996,8 @@ static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 	do {
 		msleep(delay_us / 1000);
 		status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]);
+		if (status == U64_MAX)
+			nretry /= 2;
 	} while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_ONLINE &&
 		 nretry--);
 
@@ -994,6 +1029,8 @@ static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 	do {
 		msleep(delay_us / 1000);
 		status = readq_be(&fc_regs[FC_MTIP_STATUS / 8]);
+		if (status == U64_MAX)
+			nretry /= 2;
 	} while ((status & FC_MTIP_STATUS_MASK) != FC_MTIP_STATUS_OFFLINE &&
 		 nretry--);
 
@@ -1104,15 +1141,15 @@ static const struct asyc_intr_info ainfo[] = {
 	{SISL_ASTATUS_FC0_LOGI_F, "login failed", 0, CLR_FC_ERROR},
 	{SISL_ASTATUS_FC0_LOGI_S, "login succeeded", 0, SCAN_HOST},
 	{SISL_ASTATUS_FC0_LINK_DN, "link down", 0, 0},
-	{SISL_ASTATUS_FC0_LINK_UP, "link up", 0, SCAN_HOST},
+	{SISL_ASTATUS_FC0_LINK_UP, "link up", 0, 0},
 	{SISL_ASTATUS_FC1_OTHER, "other error", 1, CLR_FC_ERROR | LINK_RESET},
 	{SISL_ASTATUS_FC1_LOGO, "target initiated LOGO", 1, 0},
 	{SISL_ASTATUS_FC1_CRC_T, "CRC threshold exceeded", 1, LINK_RESET},
-	{SISL_ASTATUS_FC1_LOGI_R, "login timed out, retrying", 1, 0},
+	{SISL_ASTATUS_FC1_LOGI_R, "login timed out, retrying", 1, LINK_RESET},
 	{SISL_ASTATUS_FC1_LOGI_F, "login failed", 1, CLR_FC_ERROR},
 	{SISL_ASTATUS_FC1_LOGI_S, "login succeeded", 1, SCAN_HOST},
 	{SISL_ASTATUS_FC1_LINK_DN, "link down", 1, 0},
-	{SISL_ASTATUS_FC1_LINK_UP, "link up", 1, SCAN_HOST},
+	{SISL_ASTATUS_FC1_LINK_UP, "link up", 1, 0},
 	{0x0, "", 0, 0}		/* terminator */
 };
 
@@ -1316,6 +1353,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 				__func__, port);
 			cfg->lr_state = LINK_RESET_REQUIRED;
 			cfg->lr_port = port;
+			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 
@@ -1336,6 +1374,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		if (info->action & SCAN_HOST) {
 			atomic_inc(&cfg->scan_host_needed);
+			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 	}
@@ -1731,6 +1770,7 @@ static int init_afu(struct cxlflash_cfg *cfg)
 		rc = -ENOMEM;
 		goto err1;
 	}
+	kref_init(&afu->mapcount);
 
 	/* No byte reverse on reading afu_version or string will be backwards */
 	reg = readq(&afu->afu_map->global.regs.afu_version);
@@ -1765,8 +1805,7 @@ out:
 	return rc;
 
 err2:
-	cxl_psa_unmap((void __iomem *)afu->afu_map);
-	afu->afu_map = NULL;
+	kref_put(&afu->mapcount, afu_unmap);
 err1:
 	term_mc(cfg, UNDO_START);
 	goto out;
@@ -1927,6 +1966,11 @@ retry:
  * cxlflash_eh_host_reset_handler() - reset the host adapter
  * @scp:	SCSI command from stack identifying host.
  *
+ * Following a reset, the state is evaluated again in case an EEH occurred
+ * during the reset. In such a scenario, the host reset will either yield
+ * until the EEH recovery is complete or return success or failure based
+ * upon the current device state.
+ *
  * Return:
  *	SUCCESS as defined in scsi/scsi.h
  *	FAILED as defined in scsi/scsi.h
@@ -1958,7 +2002,8 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 		} else
 			cfg->state = STATE_NORMAL;
 		wake_up_all(&cfg->reset_waitq);
-		break;
+		ssleep(1);
+		/* fall through */
 	case STATE_RESET:
 		wait_event(cfg->reset_waitq, cfg->state != STATE_RESET);
 		if (cfg->state == STATE_NORMAL)
@@ -2114,6 +2159,16 @@ static ssize_t lun_mode_store(struct device *dev,
 	rc = kstrtouint(buf, 10, &lun_mode);
 	if (!rc && (lun_mode < 5) && (lun_mode != afu->internal_lun)) {
 		afu->internal_lun = lun_mode;
+
+		/*
+		 * When configured for internal LUN, there is only one channel,
+		 * channel number 0, else there will be 2 (default).
+		 */
+		if (afu->internal_lun)
+			shost->max_channel = 0;
+		else
+			shost->max_channel = NUM_FC_PORTS - 1;
+
 		afu_reset(cfg);
 		scsi_scan_host(cfg->host);
 	}
@@ -2260,7 +2315,7 @@ static struct scsi_host_template driver_template = {
 	.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
 	.eh_host_reset_handler = cxlflash_eh_host_reset_handler,
 	.change_queue_depth = cxlflash_change_queue_depth,
-	.cmd_per_lun = 16,
+	.cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN,
 	.can_queue = CXLFLASH_MAX_CMDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,	/* No scatter gather support */
@@ -2274,6 +2329,7 @@ static struct scsi_host_template driver_template = {
  * Device dependent values
  */
 static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS };
+static struct dev_dependent_vals dev_flash_gt_vals = { CXLFLASH_MAX_SECTORS };
 
 /*
  * PCI device binding table
@@ -2281,6 +2337,8 @@ static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS };
 static struct pci_device_id cxlflash_pci_table[] = {
 	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CORSA,
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals},
+	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_FLASH_GT,
+	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_flash_gt_vals},
 	{}
 };
 
@@ -2339,6 +2397,7 @@ static void cxlflash_worker_thread(struct work_struct *work)
 
 	if (atomic_dec_if_positive(&cfg->scan_host_needed) >= 0)
 		scsi_scan_host(cfg->host);
+	kref_put(&afu->mapcount, afu_unmap);
 }
 
 /**
@@ -2485,6 +2544,9 @@ static void drain_ioctls(struct cxlflash_cfg *cfg)
  * @pdev:	PCI device struct.
  * @state:	PCI channel state.
  *
+ * When an EEH occurs during an active reset, wait until the reset is
+ * complete and then take action based upon the device state.
+ *
  * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT
  */
 static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
@@ -2498,6 +2560,10 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
 
 	switch (state) {
 	case pci_channel_io_frozen:
+		wait_event(cfg->reset_waitq, cfg->state != STATE_RESET);
+		if (cfg->state == STATE_FAILTERM)
+			return PCI_ERS_RESULT_DISCONNECT;
+
 		cfg->state = STATE_RESET;
 		scsi_block_requests(cfg->host);
 		drain_ioctls(cfg);
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index 60324566c14f..3d2d606fafb3 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -24,8 +24,8 @@
 #define CXLFLASH_ADAPTER_NAME	"IBM POWER CXL Flash Adapter"
 #define CXLFLASH_DRIVER_DATE	"(August 13, 2015)"
 
-#define PCI_DEVICE_ID_IBM_CORSA	0x04F0
-#define CXLFLASH_SUBS_DEV_ID	0x04F0
+#define PCI_DEVICE_ID_IBM_CORSA		0x04F0
+#define PCI_DEVICE_ID_IBM_FLASH_GT	0x0600
 
 /* Since there is only one target, make it 0 */
 #define CXLFLASH_TARGET		0
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index cac2e6a50efd..babe7ccc1777 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -1380,7 +1380,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	}
 
 	ctxid = cxl_process_element(ctx);
-	if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
+	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err2;
@@ -1508,7 +1508,7 @@ static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 	}
 
 	ctxid = cxl_process_element(ctx);
-	if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
+	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err1;
@@ -1590,6 +1590,13 @@ err1:
  * place at the same time and the failure was due to CXL services being
  * unable to keep up.
  *
+ * As this routine is called on ioctl context, it holds the ioctl r/w
+ * semaphore that is used to drain ioctls in recovery scenarios. The
+ * implementation to achieve the pacing described above (a local mutex)
+ * requires that the ioctl r/w semaphore be dropped and reacquired to
+ * avoid a 3-way deadlock when multiple process recoveries operate in
+ * parallel.
+ *
  * Because a user can detect an error condition before the kernel, it is
  * quite possible for this routine to act as the kernel's EEH detection
  * source (MMIO read of mbox_r). Because of this, there is a window of
@@ -1617,9 +1624,17 @@ static int cxlflash_afu_recover(struct scsi_device *sdev,
 	int rc = 0;
 
 	atomic_inc(&cfg->recovery_threads);
+	up_read(&cfg->ioctl_rwsem);
 	rc = mutex_lock_interruptible(mutex);
+	down_read(&cfg->ioctl_rwsem);
 	if (rc)
 		goto out;
+	rc = check_state(cfg);
+	if (rc) {
+		dev_err(dev, "%s: Failed state! rc=%d\n", __func__, rc);
+		rc = -ENODEV;
+		goto out;
+	}
 
 	dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
 		__func__, recover->reason, rctxid);
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index a53f583e2d7b..50f8e9300770 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -1008,6 +1008,8 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	virt->last_lba = last_lba;
 	virt->rsrc_handle = rsrc_handle;
 
+	if (lli->port_sel == BOTH_PORTS)
+		virt->hdr.return_flags |= DK_CXLFLASH_ALL_PORTS_ACTIVE;
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
diff --git a/drivers/scsi/device_handler/Kconfig b/drivers/scsi/device_handler/Kconfig
index e5647d59224f..0b331c9c0a8f 100644
--- a/drivers/scsi/device_handler/Kconfig
+++ b/drivers/scsi/device_handler/Kconfig
@@ -13,13 +13,13 @@ menuconfig SCSI_DH
 
 config SCSI_DH_RDAC
 	tristate "LSI RDAC Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a LSI RDAC select y. Otherwise, say N.
 
 config SCSI_DH_HP_SW
 	tristate "HP/COMPAQ MSA Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a HP/COMPAQ MSA device that requires START_STOP to
 	be sent to start it and cannot upgrade the firmware then select y.
@@ -27,13 +27,13 @@ config SCSI_DH_HP_SW
 
 config SCSI_DH_EMC
 	tristate "EMC CLARiiON Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a EMC CLARiiON select y. Otherwise, say N.
 
 config SCSI_DH_ALUA
 	tristate "SPC-3 ALUA Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	  SCSI Device handler for generic SPC-3 Asymmetric Logical Unit
 	  Access (ALUA).
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index ce129e595b55..5c935847599c 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -248,6 +248,7 @@ struct fnic {
 	struct completion *remove_wait; /* device remove thread blocks */
 
 	atomic_t in_flight;		/* io counter */
+	bool internal_reset_inprogress;
 	u32 _reserved;			/* fill hole */
 	unsigned long state_flags;	/* protected by host lock */
 	enum fnic_state state;
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 67669a9e73c1..f3a33312a9a6 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -954,8 +954,8 @@ int fnic_alloc_rq_frame(struct vnic_rq *rq)
 	skb_put(skb, len);
 	pa = pci_map_single(fnic->pdev, skb->data, len, PCI_DMA_FROMDEVICE);
 
-	r = pci_dma_mapping_error(fnic->pdev, pa);
-	if (r) {
+	if (pci_dma_mapping_error(fnic->pdev, pa)) {
+		r = -ENOMEM;
 		printk(KERN_ERR "PCI mapping failed with error %d\n", r);
 		goto free_skb;
 	}
@@ -1093,8 +1093,8 @@ static int fnic_send_frame(struct fnic *fnic, struct fc_frame *fp)
 
 	pa = pci_map_single(fnic->pdev, eth_hdr, tot_len, PCI_DMA_TODEVICE);
 
-	ret = pci_dma_mapping_error(fnic->pdev, pa);
-	if (ret) {
+	if (pci_dma_mapping_error(fnic->pdev, pa)) {
+		ret = -ENOMEM;
 		printk(KERN_ERR "DMA map failed with error %d\n", ret);
 		goto free_skb_on_err;
 	}
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 266b909fe854..82e4bc8c11c5 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -2533,6 +2533,19 @@ int fnic_host_reset(struct scsi_cmnd *sc)
 	unsigned long wait_host_tmo;
 	struct Scsi_Host *shost = sc->device->host;
 	struct fc_lport *lp = shost_priv(shost);
+	struct fnic *fnic = lport_priv(lp);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if (fnic->internal_reset_inprogress == 0) {
+		fnic->internal_reset_inprogress = 1;
+	} else {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+			"host reset in progress skipping another host reset\n");
+		return SUCCESS;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	/*
 	 * If fnic_reset is successful, wait for fabric login to complete
@@ -2553,6 +2566,9 @@ int fnic_host_reset(struct scsi_cmnd *sc)
 		}
 	}
 
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	fnic->internal_reset_inprogress = 0;
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 	return ret;
 }
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index a3860367b568..e9ce74afd13f 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3930,6 +3930,70 @@ static int hpsa_set_local_logical_count(struct ctlr_info *h,
 	return rc;
 }
 
+static bool hpsa_is_disk_spare(struct ctlr_info *h, u8 *lunaddrbytes)
+{
+	struct bmic_identify_physical_device *id_phys;
+	bool is_spare = false;
+	int rc;
+
+	id_phys = kzalloc(sizeof(*id_phys), GFP_KERNEL);
+	if (!id_phys)
+		return false;
+
+	rc = hpsa_bmic_id_physical_device(h,
+					lunaddrbytes,
+					GET_BMIC_DRIVE_NUMBER(lunaddrbytes),
+					id_phys, sizeof(*id_phys));
+	if (rc == 0)
+		is_spare = (id_phys->more_flags >> 6) & 0x01;
+
+	kfree(id_phys);
+	return is_spare;
+}
+
+#define RPL_DEV_FLAG_NON_DISK                           0x1
+#define RPL_DEV_FLAG_UNCONFIG_DISK_REPORTING_SUPPORTED  0x2
+#define RPL_DEV_FLAG_UNCONFIG_DISK                      0x4
+
+#define BMIC_DEVICE_TYPE_ENCLOSURE  6
+
+static bool hpsa_skip_device(struct ctlr_info *h, u8 *lunaddrbytes,
+				struct ext_report_lun_entry *rle)
+{
+	u8 device_flags;
+	u8 device_type;
+
+	if (!MASKED_DEVICE(lunaddrbytes))
+		return false;
+
+	device_flags = rle->device_flags;
+	device_type = rle->device_type;
+
+	if (device_flags & RPL_DEV_FLAG_NON_DISK) {
+		if (device_type == BMIC_DEVICE_TYPE_ENCLOSURE)
+			return false;
+		return true;
+	}
+
+	if (!(device_flags & RPL_DEV_FLAG_UNCONFIG_DISK_REPORTING_SUPPORTED))
+		return false;
+
+	if (device_flags & RPL_DEV_FLAG_UNCONFIG_DISK)
+		return false;
+
+	/*
+	 * Spares may be spun down, we do not want to
+	 * do an Inquiry to a RAID set spare drive as
+	 * that would have them spun up, that is a
+	 * performance hit because I/O to the RAID device
+	 * stops while the spin up occurs which can take
+	 * over 50 seconds.
+	 */
+	if (hpsa_is_disk_spare(h, lunaddrbytes))
+		return true;
+
+	return false;
+}
 
 static void hpsa_update_scsi_devices(struct ctlr_info *h)
 {
@@ -4023,6 +4087,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 		u8 *lunaddrbytes, is_OBDR = 0;
 		int rc = 0;
 		int phys_dev_index = i - (raid_ctlr_position == 0);
+		bool skip_device = false;
 
 		physical_device = i < nphysicals + (raid_ctlr_position == 0);
 
@@ -4030,10 +4095,15 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 		lunaddrbytes = figure_lunaddrbytes(h, raid_ctlr_position,
 			i, nphysicals, nlogicals, physdev_list, logdev_list);
 
-		/* skip masked non-disk devices */
-		if (MASKED_DEVICE(lunaddrbytes) && physical_device &&
-			(physdev_list->LUN[phys_dev_index].device_flags & 0x01))
-			continue;
+		/*
+		 * Skip over some devices such as a spare.
+		 */
+		if (!tmpdevice->external && physical_device) {
+			skip_device = hpsa_skip_device(h, lunaddrbytes,
+					&physdev_list->LUN[phys_dev_index]);
+			if (skip_device)
+				continue;
+		}
 
 		/* Get device type, vendor, model, device id */
 		rc = hpsa_update_device_info(h, lunaddrbytes, tmpdevice,
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 6aa317c303e2..1f9f9e5af207 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -717,7 +717,6 @@ static int ibmvfc_reset_crq(struct ibmvfc_host *vhost)
 	spin_lock_irqsave(vhost->host->host_lock, flags);
 	vhost->state = IBMVFC_NO_CRQ;
 	vhost->logged_in = 0;
-	ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_NONE);
 
 	/* Clean out the queue */
 	memset(crq->msgs, 0, PAGE_SIZE);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 536cd5a80422..7a58128a0000 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4003,13 +4003,17 @@ static ssize_t ipr_store_update_fw(struct device *dev,
 	struct ipr_sglist *sglist;
 	char fname[100];
 	char *src;
-	int len, result, dnld_size;
+	char *endline;
+	int result, dnld_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	len = snprintf(fname, 99, "%s", buf);
-	fname[len-1] = '\0';
+	snprintf(fname, sizeof(fname), "%s", buf);
+
+	endline = strchr(fname, '\n');
+	if (endline)
+		*endline = '\0';
 
 	if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) {
 		dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname);
@@ -10091,6 +10095,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 		ioa_cfg->intr_flag = IPR_USE_MSI;
 	else {
 		ioa_cfg->intr_flag = IPR_USE_LSI;
+		ioa_cfg->clear_isr = 1;
 		ioa_cfg->nvectors = 1;
 		dev_info(&pdev->dev, "Cannot enable MSI.\n");
 	}
diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c
index 1910100638a2..00602abec0ea 100644
--- a/drivers/scsi/isci/remote_node_context.c
+++ b/drivers/scsi/isci/remote_node_context.c
@@ -66,6 +66,9 @@ const char *rnc_state_name(enum scis_sds_remote_node_context_states state)
 {
 	static const char * const strings[] = RNC_STATES;
 
+	if (state >= ARRAY_SIZE(strings))
+		return "UNKNOWN";
+
 	return strings[state];
 }
 #undef C
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 6bffd91b973a..c1ccf1ee99ea 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -560,8 +560,12 @@ static void iscsi_complete_task(struct iscsi_task *task, int state)
 	WARN_ON_ONCE(task->state == ISCSI_TASK_FREE);
 	task->state = state;
 
-	if (!list_empty(&task->running))
+	spin_lock_bh(&conn->taskqueuelock);
+	if (!list_empty(&task->running)) {
+		pr_debug_once("%s while task on list", __func__);
 		list_del_init(&task->running);
+	}
+	spin_unlock_bh(&conn->taskqueuelock);
 
 	if (conn->task == task)
 		conn->task = NULL;
@@ -783,7 +787,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 		if (session->tt->xmit_task(task))
 			goto free_task;
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->mgmtqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -1474,8 +1480,10 @@ void iscsi_requeue_task(struct iscsi_task *task)
 	 * this may be on the requeue list already if the xmit_task callout
 	 * is handling the r2ts while we are adding new ones
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 	if (list_empty(&task->running))
 		list_add_tail(&task->running, &conn->requeue);
+	spin_unlock_bh(&conn->taskqueuelock);
 	iscsi_conn_queue_work(conn);
 }
 EXPORT_SYMBOL_GPL(iscsi_requeue_task);
@@ -1512,22 +1520,26 @@ static int iscsi_data_xmit(struct iscsi_conn *conn)
 	 * only have one nop-out as a ping from us and targets should not
 	 * overflow us with nop-ins
 	 */
+	spin_lock_bh(&conn->taskqueuelock);
 check_mgmt:
 	while (!list_empty(&conn->mgmtqueue)) {
 		conn->task = list_entry(conn->mgmtqueue.next,
 					 struct iscsi_task, running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (iscsi_prep_mgmt_task(conn, conn->task)) {
 			/* regular RX path uses back_lock */
 			spin_lock_bh(&conn->session->back_lock);
 			__iscsi_put_task(conn->task);
 			spin_unlock_bh(&conn->session->back_lock);
 			conn->task = NULL;
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 	}
 
 	/* process pending command queue */
@@ -1535,19 +1547,24 @@ check_mgmt:
 		conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task,
 					running);
 		list_del_init(&conn->task->running);
+		spin_unlock_bh(&conn->taskqueuelock);
 		if (conn->session->state == ISCSI_STATE_LOGGING_OUT) {
 			fail_scsi_task(conn->task, DID_IMM_RETRY);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_prep_scsi_cmd_pdu(conn->task);
 		if (rc) {
 			if (rc == -ENOMEM || rc == -EACCES) {
+				spin_lock_bh(&conn->taskqueuelock);
 				list_add_tail(&conn->task->running,
 					      &conn->cmdqueue);
 				conn->task = NULL;
+				spin_unlock_bh(&conn->taskqueuelock);
 				goto done;
 			} else
 				fail_scsi_task(conn->task, DID_ABORT);
+			spin_lock_bh(&conn->taskqueuelock);
 			continue;
 		}
 		rc = iscsi_xmit_task(conn);
@@ -1558,6 +1575,7 @@ check_mgmt:
 		 * we need to check the mgmt queue for nops that need to
 		 * be sent to aviod starvation
 		 */
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
@@ -1577,12 +1595,15 @@ check_mgmt:
 		conn->task = task;
 		list_del_init(&conn->task->running);
 		conn->task->state = ISCSI_TASK_RUNNING;
+		spin_unlock_bh(&conn->taskqueuelock);
 		rc = iscsi_xmit_task(conn);
 		if (rc)
 			goto done;
+		spin_lock_bh(&conn->taskqueuelock);
 		if (!list_empty(&conn->mgmtqueue))
 			goto check_mgmt;
 	}
+	spin_unlock_bh(&conn->taskqueuelock);
 	spin_unlock_bh(&conn->session->frwd_lock);
 	return -ENODATA;
 
@@ -1738,7 +1759,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 			goto prepd_reject;
 		}
 	} else {
+		spin_lock_bh(&conn->taskqueuelock);
 		list_add_tail(&task->running, &conn->cmdqueue);
+		spin_unlock_bh(&conn->taskqueuelock);
 		iscsi_conn_queue_work(conn);
 	}
 
@@ -2900,6 +2923,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	INIT_LIST_HEAD(&conn->mgmtqueue);
 	INIT_LIST_HEAD(&conn->cmdqueue);
 	INIT_LIST_HEAD(&conn->requeue);
+	spin_lock_init(&conn->taskqueuelock);
 	INIT_WORK(&conn->xmitwork, iscsi_xmitworker);
 
 	/* allocate login_task used for the login/text sequences */
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 9c706d8c1441..6f5e2720ffad 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -218,7 +218,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		task->num_scatter = qc->n_elem;
 	} else {
 		for_each_sg(qc->sg, sg, qc->n_elem, si)
-			xfer += sg->length;
+			xfer += sg_dma_len(sg);
 
 		task->total_xfer_len = xfer;
 		task->num_scatter = si;
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index b0e6fe46448d..80d3c740a8a8 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -72,6 +72,7 @@ void lpfc_cancel_all_vport_retry_delay_timer(struct lpfc_hba *);
 void lpfc_retry_pport_discovery(struct lpfc_hba *);
 void lpfc_release_rpi(struct lpfc_hba *, struct lpfc_vport *, uint16_t);
 
+void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index b6fa257ea3e0..c74f74ab981c 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -455,9 +455,9 @@ int
 lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 {
 	struct lpfc_hba  *phba = vport->phba;
-	LPFC_MBOXQ_t *mboxq;
+	LPFC_MBOXQ_t *mboxq = NULL;
 	struct lpfc_nodelist *ndlp;
-	struct lpfc_dmabuf *dmabuf;
+	struct lpfc_dmabuf *dmabuf = NULL;
 	int rc = 0;
 
 	/* move forward in case of SLI4 FC port loopback test and pt2pt mode */
@@ -471,25 +471,33 @@ lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 		}
 	}
 
-	dmabuf = kzalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-	if (!dmabuf) {
+	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mboxq) {
 		rc = -ENOMEM;
 		goto fail;
 	}
-	dmabuf->virt = lpfc_mbuf_alloc(phba, MEM_PRI, &dmabuf->phys);
-	if (!dmabuf->virt) {
-		rc = -ENOMEM;
-		goto fail_free_dmabuf;
-	}
 
-	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-	if (!mboxq) {
-		rc = -ENOMEM;
-		goto fail_free_coherent;
+	/* Supply CSP's only if we are fabric connect or pt-to-pt connect */
+	if ((vport->fc_flag & FC_FABRIC) || (vport->fc_flag & FC_PT2PT)) {
+		dmabuf = kzalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+		if (!dmabuf) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+		dmabuf->virt = lpfc_mbuf_alloc(phba, MEM_PRI, &dmabuf->phys);
+		if (!dmabuf->virt) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+		memcpy(dmabuf->virt, &phba->fc_fabparam,
+		       sizeof(struct serv_parm));
 	}
+
 	vport->port_state = LPFC_FABRIC_CFG_LINK;
-	memcpy(dmabuf->virt, &phba->fc_fabparam, sizeof(vport->fc_sparam));
-	lpfc_reg_vfi(mboxq, vport, dmabuf->phys);
+	if (dmabuf)
+		lpfc_reg_vfi(mboxq, vport, dmabuf->phys);
+	else
+		lpfc_reg_vfi(mboxq, vport, 0);
 
 	mboxq->mbox_cmpl = lpfc_mbx_cmpl_reg_vfi;
 	mboxq->vport = vport;
@@ -497,17 +505,19 @@ lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_NOWAIT);
 	if (rc == MBX_NOT_FINISHED) {
 		rc = -ENXIO;
-		goto fail_free_mbox;
+		goto fail;
 	}
 	return 0;
 
-fail_free_mbox:
-	mempool_free(mboxq, phba->mbox_mem_pool);
-fail_free_coherent:
-	lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
-fail_free_dmabuf:
-	kfree(dmabuf);
 fail:
+	if (mboxq)
+		mempool_free(mboxq, phba->mbox_mem_pool);
+	if (dmabuf) {
+		if (dmabuf->virt)
+			lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
+		kfree(dmabuf);
+	}
+
 	lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
 		"0289 Issue Register VFI failed: Err %d\n", rc);
@@ -711,9 +721,10 @@ lpfc_cmpl_els_flogi_fabric(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * For FC we need to do some special processing because of the SLI
 	 * Port's default settings of the Common Service Parameters.
 	 */
-	if (phba->sli4_hba.lnk_info.lnk_tp == LPFC_LNK_TYPE_FC) {
+	if ((phba->sli_rev == LPFC_SLI_REV4) &&
+	    (phba->sli4_hba.lnk_info.lnk_tp == LPFC_LNK_TYPE_FC)) {
 		/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
-		if ((phba->sli_rev == LPFC_SLI_REV4) && fabric_param_changed)
+		if (fabric_param_changed)
 			lpfc_unregister_fcf_prep(phba);
 
 		/* This should just update the VFI CSPs*/
@@ -824,13 +835,21 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	spin_lock_irq(shost->host_lock);
 	vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+	vport->fc_flag |= FC_PT2PT;
 	spin_unlock_irq(shost->host_lock);
 
-	phba->fc_edtov = FF_DEF_EDTOV;
-	phba->fc_ratov = FF_DEF_RATOV;
+	/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
+	if ((phba->sli_rev == LPFC_SLI_REV4) && phba->fc_topology_changed) {
+		lpfc_unregister_fcf_prep(phba);
+
+		spin_lock_irq(shost->host_lock);
+		vport->fc_flag &= ~FC_VFI_REGISTERED;
+		spin_unlock_irq(shost->host_lock);
+		phba->fc_topology_changed = 0;
+	}
+
 	rc = memcmp(&vport->fc_portname, &sp->portName,
 		    sizeof(vport->fc_portname));
-	memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
 
 	if (rc >= 0) {
 		/* This side will initiate the PLOGI */
@@ -839,38 +858,14 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		spin_unlock_irq(shost->host_lock);
 
 		/*
-		 * N_Port ID cannot be 0, set our to LocalID the other
-		 * side will be RemoteID.
+		 * N_Port ID cannot be 0, set our Id to LocalID
+		 * the other side will be RemoteID.
 		 */
 
 		/* not equal */
 		if (rc)
 			vport->fc_myDID = PT2PT_LocalID;
 
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!mbox)
-			goto fail;
-
-		lpfc_config_link(phba, mbox);
-
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto fail;
-		}
-
-		/*
-		 * For SLI4, the VFI/VPI are registered AFTER the
-		 * Nport with the higher WWPN sends the PLOGI with
-		 * an assigned NPortId.
-		 */
-
-		/* not equal */
-		if ((phba->sli_rev == LPFC_SLI_REV4) && rc)
-			lpfc_issue_reg_vfi(vport);
-
 		/* Decrement ndlp reference count indicating that ndlp can be
 		 * safely released when other references to it are done.
 		 */
@@ -912,29 +907,20 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* If we are pt2pt with another NPort, force NPIV off! */
 	phba->sli3_options &= ~LPFC_SLI3_NPIV_ENABLED;
 
-	spin_lock_irq(shost->host_lock);
-	vport->fc_flag |= FC_PT2PT;
-	spin_unlock_irq(shost->host_lock);
-	/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
-	if ((phba->sli_rev == LPFC_SLI_REV4) && phba->fc_topology_changed) {
-		lpfc_unregister_fcf_prep(phba);
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		goto fail;
 
-		/* The FC_VFI_REGISTERED flag will get clear in the cmpl
-		 * handler for unreg_vfi, but if we don't force the
-		 * FC_VFI_REGISTERED flag then the reg_vfi mailbox could be
-		 * built with the update bit set instead of just the vp bit to
-		 * change the Nport ID.  We need to have the vp set and the
-		 * Upd cleared on topology changes.
-		 */
-		spin_lock_irq(shost->host_lock);
-		vport->fc_flag &= ~FC_VFI_REGISTERED;
-		spin_unlock_irq(shost->host_lock);
-		phba->fc_topology_changed = 0;
-		lpfc_issue_reg_vfi(vport);
+	lpfc_config_link(phba, mbox);
+
+	mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+	mbox->vport = vport;
+	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+	if (rc == MBX_NOT_FINISHED) {
+		mempool_free(mbox, phba->mbox_mem_pool);
+		goto fail;
 	}
 
-	/* Start discovery - this should just do CLEAR_LA */
-	lpfc_disc_start(vport);
 	return 0;
 fail:
 	return -ENXIO;
@@ -1068,7 +1054,10 @@ stop_rr_fcf_flogi:
 					lpfc_sli4_unreg_all_rpis(vport);
 				}
 			}
-			lpfc_issue_reg_vfi(vport);
+
+			/* Do not register VFI if the driver aborted FLOGI */
+			if (!lpfc_error_lost_link(irsp))
+				lpfc_issue_reg_vfi(vport);
 			lpfc_nlp_put(ndlp);
 			goto out;
 		}
@@ -1157,6 +1146,7 @@ flogifail:
 	spin_lock_irq(&phba->hbalock);
 	phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 	spin_unlock_irq(&phba->hbalock);
+
 	lpfc_nlp_put(ndlp);
 
 	if (!lpfc_error_lost_link(irsp)) {
@@ -3576,12 +3566,14 @@ lpfc_els_free_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *elsiocb)
 		} else {
 			buf_ptr1 = (struct lpfc_dmabuf *) elsiocb->context2;
 			lpfc_els_free_data(phba, buf_ptr1);
+			elsiocb->context2 = NULL;
 		}
 	}
 
 	if (elsiocb->context3) {
 		buf_ptr = (struct lpfc_dmabuf *) elsiocb->context3;
 		lpfc_els_free_bpl(phba, buf_ptr);
+		elsiocb->context3 = NULL;
 	}
 	lpfc_sli_release_iocbq(phba, elsiocb);
 	return 0;
@@ -3792,14 +3784,17 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				lpfc_nlp_set_state(vport, ndlp,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			}
+
+			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
 			if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT)
 			    != MBX_NOT_FINISHED)
 				goto out;
-			else
-				/* Decrement the ndlp reference count we
-				 * set for this failed mailbox command.
-				 */
-				lpfc_nlp_put(ndlp);
+
+			/* Decrement the ndlp reference count we
+			 * set for this failed mailbox command.
+			 */
+			lpfc_nlp_put(ndlp);
+			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
 
 			/* ELS rsp: Cannot issue reg_login for <NPortid> */
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
@@ -3856,6 +3851,7 @@ out:
 				 * the routine lpfc_els_free_iocb.
 				 */
 				cmdiocb->context1 = NULL;
+
 	}
 
 	lpfc_els_free_iocb(phba, cmdiocb);
@@ -3898,6 +3894,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	IOCB_t *oldcmd;
 	struct lpfc_iocbq *elsiocb;
 	uint8_t *pcmd;
+	struct serv_parm *sp;
 	uint16_t cmdsize;
 	int rc;
 	ELS_PKT *els_pkt_ptr;
@@ -3927,6 +3924,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 			"Issue ACC:       did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
+	case ELS_CMD_FLOGI:
 	case ELS_CMD_PLOGI:
 		cmdsize = (sizeof(struct serv_parm) + sizeof(uint32_t));
 		elsiocb = lpfc_prep_els_iocb(vport, 0, cmdsize, oldiocb->retry,
@@ -3944,10 +3942,34 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 
 		*((uint32_t *) (pcmd)) = ELS_CMD_ACC;
 		pcmd += sizeof(uint32_t);
-		memcpy(pcmd, &vport->fc_sparam, sizeof(struct serv_parm));
+		sp = (struct serv_parm *)pcmd;
+
+		if (flag == ELS_CMD_FLOGI) {
+			/* Copy the received service parameters back */
+			memcpy(sp, &phba->fc_fabparam,
+			       sizeof(struct serv_parm));
+
+			/* Clear the F_Port bit */
+			sp->cmn.fPort = 0;
+
+			/* Mark all class service parameters as invalid */
+			sp->cls1.classValid = 0;
+			sp->cls2.classValid = 0;
+			sp->cls3.classValid = 0;
+			sp->cls4.classValid = 0;
+
+			/* Copy our worldwide names */
+			memcpy(&sp->portName, &vport->fc_sparam.portName,
+			       sizeof(struct lpfc_name));
+			memcpy(&sp->nodeName, &vport->fc_sparam.nodeName,
+			       sizeof(struct lpfc_name));
+		} else {
+			memcpy(pcmd, &vport->fc_sparam,
+			       sizeof(struct serv_parm));
+		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC PLOGI: did:x%x flg:x%x",
+			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_PRLO:
@@ -4681,28 +4703,25 @@ lpfc_rdp_res_speed(struct fc_rdp_port_speed_desc *desc, struct lpfc_hba *phba)
 
 	desc->tag = cpu_to_be32(RDP_PORT_SPEED_DESC_TAG);
 
-	switch (phba->sli4_hba.link_state.speed) {
-	case LPFC_FC_LA_SPEED_1G:
+	switch (phba->fc_linkspeed) {
+	case LPFC_LINK_SPEED_1GHZ:
 		rdp_speed = RDP_PS_1GB;
 		break;
-	case LPFC_FC_LA_SPEED_2G:
+	case LPFC_LINK_SPEED_2GHZ:
 		rdp_speed = RDP_PS_2GB;
 		break;
-	case LPFC_FC_LA_SPEED_4G:
+	case LPFC_LINK_SPEED_4GHZ:
 		rdp_speed = RDP_PS_4GB;
 		break;
-	case LPFC_FC_LA_SPEED_8G:
+	case LPFC_LINK_SPEED_8GHZ:
 		rdp_speed = RDP_PS_8GB;
 		break;
-	case LPFC_FC_LA_SPEED_10G:
+	case LPFC_LINK_SPEED_10GHZ:
 		rdp_speed = RDP_PS_10GB;
 		break;
-	case LPFC_FC_LA_SPEED_16G:
+	case LPFC_LINK_SPEED_16GHZ:
 		rdp_speed = RDP_PS_16GB;
 		break;
-	case LPFC_FC_LA_SPEED_32G:
-		rdp_speed = RDP_PS_32GB;
-		break;
 	default:
 		rdp_speed = RDP_PS_UNKNOWN;
 		break;
@@ -5739,7 +5758,6 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	IOCB_t *icmd = &cmdiocb->iocb;
 	struct serv_parm *sp;
 	LPFC_MBOXQ_t *mbox;
-	struct ls_rjt stat;
 	uint32_t cmd, did;
 	int rc;
 	uint32_t fc_flag = 0;
@@ -5765,135 +5783,92 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		return 1;
 	}
 
-	if ((lpfc_check_sparm(vport, ndlp, sp, CLASS3, 1))) {
-		/* For a FLOGI we accept, then if our portname is greater
-		 * then the remote portname we initiate Nport login.
-		 */
+	(void) lpfc_check_sparm(vport, ndlp, sp, CLASS3, 1);
 
-		rc = memcmp(&vport->fc_portname, &sp->portName,
-			    sizeof(struct lpfc_name));
 
-		if (!rc) {
-			if (phba->sli_rev < LPFC_SLI_REV4) {
-				mbox = mempool_alloc(phba->mbox_mem_pool,
-						     GFP_KERNEL);
-				if (!mbox)
-					return 1;
-				lpfc_linkdown(phba);
-				lpfc_init_link(phba, mbox,
-					       phba->cfg_topology,
-					       phba->cfg_link_speed);
-				mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0;
-				mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-				mbox->vport = vport;
-				rc = lpfc_sli_issue_mbox(phba, mbox,
-							 MBX_NOWAIT);
-				lpfc_set_loopback_flag(phba);
-				if (rc == MBX_NOT_FINISHED)
-					mempool_free(mbox, phba->mbox_mem_pool);
-				return 1;
-			} else {
-				/* abort the flogi coming back to ourselves
-				 * due to external loopback on the port.
-				 */
-				lpfc_els_abort_flogi(phba);
-				return 0;
-			}
-		} else if (rc > 0) {	/* greater than */
-			spin_lock_irq(shost->host_lock);
-			vport->fc_flag |= FC_PT2PT_PLOGI;
-			spin_unlock_irq(shost->host_lock);
+	/*
+	 * If our portname is greater than the remote portname,
+	 * then we initiate Nport login.
+	 */
 
-			/* If we have the high WWPN we can assign our own
-			 * myDID; otherwise, we have to WAIT for a PLOGI
-			 * from the remote NPort to find out what it
-			 * will be.
-			 */
-			vport->fc_myDID = PT2PT_LocalID;
-		} else
-			vport->fc_myDID = PT2PT_RemoteID;
+	rc = memcmp(&vport->fc_portname, &sp->portName,
+		    sizeof(struct lpfc_name));
 
-		/*
-		 * The vport state should go to LPFC_FLOGI only
-		 * AFTER we issue a FLOGI, not receive one.
+	if (!rc) {
+		if (phba->sli_rev < LPFC_SLI_REV4) {
+			mbox = mempool_alloc(phba->mbox_mem_pool,
+					     GFP_KERNEL);
+			if (!mbox)
+				return 1;
+			lpfc_linkdown(phba);
+			lpfc_init_link(phba, mbox,
+				       phba->cfg_topology,
+				       phba->cfg_link_speed);
+			mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0;
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox,
+						 MBX_NOWAIT);
+			lpfc_set_loopback_flag(phba);
+			if (rc == MBX_NOT_FINISHED)
+				mempool_free(mbox, phba->mbox_mem_pool);
+			return 1;
+		}
+
+		/* abort the flogi coming back to ourselves
+		 * due to external loopback on the port.
 		 */
+		lpfc_els_abort_flogi(phba);
+		return 0;
+
+	} else if (rc > 0) {	/* greater than */
 		spin_lock_irq(shost->host_lock);
-		fc_flag = vport->fc_flag;
-		port_state = vport->port_state;
-		vport->fc_flag |= FC_PT2PT;
-		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+		vport->fc_flag |= FC_PT2PT_PLOGI;
 		spin_unlock_irq(shost->host_lock);
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-				 "3311 Rcv Flogi PS x%x new PS x%x "
-				 "fc_flag x%x new fc_flag x%x\n",
-				 port_state, vport->port_state,
-				 fc_flag, vport->fc_flag);
 
-		/*
-		 * We temporarily set fc_myDID to make it look like we are
-		 * a Fabric. This is done just so we end up with the right
-		 * did / sid on the FLOGI ACC rsp.
+		/* If we have the high WWPN we can assign our own
+		 * myDID; otherwise, we have to WAIT for a PLOGI
+		 * from the remote NPort to find out what it
+		 * will be.
 		 */
-		did = vport->fc_myDID;
-		vport->fc_myDID = Fabric_DID;
-
+		vport->fc_myDID = PT2PT_LocalID;
 	} else {
-		/* Reject this request because invalid parameters */
-		stat.un.b.lsRjtRsvd0 = 0;
-		stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
-		stat.un.b.lsRjtRsnCodeExp = LSEXP_SPARM_OPTIONS;
-		stat.un.b.vendorUnique = 0;
-
-		/*
-		 * We temporarily set fc_myDID to make it look like we are
-		 * a Fabric. This is done just so we end up with the right
-		 * did / sid on the FLOGI LS_RJT rsp.
-		 */
-		did = vport->fc_myDID;
-		vport->fc_myDID = Fabric_DID;
-
-		lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp,
-			NULL);
+		vport->fc_myDID = PT2PT_RemoteID;
+	}
 
-		/* Now lets put fc_myDID back to what its supposed to be */
-		vport->fc_myDID = did;
+	/*
+	 * The vport state should go to LPFC_FLOGI only
+	 * AFTER we issue a FLOGI, not receive one.
+	 */
+	spin_lock_irq(shost->host_lock);
+	fc_flag = vport->fc_flag;
+	port_state = vport->port_state;
+	vport->fc_flag |= FC_PT2PT;
+	vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+	spin_unlock_irq(shost->host_lock);
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+			 "3311 Rcv Flogi PS x%x new PS x%x "
+			 "fc_flag x%x new fc_flag x%x\n",
+			 port_state, vport->port_state,
+			 fc_flag, vport->fc_flag);
 
-		return 1;
-	}
+	/*
+	 * We temporarily set fc_myDID to make it look like we are
+	 * a Fabric. This is done just so we end up with the right
+	 * did / sid on the FLOGI ACC rsp.
+	 */
+	did = vport->fc_myDID;
+	vport->fc_myDID = Fabric_DID;
 
-	/* send our FLOGI first */
-	if (vport->port_state < LPFC_FLOGI) {
-		vport->fc_myDID = 0;
-		lpfc_initial_flogi(vport);
-		vport->fc_myDID = Fabric_DID;
-	}
+	memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
 
 	/* Send back ACC */
-	lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, NULL);
+	lpfc_els_rsp_acc(vport, ELS_CMD_FLOGI, cmdiocb, ndlp, NULL);
 
 	/* Now lets put fc_myDID back to what its supposed to be */
 	vport->fc_myDID = did;
 
-	if (!(vport->fc_flag & FC_PT2PT_PLOGI)) {
-
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!mbox)
-			goto fail;
-
-		lpfc_config_link(phba, mbox);
-
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto fail;
-		}
-	}
-
 	return 0;
-fail:
-	return 1;
 }
 
 /**
@@ -7345,7 +7320,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	/* reject till our FLOGI completes */
 	if ((vport->port_state < LPFC_FABRIC_CFG_LINK) &&
-		(cmd != ELS_CMD_FLOGI)) {
+	    (cmd != ELS_CMD_FLOGI)) {
 		rjt_err = LSRJT_UNABLE_TPC;
 		rjt_exp = LSEXP_NOTHING_MORE;
 		goto lsrjt;
@@ -7381,6 +7356,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			rjt_exp = LSEXP_NOTHING_MORE;
 			break;
 		}
+
 		if (vport->port_state < LPFC_DISC_AUTH) {
 			if (!(phba->pport->fc_flag & FC_PT2PT) ||
 				(phba->pport->fc_flag & FC_PT2PT_PLOGI)) {
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index bfc2442dd74a..d3668aa555d5 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1083,7 +1083,7 @@ out:
 }
 
 
-static void
+void
 lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport *vport = pmb->vport;
@@ -1113,8 +1113,10 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	/* Start discovery by sending a FLOGI. port_state is identically
 	 * LPFC_FLOGI while waiting for FLOGI cmpl
 	 */
-	if (vport->port_state != LPFC_FLOGI || vport->fc_flag & FC_PT2PT_PLOGI)
+	if (vport->port_state != LPFC_FLOGI)
 		lpfc_initial_flogi(vport);
+	else if (vport->fc_flag & FC_PT2PT)
+		lpfc_disc_start(vport);
 	return;
 
 out:
@@ -2963,8 +2965,10 @@ lpfc_mbx_cmpl_reg_vfi(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 
 out_free_mem:
 	mempool_free(mboxq, phba->mbox_mem_pool);
-	lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
-	kfree(dmabuf);
+	if (dmabuf) {
+		lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
+		kfree(dmabuf);
+	}
 	return;
 }
 
@@ -3448,10 +3452,10 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
 		spin_unlock_irq(shost->host_lock);
-	} else
-		/* Good status, call state machine */
-		lpfc_disc_state_machine(vport, ndlp, pmb,
-				NLP_EVT_CMPL_REG_LOGIN);
+	}
+
+	/* Call state machine */
+	lpfc_disc_state_machine(vport, ndlp, pmb, NLP_EVT_CMPL_REG_LOGIN);
 
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 	kfree(mp);
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 33ec4fa39ccb..f224cdb2fce4 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1182,6 +1182,7 @@ struct lpfc_mbx_wq_create {
 #define lpfc_mbx_wq_create_page_size_SHIFT	0
 #define lpfc_mbx_wq_create_page_size_MASK	0x000000FF
 #define lpfc_mbx_wq_create_page_size_WORD	word1
+#define LPFC_WQ_PAGE_SIZE_4096	0x1
 #define lpfc_mbx_wq_create_wqe_size_SHIFT	8
 #define lpfc_mbx_wq_create_wqe_size_MASK	0x0000000F
 #define lpfc_mbx_wq_create_wqe_size_WORD	word1
@@ -1253,6 +1254,7 @@ struct rq_context {
 #define lpfc_rq_context_page_size_SHIFT	0		/* Version 1 Only */
 #define lpfc_rq_context_page_size_MASK	0x000000FF
 #define lpfc_rq_context_page_size_WORD	word0
+#define	LPFC_RQ_PAGE_SIZE_4096	0x1
 	uint32_t reserved1;
 	uint32_t word2;
 #define lpfc_rq_context_cq_id_SHIFT	16
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index db9446c612da..60c21093f865 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -2855,7 +2855,7 @@ lpfc_online(struct lpfc_hba *phba)
 	}
 
 	vports = lpfc_create_vport_work_array(phba);
-	if (vports != NULL)
+	if (vports != NULL) {
 		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 			struct Scsi_Host *shost;
 			shost = lpfc_shost_from_vport(vports[i]);
@@ -2872,7 +2872,8 @@ lpfc_online(struct lpfc_hba *phba)
 			}
 			spin_unlock_irq(shost->host_lock);
 		}
-		lpfc_destroy_vport_work_array(phba, vports);
+	}
+	lpfc_destroy_vport_work_array(phba, vports);
 
 	lpfc_unblock_mgmt_io(phba);
 	return 0;
@@ -8833,9 +8834,12 @@ found:
 				 * already mapped to this phys_id.
 				 */
 				if (cpup->irq != LPFC_VECTOR_MAP_EMPTY) {
-					chann[saved_chann] =
-						cpup->channel_id;
-					saved_chann++;
+					if (saved_chann <=
+					    LPFC_FCP_IO_CHAN_MAX) {
+						chann[saved_chann] =
+							cpup->channel_id;
+						saved_chann++;
+					}
 					goto out;
 				}
 
@@ -11383,6 +11387,7 @@ static struct pci_driver lpfc_driver = {
 	.id_table	= lpfc_id_table,
 	.probe		= lpfc_pci_probe_one,
 	.remove		= lpfc_pci_remove_one,
+	.shutdown	= lpfc_pci_remove_one,
 	.suspend        = lpfc_pci_suspend_one,
 	.resume		= lpfc_pci_resume_one,
 	.err_handler    = &lpfc_err_handler,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index f87f90e9b7df..1e34b5408a29 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2145,10 +2145,12 @@ lpfc_reg_vfi(struct lpfcMboxq *mbox, struct lpfc_vport *vport, dma_addr_t phys)
 	reg_vfi->wwn[1] = cpu_to_le32(reg_vfi->wwn[1]);
 	reg_vfi->e_d_tov = phba->fc_edtov;
 	reg_vfi->r_a_tov = phba->fc_ratov;
-	reg_vfi->bde.addrHigh = putPaddrHigh(phys);
-	reg_vfi->bde.addrLow = putPaddrLow(phys);
-	reg_vfi->bde.tus.f.bdeSize = sizeof(vport->fc_sparam);
-	reg_vfi->bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	if (phys) {
+		reg_vfi->bde.addrHigh = putPaddrHigh(phys);
+		reg_vfi->bde.addrLow = putPaddrLow(phys);
+		reg_vfi->bde.tus.f.bdeSize = sizeof(vport->fc_sparam);
+		reg_vfi->bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	}
 	bf_set(lpfc_reg_vfi_nport_id, reg_vfi, vport->fc_myDID);
 
 	/* Only FC supports upd bit */
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index ed9a2c80c4aa..193733e8c823 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -280,38 +280,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint32_t *lp;
 	IOCB_t *icmd;
 	struct serv_parm *sp;
+	uint32_t ed_tov;
 	LPFC_MBOXQ_t *mbox;
 	struct ls_rjt stat;
 	int rc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
-	if (vport->port_state <= LPFC_FDISC) {
-		/* Before responding to PLOGI, check for pt2pt mode.
-		 * If we are pt2pt, with an outstanding FLOGI, abort
-		 * the FLOGI and resend it first.
-		 */
-		if (vport->fc_flag & FC_PT2PT) {
-			 lpfc_els_abort_flogi(phba);
-		        if (!(vport->fc_flag & FC_PT2PT_PLOGI)) {
-				/* If the other side is supposed to initiate
-				 * the PLOGI anyway, just ACC it now and
-				 * move on with discovery.
-				 */
-				phba->fc_edtov = FF_DEF_EDTOV;
-				phba->fc_ratov = FF_DEF_RATOV;
-				/* Start discovery - this should just do
-				   CLEAR_LA */
-				lpfc_disc_start(vport);
-			} else
-				lpfc_initial_flogi(vport);
-		} else {
-			stat.un.b.lsRjtRsnCode = LSRJT_LOGICAL_BSY;
-			stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
-			lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
-					    ndlp, NULL);
-			return 0;
-		}
-	}
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
 	lp = (uint32_t *) pcmd->virt;
 	sp = (struct serv_parm *) ((uint8_t *) lp + sizeof (uint32_t));
@@ -404,30 +378,46 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* Check for Nport to NPort pt2pt protocol */
 	if ((vport->fc_flag & FC_PT2PT) &&
 	    !(vport->fc_flag & FC_PT2PT_PLOGI)) {
-
 		/* rcv'ed PLOGI decides what our NPortId will be */
 		vport->fc_myDID = icmd->un.rcvels.parmRo;
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (mbox == NULL)
-			goto out;
-		lpfc_config_link(phba, mbox);
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto out;
+
+		ed_tov = be32_to_cpu(sp->cmn.e_d_tov);
+		if (sp->cmn.edtovResolution) {
+			/* E_D_TOV ticks are in nanoseconds */
+			ed_tov = (phba->fc_edtov + 999999) / 1000000;
 		}
+
 		/*
-		 * For SLI4, the VFI/VPI are registered AFTER the
-		 * Nport with the higher WWPN sends us a PLOGI with
-		 * our assigned NPortId.
+		 * For pt-to-pt, use the larger EDTOV
+		 * RATOV = 2 * EDTOV
 		 */
+		if (ed_tov > phba->fc_edtov)
+			phba->fc_edtov = ed_tov;
+		phba->fc_ratov = (2 * phba->fc_edtov) / 1000;
+
+		memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
+
+		/* Issue config_link / reg_vfi to account for updated TOV's */
+
 		if (phba->sli_rev == LPFC_SLI_REV4)
 			lpfc_issue_reg_vfi(vport);
+		else {
+			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+			if (mbox == NULL)
+				goto out;
+			lpfc_config_link(phba, mbox);
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				mempool_free(mbox, phba->mbox_mem_pool);
+				goto out;
+			}
+		}
 
 		lpfc_can_disctmo(vport);
 	}
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		goto out;
@@ -1038,7 +1028,9 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	uint32_t *lp;
 	IOCB_t *irsp;
 	struct serv_parm *sp;
+	uint32_t ed_tov;
 	LPFC_MBOXQ_t *mbox;
+	int rc;
 
 	cmdiocb = (struct lpfc_iocbq *) arg;
 	rspiocb = cmdiocb->context_un.rsp_iocb;
@@ -1094,18 +1086,63 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	ndlp->nlp_maxframe =
 		((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb;
 
+	if ((vport->fc_flag & FC_PT2PT) &&
+	    (vport->fc_flag & FC_PT2PT_PLOGI)) {
+		ed_tov = be32_to_cpu(sp->cmn.e_d_tov);
+		if (sp->cmn.edtovResolution) {
+			/* E_D_TOV ticks are in nanoseconds */
+			ed_tov = (phba->fc_edtov + 999999) / 1000000;
+		}
+
+		/*
+		 * Use the larger EDTOV
+		 * RATOV = 2 * EDTOV for pt-to-pt
+		 */
+		if (ed_tov > phba->fc_edtov)
+			phba->fc_edtov = ed_tov;
+		phba->fc_ratov = (2 * phba->fc_edtov) / 1000;
+
+		memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
+
+		/* Issue config_link / reg_vfi to account for updated TOV's */
+		if (phba->sli_rev == LPFC_SLI_REV4) {
+			lpfc_issue_reg_vfi(vport);
+		} else {
+			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+			if (!mbox) {
+				lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
+						 "0133 PLOGI: no memory "
+						 "for config_link "
+						 "Data: x%x x%x x%x x%x\n",
+						 ndlp->nlp_DID, ndlp->nlp_state,
+						 ndlp->nlp_flag, ndlp->nlp_rpi);
+				goto out;
+			}
+
+			lpfc_config_link(phba, mbox);
+
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				mempool_free(mbox, phba->mbox_mem_pool);
+				goto out;
+			}
+		}
+	}
+
+	lpfc_unreg_rpi(vport, ndlp);
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
-			"0133 PLOGI: no memory for reg_login "
-			"Data: x%x x%x x%x x%x\n",
-			ndlp->nlp_DID, ndlp->nlp_state,
-			ndlp->nlp_flag, ndlp->nlp_rpi);
+				 "0018 PLOGI: no memory for reg_login "
+				 "Data: x%x x%x x%x x%x\n",
+				 ndlp->nlp_DID, ndlp->nlp_state,
+				 ndlp->nlp_flag, ndlp->nlp_rpi);
 		goto out;
 	}
 
-	lpfc_unreg_rpi(vport, ndlp);
-
 	if (lpfc_reg_rpi(phba, vport->vpi, irsp->un.elsreq64.remoteID,
 			 (uint8_t *) sp, mbox, ndlp->nlp_rpi) == 0) {
 		switch (ndlp->nlp_DID) {
@@ -2299,6 +2336,9 @@ lpfc_cmpl_reglogin_npr_node(struct lpfc_vport *vport,
 		if (vport->phba->sli_rev < LPFC_SLI_REV4)
 			ndlp->nlp_rpi = mb->un.varWords[0];
 		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+		if (ndlp->nlp_flag & NLP_LOGO_ACC) {
+			lpfc_unreg_rpi(vport, ndlp);
+		}
 	} else {
 		if (ndlp->nlp_flag & NLP_NODEV_REMOVE) {
 			lpfc_drop_node(vport, ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 4679ed4444a7..bae36cc3740b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3859,7 +3859,7 @@ int lpfc_sli4_scmd_to_wqidx_distr(struct lpfc_hba *phba,
 	uint32_t tag;
 	uint16_t hwq;
 
-	if (shost_use_blk_mq(cmnd->device->host)) {
+	if (cmnd && shost_use_blk_mq(cmnd->device->host)) {
 		tag = blk_mq_unique_tag(cmnd->request);
 		hwq = blk_mq_unique_tag_to_hwq(tag);
 
@@ -3908,9 +3908,9 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	uint32_t logit = LOG_FCP;
 
 	/* Sanity check on return of outstanding command */
-	if (!(lpfc_cmd->pCmd))
-		return;
 	cmd = lpfc_cmd->pCmd;
+	if (!cmd)
+		return;
 	shost = cmd->device->host;
 
 	lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index f9585cdd8933..38e90d9c2ced 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -5887,18 +5887,25 @@ lpfc_sli4_alloc_resource_identifiers(struct lpfc_hba *phba)
 
  free_vfi_bmask:
 	kfree(phba->sli4_hba.vfi_bmask);
+	phba->sli4_hba.vfi_bmask = NULL;
  free_xri_ids:
 	kfree(phba->sli4_hba.xri_ids);
+	phba->sli4_hba.xri_ids = NULL;
  free_xri_bmask:
 	kfree(phba->sli4_hba.xri_bmask);
+	phba->sli4_hba.xri_bmask = NULL;
  free_vpi_ids:
 	kfree(phba->vpi_ids);
+	phba->vpi_ids = NULL;
  free_vpi_bmask:
 	kfree(phba->vpi_bmask);
+	phba->vpi_bmask = NULL;
  free_rpi_ids:
 	kfree(phba->sli4_hba.rpi_ids);
+	phba->sli4_hba.rpi_ids = NULL;
  free_rpi_bmask:
 	kfree(phba->sli4_hba.rpi_bmask);
+	phba->sli4_hba.rpi_bmask = NULL;
  err_exit:
 	return rc;
 }
@@ -13475,7 +13482,7 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 			       LPFC_WQ_WQE_SIZE_128);
 			bf_set(lpfc_mbx_wq_create_page_size,
 			       &wq_create->u.request_1,
-			       (PAGE_SIZE/SLI4_PAGE_SIZE));
+			       LPFC_WQ_PAGE_SIZE_4096);
 			page = wq_create->u.request_1.page;
 			break;
 		}
@@ -13501,8 +13508,9 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 			       LPFC_WQ_WQE_SIZE_128);
 			break;
 		}
-		bf_set(lpfc_mbx_wq_create_page_size, &wq_create->u.request_1,
-		       (PAGE_SIZE/SLI4_PAGE_SIZE));
+		bf_set(lpfc_mbx_wq_create_page_size,
+		       &wq_create->u.request_1,
+		       LPFC_WQ_PAGE_SIZE_4096);
 		page = wq_create->u.request_1.page;
 		break;
 	default:
@@ -13688,7 +13696,7 @@ lpfc_rq_create(struct lpfc_hba *phba, struct lpfc_queue *hrq,
 		       LPFC_RQE_SIZE_8);
 		bf_set(lpfc_rq_context_page_size,
 		       &rq_create->u.request.context,
-		       (PAGE_SIZE/SLI4_PAGE_SIZE));
+		       LPFC_RQ_PAGE_SIZE_4096);
 	} else {
 		switch (hrq->entry_count) {
 		default:
@@ -14842,10 +14850,12 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 	struct lpfc_dmabuf *h_buf;
 	struct hbq_dmabuf *seq_dmabuf = NULL;
 	struct hbq_dmabuf *temp_dmabuf = NULL;
+	uint8_t	found = 0;
 
 	INIT_LIST_HEAD(&dmabuf->dbuf.list);
 	dmabuf->time_stamp = jiffies;
 	new_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+
 	/* Use the hdr_buf to find the sequence that this frame belongs to */
 	list_for_each_entry(h_buf, &vport->rcv_buffer_list, list) {
 		temp_hdr = (struct fc_frame_header *)h_buf->virt;
@@ -14885,7 +14895,8 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 		return seq_dmabuf;
 	}
 	/* find the correct place in the sequence to insert this frame */
-	list_for_each_entry_reverse(d_buf, &seq_dmabuf->dbuf.list, list) {
+	d_buf = list_entry(seq_dmabuf->dbuf.list.prev, typeof(*d_buf), list);
+	while (!found) {
 		temp_dmabuf = container_of(d_buf, struct hbq_dmabuf, dbuf);
 		temp_hdr = (struct fc_frame_header *)temp_dmabuf->hbuf.virt;
 		/*
@@ -14895,9 +14906,17 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 		if (be16_to_cpu(new_hdr->fh_seq_cnt) >
 			be16_to_cpu(temp_hdr->fh_seq_cnt)) {
 			list_add(&dmabuf->dbuf.list, &temp_dmabuf->dbuf.list);
-			return seq_dmabuf;
+			found = 1;
+			break;
 		}
+
+		if (&d_buf->list == &seq_dmabuf->dbuf.list)
+			break;
+		d_buf = list_entry(d_buf->list.prev, typeof(*d_buf), list);
 	}
+
+	if (found)
+		return seq_dmabuf;
 	return NULL;
 }
 
@@ -16173,7 +16192,7 @@ fail_fcf_read:
 }
 
 /**
- * lpfc_check_next_fcf_pri
+ * lpfc_check_next_fcf_pri_level
  * phba pointer to the lpfc_hba struct for this port.
  * This routine is called from the lpfc_sli4_fcf_rr_next_index_get
  * routine when the rr_bmask is empty. The FCF indecies are put into the
@@ -16329,8 +16348,12 @@ next_priority:
 
 	if (next_fcf_index < LPFC_SLI4_FCF_TBL_INDX_MAX &&
 		phba->fcf.fcf_pri[next_fcf_index].fcf_rec.flag &
-		LPFC_FCF_FLOGI_FAILED)
+		LPFC_FCF_FLOGI_FAILED) {
+		if (list_is_singular(&phba->fcf.fcf_pri_list))
+			return LPFC_FCOE_FCF_NEXT_NONE;
+
 		goto next_priority;
+	}
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_FIP,
 			"2845 Get next roundrobin failover FCF (x%x)\n",
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index c0f7c8ce54aa..aaf7da07a358 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1083,6 +1083,8 @@ struct megasas_ctrl_info {
 
 #define VD_EXT_DEBUG 0
 
+#define SCAN_PD_CHANNEL	0x1
+#define SCAN_VD_CHANNEL	0x2
 
 enum MR_SCSI_CMD_TYPE {
 	READ_WRITE_LDIO = 0,
@@ -1921,7 +1923,7 @@ struct megasas_instance_template {
 };
 
 #define MEGASAS_IS_LOGICAL(scp)						\
-	(scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1
+	((scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1)
 
 #define MEGASAS_DEV_INDEX(scp)						\
 	(((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) +	\
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 97a1c1c33b05..17c440b9d086 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -735,6 +735,7 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
@@ -1687,16 +1688,13 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		goto out_done;
 	}
 
-	switch (scmd->cmnd[0]) {
-	case SYNCHRONIZE_CACHE:
-		/*
-		 * FW takes care of flush cache on its own
-		 * No need to send it down
-		 */
+	/*
+	 * FW takes care of flush cache on its own for Virtual Disk.
+	 * No need to send it down for VD. For JBOD send SYNCHRONIZE_CACHE to FW.
+	 */
+	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd)) {
 		scmd->result = DID_OK << 16;
 		goto out_done;
-	default:
-		break;
 	}
 
 	if (instance->instancet->build_and_issue_cmd(instance, scmd)) {
@@ -4669,7 +4667,7 @@ 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));
-	if (pci_request_selected_regions(instance->pdev, instance->bar,
+	if (pci_request_selected_regions(instance->pdev, 1<<instance->bar,
 					 "megasas: LSI")) {
 		dev_printk(KERN_DEBUG, &instance->pdev->dev, "IO memory region busy!\n");
 		return -EBUSY;
@@ -4960,7 +4958,7 @@ fail_ready_state:
 	iounmap(instance->reg_set);
 
       fail_ioremap:
-	pci_release_selected_regions(instance->pdev, instance->bar);
+	pci_release_selected_regions(instance->pdev, 1<<instance->bar);
 
 	return -EINVAL;
 }
@@ -4981,7 +4979,7 @@ static void megasas_release_mfi(struct megasas_instance *instance)
 
 	iounmap(instance->reg_set);
 
-	pci_release_selected_regions(instance->pdev, instance->bar);
+	pci_release_selected_regions(instance->pdev, 1<<instance->bar);
 }
 
 /**
@@ -5476,7 +5474,6 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	spin_lock_init(&instance->hba_lock);
 	spin_lock_init(&instance->completion_lock);
 
-	mutex_init(&instance->aen_mutex);
 	mutex_init(&instance->reset_mutex);
 
 	/*
@@ -5941,11 +5938,11 @@ static void megasas_detach_one(struct pci_dev *pdev)
 			if (fusion->ld_drv_map[i])
 				free_pages((ulong)fusion->ld_drv_map[i],
 					fusion->drv_map_pages);
-				if (fusion->pd_seq_sync)
-					dma_free_coherent(&instance->pdev->dev,
-						pd_seq_map_sz,
-						fusion->pd_seq_sync[i],
-						fusion->pd_seq_phys[i]);
+			if (fusion->pd_seq_sync[i])
+				dma_free_coherent(&instance->pdev->dev,
+					pd_seq_map_sz,
+					fusion->pd_seq_sync[i],
+					fusion->pd_seq_phys[i]);
 		}
 		free_pages((ulong)instance->ctrl_context,
 			instance->ctrl_context_pages);
@@ -6282,12 +6279,13 @@ out:
 	}
 
 	for (i = 0; i < ioc->sge_count; i++) {
-		if (kbuff_arr[i])
+		if (kbuff_arr[i]) {
 			dma_free_coherent(&instance->pdev->dev,
 					  le32_to_cpu(kern_sge32[i].length),
 					  kbuff_arr[i],
 					  le32_to_cpu(kern_sge32[i].phys_addr));
 			kbuff_arr[i] = NULL;
+		}
 	}
 
 	megasas_return_cmd(instance, cmd);
@@ -6442,10 +6440,10 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	}
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 
-	mutex_lock(&instance->aen_mutex);
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, aen.seq_num,
 				     aen.class_locale_word);
-	mutex_unlock(&instance->aen_mutex);
+	mutex_unlock(&instance->reset_mutex);
 	return error;
 }
 
@@ -6476,9 +6474,9 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	int i;
 	int error = 0;
 	compat_uptr_t ptr;
-	unsigned long local_raw_ptr;
 	u32 local_sense_off;
 	u32 local_sense_len;
+	u32 user_sense_off;
 
 	if (clear_user(ioc, sizeof(*ioc)))
 		return -EFAULT;
@@ -6496,17 +6494,16 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	 * sense_len is not null, so prepare the 64bit value under
 	 * the same condition.
 	 */
-	if (get_user(local_raw_ptr, ioc->frame.raw) ||
-		get_user(local_sense_off, &ioc->sense_off) ||
-		get_user(local_sense_len, &ioc->sense_len))
+	if (get_user(local_sense_off, &ioc->sense_off) ||
+		get_user(local_sense_len, &ioc->sense_len) ||
+		get_user(user_sense_off, &cioc->sense_off))
 		return -EFAULT;
 
-
 	if (local_sense_len) {
 		void __user **sense_ioc_ptr =
-			(void __user **)((u8*)local_raw_ptr + local_sense_off);
+			(void __user **)((u8 *)((unsigned long)&ioc->frame.raw) + local_sense_off);
 		compat_uptr_t *sense_cioc_ptr =
-			(compat_uptr_t *)(cioc->frame.raw + cioc->sense_off);
+			(compat_uptr_t *)(((unsigned long)&cioc->frame.raw) + user_sense_off);
 		if (get_user(ptr, sense_cioc_ptr) ||
 		    put_user(compat_ptr(ptr), sense_ioc_ptr))
 			return -EFAULT;
@@ -6647,6 +6644,7 @@ megasas_aen_polling(struct work_struct *work)
 	int     i, j, doscan = 0;
 	u32 seq_num, wait_time = MEGASAS_RESET_WAIT_TIME;
 	int error;
+	u8  dcmd_ret = 0;
 
 	if (!instance) {
 		printk(KERN_ERR "invalid instance!\n");
@@ -6659,16 +6657,7 @@ megasas_aen_polling(struct work_struct *work)
 		wait_time = MEGASAS_ROUTINE_WAIT_TIME_VF;
 
 	/* Don't run the event workqueue thread if OCR is running */
-	for (i = 0; i < wait_time; i++) {
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL)
-			break;
-		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL)) {
-			dev_notice(&instance->pdev->dev, "%s waiting for "
-			       "controller reset to finish for scsi%d\n",
-			       __func__, instance->host->host_no);
-		}
-		msleep(1000);
-	}
+	mutex_lock(&instance->reset_mutex);
 
 	instance->ev = NULL;
 	host = instance->host;
@@ -6676,212 +6665,127 @@ megasas_aen_polling(struct work_struct *work)
 		megasas_decode_evt(instance);
 
 		switch (le32_to_cpu(instance->evt_detail->code)) {
-		case MR_EVT_PD_INSERTED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-						== MR_PD_STATE_SYSTEM) {
-					if (!sdev1)
-						scsi_add_device(host, i, j, 0);
-
-					if (sdev1)
-						scsi_device_put(sdev1);
-					}
-				}
-			}
-			}
-			doscan = 0;
-			break;
 
+		case MR_EVT_PD_INSERTED:
 		case MR_EVT_PD_REMOVED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-					== MR_PD_STATE_SYSTEM) {
-					if (sdev1)
-						scsi_device_put(sdev1);
-				} else {
-					if (sdev1) {
-						scsi_remove_device(sdev1);
-						scsi_device_put(sdev1);
-					}
-				}
-				}
-			}
-			}
-			doscan = 0;
+			dcmd_ret = megasas_get_pd_list(instance);
+			if (dcmd_ret == 0)
+				doscan = SCAN_PD_CHANNEL;
 			break;
 
 		case MR_EVT_LD_OFFLINE:
 		case MR_EVT_CFG_CLEARED:
 		case MR_EVT_LD_DELETED:
-			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (sdev1)
-								scsi_device_put(sdev1);
-						} else {
-							if (sdev1) {
-								scsi_remove_device(sdev1);
-								scsi_device_put(sdev1);
-							}
-						}
-					}
-				}
-				doscan = 0;
-			}
-			break;
 		case MR_EVT_LD_CREATED:
 			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (!sdev1)
-								scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					}
-				}
-				doscan = 0;
-			}
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret == 0)
+				doscan = SCAN_VD_CHANNEL;
+
 			break;
+
 		case MR_EVT_CTRL_HOST_BUS_SCAN_REQUESTED:
 		case MR_EVT_FOREIGN_CFG_IMPORTED:
 		case MR_EVT_LD_STATE_CHANGE:
-			doscan = 1;
+			dcmd_ret = megasas_get_pd_list(instance);
+
+			if (dcmd_ret != 0)
+				break;
+
+			if (!instance->requestorId ||
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret != 0)
+				break;
+
+			doscan = SCAN_VD_CHANNEL | SCAN_PD_CHANNEL;
+			dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
+				instance->host->host_no);
 			break;
+
 		case MR_EVT_CTRL_PROP_CHANGED:
-			megasas_get_ctrl_info(instance);
-			break;
+				dcmd_ret = megasas_get_ctrl_info(instance);
+				break;
 		default:
 			doscan = 0;
 			break;
 		}
 	} else {
 		dev_err(&instance->pdev->dev, "invalid evt_detail!\n");
+		mutex_unlock(&instance->reset_mutex);
 		kfree(ev);
 		return;
 	}
 
-	if (doscan) {
-		dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
-		       instance->host->host_no);
-		if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
-					pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
-					sdev1 = scsi_device_lookup(host, i, j, 0);
-					if (instance->pd_list[pd_index].driveState ==
-					    MR_PD_STATE_SYSTEM) {
-						if (!sdev1) {
-							scsi_add_device(host, i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	mutex_unlock(&instance->reset_mutex);
+
+	if (doscan & SCAN_PD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
+				sdev1 = scsi_device_lookup(host, i, j, 0);
+				if (instance->pd_list[pd_index].driveState ==
+							MR_PD_STATE_SYSTEM) {
+					if (!sdev1)
+						scsi_add_device(host, i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
+	}
 
-		if (!instance->requestorId ||
-		    megasas_get_ld_vf_affiliation(instance, 0)) {
-			if (megasas_ld_list_query(instance,
-						  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-				megasas_get_ld_list(instance);
-			for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				     j++) {
-					ld_index =
-						(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-					sdev1 = scsi_device_lookup(host,
-								   MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-					if (instance->ld_ids[ld_index]
-					    != 0xff) {
-						if (!sdev1)
-							scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						else
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	if (doscan & SCAN_VD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				ld_index = (i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
+				sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+				if (instance->ld_ids[ld_index] != 0xff) {
+					if (!sdev1)
+						scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
 	}
 
-	if (instance->aen_cmd != NULL) {
-		kfree(ev);
-		return ;
-	}
-
-	seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	if (dcmd_ret == 0)
+		seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	else
+		seq_num = instance->last_seq_num;
 
 	/* Register AEN with FW for latest sequence number plus 1 */
 	class_locale.members.reserved = 0;
 	class_locale.members.locale = MR_EVT_LOCALE_ALL;
 	class_locale.members.class = MR_EVT_CLASS_DEBUG;
-	mutex_lock(&instance->aen_mutex);
+
+	if (instance->aen_cmd != NULL) {
+		kfree(ev);
+		return;
+	}
+
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, seq_num,
 					class_locale.word);
-	mutex_unlock(&instance->aen_mutex);
-
 	if (error)
-		dev_err(&instance->pdev->dev, "register aen failed error %x\n", error);
+		dev_err(&instance->pdev->dev,
+			"register aen failed error %x\n", error);
 
+	mutex_unlock(&instance->reset_mutex);
 	kfree(ev);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 8d630a552b07..96007633ad39 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -201,6 +201,7 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
@@ -1855,6 +1856,8 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		io_request->DevHandle = pd_sync->seq[pd_index].devHandle;
 		pRAID_Context->regLockFlags |=
 			(MR_RL_FLAGS_SEQ_NUM_ENABLE|MR_RL_FLAGS_GRANT_DESTINATION_CUDA);
+		pRAID_Context->Type = MPI2_TYPE_CUDA;
+		pRAID_Context->nseg = 0x1;
 	} else if (fusion->fast_path_io) {
 		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
 		pRAID_Context->configSeqNum = 0;
@@ -1890,12 +1893,10 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		pRAID_Context->timeoutValue =
 			cpu_to_le16((os_timeout_value > timeout_limit) ?
 			timeout_limit : os_timeout_value);
-		if (fusion->adapter_type == INVADER_SERIES) {
-			pRAID_Context->Type = MPI2_TYPE_CUDA;
-			pRAID_Context->nseg = 0x1;
+		if (fusion->adapter_type == INVADER_SERIES)
 			io_request->IoFlags |=
 				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
-		}
+
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY <<
 				MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
@@ -2437,7 +2438,7 @@ megasas_release_fusion(struct megasas_instance *instance)
 
 	iounmap(instance->reg_set);
 
-	pci_release_selected_regions(instance->pdev, instance->bar);
+	pci_release_selected_regions(instance->pdev, 1<<instance->bar);
 }
 
 /**
@@ -2647,6 +2648,7 @@ int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
 		dev_err(&instance->pdev->dev, "pending commands remain after waiting, "
 		       "will reset adapter scsi%d.\n",
 		       instance->host->host_no);
+		*convert = 1;
 		retval = 1;
 	}
 out:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 11393ebf1a68..9b5367294116 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2020,8 +2020,10 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
 	_base_free_irq(ioc);
 	_base_disable_msix(ioc);
 
-	if (ioc->msix96_vector)
+	if (ioc->msix96_vector) {
 		kfree(ioc->replyPostRegisterIndex);
+		ioc->replyPostRegisterIndex = NULL;
+	}
 
 	if (ioc->chip_phys) {
 		iounmap(ioc->chip);
@@ -2155,6 +2157,17 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	} else
 		ioc->msix96_vector = 0;
 
+	if (ioc->is_warpdrive) {
+		ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
+		    &ioc->chip->ReplyPostHostIndex;
+
+		for (i = 1; i < ioc->cpu_msix_table_sz; i++)
+			ioc->reply_post_host_index[i] =
+			(resource_size_t __iomem *)
+			((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1)
+			* 4)));
+	}
+
 	list_for_each_entry(reply_q, &ioc->reply_queue_list, list)
 		pr_info(MPT3SAS_FMT "%s: IRQ %d\n",
 		    reply_q->name,  ((ioc->msix_enable) ? "PCI-MSI-X enabled" :
@@ -2229,6 +2242,12 @@ mpt3sas_base_get_reply_virt_addr(struct MPT3SAS_ADAPTER *ioc, u32 phys_addr)
 	return ioc->reply + (phys_addr - (u32)ioc->reply_dma);
 }
 
+static inline u8
+_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
+{
+	return ioc->cpu_msix_table[raw_smp_processor_id()];
+}
+
 /**
  * mpt3sas_base_get_smid - obtain a free smid from internal queue
  * @ioc: per adapter object
@@ -2289,6 +2308,7 @@ mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
 	request->scmd = scmd;
 	request->cb_idx = cb_idx;
 	smid = request->smid;
+	request->msix_io = _base_get_msix_index(ioc);
 	list_del(&request->tracker_list);
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 	return smid;
@@ -2411,12 +2431,6 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 }
 #endif
 
-static inline u8
-_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
-{
-	return ioc->cpu_msix_table[raw_smp_processor_id()];
-}
-
 /**
  * mpt3sas_base_put_smid_scsi_io - send SCSI_IO request to firmware
  * @ioc: per adapter object
@@ -2470,18 +2484,19 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * mpt3sas_base_put_smid_hi_priority - send Task Managment request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
- *
+ * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
  * Return nothing.
  */
 void
-mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 msix_task)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
 	u64 *request = (u64 *)&descriptor;
 
 	descriptor.HighPriority.RequestFlags =
 	    MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY;
-	descriptor.HighPriority.MSIxIndex =  0;
+	descriptor.HighPriority.MSIxIndex =  msix_task;
 	descriptor.HighPriority.SMID = cpu_to_le16(smid);
 	descriptor.HighPriority.LMID = 0;
 	descriptor.HighPriority.Reserved1 = 0;
@@ -4966,15 +4981,14 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, int sleep_flag,
 static int
 _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag)
 {
-	int r, i;
+	int r, i, index;
 	unsigned long	flags;
 	u32 reply_address;
 	u16 smid;
 	struct _tr_list *delayed_tr, *delayed_tr_next;
 	u8 hide_flag;
 	struct adapter_reply_queue *reply_q;
-	long reply_post_free;
-	u32 reply_post_free_sz, index = 0;
+	Mpi2ReplyDescriptorsUnion_t *reply_post_free_contig;
 
 	dinitprintk(ioc, pr_info(MPT3SAS_FMT "%s\n", ioc->name,
 	    __func__));
@@ -5046,27 +5060,27 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag)
 		_base_assign_reply_queues(ioc);
 
 	/* initialize Reply Post Free Queue */
-	reply_post_free_sz = ioc->reply_post_queue_depth *
-	    sizeof(Mpi2DefaultReplyDescriptor_t);
-	reply_post_free = (long)ioc->reply_post[index].reply_post_free;
+	index = 0;
+	reply_post_free_contig = ioc->reply_post[0].reply_post_free;
 	list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
+		/*
+		 * If RDPQ is enabled, switch to the next allocation.
+		 * Otherwise advance within the contiguous region.
+		 */
+		if (ioc->rdpq_array_enable) {
+			reply_q->reply_post_free =
+				ioc->reply_post[index++].reply_post_free;
+		} else {
+			reply_q->reply_post_free = reply_post_free_contig;
+			reply_post_free_contig += ioc->reply_post_queue_depth;
+		}
+
 		reply_q->reply_post_host_index = 0;
-		reply_q->reply_post_free = (Mpi2ReplyDescriptorsUnion_t *)
-		    reply_post_free;
 		for (i = 0; i < ioc->reply_post_queue_depth; i++)
 			reply_q->reply_post_free[i].Words =
 			    cpu_to_le64(ULLONG_MAX);
 		if (!_base_is_controller_msix_enabled(ioc))
 			goto skip_init_reply_post_free_queue;
-		/*
-		 * If RDPQ is enabled, switch to the next allocation.
-		 * Otherwise advance within the contiguous region.
-		 */
-		if (ioc->rdpq_array_enable)
-			reply_post_free = (long)
-			    ioc->reply_post[++index].reply_post_free;
-		else
-			reply_post_free += reply_post_free_sz;
 	}
  skip_init_reply_post_free_queue:
 
@@ -5201,17 +5215,6 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	if (r)
 		goto out_free_resources;
 
-	if (ioc->is_warpdrive) {
-		ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
-		    &ioc->chip->ReplyPostHostIndex;
-
-		for (i = 1; i < ioc->cpu_msix_table_sz; i++)
-			ioc->reply_post_host_index[i] =
-			(resource_size_t __iomem *)
-			((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1)
-			* 4)));
-	}
-
 	pci_set_drvdata(ioc->pdev, ioc->shost);
 	r = _base_get_ioc_facts(ioc, CAN_SLEEP);
 	if (r)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 5ad271efbd45..63f5965acc89 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -390,6 +390,7 @@ struct MPT3SAS_TARGET {
  * @eedp_enable: eedp support enable bit
  * @eedp_type: 0(type_1), 1(type_2), 2(type_3)
  * @eedp_block_length: block size
+ * @ata_command_pending: SATL passthrough outstanding for device
  */
 struct MPT3SAS_DEVICE {
 	struct MPT3SAS_TARGET *sas_target;
@@ -398,6 +399,17 @@ struct MPT3SAS_DEVICE {
 	u8	configured_lun;
 	u8	block;
 	u8	tlr_snoop_check;
+	/*
+	 * Bug workaround for SATL handling: the mpt2/3sas firmware
+	 * doesn't return BUSY or TASK_SET_FULL for subsequent
+	 * commands while a SATL pass through is in operation as the
+	 * spec requires, it simply does nothing with them until the
+	 * pass through completes, causing them possibly to timeout if
+	 * the passthrough is a long executing command (like format or
+	 * secure erase).  This variable allows us to do the right
+	 * thing while a SATL command is pending.
+	 */
+	unsigned long ata_command_pending;
 };
 
 #define MPT3_CMD_NOT_USED	0x8000	/* free */
@@ -643,6 +655,7 @@ struct chain_tracker {
  * @cb_idx: callback index
  * @direct_io: To indicate whether I/O is direct (WARPDRIVE)
  * @tracker_list: list of free request (ioc->free_list)
+ * @msix_io: IO's msix
  */
 struct scsiio_tracker {
 	u16	smid;
@@ -651,6 +664,7 @@ struct scsiio_tracker {
 	u8	direct_io;
 	struct list_head chain_list;
 	struct list_head tracker_list;
+	u16     msix_io;
 };
 
 /**
@@ -1213,7 +1227,8 @@ void mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
 void mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
-void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid);
+void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc,
+	u16 smid, u16 msix_task);
 void mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid);
 void mpt3sas_base_initialize_callback_handler(void);
 u8 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index d8366b056b70..4ccde5a05b70 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -817,7 +817,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		    tm_request->DevHandle));
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-		mpt3sas_base_put_smid_hi_priority(ioc, smid);
+		mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 		break;
 	}
 	case MPI2_FUNCTION_SMP_PASSTHROUGH:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9ab77b06434d..e333029e4b6c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/interrupt.h>
 #include <linux/aer.h>
 #include <linux/raid_class.h>
@@ -1275,9 +1276,9 @@ scsih_target_alloc(struct scsi_target *starget)
 			sas_target_priv_data->handle = raid_device->handle;
 			sas_target_priv_data->sas_address = raid_device->wwid;
 			sas_target_priv_data->flags |= MPT_TARGET_FLAGS_VOLUME;
-			sas_target_priv_data->raid_device = raid_device;
 			if (ioc->is_warpdrive)
-				raid_device->starget = starget;
+				sas_target_priv_data->raid_device = raid_device;
+			raid_device->starget = starget;
 		}
 		spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
 		return 0;
@@ -2193,6 +2194,7 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	unsigned long timeleft;
 	struct scsiio_tracker *scsi_lookup = NULL;
 	int rc;
+	u16 msix_task = 0;
 
 	if (m_type == TM_MUTEX_ON)
 		mutex_lock(&ioc->tm_cmds.mutex);
@@ -2256,7 +2258,12 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	int_to_scsilun(lun, (struct scsi_lun *)mpi_request->LUN);
 	mpt3sas_scsih_set_tm_flag(ioc, handle);
 	init_completion(&ioc->tm_cmds.done);
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	if ((type == MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK) &&
+			(scsi_lookup->msix_io < ioc->reply_queue_count))
+		msix_task = scsi_lookup->msix_io;
+	else
+		msix_task = 0;
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
 	timeleft = wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -3151,7 +3158,7 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 	mpt3sas_trigger_master(ioc, MASTER_TRIGGER_DEVICE_REMOVAL);
 
 out:
@@ -3332,7 +3339,7 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 }
 
 /**
@@ -3700,6 +3707,20 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	}
 }
 
+static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
+{
+	struct MPT3SAS_DEVICE *priv = scmd->device->hostdata;
+
+	if (scmd->cmnd[0] != ATA_12 && scmd->cmnd[0] != ATA_16)
+		return 0;
+
+	if (pending)
+		return test_and_set_bit(0, &priv->ata_command_pending);
+
+	clear_bit(0, &priv->ata_command_pending);
+	return 0;
+}
+
 /**
  * _scsih_flush_running_cmds - completing outstanding commands.
  * @ioc: per adapter object
@@ -3721,6 +3742,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		if (!scmd)
 			continue;
 		count++;
+		_scsih_set_satl_pending(scmd, false);
 		mpt3sas_base_free_smid(ioc, smid);
 		scsi_dma_unmap(scmd);
 		if (ioc->pci_error_recovery)
@@ -3825,8 +3847,6 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 	    SAM_STAT_CHECK_CONDITION;
 }
 
-
-
 /**
  * scsih_qcmd - main scsi request entry point
  * @scmd: pointer to scsi command object
@@ -3866,6 +3886,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		return 0;
 	}
 
+	/*
+	 * Bug work around for firmware SATL handling.  The loop
+	 * is based on atomic operations and ensures consistency
+	 * since we're lockless at this point
+	 */
+	do {
+		if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
+			scmd->result = SAM_STAT_BUSY;
+			scmd->scsi_done(scmd);
+			return 0;
+		}
+	} while (_scsih_set_satl_pending(scmd, true));
+
 	sas_target_priv_data = sas_device_priv_data->sas_target;
 
 	/* invalid device handle */
@@ -4419,12 +4452,15 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
 	if (scmd == NULL)
 		return 1;
 
+	_scsih_set_satl_pending(scmd, false);
+
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 
 	if (mpi_reply == NULL) {
@@ -4475,6 +4511,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);
@@ -4504,7 +4554,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 			    le16_to_cpu(mpi_reply->DevHandle));
 		mpt3sas_trigger_scsi(ioc, data.skey, data.asc, data.ascq);
 
-		if (!(ioc->logging_level & MPT_DEBUG_REPLY) &&
+		if ((ioc->logging_level & MPT_DEBUG_REPLY) &&
 		     ((scmd->sense_buffer[2] == UNIT_ATTENTION) ||
 		     (scmd->sense_buffer[2] == MEDIUM_ERROR) ||
 		     (scmd->sense_buffer[2] == HARDWARE_ERROR)))
@@ -8461,6 +8511,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	switch (hba_mpi_version) {
 	case MPI2_VERSION:
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+			PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
 		/* Use mpt2sas driver host template for SAS 2.0 HBA's */
 		shost = scsi_host_alloc(&mpt2sas_driver_template,
 		  sizeof(struct MPT3SAS_ADAPTER));
diff --git a/drivers/scsi/mvsas/mv_94xx.c b/drivers/scsi/mvsas/mv_94xx.c
index 9270d15ff1a4..7353ac8d0d39 100644
--- a/drivers/scsi/mvsas/mv_94xx.c
+++ b/drivers/scsi/mvsas/mv_94xx.c
@@ -621,7 +621,7 @@ static void mvs_94xx_command_active(struct mvs_info *mvi, u32 slot_idx)
 {
 	u32 tmp;
 	tmp = mvs_cr32(mvi, MVS_COMMAND_ACTIVE+(slot_idx >> 3));
-	if (tmp && 1 << (slot_idx % 32)) {
+	if (tmp & 1 << (slot_idx % 32)) {
 		mv_printk("command active %08X,  slot [%x].\n", tmp, slot_idx);
 		mvs_cw32(mvi, MVS_COMMAND_ACTIVE + (slot_idx >> 3),
 			1 << (slot_idx % 32));
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index 9c780740fb82..e712fe745955 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -737,8 +737,8 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf
 			mv_dprintk("device %016llx not ready.\n",
 				SAS_ADDR(dev->sas_addr));
 
-			rc = SAS_PHY_DOWN;
-			return rc;
+		rc = SAS_PHY_DOWN;
+		return rc;
 	}
 	tei.port = dev->port->lldd_port;
 	if (tei.port && !tei.port->port_attached && !tmf) {
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 5d0ec42a9317..634254a52301 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -4214,7 +4214,7 @@ static struct scsi_host_template qla1280_driver_template = {
 	.eh_bus_reset_handler	= qla1280_eh_bus_reset,
 	.eh_host_reset_handler	= qla1280_eh_adapter_reset,
 	.bios_param		= qla1280_biosparam,
-	.can_queue		= 0xfffff,
+	.can_queue		= MAX_OUTSTANDING_COMMANDS,
 	.this_id		= -1,
 	.sg_tablesize		= SG_ALL,
 	.use_clustering		= ENABLE_CLUSTERING,
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 6b942d9e5b74..1ed85dfc008d 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -329,12 +329,15 @@ qla2x00_sysfs_read_optrom(struct file *filp, struct kobject *kobj,
 	struct qla_hw_data *ha = vha->hw;
 	ssize_t rval = 0;
 
+	mutex_lock(&ha->optrom_mutex);
+
 	if (ha->optrom_state != QLA_SREADING)
-		return 0;
+		goto out;
 
-	mutex_lock(&ha->optrom_mutex);
 	rval = memory_read_from_buffer(buf, count, &off, ha->optrom_buffer,
 	    ha->optrom_region_size);
+
+out:
 	mutex_unlock(&ha->optrom_mutex);
 
 	return rval;
@@ -349,14 +352,19 @@ qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj,
 	    struct device, kobj)));
 	struct qla_hw_data *ha = vha->hw;
 
-	if (ha->optrom_state != QLA_SWRITING)
+	mutex_lock(&ha->optrom_mutex);
+
+	if (ha->optrom_state != QLA_SWRITING) {
+		mutex_unlock(&ha->optrom_mutex);
 		return -EINVAL;
-	if (off > ha->optrom_region_size)
+	}
+	if (off > ha->optrom_region_size) {
+		mutex_unlock(&ha->optrom_mutex);
 		return -ERANGE;
+	}
 	if (off + count > ha->optrom_region_size)
 		count = ha->optrom_region_size - off;
 
-	mutex_lock(&ha->optrom_mutex);
 	memcpy(&ha->optrom_buffer[off], buf, count);
 	mutex_unlock(&ha->optrom_mutex);
 
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 0e59731f95ad..1f6a3b86965f 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2466,6 +2466,10 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt)
 	if (pkt->entry_status & RF_BUSY)
 		res = DID_BUS_BUSY << 16;
 
+	if (pkt->entry_type == NOTIFY_ACK_TYPE &&
+	    pkt->handle == QLA_TGT_SKIP_HANDLE)
+		return;
+
 	sp = qla2x00_get_sp_from_handle(vha, func, req, pkt);
 	if (sp) {
 		sp->done(ha, sp, res);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index fc6674db4f2d..5cbf20ab94aa 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2257,6 +2257,8 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time)
 {
 	scsi_qla_host_t *vha = shost_priv(shost);
 
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		return 1;
 	if (!vha->host)
 		return 1;
 	if (time > vha->hw->loop_reset_delay * HZ)
@@ -2309,10 +2311,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	if (mem_only) {
 		if (pci_enable_device_mem(pdev))
-			goto probe_out;
+			return ret;
 	} else {
 		if (pci_enable_device(pdev))
-			goto probe_out;
+			return ret;
 	}
 
 	/* This may fail but that's ok */
@@ -2322,7 +2324,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!ha) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0009,
 		    "Unable to allocate memory for ha.\n");
-		goto probe_out;
+		goto disable_device;
 	}
 	ql_dbg_pci(ql_dbg_init, pdev, 0x000a,
 	    "Memory allocated for ha=%p.\n", ha);
@@ -2921,7 +2923,7 @@ iospace_config_failed:
 	kfree(ha);
 	ha = NULL;
 
-probe_out:
+disable_device:
 	pci_disable_device(pdev);
 	return ret;
 }
@@ -3363,7 +3365,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 				sizeof(struct ct6_dsd), 0,
 				SLAB_HWCACHE_ALIGN, NULL);
 			if (!ctx_cachep)
-				goto fail_free_gid_list;
+				goto fail_free_srb_mempool;
 		}
 		ha->ctx_mempool = mempool_create_slab_pool(SRB_MIN_REQ,
 			ctx_cachep);
@@ -3516,7 +3518,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	ha->loop_id_map = kzalloc(BITS_TO_LONGS(LOOPID_MAP_SIZE) * sizeof(long),
 	    GFP_KERNEL);
 	if (!ha->loop_id_map)
-		goto fail_async_pd;
+		goto fail_loop_id_map;
 	else {
 		qla2x00_set_reserved_loop_ids(ha);
 		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
@@ -3525,6 +3527,8 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 
 	return 0;
 
+fail_loop_id_map:
+	dma_pool_free(ha->s_dma_pool, ha->async_pd, ha->async_pd_dma);
 fail_async_pd:
 	dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
 fail_ex_init_cb:
@@ -3552,6 +3556,10 @@ fail_free_ms_iocb:
 	dma_pool_free(ha->s_dma_pool, ha->ms_iocb, ha->ms_iocb_dma);
 	ha->ms_iocb = NULL;
 	ha->ms_iocb_dma = 0;
+
+	if (ha->sns_cmd)
+		dma_free_coherent(&ha->pdev->dev, sizeof(struct sns_cmd_pkt),
+		    ha->sns_cmd, ha->sns_cmd_dma);
 fail_dma_pool:
 	if (IS_QLA82XX(ha) || ql2xenabledif) {
 		dma_pool_destroy(ha->fcp_cmnd_dma_pool);
@@ -3569,10 +3577,12 @@ fail_free_nvram:
 	kfree(ha->nvram);
 	ha->nvram = NULL;
 fail_free_ctx_mempool:
-	mempool_destroy(ha->ctx_mempool);
+	if (ha->ctx_mempool)
+		mempool_destroy(ha->ctx_mempool);
 	ha->ctx_mempool = NULL;
 fail_free_srb_mempool:
-	mempool_destroy(ha->srb_mempool);
+	if (ha->srb_mempool)
+		mempool_destroy(ha->srb_mempool);
 	ha->srb_mempool = NULL;
 fail_free_gid_list:
 	dma_free_coherent(&ha->pdev->dev, qla2x00_gid_list_size(ha),
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 75514a15bea0..e6faa0b050d1 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1578,7 +1578,7 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
 		    0, 0, 0, 0, 0, 0);
 	else {
-		if (mcmd->se_cmd.se_tmr_req->function == TMR_ABORT_TASK)
+		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
 		else
@@ -2865,7 +2865,7 @@ static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
 
 	pkt->entry_type = NOTIFY_ACK_TYPE;
 	pkt->entry_count = 1;
-	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+	pkt->handle = QLA_TGT_SKIP_HANDLE;
 
 	nack = (struct nack_to_isp *)pkt;
 	nack->ox_id = ntfy->ox_id;
diff --git a/drivers/scsi/scsi_common.c b/drivers/scsi/scsi_common.c
index c126966130ab..ce79de822e46 100644
--- a/drivers/scsi/scsi_common.c
+++ b/drivers/scsi/scsi_common.c
@@ -278,8 +278,16 @@ int scsi_set_sense_information(u8 *buf, int buf_len, u64 info)
 		ucp[3] = 0;
 		put_unaligned_be64(info, &ucp[4]);
 	} else if ((buf[0] & 0x7f) == 0x70) {
-		buf[0] |= 0x80;
-		put_unaligned_be64(info, &buf[3]);
+		/*
+		 * Only set the 'VALID' bit if we can represent the value
+		 * correctly; otherwise just fill out the lower bytes and
+		 * clear the 'VALID' flag.
+		 */
+		if (info <= 0xffffffffUL)
+			buf[0] |= 0x80;
+		else
+			buf[0] &= 0x7f;
+		put_unaligned_be32((u32)info, &buf[3]);
 	}
 
 	return 0;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index d09d60293c27..e357a393d56e 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4981,6 +4981,7 @@ static void __exit scsi_debug_exit(void)
 	bus_unregister(&pseudo_lld_bus);
 	root_device_unregister(pseudo_primary);
 
+	vfree(map_storep);
 	vfree(dif_storep);
 	vfree(fake_storep);
 }
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index da2e068ee47d..11cdb172cfaf 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -227,6 +227,7 @@ static struct {
 	{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
 	{"Promise", "", NULL, BLIST_SPARSELUN},
+	{"QEMU", "QEMU CD-ROM", NULL, BLIST_SKIP_VPD_PAGES},
 	{"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024},
 	{"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024},
 	{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
@@ -425,7 +426,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	 * here, and we don't know what device it is
 	 * trying to work with, leave it as-is.
 	 */
-	vmax = 8;	/* max length of vendor */
+	vmax = sizeof(devinfo->vendor);
 	vskip = vendor;
 	while (vmax > 0 && *vskip == ' ') {
 		vmax--;
@@ -435,7 +436,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	while (vmax > 0 && vskip[vmax - 1] == ' ')
 		--vmax;
 
-	mmax = 16;	/* max length of model */
+	mmax = sizeof(devinfo->model);
 	mskip = model;
 	while (mmax > 0 && *mskip == ' ') {
 		mmax--;
@@ -451,10 +452,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 			 * Behave like the older version of get_device_flags.
 			 */
 			if (memcmp(devinfo->vendor, vskip, vmax) ||
-					devinfo->vendor[vmax])
+					(vmax < sizeof(devinfo->vendor) &&
+						devinfo->vendor[vmax]))
 				continue;
 			if (memcmp(devinfo->model, mskip, mmax) ||
-					devinfo->model[mmax])
+					(mmax < sizeof(devinfo->model) &&
+						devinfo->model[mmax]))
 				continue;
 			return devinfo;
 		} else {
diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c
index e7649ed3f667..4d655b568269 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -289,20 +289,6 @@ int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh)
 }
 EXPORT_SYMBOL_GPL(scsi_unregister_device_handler);
 
-static struct scsi_device *get_sdev_from_queue(struct request_queue *q)
-{
-	struct scsi_device *sdev;
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-	sdev = q->queuedata;
-	if (!sdev || !get_device(&sdev->sdev_gendev))
-		sdev = NULL;
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
-	return sdev;
-}
-
 /*
  * scsi_dh_activate - activate the path associated with the scsi_device
  *      corresponding to the given request queue.
@@ -321,7 +307,7 @@ int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data)
 	struct scsi_device *sdev;
 	int err = SCSI_DH_NOSYS;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev) {
 		if (fn)
 			fn(data, err);
@@ -368,7 +354,7 @@ int scsi_dh_set_params(struct request_queue *q, const char *params)
 	struct scsi_device *sdev;
 	int err = -SCSI_DH_NOSYS;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return err;
 
@@ -391,7 +377,7 @@ int scsi_dh_attach(struct request_queue *q, const char *name)
 	struct scsi_device_handler *scsi_dh;
 	int err = 0;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return -ENODEV;
 
@@ -429,7 +415,7 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp)
 	struct scsi_device *sdev;
 	const char *handler_name = NULL;
 
-	sdev = get_sdev_from_queue(q);
+	sdev = scsi_device_from_queue(q);
 	if (!sdev)
 		return NULL;
 
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 984ddcb4786d..1b9c049bd5c5 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1127,7 +1127,6 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
  */
 void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
 {
-	scmd->device->host->host_failed--;
 	scmd->eh_eflags = 0;
 	list_move_tail(&scmd->eh_entry, done_q);
 }
@@ -2226,6 +2225,9 @@ int scsi_error_handler(void *data)
 		else
 			scsi_unjam_host(shost);
 
+		/* All scmds have been handled */
+		shost->host_failed = 0;
+
 		/*
 		 * Note - if the above fails completely, the action is to take
 		 * individual devices offline and flush the queue of any
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index dd8ad2a44510..887045ae5d10 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -910,9 +910,12 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	}
 
 	/*
-	 * If we finished all bytes in the request we are done now.
+	 * special case: failed zero length commands always need to
+	 * drop down into the retry code. Otherwise, if we finished
+	 * all bytes in the request we are done now.
 	 */
-	if (!scsi_end_request(req, error, good_bytes, 0))
+	if (!(blk_rq_bytes(req) == 0 && error) &&
+	    !scsi_end_request(req, error, good_bytes, 0))
 		return;
 
 	/*
@@ -1117,7 +1120,8 @@ int scsi_init_io(struct scsi_cmnd *cmd)
 	bool is_mq = (rq->mq_ctx != NULL);
 	int error;
 
-	BUG_ON(!rq->nr_phys_segments);
+	if (WARN_ON_ONCE(!rq->nr_phys_segments))
+		return -EINVAL;
 
 	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
@@ -2211,6 +2215,29 @@ void scsi_mq_destroy_tags(struct Scsi_Host *shost)
 	blk_mq_free_tag_set(&shost->tag_set);
 }
 
+/**
+ * scsi_device_from_queue - return sdev associated with a request_queue
+ * @q: The request queue to return the sdev from
+ *
+ * Return the sdev associated with a request queue or NULL if the
+ * request_queue does not reference a SCSI device.
+ */
+struct scsi_device *scsi_device_from_queue(struct request_queue *q)
+{
+	struct scsi_device *sdev = NULL;
+
+	if (q->mq_ops) {
+		if (q->mq_ops == &scsi_mq_ops)
+			sdev = q->queuedata;
+	} else if (q->request_fn == scsi_request_fn)
+		sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		sdev = NULL;
+
+	return sdev;
+}
+EXPORT_SYMBOL_GPL(scsi_device_from_queue);
+
 /*
  * Function:    scsi_block_requests()
  *
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 054923e3393c..692445bcca6f 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -314,6 +314,7 @@ static void scsi_target_destroy(struct scsi_target *starget)
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
 	unsigned long flags;
 
+	BUG_ON(starget->state == STARGET_DEL);
 	starget->state = STARGET_DEL;
 	transport_destroy_device(dev);
 	spin_lock_irqsave(shost->host_lock, flags);
@@ -1458,12 +1459,12 @@ retry:
  out_err:
 	kfree(lun_data);
  out:
-	scsi_device_put(sdev);
 	if (scsi_device_created(sdev))
 		/*
 		 * the sdev we used didn't appear in the report luns scan
 		 */
 		__scsi_remove_device(sdev);
+	scsi_device_put(sdev);
 	return ret;
 }
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index c8115b4fe474..4477e999ec70 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1031,10 +1031,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 	struct request_queue *rq = sdev->request_queue;
 	struct scsi_target *starget = sdev->sdev_target;
 
-	error = scsi_device_set_state(sdev, SDEV_RUNNING);
-	if (error)
-		return error;
-
 	error = scsi_target_add(starget);
 	if (error)
 		return error;
@@ -1058,11 +1054,12 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 	}
 
 	error = scsi_dh_add_device(sdev);
-	if (error) {
+	if (error)
+		/*
+		 * device_handler is optional, so any error can be ignored
+		 */
 		sdev_printk(KERN_INFO, sdev,
 				"failed to add device handler: %d\n", error);
-		return error;
-	}
 
 	device_enable_async_suspend(&sdev->sdev_dev);
 	error = device_add(&sdev->sdev_dev);
@@ -1192,18 +1189,18 @@ static void __scsi_remove_target(struct scsi_target *starget)
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget, *last_target = NULL;
+	struct scsi_target *starget;
 	unsigned long flags;
 
 restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
 		if (starget->state == STARGET_DEL ||
-		    starget == last_target)
+		    starget->state == STARGET_REMOVE)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			kref_get(&starget->reap_ref);
-			last_target = starget;
+			starget->state = STARGET_REMOVE;
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			__scsi_remove_target(starget);
 			scsi_target_reap(starget);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bb669d32ccd0..8750c86f95f9 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -648,7 +648,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	 */
 	if (sdkp->lbprz) {
 		q->limits.discard_alignment = 0;
-		q->limits.discard_granularity = 1;
+		q->limits.discard_granularity = logical_block_size;
 	} else {
 		q->limits.discard_alignment = sdkp->unmap_alignment *
 			logical_block_size;
@@ -1275,18 +1275,19 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
 	struct scsi_device *sdp = sdkp->device;
 	struct Scsi_Host *host = sdp->host;
+	sector_t capacity = logical_to_sectors(sdp, sdkp->capacity);
 	int diskinfo[4];
 
 	/* default to most commonly used values */
-        diskinfo[0] = 0x40;	/* 1 << 6 */
-       	diskinfo[1] = 0x20;	/* 1 << 5 */
-       	diskinfo[2] = sdkp->capacity >> 11;
-	
+	diskinfo[0] = 0x40;	/* 1 << 6 */
+	diskinfo[1] = 0x20;	/* 1 << 5 */
+	diskinfo[2] = capacity >> 11;
+
 	/* override with calculated, extended default, or driver values */
 	if (host->hostt->bios_param)
-		host->hostt->bios_param(sdp, bdev, sdkp->capacity, diskinfo);
+		host->hostt->bios_param(sdp, bdev, capacity, diskinfo);
 	else
-		scsicam_bios_param(bdev, sdkp->capacity, diskinfo);
+		scsicam_bios_param(bdev, capacity, diskinfo);
 
 	geo->heads = diskinfo[0];
 	geo->sectors = diskinfo[1];
@@ -1397,11 +1398,15 @@ static int media_not_present(struct scsi_disk *sdkp,
  **/
 static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
 {
-	struct scsi_disk *sdkp = scsi_disk(disk);
-	struct scsi_device *sdp = sdkp->device;
+	struct scsi_disk *sdkp = scsi_disk_get(disk);
+	struct scsi_device *sdp;
 	struct scsi_sense_hdr *sshdr = NULL;
 	int retval;
 
+	if (!sdkp)
+		return 0;
+
+	sdp = sdkp->device;
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n"));
 
 	/*
@@ -1458,6 +1463,7 @@ out:
 	kfree(sshdr);
 	retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
 	sdp->changed = 0;
+	scsi_disk_put(sdkp);
 	return retval;
 }
 
@@ -2045,6 +2051,22 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
 
 #define READ_CAPACITY_RETRIES_ON_RESET	10
 
+/*
+ * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set
+ * and the reported logical block size is bigger than 512 bytes. Note
+ * that last_sector is a u64 and therefore logical_to_sectors() is not
+ * applicable.
+ */
+static bool sd_addressable_capacity(u64 lba, unsigned int sector_size)
+{
+	u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9);
+
+	if (sizeof(sector_t) == 4 && last_sector > U32_MAX)
+		return false;
+
+	return true;
+}
+
 static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 						unsigned char *buffer)
 {
@@ -2110,7 +2132,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 		return -ENODEV;
 	}
 
-	if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) {
+	if (!sd_addressable_capacity(lba, sector_size)) {
 		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
 			"kernel compiled with support for large block "
 			"devices.\n");
@@ -2196,7 +2218,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
 		return sector_size;
 	}
 
-	if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) {
+	if (!sd_addressable_capacity(lba, sector_size)) {
 		sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
 			"kernel compiled with support for large block "
 			"devices.\n");
@@ -2337,14 +2359,6 @@ got_data:
 	if (sdkp->capacity > 0xffffffff)
 		sdp->use_16_for_rw = 1;
 
-	/* Rescale capacity to 512-byte units */
-	if (sector_size == 4096)
-		sdkp->capacity <<= 3;
-	else if (sector_size == 2048)
-		sdkp->capacity <<= 2;
-	else if (sector_size == 1024)
-		sdkp->capacity <<= 1;
-
 	blk_queue_physical_block_size(sdp->request_queue,
 				      sdkp->physical_block_size);
 	sdkp->device->sector_size = sector_size;
@@ -2552,7 +2566,8 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 		if (sdp->broken_fua) {
 			sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
 			sdkp->DPOFUA = 0;
-		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
+		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw &&
+			   !sdkp->device->use_16_for_rw) {
 			sd_first_printk(KERN_NOTICE, sdkp,
 				  "Uses READ/WRITE(6), disabling FUA\n");
 			sdkp->DPOFUA = 0;
@@ -2812,11 +2827,6 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp)
 	return 0;
 }
 
-static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks)
-{
-	return blocks << (ilog2(sdev->sector_size) - 9);
-}
-
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -2891,16 +2901,17 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	if (sdkp->opt_xfer_blocks &&
 	    sdkp->opt_xfer_blocks <= dev_max &&
 	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
-	    sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE)
-		rw_max = q->limits.io_opt =
-			sdkp->opt_xfer_blocks * sdp->sector_size;
-	else
-		rw_max = BLK_DEF_MAX_SECTORS;
+	    logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_CACHE_SIZE) {
+		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
+		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+	} else
+		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
+				      (sector_t)BLK_DEF_MAX_SECTORS);
 
 	/* Combine with controller limits */
 	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
 
-	set_capacity(disk, sdkp->capacity);
+	set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
 	sd_config_write_same(sdkp);
 	kfree(buffer);
 
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 5f2a84aff29f..765a6f1ac1b7 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -65,7 +65,7 @@ struct scsi_disk {
 	struct device	dev;
 	struct gendisk	*disk;
 	atomic_t	openers;
-	sector_t	capacity;	/* size in 512-byte sectors */
+	sector_t	capacity;	/* size in logical blocks */
 	u32		max_xfer_blocks;
 	u32		opt_xfer_blocks;
 	u32		max_ws_blocks;
@@ -146,6 +146,16 @@ static inline int scsi_medium_access_command(struct scsi_cmnd *scmd)
 	return 0;
 }
 
+static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks)
+{
+	return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
+static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks)
+{
+	return blocks * sdev->sector_size;
+}
+
 /*
  * A DIF-capable target device can be formatted with different
  * protection schemes.  Currently 0 through 3 are defined:
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 5e820674432c..71325972e503 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -153,6 +153,7 @@ typedef struct sg_fd {		/* holds the state of a file descriptor */
 	struct sg_device *parentdp;	/* owning device */
 	wait_queue_head_t read_wait;	/* queue read until command done */
 	rwlock_t rq_list_lock;	/* protect access to list in req_arr */
+	struct mutex f_mutex;	/* protect against changes in this fd */
 	int timeout;		/* defaults to SG_DEFAULT_TIMEOUT      */
 	int timeout_user;	/* defaults to SG_DEFAULT_TIMEOUT_USER */
 	Sg_scatter_hold reserve;	/* buffer held for this file descriptor */
@@ -166,6 +167,7 @@ typedef struct sg_fd {		/* holds the state of a file descriptor */
 	unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */
 	char keep_orphan;	/* 0 -> drop orphan (def), 1 -> keep for read() */
 	char mmap_called;	/* 0 -> mmap() never called on this fd */
+	char res_in_use;	/* 1 -> 'reserve' array in use */
 	struct kref f_ref;
 	struct execute_work ew;
 } Sg_fd;
@@ -209,7 +211,6 @@ static void sg_remove_sfp(struct kref *);
 static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id);
 static Sg_request *sg_add_request(Sg_fd * sfp);
 static int sg_remove_request(Sg_fd * sfp, Sg_request * srp);
-static int sg_res_in_use(Sg_fd * sfp);
 static Sg_device *sg_get_dev(int dev);
 static void sg_device_destroy(struct kref *kref);
 
@@ -592,6 +593,9 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
 
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EINVAL;
+
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
@@ -622,6 +626,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	}
 	buf += SZ_SG_HEADER;
 	__get_user(opcode, buf);
+	mutex_lock(&sfp->f_mutex);
 	if (sfp->next_cmd_len > 0) {
 		cmd_size = sfp->next_cmd_len;
 		sfp->next_cmd_len = 0;	/* reset so only this write() effected */
@@ -630,6 +635,7 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 		if ((opcode >= 0xc0) && old_hdr.twelve_byte)
 			cmd_size = 12;
 	}
+	mutex_unlock(&sfp->f_mutex);
 	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
 		"sg_write:   scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size));
 /* Determine buffer size.  */
@@ -652,7 +658,8 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	else
 		hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE;
 	hp->dxfer_len = mxsize;
-	if (hp->dxfer_direction == SG_DXFER_TO_DEV)
+	if ((hp->dxfer_direction == SG_DXFER_TO_DEV) ||
+	    (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV))
 		hp->dxferp = (char __user *)buf + cmd_size;
 	else
 		hp->dxferp = NULL;
@@ -728,7 +735,7 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf,
 			sg_remove_request(sfp, srp);
 			return -EINVAL;	/* either MMAP_IO or DIRECT_IO (not both) */
 		}
-		if (sg_res_in_use(sfp)) {
+		if (sfp->res_in_use) {
 			sg_remove_request(sfp, srp);
 			return -EBUSY;	/* reserve buffer already being used */
 		}
@@ -898,7 +905,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			return result;
 		if (val) {
 			sfp->low_dma = 1;
-			if ((0 == sfp->low_dma) && (0 == sg_res_in_use(sfp))) {
+			if ((0 == sfp->low_dma) && !sfp->res_in_use) {
 				val = (int) sfp->reserve.bufflen;
 				sg_remove_scat(sfp, &sfp->reserve);
 				sg_build_reserve(sfp, val);
@@ -973,12 +980,18 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
                         return -EINVAL;
 		val = min_t(int, val,
 			    max_sectors_bytes(sdp->device->request_queue));
+		mutex_lock(&sfp->f_mutex);
 		if (val != sfp->reserve.bufflen) {
-			if (sg_res_in_use(sfp) || sfp->mmap_called)
+			if (sfp->mmap_called ||
+			    sfp->res_in_use) {
+				mutex_unlock(&sfp->f_mutex);
 				return -EBUSY;
+			}
+
 			sg_remove_scat(sfp, &sfp->reserve);
 			sg_build_reserve(sfp, val);
 		}
+		mutex_unlock(&sfp->f_mutex);
 		return 0;
 	case SG_GET_RESERVED_SIZE:
 		val = min_t(int, sfp->reserve.bufflen,
@@ -1004,6 +1017,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 		result = get_user(val, ip);
 		if (result)
 			return result;
+		if (val > SG_MAX_CDB_SIZE)
+			return -ENOMEM;
 		sfp->next_cmd_len = (val > 0) ? val : 0;
 		return 0;
 	case SG_GET_VERSION_NUM:
@@ -1239,6 +1254,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	unsigned long req_sz, len, sa;
 	Sg_scatter_hold *rsv_schp;
 	int k, length;
+	int ret = 0;
 
 	if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data)))
 		return -ENXIO;
@@ -1249,8 +1265,11 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (vma->vm_pgoff)
 		return -EINVAL;	/* want no offset */
 	rsv_schp = &sfp->reserve;
-	if (req_sz > rsv_schp->bufflen)
-		return -ENOMEM;	/* cannot map more than reserved buffer */
+	mutex_lock(&sfp->f_mutex);
+	if (req_sz > rsv_schp->bufflen) {
+		ret = -ENOMEM;	/* cannot map more than reserved buffer */
+		goto out;
+	}
 
 	sa = vma->vm_start;
 	length = 1 << (PAGE_SHIFT + rsv_schp->page_order);
@@ -1264,7 +1283,9 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_private_data = sfp;
 	vma->vm_ops = &sg_mmap_vm_ops;
-	return 0;
+out:
+	mutex_unlock(&sfp->f_mutex);
+	return ret;
 }
 
 static void
@@ -1731,13 +1752,25 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 		md = &map_data;
 
 	if (md) {
-		if (!sg_res_in_use(sfp) && dxfer_len <= rsv_schp->bufflen)
+		mutex_lock(&sfp->f_mutex);
+		if (dxfer_len <= rsv_schp->bufflen &&
+		    !sfp->res_in_use) {
+			sfp->res_in_use = 1;
 			sg_link_reserve(sfp, srp, dxfer_len);
-		else {
+		} else if (hp->flags & SG_FLAG_MMAP_IO) {
+			res = -EBUSY; /* sfp->res_in_use == 1 */
+			if (dxfer_len > rsv_schp->bufflen)
+				res = -ENOMEM;
+			mutex_unlock(&sfp->f_mutex);
+			return res;
+		} else {
 			res = sg_build_indirect(req_schp, sfp, dxfer_len);
-			if (res)
+			if (res) {
+				mutex_unlock(&sfp->f_mutex);
 				return res;
+			}
 		}
+		mutex_unlock(&sfp->f_mutex);
 
 		md->pages = req_schp->pages;
 		md->page_order = req_schp->page_order;
@@ -1759,6 +1792,10 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			return res;
 
 		iov_iter_truncate(&i, hp->dxfer_len);
+		if (!iov_iter_count(&i)) {
+			kfree(iov);
+			return -EINVAL;
+		}
 
 		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
 		kfree(iov);
@@ -2024,6 +2061,8 @@ sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp)
 	req_schp->sglist_len = 0;
 	sfp->save_scat_len = 0;
 	srp->res_used = 0;
+	/* Called without mutex lock to avoid deadlock */
+	sfp->res_in_use = 0;
 }
 
 static Sg_request *
@@ -2135,6 +2174,7 @@ sg_add_sfp(Sg_device * sdp)
 	rwlock_init(&sfp->rq_list_lock);
 
 	kref_init(&sfp->f_ref);
+	mutex_init(&sfp->f_mutex);
 	sfp->timeout = SG_DEFAULT_TIMEOUT;
 	sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER;
 	sfp->force_packid = SG_DEF_FORCE_PACK_ID;
@@ -2210,20 +2250,6 @@ sg_remove_sfp(struct kref *kref)
 	schedule_work(&sfp->ew.work);
 }
 
-static int
-sg_res_in_use(Sg_fd * sfp)
-{
-	const Sg_request *srp;
-	unsigned long iflags;
-
-	read_lock_irqsave(&sfp->rq_list_lock, iflags);
-	for (srp = sfp->headrp; srp; srp = srp->nextrp)
-		if (srp->res_used)
-			break;
-	read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
-	return srp ? 1 : 0;
-}
-
 #ifdef CONFIG_SCSI_PROC_FS
 static int
 sg_idr_max_id(int id, void *p, void *data)
diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c
index 2b3c25371d76..8175f997e82c 100644
--- a/drivers/scsi/snic/snic_main.c
+++ b/drivers/scsi/snic/snic_main.c
@@ -584,6 +584,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!pool) {
 		SNIC_HOST_ERR(shost, "dflt sgl pool creation failed\n");
 
+		ret = -ENOMEM;
 		goto err_free_res;
 	}
 
@@ -594,6 +595,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!pool) {
 		SNIC_HOST_ERR(shost, "max sgl pool creation failed\n");
 
+		ret = -ENOMEM;
 		goto err_free_dflt_sgl_pool;
 	}
 
@@ -604,6 +606,7 @@ snic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!pool) {
 		SNIC_HOST_ERR(shost, "snic tmreq info pool creation failed.\n");
 
+		ret = -ENOMEM;
 		goto err_free_max_sgl_pool;
 	}
 
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 64c867405ad4..804586aeaffe 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -834,6 +834,7 @@ static void get_capabilities(struct scsi_cd *cd)
 	unsigned char *buffer;
 	struct scsi_mode_data data;
 	struct scsi_sense_hdr sshdr;
+	unsigned int ms_len = 128;
 	int rc, n;
 
 	static const char *loadmech[] =
@@ -860,10 +861,11 @@ static void get_capabilities(struct scsi_cd *cd)
 	scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr);
 
 	/* ask for mode page 0x2a */
-	rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, 128,
+	rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len,
 			     SR_TIMEOUT, 3, &data, NULL);
 
-	if (!scsi_status_is_good(rc)) {
+	if (!scsi_status_is_good(rc) || data.length > ms_len ||
+	    data.header_length + data.block_descriptor_length > data.length) {
 		/* failed, drive doesn't have capabilities mode page */
 		cd->cdi.speed = 1;
 		cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R |
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 3fba42ad9fb8..cd5c1c060481 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -135,6 +135,8 @@ struct hv_fc_wwn_packet {
 #define SRB_FLAGS_PORT_DRIVER_RESERVED		0x0F000000
 #define SRB_FLAGS_CLASS_DRIVER_RESERVED		0xF0000000
 
+#define SP_UNTAGGED			((unsigned char) ~0)
+#define SRB_SIMPLE_TAG_REQUEST		0x20
 
 /*
  * Platform neutral description of a scsi request -
@@ -354,6 +356,7 @@ enum storvsc_request_type {
 #define SRB_STATUS_SUCCESS	0x01
 #define SRB_STATUS_ABORTED	0x02
 #define SRB_STATUS_ERROR	0x04
+#define SRB_STATUS_DATA_OVERRUN	0x12
 
 #define SRB_STATUS(status) \
 	(status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN))
@@ -864,6 +867,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 	switch (SRB_STATUS(vm_srb->srb_status)) {
 	case SRB_STATUS_ERROR:
 		/*
+		 * Let upper layer deal with error when
+		 * sense message is present.
+		 */
+
+		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID)
+			break;
+		/*
 		 * If there is an error; offline the device since all
 		 * error recovery strategies would have already been
 		 * deployed on the host side. However, if the command
@@ -889,8 +899,9 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 		do_work = true;
 		process_err_fn = storvsc_remove_lun;
 		break;
-	case (SRB_STATUS_ABORTED | SRB_STATUS_AUTOSENSE_VALID):
-		if ((asc == 0x2a) && (ascq == 0x9)) {
+	case SRB_STATUS_ABORTED:
+		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID &&
+		    (asc == 0x2a) && (ascq == 0x9)) {
 			do_work = true;
 			process_err_fn = storvsc_device_scan;
 			/*
@@ -926,6 +937,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request)
 	struct hv_host_device *host_dev = shost_priv(scmnd->device->host);
 	struct scsi_sense_hdr sense_hdr;
 	struct vmscsi_request *vm_srb;
+	u32 data_transfer_length;
 	struct Scsi_Host *host;
 	struct storvsc_device *stor_dev;
 	struct hv_device *dev = host_dev->dev;
@@ -936,6 +948,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request)
 	host = stor_dev->host;
 
 	vm_srb = &cmd_request->vstor_packet.vm_srb;
+	data_transfer_length = vm_srb->data_transfer_length;
 
 	scmnd->result = vm_srb->scsi_status;
 
@@ -946,13 +959,20 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request)
 					     &sense_hdr);
 	}
 
-	if (vm_srb->srb_status != SRB_STATUS_SUCCESS)
+	if (vm_srb->srb_status != SRB_STATUS_SUCCESS) {
 		storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc,
 					 sense_hdr.ascq);
+		/*
+		 * The Windows driver set data_transfer_length on
+		 * SRB_STATUS_DATA_OVERRUN. On other errors, this value
+		 * is untouched.  In these cases we set it to 0.
+		 */
+		if (vm_srb->srb_status != SRB_STATUS_DATA_OVERRUN)
+			data_transfer_length = 0;
+	}
 
 	scsi_set_resid(scmnd,
-		cmd_request->payload->range.len -
-		vm_srb->data_transfer_length);
+		cmd_request->payload->range.len - data_transfer_length);
 
 	scmnd->scsi_done(scmnd);
 
@@ -1408,6 +1428,13 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	vm_srb->win8_extension.srb_flags |=
 		SRB_FLAGS_DISABLE_SYNCH_TRANSFER;
 
+	if (scmnd->device->tagged_supported) {
+		vm_srb->win8_extension.srb_flags |=
+		(SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE);
+		vm_srb->win8_extension.queue_tag = SP_UNTAGGED;
+		vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST;
+	}
+
 	/* Build the SRB */
 	switch (scmnd->sc_data_direction) {
 	case DMA_TO_DEVICE:
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 7dbbb29d24c6..03a2aadf0d3c 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -533,7 +533,9 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 {
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
 	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+	unsigned long flags;
 	int req_size;
+	int ret;
 
 	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);
 
@@ -561,8 +563,15 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 		req_size = sizeof(cmd->req.cmd);
 	}
 
-	if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+	ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd));
+	if (ret == -EIO) {
+		cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+		spin_lock_irqsave(&req_vq->vq_lock, flags);
+		virtscsi_complete_cmd(vscsi, cmd);
+		spin_unlock_irqrestore(&req_vq->vq_lock, flags);
+	} else if (ret != 0) {
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 	return 0;
 }
 
diff --git a/drivers/soc/qcom/spm.c b/drivers/soc/qcom/spm.c
index b04b05a0904e..65bce1eecaf8 100644
--- a/drivers/soc/qcom/spm.c
+++ b/drivers/soc/qcom/spm.c
@@ -288,7 +288,7 @@ static struct spm_driver_data *spm_get_drv(struct platform_device *pdev,
 	struct spm_driver_data *drv = NULL;
 	struct device_node *cpu_node, *saw_node;
 	int cpu;
-	bool found;
+	bool found = 0;
 
 	for_each_possible_cpu(cpu) {
 		cpu_node = of_cpu_device_node_get(cpu);
diff --git a/drivers/soc/rockchip/pm_domains.c b/drivers/soc/rockchip/pm_domains.c
index 534c58937a56..4a65c5bda146 100644
--- a/drivers/soc/rockchip/pm_domains.c
+++ b/drivers/soc/rockchip/pm_domains.c
@@ -419,6 +419,7 @@ static int rockchip_pm_domain_probe(struct platform_device *pdev)
 		if (error) {
 			dev_err(dev, "failed to handle node %s: %d\n",
 				node->name, error);
+			of_node_put(node);
 			goto err_out;
 		}
 	}
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 7d3af3eacf57..1ddba9ae8c0f 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -651,7 +651,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 			buf = t->rx_buf;
 		t->rx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_FROM_DEVICE);
-		if (!t->rx_dma) {
+		if (dma_mapping_error(&spi->dev, !t->rx_dma)) {
 			ret = -EFAULT;
 			goto err_rx_map;
 		}
@@ -665,7 +665,7 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 			buf = (void *)t->tx_buf;
 		t->tx_dma = dma_map_single(&spi->dev, buf,
 				t->len, DMA_TO_DEVICE);
-		if (!t->tx_dma) {
+		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
 			ret = -EFAULT;
 			goto err_tx_map;
 		}
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 882cd6618cd5..87a0e47eeae6 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -107,7 +107,10 @@ static const struct file_operations dw_spi_regs_ops = {
 
 static int dw_spi_debugfs_init(struct dw_spi *dws)
 {
-	dws->debugfs = debugfs_create_dir("dw_spi", NULL);
+	char name[128];
+
+	snprintf(name, 128, "dw_spi-%s", dev_name(&dws->master->dev));
+	dws->debugfs = debugfs_create_dir(name, NULL);
 	if (!dws->debugfs)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 39412c9097c6..a3965cac1b34 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -753,7 +753,6 @@ static int dspi_remove(struct platform_device *pdev)
 	/* Disconnect from the SPI framework */
 	clk_disable_unprepare(dspi->clk);
 	spi_unregister_master(dspi->master);
-	spi_master_put(dspi->master);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index a87cfd4ba17b..61a86d391599 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -127,37 +127,62 @@ static int orion_spi_baudrate_set(struct spi_device *spi, unsigned int speed)
 	tclk_hz = clk_get_rate(orion_spi->clk);
 
 	if (devdata->typ == ARMADA_SPI) {
-		unsigned int clk, spr, sppr, sppr2, err;
-		unsigned int best_spr, best_sppr, best_err;
-
-		best_err = speed;
-		best_spr = 0;
-		best_sppr = 0;
-
-		/* Iterate over the valid range looking for best fit */
-		for (sppr = 0; sppr < 8; sppr++) {
-			sppr2 = 0x1 << sppr;
-
-			spr = tclk_hz / sppr2;
-			spr = DIV_ROUND_UP(spr, speed);
-			if ((spr == 0) || (spr > 15))
-				continue;
-
-			clk = tclk_hz / (spr * sppr2);
-			err = speed - clk;
-
-			if (err < best_err) {
-				best_spr = spr;
-				best_sppr = sppr;
-				best_err = err;
-			}
-		}
+		/*
+		 * Given the core_clk (tclk_hz) and the target rate (speed) we
+		 * determine the best values for SPR (in [0 .. 15]) and SPPR (in
+		 * [0..7]) such that
+		 *
+		 * 	core_clk / (SPR * 2 ** SPPR)
+		 *
+		 * is as big as possible but not bigger than speed.
+		 */
 
-		if ((best_sppr == 0) && (best_spr == 0))
-			return -EINVAL;
+		/* best integer divider: */
+		unsigned divider = DIV_ROUND_UP(tclk_hz, speed);
+		unsigned spr, sppr;
+
+		if (divider < 16) {
+			/* This is the easy case, divider is less than 16 */
+			spr = divider;
+			sppr = 0;
+
+		} else {
+			unsigned two_pow_sppr;
+			/*
+			 * Find the highest bit set in divider. This and the
+			 * three next bits define SPR (apart from rounding).
+			 * SPPR is then the number of zero bits that must be
+			 * appended:
+			 */
+			sppr = fls(divider) - 4;
+
+			/*
+			 * As SPR only has 4 bits, we have to round divider up
+			 * to the next multiple of 2 ** sppr.
+			 */
+			two_pow_sppr = 1 << sppr;
+			divider = (divider + two_pow_sppr - 1) & -two_pow_sppr;
+
+			/*
+			 * recalculate sppr as rounding up divider might have
+			 * increased it enough to change the position of the
+			 * highest set bit. In this case the bit that now
+			 * doesn't make it into SPR is 0, so there is no need to
+			 * round again.
+			 */
+			sppr = fls(divider) - 4;
+			spr = divider >> sppr;
+
+			/*
+			 * Now do range checking. SPR is constructed to have a
+			 * width of 4 bits, so this is fine for sure. So we
+			 * still need to check for sppr to fit into 3 bits:
+			 */
+			if (sppr > 7)
+				return -EINVAL;
+		}
 
-		prescale = ((best_sppr & 0x6) << 5) |
-			((best_sppr & 0x1) << 4) | best_spr;
+		prescale = ((sppr & 0x6) << 5) | ((sppr & 0x1) << 4) | spr;
 	} else {
 		/*
 		 * the supported rates are: 4,6,8...30
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index b25dc71b0ea9..3cac73e4c3e4 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -111,7 +111,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.reg_general = -1,
 		.reg_ssp = 0x20,
 		.reg_cs_ctrl = 0x24,
-		.reg_capabilities = 0xfc,
+		.reg_capabilities = -1,
 		.rx_threshold = 1,
 		.tx_threshold_lo = 32,
 		.tx_threshold_hi = 56,
@@ -548,7 +548,14 @@ static void reset_sccr1(struct driver_data *drv_data)
 	u32 sccr1_reg;
 
 	sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1;
-	sccr1_reg &= ~SSCR1_RFT;
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		sccr1_reg &= ~QUARK_X1000_SSCR1_RFT;
+		break;
+	default:
+		sccr1_reg &= ~SSCR1_RFT;
+		break;
+	}
 	sccr1_reg |= chip->threshold;
 	pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg);
 }
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 79a8bc4f6cec..035767c02072 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -265,7 +265,10 @@ static inline u32 rx_max(struct rockchip_spi *rs)
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	u32 ser;
-	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_get_sync(rs->dev);
 
 	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
 
@@ -290,6 +293,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 		ser &= ~(1 << spi->chip_select);
 
 	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+
+	pm_runtime_put_sync(rs->dev);
 }
 
 static int rockchip_spi_prepare_message(struct spi_master *master,
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index a7934ab00b96..d22de4c8c399 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -263,6 +263,9 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 
 	for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
 		brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
+		/* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
+		if (sh_msiof_spi_div_table[k].div == 1 && brps > 2)
+			continue;
 		if (brps <= 32) /* max of brdv is 32 */
 			break;
 	}
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index fbb0a4d74e91..39d7c7c70112 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -170,13 +170,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun4i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
 
 	/* We don't support transfer larger than the FIFO */
 	if (tfr->len > SUN4I_FIFO_DEPTH)
-		return -EINVAL;
+		return -EMSGSIZE;
+
+	if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH)
+		return -EMSGSIZE;
 
 	reinit_completion(&sspi->done);
 	sspi->tx_buf = tfr->tx_buf;
@@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len));
 	sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len));
 
-	/* Fill the TX FIFO */
-	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH);
+	/*
+	 * Fill the TX FIFO
+	 * Filling the FIFO fully causes timeout for some reason
+	 * at least on spi2 on A10s
+	 */
+	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1);
 
 	/* Enable the interrupts */
 	sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC);
@@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index ac48f59705a8..e77add01b0e9 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
@@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 64318fcfacf2..5044c6198332 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -94,6 +94,7 @@ struct ti_qspi {
 #define QSPI_FLEN(n)			((n - 1) << 0)
 #define QSPI_WLEN_MAX_BITS		128
 #define QSPI_WLEN_MAX_BYTES		16
+#define QSPI_WLEN_MASK			QSPI_WLEN(QSPI_WLEN_MAX_BITS)
 
 /* STATUS REGISTER */
 #define BUSY				0x01
@@ -224,16 +225,16 @@ static inline int ti_qspi_poll_wc(struct ti_qspi *qspi)
 	return  -ETIMEDOUT;
 }
 
-static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			  int count)
 {
-	int wlen, count, xfer_len;
+	int wlen, xfer_len;
 	unsigned int cmd;
 	const u8 *txbuf;
 	u32 data;
 
 	txbuf = t->tx_buf;
 	cmd = qspi->cmd | QSPI_WR_SNGL;
-	count = t->len;
 	wlen = t->bits_per_word >> 3;	/* in bytes */
 	xfer_len = wlen;
 
@@ -293,9 +294,10 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
-static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			 int count)
 {
-	int wlen, count;
+	int wlen;
 	unsigned int cmd;
 	u8 *rxbuf;
 
@@ -312,7 +314,6 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 		cmd |= QSPI_RD_SNGL;
 		break;
 	}
-	count = t->len;
 	wlen = t->bits_per_word >> 3;	/* in bytes */
 
 	while (count) {
@@ -343,12 +344,13 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
-static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			     int count)
 {
 	int ret;
 
 	if (t->tx_buf) {
-		ret = qspi_write_msg(qspi, t);
+		ret = qspi_write_msg(qspi, t, count);
 		if (ret) {
 			dev_dbg(qspi->dev, "Error while writing\n");
 			return ret;
@@ -356,7 +358,7 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	}
 
 	if (t->rx_buf) {
-		ret = qspi_read_msg(qspi, t);
+		ret = qspi_read_msg(qspi, t, count);
 		if (ret) {
 			dev_dbg(qspi->dev, "Error while reading\n");
 			return ret;
@@ -373,7 +375,8 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t;
 	int status = 0, ret;
-	int frame_length;
+	unsigned int frame_len_words, transfer_len_words;
+	int wlen;
 
 	/* setup device control reg */
 	qspi->dc = 0;
@@ -385,30 +388,38 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 	if (spi->mode & SPI_CS_HIGH)
 		qspi->dc |= QSPI_CSPOL(spi->chip_select);
 
-	frame_length = (m->frame_length << 3) / spi->bits_per_word;
-
-	frame_length = clamp(frame_length, 0, QSPI_FRAME);
+	frame_len_words = 0;
+	list_for_each_entry(t, &m->transfers, transfer_list)
+		frame_len_words += t->len / (t->bits_per_word >> 3);
+	frame_len_words = min_t(unsigned int, frame_len_words, QSPI_FRAME);
 
 	/* setup command reg */
 	qspi->cmd = 0;
 	qspi->cmd |= QSPI_EN_CS(spi->chip_select);
-	qspi->cmd |= QSPI_FLEN(frame_length);
+	qspi->cmd |= QSPI_FLEN(frame_len_words);
 
 	ti_qspi_write(qspi, qspi->dc, QSPI_SPI_DC_REG);
 
 	mutex_lock(&qspi->list_lock);
 
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		qspi->cmd |= QSPI_WLEN(t->bits_per_word);
+		qspi->cmd = ((qspi->cmd & ~QSPI_WLEN_MASK) |
+			     QSPI_WLEN(t->bits_per_word));
+
+		wlen = t->bits_per_word >> 3;
+		transfer_len_words = min(t->len / wlen, frame_len_words);
 
-		ret = qspi_transfer_msg(qspi, t);
+		ret = qspi_transfer_msg(qspi, t, transfer_len_words * wlen);
 		if (ret) {
 			dev_dbg(qspi->dev, "transfer message failed\n");
 			mutex_unlock(&qspi->list_lock);
 			return -EINVAL;
 		}
 
-		m->actual_length += t->len;
+		m->actual_length += transfer_len_words * wlen;
+		frame_len_words -= transfer_len_words;
+		if (frame_len_words == 0)
+			break;
 	}
 
 	mutex_unlock(&qspi->list_lock);
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 6b3da1bb0d63..2db681722d2c 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -364,11 +364,23 @@ static int spmi_drv_remove(struct device *dev)
 	return 0;
 }
 
+static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	int ret;
+
+	ret = of_device_uevent_modalias(dev, env);
+	if (ret != -ENODEV)
+		return ret;
+
+	return 0;
+}
+
 static struct bus_type spmi_bus_type = {
 	.name		= "spmi",
 	.match		= spmi_device_match,
 	.probe		= spmi_drv_probe,
 	.remove		= spmi_drv_remove,
+	.uevent		= spmi_drv_uevent,
 };
 
 /**
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 0f28c08fcb3c..77b551da5728 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -909,6 +909,7 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 			if (err) {
 				ssb_warn("WARNING: Using fallback SPROM failed (err %d)\n",
 					 err);
+				goto out_free;
 			} else {
 				ssb_dbg("Using SPROM revision %d provided by platform\n",
 					sprom->revision);
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 3f2a3d611e4b..9c6357c03905 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -392,6 +392,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = PTR_ERR(vmfile);
 			goto out;
 		}
+		vmfile->f_mode |= FMODE_LSEEK;
 		asma->file = vmfile;
 	}
 	get_file(asma->file);
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index e237e9f3312d..374f840f31a4 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -251,8 +251,10 @@ static struct ion_buffer *ion_buffer_create(struct ion_heap *heap,
 	 * memory coming from the heaps is ready for dma, ie if it has a
 	 * cached mapping that mapping has been invalidated
 	 */
-	for_each_sg(buffer->sg_table->sgl, sg, buffer->sg_table->nents, i)
+	for_each_sg(buffer->sg_table->sgl, sg, buffer->sg_table->nents, i) {
 		sg_dma_address(sg) = sg_phys(sg);
+		sg_dma_len(sg) = sg->length;
+	}
 	mutex_lock(&dev->buffer_lock);
 	ion_buffer_add(dev, buffer);
 	mutex_unlock(&dev->buffer_lock);
@@ -385,13 +387,22 @@ static void ion_handle_get(struct ion_handle *handle)
 	kref_get(&handle->ref);
 }
 
-static int ion_handle_put(struct ion_handle *handle)
+static int ion_handle_put_nolock(struct ion_handle *handle)
+{
+	int ret;
+
+	ret = kref_put(&handle->ref, ion_handle_destroy);
+
+	return ret;
+}
+
+int ion_handle_put(struct ion_handle *handle)
 {
 	struct ion_client *client = handle->client;
 	int ret;
 
 	mutex_lock(&client->lock);
-	ret = kref_put(&handle->ref, ion_handle_destroy);
+	ret = ion_handle_put_nolock(handle);
 	mutex_unlock(&client->lock);
 
 	return ret;
@@ -415,20 +426,30 @@ static struct ion_handle *ion_handle_lookup(struct ion_client *client,
 	return ERR_PTR(-EINVAL);
 }
 
-static struct ion_handle *ion_handle_get_by_id(struct ion_client *client,
+static struct ion_handle *ion_handle_get_by_id_nolock(struct ion_client *client,
 						int id)
 {
 	struct ion_handle *handle;
 
-	mutex_lock(&client->lock);
 	handle = idr_find(&client->idr, id);
 	if (handle)
 		ion_handle_get(handle);
-	mutex_unlock(&client->lock);
 
 	return handle ? handle : ERR_PTR(-EINVAL);
 }
 
+struct ion_handle *ion_handle_get_by_id(struct ion_client *client,
+						int id)
+{
+	struct ion_handle *handle;
+
+	mutex_lock(&client->lock);
+	handle = ion_handle_get_by_id_nolock(client, id);
+	mutex_unlock(&client->lock);
+
+	return handle;
+}
+
 static bool ion_handle_validate(struct ion_client *client,
 				struct ion_handle *handle)
 {
@@ -530,22 +551,28 @@ struct ion_handle *ion_alloc(struct ion_client *client, size_t len,
 }
 EXPORT_SYMBOL(ion_alloc);
 
-void ion_free(struct ion_client *client, struct ion_handle *handle)
+static void ion_free_nolock(struct ion_client *client, struct ion_handle *handle)
 {
 	bool valid_handle;
 
 	BUG_ON(client != handle->client);
 
-	mutex_lock(&client->lock);
 	valid_handle = ion_handle_validate(client, handle);
 
 	if (!valid_handle) {
 		WARN(1, "%s: invalid handle passed to free.\n", __func__);
-		mutex_unlock(&client->lock);
 		return;
 	}
+	ion_handle_put_nolock(handle);
+}
+
+void ion_free(struct ion_client *client, struct ion_handle *handle)
+{
+	BUG_ON(client != handle->client);
+
+	mutex_lock(&client->lock);
+	ion_free_nolock(client, handle);
 	mutex_unlock(&client->lock);
-	ion_handle_put(handle);
 }
 EXPORT_SYMBOL(ion_free);
 
@@ -1281,11 +1308,15 @@ static long ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	{
 		struct ion_handle *handle;
 
-		handle = ion_handle_get_by_id(client, data.handle.handle);
-		if (IS_ERR(handle))
+		mutex_lock(&client->lock);
+		handle = ion_handle_get_by_id_nolock(client, data.handle.handle);
+		if (IS_ERR(handle)) {
+			mutex_unlock(&client->lock);
 			return PTR_ERR(handle);
-		ion_free(client, handle);
-		ion_handle_put(handle);
+		}
+		ion_free_nolock(client, handle);
+		ion_handle_put_nolock(handle);
+		mutex_unlock(&client->lock);
 		break;
 	}
 	case ION_IOC_SHARE:
diff --git a/drivers/staging/android/ion/ion_test.c b/drivers/staging/android/ion/ion_test.c
index b8dcf5a26cc4..58d46893e5ff 100644
--- a/drivers/staging/android/ion/ion_test.c
+++ b/drivers/staging/android/ion/ion_test.c
@@ -285,8 +285,8 @@ static int __init ion_test_init(void)
 {
 	ion_test_pdev = platform_device_register_simple("ion-test",
 							-1, NULL, 0);
-	if (!ion_test_pdev)
-		return -ENODEV;
+	if (IS_ERR(ion_test_pdev))
+		return PTR_ERR(ion_test_pdev);
 
 	return platform_driver_probe(&ion_test_platform_driver, ion_test_probe);
 }
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 7b4af519e17e..b831f08e2769 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2901,9 +2901,6 @@ static int __init comedi_init(void)
 
 	comedi_class->dev_groups = comedi_dev_groups;
 
-	/* XXX requires /proc interface */
-	comedi_proc_init();
-
 	/* create devices files for legacy/manual use */
 	for (i = 0; i < comedi_num_legacy_minors; i++) {
 		struct comedi_device *dev;
@@ -2911,6 +2908,7 @@ static int __init comedi_init(void)
 		dev = comedi_alloc_board_minor(NULL);
 		if (IS_ERR(dev)) {
 			comedi_cleanup_board_minors();
+			class_destroy(comedi_class);
 			cdev_del(&comedi_cdev);
 			unregister_chrdev_region(MKDEV(COMEDI_MAJOR, 0),
 						 COMEDI_NUM_MINORS);
@@ -2920,6 +2918,9 @@ static int __init comedi_init(void)
 		mutex_unlock(&dev->mutex);
 	}
 
+	/* XXX requires /proc interface */
+	comedi_proc_init();
+
 	return 0;
 }
 module_init(comedi_init);
diff --git a/drivers/staging/comedi/drivers/comedi_test.c b/drivers/staging/comedi/drivers/comedi_test.c
index 4ab186669f0c..ec5b9a23494d 100644
--- a/drivers/staging/comedi/drivers/comedi_test.c
+++ b/drivers/staging/comedi/drivers/comedi_test.c
@@ -56,11 +56,6 @@
 
 #define N_CHANS 8
 
-enum waveform_state_bits {
-	WAVEFORM_AI_RUNNING,
-	WAVEFORM_AO_RUNNING
-};
-
 /* Data unique to this driver */
 struct waveform_private {
 	struct timer_list ai_timer;	/* timer for AI commands */
@@ -68,7 +63,6 @@ struct waveform_private {
 	unsigned int wf_amplitude;	/* waveform amplitude in microvolts */
 	unsigned int wf_period;		/* waveform period in microseconds */
 	unsigned int wf_current;	/* current time in waveform period */
-	unsigned long state_bits;
 	unsigned int ai_scan_period;	/* AI scan period in usec */
 	unsigned int ai_convert_period;	/* AI conversion period in usec */
 	struct timer_list ao_timer;	/* timer for AO commands */
@@ -191,10 +185,6 @@ static void waveform_ai_timer(unsigned long arg)
 	unsigned int nsamples;
 	unsigned int time_increment;
 
-	/* check command is still active */
-	if (!test_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits))
-		return;
-
 	now = ktime_to_us(ktime_get());
 	nsamples = comedi_nsamples_left(s, UINT_MAX);
 
@@ -386,11 +376,6 @@ static int waveform_ai_cmd(struct comedi_device *dev,
 	 */
 	devpriv->ai_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1;
-
-	/* mark command as active */
-	smp_mb__before_atomic();
-	set_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits);
-	smp_mb__after_atomic();
 	add_timer(&devpriv->ai_timer);
 	return 0;
 }
@@ -400,11 +385,12 @@ static int waveform_ai_cancel(struct comedi_device *dev,
 {
 	struct waveform_private *devpriv = dev->private;
 
-	/* mark command as no longer active */
-	clear_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits);
-	smp_mb__after_atomic();
-	/* cannot call del_timer_sync() as may be called from timer routine */
-	del_timer(&devpriv->ai_timer);
+	if (in_softirq()) {
+		/* Assume we were called from the timer routine itself. */
+		del_timer(&devpriv->ai_timer);
+	} else {
+		del_timer_sync(&devpriv->ai_timer);
+	}
 	return 0;
 }
 
@@ -436,10 +422,6 @@ static void waveform_ao_timer(unsigned long arg)
 	u64 scans_since;
 	unsigned int scans_avail = 0;
 
-	/* check command is still active */
-	if (!test_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits))
-		return;
-
 	/* determine number of scan periods since last time */
 	now = ktime_to_us(ktime_get());
 	scans_since = now - devpriv->ao_last_scan_time;
@@ -518,11 +500,6 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev,
 	devpriv->ao_last_scan_time = ktime_to_us(ktime_get());
 	devpriv->ao_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ao_scan_period);
-
-	/* mark command as active */
-	smp_mb__before_atomic();
-	set_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits);
-	smp_mb__after_atomic();
 	add_timer(&devpriv->ao_timer);
 
 	return 1;
@@ -608,11 +585,12 @@ static int waveform_ao_cancel(struct comedi_device *dev,
 	struct waveform_private *devpriv = dev->private;
 
 	s->async->inttrig = NULL;
-	/* mark command as no longer active */
-	clear_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits);
-	smp_mb__after_atomic();
-	/* cannot call del_timer_sync() as may be called from timer routine */
-	del_timer(&devpriv->ao_timer);
+	if (in_softirq()) {
+		/* Assume we were called from the timer routine itself. */
+		del_timer(&devpriv->ao_timer);
+	} else {
+		del_timer_sync(&devpriv->ao_timer);
+	}
 	return 0;
 }
 
diff --git a/drivers/staging/comedi/drivers/daqboard2000.c b/drivers/staging/comedi/drivers/daqboard2000.c
index 57ab6680e3ae..e5fee6e0fb47 100644
--- a/drivers/staging/comedi/drivers/daqboard2000.c
+++ b/drivers/staging/comedi/drivers/daqboard2000.c
@@ -636,7 +636,7 @@ static const void *daqboard2000_find_boardinfo(struct comedi_device *dev,
 	const struct daq200_boardtype *board;
 	int i;
 
-	if (pcidev->subsystem_device != PCI_VENDOR_ID_IOTECH)
+	if (pcidev->subsystem_vendor != PCI_VENDOR_ID_IOTECH)
 		return NULL;
 
 	for (i = 0; i < ARRAY_SIZE(boardtypes); i++) {
diff --git a/drivers/staging/comedi/drivers/das1800.c b/drivers/staging/comedi/drivers/das1800.c
index 940781183fac..3be10963f98b 100644
--- a/drivers/staging/comedi/drivers/das1800.c
+++ b/drivers/staging/comedi/drivers/das1800.c
@@ -567,14 +567,17 @@ static int das1800_cancel(struct comedi_device *dev, struct comedi_subdevice *s)
 	struct comedi_isadma_desc *desc;
 	int i;
 
-	outb(0x0, dev->iobase + DAS1800_STATUS);	/* disable conversions */
-	outb(0x0, dev->iobase + DAS1800_CONTROL_B);	/* disable interrupts and dma */
-	outb(0x0, dev->iobase + DAS1800_CONTROL_A);	/* disable and clear fifo and stop triggering */
-
-	for (i = 0; i < 2; i++) {
-		desc = &dma->desc[i];
-		if (desc->chan)
-			comedi_isadma_disable(desc->chan);
+	/* disable and stop conversions */
+	outb(0x0, dev->iobase + DAS1800_STATUS);
+	outb(0x0, dev->iobase + DAS1800_CONTROL_B);
+	outb(0x0, dev->iobase + DAS1800_CONTROL_A);
+
+	if (dma) {
+		for (i = 0; i < 2; i++) {
+			desc = &dma->desc[i];
+			if (desc->chan)
+				comedi_isadma_disable(desc->chan);
+		}
 	}
 
 	return 0;
@@ -934,13 +937,14 @@ static void das1800_ai_setup_dma(struct comedi_device *dev,
 {
 	struct das1800_private *devpriv = dev->private;
 	struct comedi_isadma *dma = devpriv->dma;
-	struct comedi_isadma_desc *desc = &dma->desc[0];
+	struct comedi_isadma_desc *desc;
 	unsigned int bytes;
 
 	if ((devpriv->irq_dma_bits & DMA_ENABLED) == 0)
 		return;
 
 	dma->cur_dma = 0;
+	desc = &dma->desc[0];
 
 	/* determine a dma transfer size to fill buffer in 0.3 sec */
 	bytes = das1800_ai_transfer_size(dev, s, desc->maxsize, 300000000);
diff --git a/drivers/staging/comedi/drivers/dt282x.c b/drivers/staging/comedi/drivers/dt282x.c
index 5a536a00066f..b63472de761a 100644
--- a/drivers/staging/comedi/drivers/dt282x.c
+++ b/drivers/staging/comedi/drivers/dt282x.c
@@ -69,48 +69,49 @@
  * Register map
  */
 #define DT2821_ADCSR_REG		0x00
-#define DT2821_ADCSR_ADERR		(1 << 15)
-#define DT2821_ADCSR_ADCLK		(1 << 9)
-#define DT2821_ADCSR_MUXBUSY		(1 << 8)
-#define DT2821_ADCSR_ADDONE		(1 << 7)
-#define DT2821_ADCSR_IADDONE		(1 << 6)
+#define DT2821_ADCSR_ADERR		BIT(15)
+#define DT2821_ADCSR_ADCLK		BIT(9)
+#define DT2821_ADCSR_MUXBUSY		BIT(8)
+#define DT2821_ADCSR_ADDONE		BIT(7)
+#define DT2821_ADCSR_IADDONE		BIT(6)
 #define DT2821_ADCSR_GS(x)		(((x) & 0x3) << 4)
 #define DT2821_ADCSR_CHAN(x)		(((x) & 0xf) << 0)
 #define DT2821_CHANCSR_REG		0x02
-#define DT2821_CHANCSR_LLE		(1 << 15)
-#define DT2821_CHANCSR_PRESLA(x)	(((x) & 0xf) >> 8)
+#define DT2821_CHANCSR_LLE		BIT(15)
+#define DT2821_CHANCSR_TO_PRESLA(x)	(((x) >> 8) & 0xf)
 #define DT2821_CHANCSR_NUMB(x)		((((x) - 1) & 0xf) << 0)
 #define DT2821_ADDAT_REG		0x04
 #define DT2821_DACSR_REG		0x06
-#define DT2821_DACSR_DAERR		(1 << 15)
+#define DT2821_DACSR_DAERR		BIT(15)
 #define DT2821_DACSR_YSEL(x)		((x) << 9)
-#define DT2821_DACSR_SSEL		(1 << 8)
-#define DT2821_DACSR_DACRDY		(1 << 7)
-#define DT2821_DACSR_IDARDY		(1 << 6)
-#define DT2821_DACSR_DACLK		(1 << 5)
-#define DT2821_DACSR_HBOE		(1 << 1)
-#define DT2821_DACSR_LBOE		(1 << 0)
+#define DT2821_DACSR_SSEL		BIT(8)
+#define DT2821_DACSR_DACRDY		BIT(7)
+#define DT2821_DACSR_IDARDY		BIT(6)
+#define DT2821_DACSR_DACLK		BIT(5)
+#define DT2821_DACSR_HBOE		BIT(1)
+#define DT2821_DACSR_LBOE		BIT(0)
 #define DT2821_DADAT_REG		0x08
 #define DT2821_DIODAT_REG		0x0a
 #define DT2821_SUPCSR_REG		0x0c
-#define DT2821_SUPCSR_DMAD		(1 << 15)
-#define DT2821_SUPCSR_ERRINTEN		(1 << 14)
-#define DT2821_SUPCSR_CLRDMADNE		(1 << 13)
-#define DT2821_SUPCSR_DDMA		(1 << 12)
-#define DT2821_SUPCSR_DS_PIO		(0 << 10)
-#define DT2821_SUPCSR_DS_AD_CLK		(1 << 10)
-#define DT2821_SUPCSR_DS_DA_CLK		(2 << 10)
-#define DT2821_SUPCSR_DS_AD_TRIG	(3 << 10)
-#define DT2821_SUPCSR_BUFFB		(1 << 9)
-#define DT2821_SUPCSR_SCDN		(1 << 8)
-#define DT2821_SUPCSR_DACON		(1 << 7)
-#define DT2821_SUPCSR_ADCINIT		(1 << 6)
-#define DT2821_SUPCSR_DACINIT		(1 << 5)
-#define DT2821_SUPCSR_PRLD		(1 << 4)
-#define DT2821_SUPCSR_STRIG		(1 << 3)
-#define DT2821_SUPCSR_XTRIG		(1 << 2)
-#define DT2821_SUPCSR_XCLK		(1 << 1)
-#define DT2821_SUPCSR_BDINIT		(1 << 0)
+#define DT2821_SUPCSR_DMAD		BIT(15)
+#define DT2821_SUPCSR_ERRINTEN		BIT(14)
+#define DT2821_SUPCSR_CLRDMADNE		BIT(13)
+#define DT2821_SUPCSR_DDMA		BIT(12)
+#define DT2821_SUPCSR_DS(x)		(((x) & 0x3) << 10)
+#define DT2821_SUPCSR_DS_PIO		DT2821_SUPCSR_DS(0)
+#define DT2821_SUPCSR_DS_AD_CLK		DT2821_SUPCSR_DS(1)
+#define DT2821_SUPCSR_DS_DA_CLK		DT2821_SUPCSR_DS(2)
+#define DT2821_SUPCSR_DS_AD_TRIG	DT2821_SUPCSR_DS(3)
+#define DT2821_SUPCSR_BUFFB		BIT(9)
+#define DT2821_SUPCSR_SCDN		BIT(8)
+#define DT2821_SUPCSR_DACON		BIT(7)
+#define DT2821_SUPCSR_ADCINIT		BIT(6)
+#define DT2821_SUPCSR_DACINIT		BIT(5)
+#define DT2821_SUPCSR_PRLD		BIT(4)
+#define DT2821_SUPCSR_STRIG		BIT(3)
+#define DT2821_SUPCSR_XTRIG		BIT(2)
+#define DT2821_SUPCSR_XCLK		BIT(1)
+#define DT2821_SUPCSR_BDINIT		BIT(0)
 #define DT2821_TMRCTR_REG		0x0e
 
 static const struct comedi_lrange range_dt282x_ai_lo_bipolar = {
diff --git a/drivers/staging/comedi/drivers/jr3_pci.c b/drivers/staging/comedi/drivers/jr3_pci.c
index b87192e0f9aa..109becdabc24 100644
--- a/drivers/staging/comedi/drivers/jr3_pci.c
+++ b/drivers/staging/comedi/drivers/jr3_pci.c
@@ -610,7 +610,7 @@ static void jr3_pci_poll_dev(unsigned long data)
 		s = &dev->subdevices[i];
 		spriv = s->private;
 
-		if (now > spriv->next_time_min) {
+		if (time_after_eq(now, spriv->next_time_min)) {
 			struct jr3_pci_poll_delay sub_delay;
 
 			sub_delay = jr3_pci_poll_subdevice(s);
@@ -726,11 +726,12 @@ static int jr3_pci_auto_attach(struct comedi_device *dev,
 		s->insn_read	= jr3_pci_ai_insn_read;
 
 		spriv = jr3_pci_alloc_spriv(dev, s);
-		if (spriv) {
-			/* Channel specific range and maxdata */
-			s->range_table_list	= spriv->range_table_list;
-			s->maxdata_list		= spriv->maxdata_list;
-		}
+		if (!spriv)
+			return -ENOMEM;
+
+		/* Channel specific range and maxdata */
+		s->range_table_list	= spriv->range_table_list;
+		s->maxdata_list		= spriv->maxdata_list;
 	}
 
 	/*  Reset DSP card */
diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c
index 6cc304a4c59b..c975f6e8be49 100644
--- a/drivers/staging/comedi/drivers/ni_mio_common.c
+++ b/drivers/staging/comedi/drivers/ni_mio_common.c
@@ -246,24 +246,24 @@ static void ni_writel(struct comedi_device *dev, uint32_t data, int reg)
 {
 	if (dev->mmio)
 		writel(data, dev->mmio + reg);
-
-	outl(data, dev->iobase + reg);
+	else
+		outl(data, dev->iobase + reg);
 }
 
 static void ni_writew(struct comedi_device *dev, uint16_t data, int reg)
 {
 	if (dev->mmio)
 		writew(data, dev->mmio + reg);
-
-	outw(data, dev->iobase + reg);
+	else
+		outw(data, dev->iobase + reg);
 }
 
 static void ni_writeb(struct comedi_device *dev, uint8_t data, int reg)
 {
 	if (dev->mmio)
 		writeb(data, dev->mmio + reg);
-
-	outb(data, dev->iobase + reg);
+	else
+		outb(data, dev->iobase + reg);
 }
 
 static uint32_t ni_readl(struct comedi_device *dev, int reg)
@@ -1929,7 +1929,7 @@ static int ni_ai_insn_read(struct comedi_device *dev,
 			   unsigned int *data)
 {
 	struct ni_private *devpriv = dev->private;
-	unsigned int mask = (s->maxdata + 1) >> 1;
+	unsigned int mask = s->maxdata;
 	int i, n;
 	unsigned signbits;
 	unsigned int d;
@@ -1972,7 +1972,7 @@ static int ni_ai_insn_read(struct comedi_device *dev,
 				return -ETIME;
 			}
 			d += signbits;
-			data[n] = d;
+			data[n] = d & 0xffff;
 		}
 	} else if (devpriv->is_6143) {
 		for (n = 0; n < insn->n; n++) {
@@ -2017,8 +2017,8 @@ static int ni_ai_insn_read(struct comedi_device *dev,
 				data[n] = dl;
 			} else {
 				d = ni_readw(dev, NI_E_AI_FIFO_DATA_REG);
-				d += signbits;	/* subtle: needs to be short addition */
-				data[n] = d;
+				d += signbits;
+				data[n] = d & 0xffff;
 			}
 		}
 	}
@@ -2823,7 +2823,15 @@ static int ni_ao_inttrig(struct comedi_device *dev,
 	int i;
 	static const int timeout = 1000;
 
-	if (trig_num != cmd->start_arg)
+	/*
+	 * Require trig_num == cmd->start_arg when cmd->start_src == TRIG_INT.
+	 * For backwards compatibility, also allow trig_num == 0 when
+	 * cmd->start_src != TRIG_INT (i.e. when cmd->start_src == TRIG_EXT);
+	 * in that case, the internal trigger is being used as a pre-trigger
+	 * before the external trigger.
+	 */
+	if (!(trig_num == cmd->start_arg ||
+	      (trig_num == 0 && cmd->start_src != TRIG_INT)))
 		return -EINVAL;
 
 	/* Null trig at beginning prevent ao start trigger from executing more than
@@ -5346,7 +5354,7 @@ static int ni_E_init(struct comedi_device *dev,
 		s->maxdata	= (devpriv->is_m_series) ? 0xffffffff
 							 : 0x00ffffff;
 		s->insn_read	= ni_tio_insn_read;
-		s->insn_write	= ni_tio_insn_read;
+		s->insn_write	= ni_tio_insn_write;
 		s->insn_config	= ni_tio_insn_config;
 #ifdef PCIDMA
 		if (dev->irq && devpriv->mite) {
diff --git a/drivers/staging/comedi/drivers/ni_tiocmd.c b/drivers/staging/comedi/drivers/ni_tiocmd.c
index 437f723bb34d..823e47910004 100644
--- a/drivers/staging/comedi/drivers/ni_tiocmd.c
+++ b/drivers/staging/comedi/drivers/ni_tiocmd.c
@@ -92,7 +92,7 @@ static int ni_tio_input_inttrig(struct comedi_device *dev,
 	unsigned long flags;
 	int ret = 0;
 
-	if (trig_num != cmd->start_src)
+	if (trig_num != cmd->start_arg)
 		return -EINVAL;
 
 	spin_lock_irqsave(&counter->lock, flags);
diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c
index 4e6c16af40fc..91ff8fb0cc3a 100644
--- a/drivers/staging/emxx_udc/emxx_udc.c
+++ b/drivers/staging/emxx_udc/emxx_udc.c
@@ -3181,7 +3181,7 @@ static const struct {
 };
 
 /*-------------------------------------------------------------------------*/
-static void __init nbu2ss_drv_ep_init(struct nbu2ss_udc *udc)
+static void nbu2ss_drv_ep_init(struct nbu2ss_udc *udc)
 {
 	int	i;
 
@@ -3211,7 +3211,7 @@ static void __init nbu2ss_drv_ep_init(struct nbu2ss_udc *udc)
 
 /*-------------------------------------------------------------------------*/
 /* platform_driver */
-static int __init nbu2ss_drv_contest_init(
+static int nbu2ss_drv_contest_init(
 	struct platform_device *pdev,
 	struct nbu2ss_udc *udc)
 {
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index b1e45161eefc..18c2b6daf588 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -392,11 +392,11 @@ static void fbtft_update_display(struct fbtft_par *par, unsigned start_line,
 
 	if (unlikely(timeit)) {
 		ts_end = ktime_get();
-		if (ktime_to_ns(par->update_time))
+		if (!ktime_to_ns(par->update_time))
 			par->update_time = ts_start;
 
-		par->update_time = ts_start;
 		fps = ktime_us_delta(ts_start, par->update_time);
+		par->update_time = ts_start;
 		fps = fps ? 1000000 / fps : 0;
 
 		throughput = ktime_us_delta(ts_end, ts_start);
diff --git a/drivers/staging/gdm724x/gdm_mux.c b/drivers/staging/gdm724x/gdm_mux.c
index 445f83615575..fb4f3fea6c66 100644
--- a/drivers/staging/gdm724x/gdm_mux.c
+++ b/drivers/staging/gdm724x/gdm_mux.c
@@ -670,14 +670,14 @@ static int __init gdm_usb_mux_init(void)
 
 static void __exit gdm_usb_mux_exit(void)
 {
-	unregister_lte_tty_driver();
-
 	if (mux_rx_wq) {
 		flush_workqueue(mux_rx_wq);
 		destroy_workqueue(mux_rx_wq);
 	}
 
 	usb_deregister(&gdm_mux_driver);
+	unregister_lte_tty_driver();
+
 }
 
 module_init(gdm_usb_mux_init);
diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index 02e930c55570..e4839ee4ca61 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -595,7 +595,7 @@ static ssize_t sca3000_read_frequency(struct device *dev,
 		goto error_ret_mut;
 	ret = sca3000_read_ctrl_reg(st, SCA3000_REG_CTRL_SEL_OUT_CTRL);
 	mutex_unlock(&st->lock);
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	val = ret;
 	if (base_freq > 0)
diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c
index bb40f3728742..20314ff08be0 100644
--- a/drivers/staging/iio/adc/ad7192.c
+++ b/drivers/staging/iio/adc/ad7192.c
@@ -236,7 +236,7 @@ static int ad7192_setup(struct ad7192_state *st,
 			st->mclk = pdata->ext_clk_hz;
 		else
 			st->mclk = AD7192_INT_FREQ_MHZ;
-			break;
+		break;
 	default:
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/staging/iio/adc/ad7606_core.c b/drivers/staging/iio/adc/ad7606_core.c
index 5796ed2409d0..39bbbaaff07c 100644
--- a/drivers/staging/iio/adc/ad7606_core.c
+++ b/drivers/staging/iio/adc/ad7606_core.c
@@ -189,7 +189,7 @@ static ssize_t ad7606_store_oversampling_ratio(struct device *dev,
 	mutex_lock(&indio_dev->mlock);
 	gpio_set_value(st->pdata->gpio_os0, (ret >> 0) & 1);
 	gpio_set_value(st->pdata->gpio_os1, (ret >> 1) & 1);
-	gpio_set_value(st->pdata->gpio_os1, (ret >> 2) & 1);
+	gpio_set_value(st->pdata->gpio_os2, (ret >> 2) & 1);
 	st->oversampling = lval;
 	mutex_unlock(&indio_dev->mlock);
 
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 10c43dda0f5a..196da09e20a1 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -647,6 +647,7 @@ static void ad5933_work(struct work_struct *work)
 	__be16 buf[2];
 	int val[2];
 	unsigned char status;
+	int ret;
 
 	mutex_lock(&indio_dev->mlock);
 	if (st->state == AD5933_CTRL_INIT_START_FREQ) {
@@ -654,19 +655,22 @@ static void ad5933_work(struct work_struct *work)
 		ad5933_cmd(st, AD5933_CTRL_START_SWEEP);
 		st->state = AD5933_CTRL_START_SWEEP;
 		schedule_delayed_work(&st->work, st->poll_time_jiffies);
-		mutex_unlock(&indio_dev->mlock);
-		return;
+		goto out;
 	}
 
-	ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status);
+	ret = ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status);
+	if (ret)
+		goto out;
 
 	if (status & AD5933_STAT_DATA_VALID) {
 		int scan_count = bitmap_weight(indio_dev->active_scan_mask,
 					       indio_dev->masklength);
-		ad5933_i2c_read(st->client,
+		ret = ad5933_i2c_read(st->client,
 				test_bit(1, indio_dev->active_scan_mask) ?
 				AD5933_REG_REAL_DATA : AD5933_REG_IMAG_DATA,
 				scan_count * 2, (u8 *)buf);
+		if (ret)
+			goto out;
 
 		if (scan_count == 2) {
 			val[0] = be16_to_cpu(buf[0]);
@@ -678,8 +682,7 @@ static void ad5933_work(struct work_struct *work)
 	} else {
 		/* no data available - try again later */
 		schedule_delayed_work(&st->work, st->poll_time_jiffies);
-		mutex_unlock(&indio_dev->mlock);
-		return;
+		goto out;
 	}
 
 	if (status & AD5933_STAT_SWEEP_DONE) {
@@ -691,7 +694,7 @@ static void ad5933_work(struct work_struct *work)
 		ad5933_cmd(st, AD5933_CTRL_INC_FREQ);
 		schedule_delayed_work(&st->work, st->poll_time_jiffies);
 	}
-
+out:
 	mutex_unlock(&indio_dev->mlock);
 }
 
diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c
index d97aa2827412..8eb7179da342 100644
--- a/drivers/staging/iio/resolver/ad2s1210.c
+++ b/drivers/staging/iio/resolver/ad2s1210.c
@@ -468,7 +468,7 @@ static int ad2s1210_read_raw(struct iio_dev *indio_dev,
 			     long m)
 {
 	struct ad2s1210_state *st = iio_priv(indio_dev);
-	bool negative;
+	u16 negative;
 	int ret = 0;
 	u16 pos;
 	s16 vel;
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 9096d311e45d..c2d9b793759d 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -631,8 +631,6 @@ struct ll_file_data {
 
 struct lov_stripe_md;
 
-extern spinlock_t inode_lock;
-
 extern struct dentry *llite_root;
 extern struct kset *llite_kset;
 
diff --git a/drivers/staging/lustre/lustre/lov/lov_pack.c b/drivers/staging/lustre/lustre/lov/lov_pack.c
index 2fb1e974cc70..e11b1001d1f6 100644
--- a/drivers/staging/lustre/lustre/lov/lov_pack.c
+++ b/drivers/staging/lustre/lustre/lov/lov_pack.c
@@ -399,18 +399,10 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm,
 	struct lov_mds_md *lmmk = NULL;
 	int rc, lmm_size;
 	int lum_size;
-	mm_segment_t seg;
 
 	if (!lsm)
 		return -ENODATA;
 
-	/*
-	 * "Switch to kernel segment" to allow copying from kernel space by
-	 * copy_{to,from}_user().
-	 */
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-
 	/* we only need the header part from user space to get lmm_magic and
 	 * lmm_stripe_count, (the header part is common to v1 and v3) */
 	lum_size = sizeof(struct lov_user_md_v1);
@@ -485,6 +477,5 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm,
 
 	obd_free_diskmd(exp, &lmmk);
 out_set:
-	set_fs(seg);
 	return rc;
 }
diff --git a/drivers/staging/nvec/nvec_ps2.c b/drivers/staging/nvec/nvec_ps2.c
index 0922dd3a08d3..196f6b0a288f 100644
--- a/drivers/staging/nvec/nvec_ps2.c
+++ b/drivers/staging/nvec/nvec_ps2.c
@@ -106,13 +106,12 @@ static int nvec_mouse_probe(struct platform_device *pdev)
 {
 	struct nvec_chip *nvec = dev_get_drvdata(pdev->dev.parent);
 	struct serio *ser_dev;
-	char mouse_reset[] = { NVEC_PS2, SEND_COMMAND, PSMOUSE_RST, 3 };
 
-	ser_dev = devm_kzalloc(&pdev->dev, sizeof(struct serio), GFP_KERNEL);
+	ser_dev = kzalloc(sizeof(struct serio), GFP_KERNEL);
 	if (!ser_dev)
 		return -ENOMEM;
 
-	ser_dev->id.type = SERIO_PS_PSTHRU;
+	ser_dev->id.type = SERIO_8042;
 	ser_dev->write = ps2_sendcommand;
 	ser_dev->start = ps2_startstreaming;
 	ser_dev->stop = ps2_stopstreaming;
@@ -127,9 +126,6 @@ static int nvec_mouse_probe(struct platform_device *pdev)
 
 	serio_register_port(ser_dev);
 
-	/* mouse reset */
-	nvec_write_async(nvec, mouse_reset, sizeof(mouse_reset));
-
 	return 0;
 }
 
diff --git a/drivers/staging/rdma/ehca/ehca_mrmw.c b/drivers/staging/rdma/ehca/ehca_mrmw.c
index f914b30999f8..4d52ca42644a 100644
--- a/drivers/staging/rdma/ehca/ehca_mrmw.c
+++ b/drivers/staging/rdma/ehca/ehca_mrmw.c
@@ -1921,7 +1921,7 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 				  u64 *kpage)
 {
 	int ret = 0;
-	u64 pgaddr, prev_pgaddr;
+	u64 pgaddr, prev_pgaddr = 0;
 	u32 j = 0;
 	int kpages_per_hwpage = pginfo->hwpage_size / PAGE_SIZE;
 	int nr_kpages = kpages_per_hwpage;
@@ -2417,6 +2417,7 @@ static int ehca_reg_bmap_mr_rpages(struct ehca_shca *shca,
 		ehca_err(&shca->ib_device, "kpage alloc failed");
 		return -ENOMEM;
 	}
+	hret = H_SUCCESS;
 	for (top = 0; top < EHCA_MAP_ENTRIES; top++) {
 		if (!ehca_bmap_valid(ehca_bmap->top[top]))
 			continue;
diff --git a/drivers/staging/rdma/hfi1/TODO b/drivers/staging/rdma/hfi1/TODO
index 05de0dad8762..4c6f1d7d2eaf 100644
--- a/drivers/staging/rdma/hfi1/TODO
+++ b/drivers/staging/rdma/hfi1/TODO
@@ -3,4 +3,4 @@ July, 2015
 - Remove unneeded file entries in sysfs
 - Remove software processing of IB protocol and place in library for use
   by qib, ipath (if still present), hfi1, and eventually soft-roce
-
+- Replace incorrect uAPI
diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c
index aae9826ec62b..c851e51b1dc3 100644
--- a/drivers/staging/rdma/hfi1/file_ops.c
+++ b/drivers/staging/rdma/hfi1/file_ops.c
@@ -62,6 +62,8 @@
 #include <linux/cred.h>
 #include <linux/uio.h>
 
+#include <rdma/ib.h>
+
 #include "hfi.h"
 #include "pio.h"
 #include "device.h"
@@ -214,6 +216,10 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data,
 	int uctxt_required = 1;
 	int must_be_root = 0;
 
+	/* FIXME: This interface cannot continue out of staging */
+	if (WARN_ON_ONCE(!ib_safe_file_access(fp)))
+		return -EACCES;
+
 	if (count < sizeof(cmd)) {
 		ret = -EINVAL;
 		goto bail;
diff --git a/drivers/staging/rdma/ipath/ipath_file_ops.c b/drivers/staging/rdma/ipath/ipath_file_ops.c
index 13c3cd11ab92..05d30f433b19 100644
--- a/drivers/staging/rdma/ipath/ipath_file_ops.c
+++ b/drivers/staging/rdma/ipath/ipath_file_ops.c
@@ -45,6 +45,8 @@
 #include <linux/uio.h>
 #include <asm/pgtable.h>
 
+#include <rdma/ib.h>
+
 #include "ipath_kernel.h"
 #include "ipath_common.h"
 #include "ipath_user_sdma.h"
@@ -2243,6 +2245,9 @@ static ssize_t ipath_write(struct file *fp, const char __user *data,
 	ssize_t ret = 0;
 	void *dest;
 
+	if (WARN_ON_ONCE(!ib_safe_file_access(fp)))
+		return -EACCES;
+
 	if (count < sizeof(cmd.type)) {
 		ret = -EINVAL;
 		goto bail;
diff --git a/drivers/staging/rtl8188eu/core/rtw_ap.c b/drivers/staging/rtl8188eu/core/rtw_ap.c
index 3cdb40fea5ee..f5cedbbc552a 100644
--- a/drivers/staging/rtl8188eu/core/rtw_ap.c
+++ b/drivers/staging/rtl8188eu/core/rtw_ap.c
@@ -894,7 +894,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 		return _FAIL;
 
 
-	if (len > MAX_IE_SZ)
+	if (len < 0 || len > MAX_IE_SZ)
 		return _FAIL;
 
 	pbss_network->IELength = len;
diff --git a/drivers/staging/rtl8188eu/core/rtw_cmd.c b/drivers/staging/rtl8188eu/core/rtw_cmd.c
index 9b7026e7d55b..45d0a87f55d2 100644
--- a/drivers/staging/rtl8188eu/core/rtw_cmd.c
+++ b/drivers/staging/rtl8188eu/core/rtw_cmd.c
@@ -718,13 +718,13 @@ u8 rtw_addbareq_cmd(struct adapter *padapter, u8 tid, u8 *addr)
 	u8	res = _SUCCESS;
 
 
-	ph2c = kzalloc(sizeof(struct cmd_obj), GFP_KERNEL);
+	ph2c = kzalloc(sizeof(struct cmd_obj), GFP_ATOMIC);
 	if (ph2c == NULL) {
 		res = _FAIL;
 		goto exit;
 	}
 
-	paddbareq_parm = kzalloc(sizeof(struct addBaReq_parm), GFP_KERNEL);
+	paddbareq_parm = kzalloc(sizeof(struct addBaReq_parm), GFP_ATOMIC);
 	if (paddbareq_parm == NULL) {
 		kfree(ph2c);
 		res = _FAIL;
diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c
index 110b8c0b6cd7..0f2fe34e14c2 100644
--- a/drivers/staging/rtl8188eu/core/rtw_recv.c
+++ b/drivers/staging/rtl8188eu/core/rtw_recv.c
@@ -1405,6 +1405,9 @@ static int wlanhdr_to_ethhdr(struct recv_frame *precvframe)
 		ptr = recvframe_pull(precvframe, (rmv_len-sizeof(struct ethhdr) + (bsnaphdr ? 2 : 0)));
 	}
 
+	if (!ptr)
+		return _FAIL;
+
 	memcpy(ptr, pattrib->dst, ETH_ALEN);
 	memcpy(ptr+ETH_ALEN, pattrib->src, ETH_ALEN);
 
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 82a7c27c517f..c2d2c17550a7 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -47,7 +47,9 @@ static struct usb_device_id rtw_usb_id_tbl[] = {
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
 	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
 	{USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */
+	{USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */
 	{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
+	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
index e9c4f973bba9..7a8ceb961bb6 100644
--- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
+++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c
@@ -97,8 +97,9 @@ void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val)
 
 	switch (variable) {
 	case HW_VAR_BSSID:
-		rtl92e_writel(dev, BSSIDR, ((u32 *)(val))[0]);
-		rtl92e_writew(dev, BSSIDR+2, ((u16 *)(val+2))[0]);
+		/* BSSIDR 2 byte alignment */
+		rtl92e_writew(dev, BSSIDR, *(u16 *)val);
+		rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(val + 2));
 		break;
 
 	case HW_VAR_MEDIA_STATUS:
@@ -626,7 +627,7 @@ void rtl92e_get_eeprom_size(struct net_device *dev)
 	struct r8192_priv *priv = rtllib_priv(dev);
 
 	RT_TRACE(COMP_INIT, "===========>%s()\n", __func__);
-	curCR = rtl92e_readl(dev, EPROM_CMD);
+	curCR = rtl92e_readw(dev, EPROM_CMD);
 	RT_TRACE(COMP_INIT, "read from Reg Cmd9346CR(%x):%x\n", EPROM_CMD,
 		 curCR);
 	priv->epromtype = (curCR & EPROM_CMD_9356SEL) ? EEPROM_93C56 :
@@ -963,8 +964,8 @@ static void _rtl92e_net_update(struct net_device *dev)
 	rtl92e_config_rate(dev, &rate_config);
 	priv->dot11CurrentPreambleMode = PREAMBLE_AUTO;
 	 priv->basic_rate = rate_config &= 0x15f;
-	rtl92e_writel(dev, BSSIDR, ((u32 *)net->bssid)[0]);
-	rtl92e_writew(dev, BSSIDR+4, ((u16 *)net->bssid)[2]);
+	rtl92e_writew(dev, BSSIDR, *(u16 *)net->bssid);
+	rtl92e_writel(dev, BSSIDR + 2, *(u32 *)(net->bssid + 2));
 
 	if (priv->rtllib->iw_mode == IW_MODE_ADHOC) {
 		rtl92e_writew(dev, ATIMWND, 2);
@@ -1184,8 +1185,7 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 			  struct cb_desc *cb_desc, struct sk_buff *skb)
 {
 	struct r8192_priv *priv = rtllib_priv(dev);
-	dma_addr_t mapping = pci_map_single(priv->pdev, skb->data, skb->len,
-			 PCI_DMA_TODEVICE);
+	dma_addr_t mapping;
 	struct tx_fwinfo_8190pci *pTxFwInfo = NULL;
 
 	pTxFwInfo = (struct tx_fwinfo_8190pci *)skb->data;
@@ -1196,8 +1196,6 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 	pTxFwInfo->Short = _rtl92e_query_is_short(pTxFwInfo->TxHT,
 						  pTxFwInfo->TxRate, cb_desc);
 
-	if (pci_dma_mapping_error(priv->pdev, mapping))
-		netdev_err(dev, "%s(): DMA Mapping error\n", __func__);
 	if (cb_desc->bAMPDUEnable) {
 		pTxFwInfo->AllowAggregation = 1;
 		pTxFwInfo->RxMF = cb_desc->ampdu_factor;
@@ -1232,6 +1230,14 @@ void  rtl92e_fill_tx_desc(struct net_device *dev, struct tx_desc *pdesc,
 	}
 
 	memset((u8 *)pdesc, 0, 12);
+
+	mapping = pci_map_single(priv->pdev, skb->data, skb->len,
+				 PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(priv->pdev, mapping)) {
+		netdev_err(dev, "%s(): DMA Mapping error\n", __func__);
+		return;
+	}
+
 	pdesc->LINIP = 0;
 	pdesc->CmdInit = 1;
 	pdesc->Offset = sizeof(struct tx_fwinfo_8190pci) + 8;
diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c
index 4ff530155187..04ac23cc47a8 100644
--- a/drivers/staging/rtl8712/rtl871x_recv.c
+++ b/drivers/staging/rtl8712/rtl871x_recv.c
@@ -641,11 +641,16 @@ sint r8712_wlanhdr_to_ethhdr(union recv_frame *precvframe)
 		/* append rx status for mp test packets */
 		ptr = recvframe_pull(precvframe, (rmv_len -
 		      sizeof(struct ethhdr) + 2) - 24);
+		if (!ptr)
+			return _FAIL;
 		memcpy(ptr, get_rxmem(precvframe), 24);
 		ptr += 24;
-	} else
+	} else {
 		ptr = recvframe_pull(precvframe, (rmv_len -
 		      sizeof(struct ethhdr) + (bsnaphdr ? 2 : 0)));
+		if (!ptr)
+			return _FAIL;
+	}
 
 	memcpy(ptr, pattrib->dst, ETH_ALEN);
 	memcpy(ptr + ETH_ALEN, pattrib->src, ETH_ALEN);
diff --git a/drivers/staging/rts5208/rtsx_scsi.c b/drivers/staging/rts5208/rtsx_scsi.c
index 60871f3022b1..12a3893b98fd 100644
--- a/drivers/staging/rts5208/rtsx_scsi.c
+++ b/drivers/staging/rts5208/rtsx_scsi.c
@@ -414,7 +414,7 @@ void set_sense_data(struct rtsx_chip *chip, unsigned int lun, u8 err_code,
 	sense->ascq = ascq;
 	if (sns_key_info0 != 0) {
 		sense->sns_key_info[0] = SKSV | sns_key_info0;
-		sense->sns_key_info[1] = (sns_key_info1 & 0xf0) >> 8;
+		sense->sns_key_info[1] = (sns_key_info1 & 0xf0) >> 4;
 		sense->sns_key_info[2] = sns_key_info1 & 0x0f;
 	}
 }
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 01e642db311e..f35ee85f61b5 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -529,6 +529,9 @@ static int vnt_start(struct ieee80211_hw *hw)
 		goto free_all;
 	}
 
+	if (vnt_key_init_table(priv))
+		goto free_all;
+
 	priv->int_interval = 1;  /* bInterval is set to 1 */
 
 	vnt_int_start_interrupt(priv);
diff --git a/drivers/staging/vt6656/usbpipe.c b/drivers/staging/vt6656/usbpipe.c
index c975c3b87093..cfc3017fd64a 100644
--- a/drivers/staging/vt6656/usbpipe.c
+++ b/drivers/staging/vt6656/usbpipe.c
@@ -50,15 +50,25 @@ int vnt_control_out(struct vnt_private *priv, u8 request, u16 value,
 		u16 index, u16 length, u8 *buffer)
 {
 	int status = 0;
+	u8 *usb_buffer;
 
 	if (test_bit(DEVICE_FLAGS_DISCONNECTED, &priv->flags))
 		return STATUS_FAILURE;
 
 	mutex_lock(&priv->usb_lock);
 
+	usb_buffer = kmemdup(buffer, length, GFP_KERNEL);
+	if (!usb_buffer) {
+		mutex_unlock(&priv->usb_lock);
+		return -ENOMEM;
+	}
+
 	status = usb_control_msg(priv->usb,
-		usb_sndctrlpipe(priv->usb, 0), request, 0x40, value,
-			index, buffer, length, USB_CTL_WAIT);
+				 usb_sndctrlpipe(priv->usb, 0),
+				 request, 0x40, value,
+				 index, usb_buffer, length, USB_CTL_WAIT);
+
+	kfree(usb_buffer);
 
 	mutex_unlock(&priv->usb_lock);
 
@@ -78,15 +88,28 @@ int vnt_control_in(struct vnt_private *priv, u8 request, u16 value,
 		u16 index, u16 length, u8 *buffer)
 {
 	int status;
+	u8 *usb_buffer;
 
 	if (test_bit(DEVICE_FLAGS_DISCONNECTED, &priv->flags))
 		return STATUS_FAILURE;
 
 	mutex_lock(&priv->usb_lock);
 
+	usb_buffer = kmalloc(length, GFP_KERNEL);
+	if (!usb_buffer) {
+		mutex_unlock(&priv->usb_lock);
+		return -ENOMEM;
+	}
+
 	status = usb_control_msg(priv->usb,
-		usb_rcvctrlpipe(priv->usb, 0), request, 0xc0, value,
-			index, buffer, length, USB_CTL_WAIT);
+				 usb_rcvctrlpipe(priv->usb, 0),
+				 request, 0xc0, value,
+				 index, usb_buffer, length, USB_CTL_WAIT);
+
+	if (status == length)
+		memcpy(buffer, usb_buffer, length);
+
+	kfree(usb_buffer);
 
 	mutex_unlock(&priv->usb_lock);
 
diff --git a/drivers/staging/wlan-ng/p80211netdev.c b/drivers/staging/wlan-ng/p80211netdev.c
index a9c1e0bafa62..e35fbece3d2f 100644
--- a/drivers/staging/wlan-ng/p80211netdev.c
+++ b/drivers/staging/wlan-ng/p80211netdev.c
@@ -232,7 +232,7 @@ static int p80211_convert_to_ether(wlandevice_t *wlandev, struct sk_buff *skb)
 	struct p80211_hdr_a3 *hdr;
 
 	hdr = (struct p80211_hdr_a3 *) skb->data;
-	if (p80211_rx_typedrop(wlandev, hdr->fc))
+	if (p80211_rx_typedrop(wlandev, le16_to_cpu(hdr->fc)))
 		return CONV_TO_ETHER_SKIPPED;
 
 	/* perform mcast filtering: allow my local address through but reject
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 72204fbf2bb1..1ff1c83e2df5 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -418,6 +418,7 @@ int iscsit_reset_np_thread(
 		return 0;
 	}
 	np->np_thread_state = ISCSI_NP_THREAD_RESET;
+	atomic_inc(&np->np_reset_count);
 
 	if (np->np_thread) {
 		spin_unlock_bh(&np->np_thread_lock);
@@ -492,7 +493,8 @@ static void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 	bool scsi_cmd = (cmd->iscsi_opcode == ISCSI_OP_SCSI_CMD);
 
 	spin_lock_bh(&conn->cmd_lock);
-	if (!list_empty(&cmd->i_conn_node))
+	if (!list_empty(&cmd->i_conn_node) &&
+	    !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP))
 		list_del_init(&cmd->i_conn_node);
 	spin_unlock_bh(&conn->cmd_lock);
 
@@ -1111,6 +1113,18 @@ iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
 	 */
 	if (dump_payload)
 		goto after_immediate_data;
+	/*
+	 * Check for underflow case where both EDTL and immediate data payload
+	 * exceeds what is presented by CDB's TRANSFER LENGTH, and what has
+	 * already been set in target_cmd_size_check() as se_cmd->data_length.
+	 *
+	 * For this special case, fail the command and dump the immediate data
+	 * payload.
+	 */
+	if (cmd->first_burst_len > cmd->se_cmd.data_length) {
+		cmd->sense_reason = TCM_INVALID_CDB_FIELD;
+		goto after_immediate_data;
+	}
 
 	immed_ret = iscsit_handle_immediate_data(cmd, hdr,
 					cmd->first_burst_len);
@@ -1983,6 +1997,7 @@ iscsit_setup_text_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	cmd->cmd_sn		= be32_to_cpu(hdr->cmdsn);
 	cmd->exp_stat_sn	= be32_to_cpu(hdr->exp_statsn);
 	cmd->data_direction	= DMA_NONE;
+	kfree(cmd->text_in_ptr);
 	cmd->text_in_ptr	= NULL;
 
 	return 0;
@@ -3435,7 +3450,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
 
 			if ((tpg->tpg_attrib.generate_node_acls == 0) &&
 			    (tpg->tpg_attrib.demo_mode_discovery == 0) &&
-			    (!core_tpg_get_initiator_node_acl(&tpg->tpg_se_tpg,
+			    (!target_tpg_has_node_acl(&tpg->tpg_se_tpg,
 				cmd->conn->sess->sess_ops->InitiatorName))) {
 				continue;
 			}
@@ -3952,6 +3967,8 @@ int iscsi_target_tx_thread(void *arg)
 {
 	int ret = 0;
 	struct iscsi_conn *conn = arg;
+	bool conn_freed = false;
+
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
 	 * connection recovery / failure event can be triggered externally.
@@ -3977,12 +3994,14 @@ get_immediate:
 			goto transport_err;
 
 		ret = iscsit_handle_response_queue(conn);
-		if (ret == 1)
+		if (ret == 1) {
 			goto get_immediate;
-		else if (ret == -ECONNRESET)
+		} else if (ret == -ECONNRESET) {
+			conn_freed = true;
 			goto out;
-		else if (ret < 0)
+		} else if (ret < 0) {
 			goto transport_err;
+		}
 	}
 
 transport_err:
@@ -3992,8 +4011,13 @@ transport_err:
 	 * responsible for cleaning up the early connection failure.
 	 */
 	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
-		iscsit_take_action_for_connection_exit(conn);
+		iscsit_take_action_for_connection_exit(conn, &conn_freed);
 out:
+	if (!conn_freed) {
+		while (!kthread_should_stop()) {
+			msleep(100);
+		}
+	}
 	return 0;
 }
 
@@ -4092,6 +4116,7 @@ int iscsi_target_rx_thread(void *arg)
 	u32 checksum = 0, digest = 0;
 	struct iscsi_conn *conn = arg;
 	struct kvec iov;
+	bool conn_freed = false;
 	/*
 	 * Allow ourselves to be interrupted by SIGINT so that a
 	 * connection recovery / failure event can be triggered externally.
@@ -4103,7 +4128,7 @@ int iscsi_target_rx_thread(void *arg)
 	 */
 	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
 	if (rc < 0 || iscsi_target_check_conn_state(conn))
-		return 0;
+		goto out;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
@@ -4188,12 +4213,19 @@ int iscsi_target_rx_thread(void *arg)
 transport_err:
 	if (!signal_pending(current))
 		atomic_set(&conn->transport_failed, 1);
-	iscsit_take_action_for_connection_exit(conn);
+	iscsit_take_action_for_connection_exit(conn, &conn_freed);
+out:
+	if (!conn_freed) {
+		while (!kthread_should_stop()) {
+			msleep(100);
+		}
+	}
 	return 0;
 }
 
 static void iscsit_release_commands_from_conn(struct iscsi_conn *conn)
 {
+	LIST_HEAD(tmp_list);
 	struct iscsi_cmd *cmd = NULL, *cmd_tmp = NULL;
 	struct iscsi_session *sess = conn->sess;
 	/*
@@ -4202,18 +4234,26 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn)
 	 * has been reset -> returned sleeping pre-handler state.
 	 */
 	spin_lock_bh(&conn->cmd_lock);
-	list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
+	list_splice_init(&conn->conn_cmd_list, &tmp_list);
+
+	list_for_each_entry(cmd, &tmp_list, i_conn_node) {
+		struct se_cmd *se_cmd = &cmd->se_cmd;
 
+		if (se_cmd->se_tfo != NULL) {
+			spin_lock(&se_cmd->t_state_lock);
+			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+			spin_unlock(&se_cmd->t_state_lock);
+		}
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) {
 		list_del_init(&cmd->i_conn_node);
-		spin_unlock_bh(&conn->cmd_lock);
 
 		iscsit_increment_maxcmdsn(cmd, sess);
-
 		iscsit_free_cmd(cmd, true);
 
-		spin_lock_bh(&conn->cmd_lock);
 	}
-	spin_unlock_bh(&conn->cmd_lock);
 }
 
 static void iscsit_stop_timers_for_cmds(
@@ -4553,8 +4593,11 @@ static void iscsit_logout_post_handler_closesession(
 	 * always sleep waiting for RX/TX thread shutdown to complete
 	 * within iscsit_close_connection().
 	 */
-	if (conn->conn_transport->transport_type == ISCSI_TCP)
+	if (conn->conn_transport->transport_type == ISCSI_TCP) {
 		sleep = cmpxchg(&conn->tx_thread_active, true, false);
+		if (!sleep)
+			return;
+	}
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4570,8 +4613,11 @@ static void iscsit_logout_post_handler_samecid(
 {
 	int sleep = 1;
 
-	if (conn->conn_transport->transport_type == ISCSI_TCP)
+	if (conn->conn_transport->transport_type == ISCSI_TCP) {
 		sleep = cmpxchg(&conn->tx_thread_active, true, false);
+		if (!sleep)
+			return;
+	}
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4811,6 +4857,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 			continue;
 		}
 		atomic_set(&sess->session_reinstatement, 1);
+		atomic_set(&sess->session_fall_back_to_erl0, 1);
 		spin_unlock(&sess->conn_lock);
 
 		list_move_tail(&se_sess->sess_list, &free_list);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index b4bfd706ac94..634ad3662ed6 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -725,11 +725,8 @@ static ssize_t lio_target_nacl_cmdsn_depth_store(struct config_item *item,
 
 	if (iscsit_get_tpg(tpg) < 0)
 		return -EINVAL;
-	/*
-	 * iscsit_tpg_set_initiator_node_queue_depth() assumes force=1
-	 */
-	ret = iscsit_tpg_set_initiator_node_queue_depth(tpg,
-				config_item_name(acl_ci), cmdsn_depth, 1);
+
+	ret = core_tpg_set_initiator_node_queue_depth(se_nacl, cmdsn_depth);
 
 	pr_debug("LIO_Target_ConfigFS: %s/%s Set CmdSN Window: %u for"
 		"InitiatorName: %s\n", config_item_name(wwn_ci),
@@ -871,6 +868,7 @@ DEF_TPG_ATTRIB(default_erl);
 DEF_TPG_ATTRIB(t10_pi);
 DEF_TPG_ATTRIB(fabric_prot_type);
 DEF_TPG_ATTRIB(tpg_enabled_sendtargets);
+DEF_TPG_ATTRIB(login_keys_workaround);
 
 static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = {
 	&iscsi_tpg_attrib_attr_authentication,
@@ -886,6 +884,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = {
 	&iscsi_tpg_attrib_attr_t10_pi,
 	&iscsi_tpg_attrib_attr_fabric_prot_type,
 	&iscsi_tpg_attrib_attr_tpg_enabled_sendtargets,
+	&iscsi_tpg_attrib_attr_login_keys_workaround,
 	NULL,
 };
 
@@ -1593,42 +1592,31 @@ static int lio_tpg_check_prot_fabric_only(
 }
 
 /*
- * Called with spin_lock_irq(struct se_portal_group->session_lock) held
- * or not held.
- *
- * Also, this function calls iscsit_inc_session_usage_count() on the
+ * This function calls iscsit_inc_session_usage_count() on the
  * struct iscsi_session in question.
  */
 static int lio_tpg_shutdown_session(struct se_session *se_sess)
 {
 	struct iscsi_session *sess = se_sess->fabric_sess_ptr;
-	struct se_portal_group *se_tpg = se_sess->se_tpg;
-	bool local_lock = false;
-
-	if (!spin_is_locked(&se_tpg->session_lock)) {
-		spin_lock_irq(&se_tpg->session_lock);
-		local_lock = true;
-	}
+	struct se_portal_group *se_tpg = &sess->tpg->tpg_se_tpg;
 
+	spin_lock_bh(&se_tpg->session_lock);
 	spin_lock(&sess->conn_lock);
 	if (atomic_read(&sess->session_fall_back_to_erl0) ||
 	    atomic_read(&sess->session_logout) ||
 	    (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
 		spin_unlock(&sess->conn_lock);
-		if (local_lock)
-			spin_unlock_irq(&sess->conn_lock);
+		spin_unlock_bh(&se_tpg->session_lock);
 		return 0;
 	}
 	atomic_set(&sess->session_reinstatement, 1);
+	atomic_set(&sess->session_fall_back_to_erl0, 1);
 	spin_unlock(&sess->conn_lock);
 
 	iscsit_stop_time2retain_timer(sess);
-	spin_unlock_irq(&se_tpg->session_lock);
+	spin_unlock_bh(&se_tpg->session_lock);
 
 	iscsit_stop_session(sess, 1, 1);
-	if (!local_lock)
-		spin_lock_irq(&se_tpg->session_lock);
-
 	return 1;
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 210f6e4830e3..6c88fb021444 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -930,8 +930,10 @@ static void iscsit_handle_connection_cleanup(struct iscsi_conn *conn)
 	}
 }
 
-void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
+void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn, bool *conn_freed)
 {
+	*conn_freed = false;
+
 	spin_lock_bh(&conn->state_lock);
 	if (atomic_read(&conn->connection_exit)) {
 		spin_unlock_bh(&conn->state_lock);
@@ -942,6 +944,7 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
 	if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) {
 		spin_unlock_bh(&conn->state_lock);
 		iscsit_close_connection(conn);
+		*conn_freed = true;
 		return;
 	}
 
@@ -955,4 +958,5 @@ void iscsit_take_action_for_connection_exit(struct iscsi_conn *conn)
 	spin_unlock_bh(&conn->state_lock);
 
 	iscsit_handle_connection_cleanup(conn);
+	*conn_freed = true;
 }
diff --git a/drivers/target/iscsi/iscsi_target_erl0.h b/drivers/target/iscsi/iscsi_target_erl0.h
index a9e2f9497fb2..fbc1d84a63c3 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.h
+++ b/drivers/target/iscsi/iscsi_target_erl0.h
@@ -9,6 +9,6 @@ extern int iscsit_stop_time2retain_timer(struct iscsi_session *);
 extern void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *);
 extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int);
 extern void iscsit_fall_back_to_erl0(struct iscsi_session *);
-extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *);
+extern void iscsit_take_action_for_connection_exit(struct iscsi_conn *, bool *);
 
 #endif   /*** ISCSI_TARGET_ERL0_H ***/
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 96e78c823d13..bc2cbffec27e 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -195,6 +195,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn)
 			    initiatorname_param->value) &&
 		   (sess_p->sess_ops->SessionType == sessiontype))) {
 			atomic_set(&sess_p->session_reinstatement, 1);
+			atomic_set(&sess_p->session_fall_back_to_erl0, 1);
 			spin_unlock(&sess_p->conn_lock);
 			iscsit_inc_session_usage_count(sess_p);
 			iscsit_stop_time2retain_timer(sess_p);
@@ -1218,9 +1219,11 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	flush_signals(current);
 
 	spin_lock_bh(&np->np_thread_lock);
-	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+	if (atomic_dec_if_positive(&np->np_reset_count) >= 0) {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
+		spin_unlock_bh(&np->np_thread_lock);
 		complete(&np->np_restart_comp);
+		return 1;
 	} else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) {
 		spin_unlock_bh(&np->np_thread_lock);
 		goto exit;
@@ -1253,7 +1256,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 		goto exit;
 	} else if (rc < 0) {
 		spin_lock_bh(&np->np_thread_lock);
-		if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+		if (atomic_dec_if_positive(&np->np_reset_count) >= 0) {
+			np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 			spin_unlock_bh(&np->np_thread_lock);
 			complete(&np->np_restart_comp);
 			iscsit_put_transport(conn->conn_transport);
@@ -1357,8 +1361,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	}
 	login->zero_tsih = zero_tsih;
 
-	conn->sess->se_sess->sup_prot_ops =
-		conn->conn_transport->iscsit_get_sup_prot_ops(conn);
+	if (conn->sess)
+		conn->sess->se_sess->sup_prot_ops =
+			conn->conn_transport->iscsit_get_sup_prot_ops(conn);
 
 	tpg = conn->tpg;
 	if (!tpg) {
@@ -1434,5 +1439,9 @@ int iscsi_target_login_thread(void *arg)
 			break;
 	}
 
+	while (!kthread_should_stop()) {
+		msleep(100);
+	}
+
 	return 0;
 }
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 9fc9117d0f22..58c629aec73c 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -489,14 +489,60 @@ static void iscsi_target_restore_sock_callbacks(struct iscsi_conn *conn)
 
 static int iscsi_target_do_login(struct iscsi_conn *, struct iscsi_login *);
 
-static bool iscsi_target_sk_state_check(struct sock *sk)
+static bool __iscsi_target_sk_check_close(struct sock *sk)
 {
 	if (sk->sk_state == TCP_CLOSE_WAIT || sk->sk_state == TCP_CLOSE) {
-		pr_debug("iscsi_target_sk_state_check: TCP_CLOSE_WAIT|TCP_CLOSE,"
+		pr_debug("__iscsi_target_sk_check_close: TCP_CLOSE_WAIT|TCP_CLOSE,"
 			"returning FALSE\n");
-		return false;
+		return true;
 	}
-	return true;
+	return false;
+}
+
+static bool iscsi_target_sk_check_close(struct iscsi_conn *conn)
+{
+	bool state = false;
+
+	if (conn->sock) {
+		struct sock *sk = conn->sock->sk;
+
+		read_lock_bh(&sk->sk_callback_lock);
+		state = (__iscsi_target_sk_check_close(sk) ||
+			 test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags));
+		read_unlock_bh(&sk->sk_callback_lock);
+	}
+	return state;
+}
+
+static bool iscsi_target_sk_check_flag(struct iscsi_conn *conn, unsigned int flag)
+{
+	bool state = false;
+
+	if (conn->sock) {
+		struct sock *sk = conn->sock->sk;
+
+		read_lock_bh(&sk->sk_callback_lock);
+		state = test_bit(flag, &conn->login_flags);
+		read_unlock_bh(&sk->sk_callback_lock);
+	}
+	return state;
+}
+
+static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned int flag)
+{
+	bool state = false;
+
+	if (conn->sock) {
+		struct sock *sk = conn->sock->sk;
+
+		write_lock_bh(&sk->sk_callback_lock);
+		state = (__iscsi_target_sk_check_close(sk) ||
+			 test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags));
+		if (!state)
+			clear_bit(flag, &conn->login_flags);
+		write_unlock_bh(&sk->sk_callback_lock);
+	}
+	return state;
 }
 
 static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
@@ -536,6 +582,20 @@ static void iscsi_target_do_login_rx(struct work_struct *work)
 
 	pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n",
 			conn, current->comm, current->pid);
+	/*
+	 * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready()
+	 * before initial PDU processing in iscsi_target_start_negotiation()
+	 * has completed, go ahead and retry until it's cleared.
+	 *
+	 * Otherwise if the TCP connection drops while this is occuring,
+	 * iscsi_target_start_negotiation() will detect the failure, call
+	 * cancel_delayed_work_sync(&conn->login_work), and cleanup the
+	 * remaining iscsi connection resources from iscsi_np process context.
+	 */
+	if (iscsi_target_sk_check_flag(conn, LOGIN_FLAGS_INITIAL_PDU)) {
+		schedule_delayed_work(&conn->login_work, msecs_to_jiffies(10));
+		return;
+	}
 
 	spin_lock(&tpg->tpg_state_lock);
 	state = (tpg->tpg_state == TPG_STATE_ACTIVE);
@@ -543,26 +603,12 @@ static void iscsi_target_do_login_rx(struct work_struct *work)
 
 	if (!state) {
 		pr_debug("iscsi_target_do_login_rx: tpg_state != TPG_STATE_ACTIVE\n");
-		iscsi_target_restore_sock_callbacks(conn);
-		iscsi_target_login_drop(conn, login);
-		iscsit_deaccess_np(np, tpg, tpg_np);
-		return;
+		goto err;
 	}
 
-	if (conn->sock) {
-		struct sock *sk = conn->sock->sk;
-
-		read_lock_bh(&sk->sk_callback_lock);
-		state = iscsi_target_sk_state_check(sk);
-		read_unlock_bh(&sk->sk_callback_lock);
-
-		if (!state) {
-			pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
-			iscsi_target_restore_sock_callbacks(conn);
-			iscsi_target_login_drop(conn, login);
-			iscsit_deaccess_np(np, tpg, tpg_np);
-			return;
-		}
+	if (iscsi_target_sk_check_close(conn)) {
+		pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
+		goto err;
 	}
 
 	conn->login_kworker = current;
@@ -580,34 +626,29 @@ static void iscsi_target_do_login_rx(struct work_struct *work)
 	flush_signals(current);
 	conn->login_kworker = NULL;
 
-	if (rc < 0) {
-		iscsi_target_restore_sock_callbacks(conn);
-		iscsi_target_login_drop(conn, login);
-		iscsit_deaccess_np(np, tpg, tpg_np);
-		return;
-	}
+	if (rc < 0)
+		goto err;
 
 	pr_debug("iscsi_target_do_login_rx after rx_login_io, %p, %s:%d\n",
 			conn, current->comm, current->pid);
 
 	rc = iscsi_target_do_login(conn, login);
 	if (rc < 0) {
-		iscsi_target_restore_sock_callbacks(conn);
-		iscsi_target_login_drop(conn, login);
-		iscsit_deaccess_np(np, tpg, tpg_np);
+		goto err;
 	} else if (!rc) {
-		if (conn->sock) {
-			struct sock *sk = conn->sock->sk;
-
-			write_lock_bh(&sk->sk_callback_lock);
-			clear_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags);
-			write_unlock_bh(&sk->sk_callback_lock);
-		}
+		if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_READ_ACTIVE))
+			goto err;
 	} else if (rc == 1) {
 		iscsi_target_nego_release(conn);
 		iscsi_post_login_handler(np, conn, zero_tsih);
 		iscsit_deaccess_np(np, tpg, tpg_np);
 	}
+	return;
+
+err:
+	iscsi_target_restore_sock_callbacks(conn);
+	iscsi_target_login_drop(conn, login);
+	iscsit_deaccess_np(np, tpg, tpg_np);
 }
 
 static void iscsi_target_do_cleanup(struct work_struct *work)
@@ -655,31 +696,54 @@ static void iscsi_target_sk_state_change(struct sock *sk)
 		orig_state_change(sk);
 		return;
 	}
+	state = __iscsi_target_sk_check_close(sk);
+	pr_debug("__iscsi_target_sk_close_change: state: %d\n", state);
+
 	if (test_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) {
 		pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1 sk_state_change"
 			 " conn: %p\n", conn);
+		if (state)
+			set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags);
 		write_unlock_bh(&sk->sk_callback_lock);
 		orig_state_change(sk);
 		return;
 	}
-	if (test_and_set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
+	if (test_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags)) {
 		pr_debug("Got LOGIN_FLAGS_CLOSED=1 sk_state_change conn: %p\n",
 			 conn);
 		write_unlock_bh(&sk->sk_callback_lock);
 		orig_state_change(sk);
 		return;
 	}
+	/*
+	 * If the TCP connection has dropped, go ahead and set LOGIN_FLAGS_CLOSED,
+	 * but only queue conn->login_work -> iscsi_target_do_login_rx()
+	 * processing if LOGIN_FLAGS_INITIAL_PDU has already been cleared.
+	 *
+	 * When iscsi_target_do_login_rx() runs, iscsi_target_sk_check_close()
+	 * will detect the dropped TCP connection from delayed workqueue context.
+	 *
+	 * If LOGIN_FLAGS_INITIAL_PDU is still set, which means the initial
+	 * iscsi_target_start_negotiation() is running, iscsi_target_do_login()
+	 * via iscsi_target_sk_check_close() or iscsi_target_start_negotiation()
+	 * via iscsi_target_sk_check_and_clear() is responsible for detecting the
+	 * dropped TCP connection in iscsi_np process context, and cleaning up
+	 * the remaining iscsi connection resources.
+	 */
+	if (state) {
+		pr_debug("iscsi_target_sk_state_change got failed state\n");
+		set_bit(LOGIN_FLAGS_CLOSED, &conn->login_flags);
+		state = test_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags);
+		write_unlock_bh(&sk->sk_callback_lock);
 
-	state = iscsi_target_sk_state_check(sk);
-	write_unlock_bh(&sk->sk_callback_lock);
-
-	pr_debug("iscsi_target_sk_state_change: state: %d\n", state);
+		orig_state_change(sk);
 
-	if (!state) {
-		pr_debug("iscsi_target_sk_state_change got failed state\n");
-		schedule_delayed_work(&conn->login_cleanup_work, 0);
+		if (!state)
+			schedule_delayed_work(&conn->login_work, 0);
 		return;
 	}
+	write_unlock_bh(&sk->sk_callback_lock);
+
 	orig_state_change(sk);
 }
 
@@ -818,7 +882,8 @@ static int iscsi_target_handle_csg_zero(
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
-			conn->param_list);
+			conn->param_list,
+			conn->tpg->tpg_attrib.login_keys_workaround);
 	if (ret < 0)
 		return -1;
 
@@ -888,7 +953,8 @@ static int iscsi_target_handle_csg_one(struct iscsi_conn *conn, struct iscsi_log
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
-			conn->param_list);
+			conn->param_list,
+			conn->tpg->tpg_attrib.login_keys_workaround);
 	if (ret < 0) {
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
 				ISCSI_LOGIN_STATUS_INIT_ERR);
@@ -942,6 +1008,15 @@ static int iscsi_target_do_login(struct iscsi_conn *conn, struct iscsi_login *lo
 			if (iscsi_target_handle_csg_one(conn, login) < 0)
 				return -1;
 			if (login_rsp->flags & ISCSI_FLAG_LOGIN_TRANSIT) {
+				/*
+				 * Check to make sure the TCP connection has not
+				 * dropped asynchronously while session reinstatement
+				 * was occuring in this kthread context, before
+				 * transitioning to full feature phase operation.
+				 */
+				if (iscsi_target_sk_check_close(conn))
+					return -1;
+
 				login->tsih = conn->sess->tsih;
 				login->login_complete = 1;
 				iscsi_target_restore_sock_callbacks(conn);
@@ -968,21 +1043,6 @@ static int iscsi_target_do_login(struct iscsi_conn *conn, struct iscsi_login *lo
 		break;
 	}
 
-	if (conn->sock) {
-		struct sock *sk = conn->sock->sk;
-		bool state;
-
-		read_lock_bh(&sk->sk_callback_lock);
-		state = iscsi_target_sk_state_check(sk);
-		read_unlock_bh(&sk->sk_callback_lock);
-
-		if (!state) {
-			pr_debug("iscsi_target_do_login() failed state for"
-				 " conn: %p\n", conn);
-			return -1;
-		}
-	}
-
 	return 0;
 }
 
@@ -1246,16 +1306,28 @@ int iscsi_target_start_negotiation(
 {
 	int ret;
 
+       if (conn->sock) {
+               struct sock *sk = conn->sock->sk;
+
+		write_lock_bh(&sk->sk_callback_lock);
+		set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
+		set_bit(LOGIN_FLAGS_INITIAL_PDU, &conn->login_flags);
+		write_unlock_bh(&sk->sk_callback_lock);
+	}
+	/*
+	 * If iscsi_target_do_login returns zero to signal more PDU
+	 * exchanges are required to complete the login, go ahead and
+	 * clear LOGIN_FLAGS_INITIAL_PDU but only if the TCP connection
+	 * is still active.
+	 *
+	 * Otherwise if TCP connection dropped asynchronously, go ahead
+	 * and perform connection cleanup now.
+	 */
 	ret = iscsi_target_do_login(conn, login);
-	if (!ret) {
-		if (conn->sock) {
-			struct sock *sk = conn->sock->sk;
+	if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU))
+		ret = -1;
 
-			write_lock_bh(&sk->sk_callback_lock);
-			set_bit(LOGIN_FLAGS_READY, &conn->login_flags);
-			write_unlock_bh(&sk->sk_callback_lock);
-		}
-	} else if (ret < 0) {
+	if (ret < 0) {
 		cancel_delayed_work_sync(&conn->login_work);
 		cancel_delayed_work_sync(&conn->login_cleanup_work);
 		iscsi_target_restore_sock_callbacks(conn);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 2cbea2af7cd0..76bde76edad1 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -764,7 +764,8 @@ static int iscsi_check_for_auth_key(char *key)
 	return 0;
 }
 
-static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param)
+static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param,
+						    bool keys_workaround)
 {
 	if (IS_TYPE_BOOL_AND(param)) {
 		if (!strcmp(param->value, NO))
@@ -772,35 +773,31 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param)
 	} else if (IS_TYPE_BOOL_OR(param)) {
 		if (!strcmp(param->value, YES))
 			SET_PSTATE_REPLY_OPTIONAL(param);
-		 /*
-		  * Required for gPXE iSCSI boot client
-		  */
-		if (!strcmp(param->name, IMMEDIATEDATA))
-			SET_PSTATE_REPLY_OPTIONAL(param);
+
+		if (keys_workaround) {
+			/*
+			 * Required for gPXE iSCSI boot client
+			 */
+			if (!strcmp(param->name, IMMEDIATEDATA))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+		}
 	} else if (IS_TYPE_NUMBER(param)) {
 		if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH))
 			SET_PSTATE_REPLY_OPTIONAL(param);
-		/*
-		 * The GlobalSAN iSCSI Initiator for MacOSX does
-		 * not respond to MaxBurstLength, FirstBurstLength,
-		 * DefaultTime2Wait or DefaultTime2Retain parameter keys.
-		 * So, we set them to 'reply optional' here, and assume the
-		 * the defaults from iscsi_parameters.h if the initiator
-		 * is not RFC compliant and the keys are not negotiated.
-		 */
-		if (!strcmp(param->name, MAXBURSTLENGTH))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, FIRSTBURSTLENGTH))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, DEFAULTTIME2WAIT))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		if (!strcmp(param->name, DEFAULTTIME2RETAIN))
-			SET_PSTATE_REPLY_OPTIONAL(param);
-		/*
-		 * Required for gPXE iSCSI boot client
-		 */
-		if (!strcmp(param->name, MAXCONNECTIONS))
-			SET_PSTATE_REPLY_OPTIONAL(param);
+
+		if (keys_workaround) {
+			/*
+			 * Required for Mellanox Flexboot PXE boot ROM
+			 */
+			if (!strcmp(param->name, FIRSTBURSTLENGTH))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+
+			/*
+			 * Required for gPXE iSCSI boot client
+			 */
+			if (!strcmp(param->name, MAXCONNECTIONS))
+				SET_PSTATE_REPLY_OPTIONAL(param);
+		}
 	} else if (IS_PHASE_DECLARATIVE(param))
 		SET_PSTATE_REPLY_OPTIONAL(param);
 }
@@ -1437,7 +1434,8 @@ int iscsi_encode_text_output(
 	u8 sender,
 	char *textbuf,
 	u32 *length,
-	struct iscsi_param_list *param_list)
+	struct iscsi_param_list *param_list,
+	bool keys_workaround)
 {
 	char *output_buf = NULL;
 	struct iscsi_extra_response *er;
@@ -1473,7 +1471,8 @@ int iscsi_encode_text_output(
 			*length += 1;
 			output_buf = textbuf + *length;
 			SET_PSTATE_PROPOSER(param);
-			iscsi_check_proposer_for_optional_reply(param);
+			iscsi_check_proposer_for_optional_reply(param,
+							        keys_workaround);
 			pr_debug("Sending key: %s=%s\n",
 				param->name, param->value);
 		}
diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h
index a0751e3f0813..17a58c2913f2 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.h
+++ b/drivers/target/iscsi/iscsi_target_parameters.h
@@ -40,7 +40,7 @@ extern int iscsi_extract_key_value(char *, char **, char **);
 extern int iscsi_update_param_value(struct iscsi_param *, char *);
 extern int iscsi_decode_text_input(u8, u8, char *, u32, struct iscsi_conn *);
 extern int iscsi_encode_text_output(u8, u8, char *, u32 *,
-			struct iscsi_param_list *);
+			struct iscsi_param_list *, bool);
 extern int iscsi_check_negotiated_keys(struct iscsi_param_list *);
 extern void iscsi_set_connection_parameters(struct iscsi_conn_ops *,
 			struct iscsi_param_list *);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 23c95cd14167..63e1dcc5914d 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -227,6 +227,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg)
 	a->t10_pi = TA_DEFAULT_T10_PI;
 	a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE;
 	a->tpg_enabled_sendtargets = TA_DEFAULT_TPG_ENABLED_SENDTARGETS;
+	a->login_keys_workaround = TA_DEFAULT_LOGIN_KEYS_WORKAROUND;
 }
 
 int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg)
@@ -260,7 +261,6 @@ err_out:
 		iscsi_release_param_list(tpg->param_list);
 		tpg->param_list = NULL;
 	}
-	kfree(tpg);
 	return -ENOMEM;
 }
 
@@ -590,16 +590,6 @@ int iscsit_tpg_del_network_portal(
 	return iscsit_tpg_release_np(tpg_np, tpg, np);
 }
 
-int iscsit_tpg_set_initiator_node_queue_depth(
-	struct iscsi_portal_group *tpg,
-	unsigned char *initiatorname,
-	u32 queue_depth,
-	int force)
-{
-	return core_tpg_set_initiator_node_queue_depth(&tpg->tpg_se_tpg,
-		initiatorname, queue_depth, force);
-}
-
 int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication)
 {
 	unsigned char buf1[256], buf2[256], *none = NULL;
@@ -910,3 +900,21 @@ int iscsit_ta_tpg_enabled_sendtargets(
 
 	return 0;
 }
+
+int iscsit_ta_login_keys_workaround(
+	struct iscsi_portal_group *tpg,
+	u32 flag)
+{
+	struct iscsi_tpg_attrib *a = &tpg->tpg_attrib;
+
+	if ((flag != 0) && (flag != 1)) {
+		pr_err("Illegal value %d\n", flag);
+		return -EINVAL;
+	}
+
+	a->login_keys_workaround = flag;
+	pr_debug("iSCSI_TPG[%hu] - TPG enabled bit for login keys workaround: %s ",
+		tpg->tpgt, (a->login_keys_workaround) ? "ON" : "OFF");
+
+	return 0;
+}
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index 9db32bd24cd4..901a712180f0 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -26,8 +26,6 @@ extern struct iscsi_tpg_np *iscsit_tpg_add_network_portal(struct iscsi_portal_gr
 			int);
 extern int iscsit_tpg_del_network_portal(struct iscsi_portal_group *,
 			struct iscsi_tpg_np *);
-extern int iscsit_tpg_set_initiator_node_queue_depth(struct iscsi_portal_group *,
-			unsigned char *, u32, int);
 extern int iscsit_ta_authentication(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_login_timeout(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_netif_timeout(struct iscsi_portal_group *, u32);
@@ -41,5 +39,6 @@ extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32);
 extern int iscsit_ta_tpg_enabled_sendtargets(struct iscsi_portal_group *, u32);
+extern int iscsit_ta_login_keys_workaround(struct iscsi_portal_group *, u32);
 
 #endif /* ISCSI_TARGET_TPG_H */
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 428b0d9e3dba..93590521ae33 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -731,21 +731,23 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 {
 	struct se_cmd *se_cmd = NULL;
 	int rc;
+	bool op_scsi = false;
 	/*
 	 * Determine if a struct se_cmd is associated with
 	 * this struct iscsi_cmd.
 	 */
 	switch (cmd->iscsi_opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		se_cmd = &cmd->se_cmd;
-		__iscsit_free_cmd(cmd, true, shutdown);
+		op_scsi = true;
 		/*
 		 * Fallthrough
 		 */
 	case ISCSI_OP_SCSI_TMFUNC:
-		rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
-		if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
-			__iscsit_free_cmd(cmd, true, shutdown);
+		se_cmd = &cmd->se_cmd;
+		__iscsit_free_cmd(cmd, op_scsi, shutdown);
+		rc = transport_generic_free_cmd(se_cmd, shutdown);
+		if (!rc && shutdown && se_cmd->se_sess) {
+			__iscsit_free_cmd(cmd, op_scsi, shutdown);
 			target_put_sess_cmd(se_cmd);
 		}
 		break;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 3436a83568ea..bb6a6c35324a 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -77,12 +77,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 					&deve->read_bytes);
 
 		se_lun = rcu_dereference(deve->se_lun);
+
+		if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
+			se_lun = NULL;
+			goto out_unlock;
+		}
+
 		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
-
-		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
 
 		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
@@ -96,6 +100,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 			goto ref_dev;
 		}
 	}
+out_unlock:
 	rcu_read_unlock();
 
 	if (!se_lun) {
@@ -362,7 +367,15 @@ int core_enable_device_list_for_node(
 			kfree(new);
 			return -EINVAL;
 		}
-		BUG_ON(orig->se_lun_acl != NULL);
+		if (orig->se_lun_acl != NULL) {
+			pr_warn_ratelimited("Detected existing explicit"
+				" se_lun_acl->se_lun_group reference for %s"
+				" mapped_lun: %llu, failing\n",
+				 nacl->initiatorname, mapped_lun);
+			mutex_unlock(&nacl->lun_entry_mutex);
+			kfree(new);
+			return -EINVAL;
+		}
 
 		rcu_assign_pointer(new->se_lun, lun);
 		rcu_assign_pointer(new->se_lun_acl, lun_acl);
@@ -818,6 +831,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	xcopy_lun = &dev->xcopy_lun;
 	rcu_assign_pointer(xcopy_lun->lun_se_dev, dev);
 	init_completion(&xcopy_lun->lun_ref_comp);
+	init_completion(&xcopy_lun->lun_shutdown_comp);
 	INIT_LIST_HEAD(&xcopy_lun->lun_deve_list);
 	INIT_LIST_HEAD(&xcopy_lun->lun_dev_link);
 	mutex_init(&xcopy_lun->lun_tg_pt_md_mutex);
@@ -832,13 +846,15 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
  * in ATA and we need to set TPE=1
  */
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
-				       struct request_queue *q, int block_size)
+				       struct request_queue *q)
 {
+	int block_size = queue_logical_block_size(q);
+
 	if (!blk_queue_discard(q))
 		return false;
 
-	attrib->max_unmap_lba_count = (q->limits.max_discard_sectors << 9) /
-								block_size;
+	attrib->max_unmap_lba_count =
+		q->limits.max_discard_sectors >> (ilog2(block_size) - 9);
 	/*
 	 * Currently hardcoded to 1 in Linux/SCSI code..
 	 */
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index f916d18ccb48..b070ddf1dc37 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -92,6 +92,11 @@ static int target_fabric_mappedlun_link(
 		pr_err("Source se_lun->lun_se_dev does not exist\n");
 		return -EINVAL;
 	}
+	if (lun->lun_shutdown) {
+		pr_err("Unable to create mappedlun symlink because"
+			" lun->lun_shutdown=true\n");
+		return -EINVAL;
+	}
 	se_tpg = lun->lun_tpg;
 
 	nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item;
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 75f0f08b2a34..041a56987845 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -161,8 +161,7 @@ static int fd_configure_device(struct se_device *dev)
 			dev_size, div_u64(dev_size, fd_dev->fd_block_size),
 			fd_dev->fd_block_size);
 
-		if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
-						      fd_dev->fd_block_size))
+		if (target_configure_unmap_from_queue(&dev->dev_attrib, q))
 			pr_debug("IFILE: BLOCK Discard support available,"
 				 " disabled by default\n");
 		/*
@@ -595,8 +594,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	if (ret < 0)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	if (ret)
-		target_complete_cmd(cmd, SAM_STAT_GOOD);
+	target_complete_cmd(cmd, SAM_STAT_GOOD);
 	return 0;
 }
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 2c53dcefff3e..4620c1dcdbc7 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -121,8 +121,7 @@ static int iblock_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
-	if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
-					      dev->dev_attrib.hw_block_size))
+	if (target_configure_unmap_from_queue(&dev->dev_attrib, q))
 		pr_debug("IBLOCK: BLOCK Discard support available,"
 			 " disabled by default\n");
 
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dae0750c2032..272e6f755322 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -132,7 +132,7 @@ int	init_se_kmem_caches(void);
 void	release_se_kmem_caches(void);
 u32	scsi_get_new_index(scsi_index_t);
 void	transport_subsystem_check_init(void);
-void	transport_cmd_finish_abort(struct se_cmd *, int);
+int	transport_cmd_finish_abort(struct se_cmd *, int);
 unsigned char *transport_dump_cmd_direction(struct se_cmd *);
 void	transport_dump_dev_state(struct se_device *, char *, int *);
 void	transport_dump_dev_info(struct se_device *, struct se_lun *,
@@ -148,6 +148,7 @@ sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
 void	target_qf_do_work(struct work_struct *work);
 bool	target_check_wce(struct se_device *dev);
 bool	target_check_fua(struct se_device *dev);
+void	__target_execute_cmd(struct se_cmd *, bool);
 
 /* target_core_stat.c */
 void	target_stat_setup_dev_default_groups(struct se_device *);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index de18790eb21c..d72a4058fd08 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -154,7 +154,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 
 	buf = kzalloc(12, GFP_KERNEL);
 	if (!buf)
-		return;
+		goto out_free;
 
 	memset(cdb, 0, MAX_COMMAND_SIZE);
 	cdb[0] = MODE_SENSE;
@@ -169,9 +169,10 @@ static void pscsi_tape_read_blocksize(struct se_device *dev,
 	 * If MODE_SENSE still returns zero, set the default value to 1024.
 	 */
 	sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]);
+out_free:
 	if (!sdev->sector_size)
 		sdev->sector_size = 1024;
-out_free:
+
 	kfree(buf);
 }
 
@@ -314,9 +315,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 				sd->lun, sd->queue_depth);
 	}
 
-	dev->dev_attrib.hw_block_size = sd->sector_size;
+	dev->dev_attrib.hw_block_size =
+		min_not_zero((int)sd->sector_size, 512);
 	dev->dev_attrib.hw_max_sectors =
-		min_t(int, sd->host->max_sectors, queue_max_hw_sectors(q));
+		min_not_zero(sd->host->max_sectors, queue_max_hw_sectors(q));
 	dev->dev_attrib.hw_queue_depth = sd->queue_depth;
 
 	/*
@@ -339,8 +341,10 @@ static int pscsi_add_device_to_list(struct se_device *dev,
 	/*
 	 * For TYPE_TAPE, attempt to determine blocksize with MODE_SENSE.
 	 */
-	if (sd->type == TYPE_TAPE)
+	if (sd->type == TYPE_TAPE) {
 		pscsi_tape_read_blocksize(dev, sd);
+		dev->dev_attrib.hw_block_size = sd->sector_size;
+	}
 	return 0;
 }
 
@@ -406,7 +410,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 /*
  * Called with struct Scsi_Host->host_lock called.
  */
-static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
+static int pscsi_create_type_nondisk(struct se_device *dev, struct scsi_device *sd)
 	__releases(sh->host_lock)
 {
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
@@ -433,28 +437,6 @@ static int pscsi_create_type_rom(struct se_device *dev, struct scsi_device *sd)
 	return 0;
 }
 
-/*
- * Called with struct Scsi_Host->host_lock called.
- */
-static int pscsi_create_type_other(struct se_device *dev,
-		struct scsi_device *sd)
-	__releases(sh->host_lock)
-{
-	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
-	struct Scsi_Host *sh = sd->host;
-	int ret;
-
-	spin_unlock_irq(sh->host_lock);
-	ret = pscsi_add_device_to_list(dev, sd);
-	if (ret)
-		return ret;
-
-	pr_debug("CORE_PSCSI[%d] - Added Type: %s for %d:%d:%d:%llu\n",
-		phv->phv_host_id, scsi_device_type(sd->type), sh->host_no,
-		sd->channel, sd->id, sd->lun);
-	return 0;
-}
-
 static int pscsi_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
@@ -542,11 +524,8 @@ static int pscsi_configure_device(struct se_device *dev)
 		case TYPE_DISK:
 			ret = pscsi_create_type_disk(dev, sd);
 			break;
-		case TYPE_ROM:
-			ret = pscsi_create_type_rom(dev, sd);
-			break;
 		default:
-			ret = pscsi_create_type_other(dev, sd);
+			ret = pscsi_create_type_nondisk(dev, sd);
 			break;
 		}
 
@@ -611,8 +590,7 @@ static void pscsi_free_device(struct se_device *dev)
 		else if (pdv->pdv_lld_host)
 			scsi_host_put(pdv->pdv_lld_host);
 
-		if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
-			scsi_device_put(sd);
+		scsi_device_put(sd);
 
 		pdv->pdv_sd = NULL;
 	}
@@ -1088,7 +1066,6 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 	if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
 		return pdv->pdv_bd->bd_part->nr_sects;
 
-	dump_stack();
 	return 0;
 }
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 98698d875742..608117819366 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -442,6 +442,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 					     int *post_ret)
 {
 	struct se_device *dev = cmd->se_dev;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	/*
 	 * Only set SCF_COMPARE_AND_WRITE_POST to force a response fall-through
@@ -449,9 +450,12 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 * sent to the backend driver.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
-	if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
+	if (cmd->transport_state & CMD_T_SENT) {
 		cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
 		*post_ret = 1;
+
+		if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION)
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	spin_unlock_irq(&cmd->t_state_lock);
 
@@ -461,7 +465,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 */
 	up(&dev->caw_sem);
 
-	return TCM_NO_SENSE;
+	return ret;
 }
 
 static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
@@ -494,8 +498,11 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes
 	 * been failed with a non-zero SCSI status.
 	 */
 	if (cmd->scsi_status) {
-		pr_err("compare_and_write_callback: non zero scsi_status:"
+		pr_debug("compare_and_write_callback: non zero scsi_status:"
 			" 0x%02x\n", cmd->scsi_status);
+		*post_ret = 1;
+		if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION)
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		goto out;
 	}
 
@@ -594,7 +601,7 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes
 	cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT;
 	spin_unlock_irq(&cmd->t_state_lock);
 
-	__target_execute_cmd(cmd);
+	__target_execute_cmd(cmd, false);
 
 	kfree(buf);
 	return ret;
@@ -1092,9 +1099,15 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			return ret;
 		break;
 	case VERIFY:
+	case VERIFY_16:
 		size = 0;
-		sectors = transport_get_sectors_10(cdb);
-		cmd->t_task_lba = transport_lba_32(cdb);
+		if (cdb[0] == VERIFY) {
+			sectors = transport_get_sectors_10(cdb);
+			cmd->t_task_lba = transport_lba_32(cdb);
+		} else {
+			sectors = transport_get_sectors_16(cdb);
+			cmd->t_task_lba = transport_lba_64(cdb);
+		}
 		cmd->execute_cmd = sbc_emulate_noop;
 		goto check_lba;
 	case REZERO_UNIT:
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 46b1991fbb50..c9be953496ec 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -75,7 +75,7 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 	kfree(tmr);
 }
 
-static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
+static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
 	unsigned long flags;
 	bool remove = true, send_tas;
@@ -91,7 +91,7 @@ static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 		transport_send_task_abort(cmd);
 	}
 
-	transport_cmd_finish_abort(cmd, remove);
+	return transport_cmd_finish_abort(cmd, remove);
 }
 
 static int target_check_cdb_and_preempt(struct list_head *list,
@@ -185,8 +185,8 @@ void core_tmr_abort_task(
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		transport_cmd_finish_abort(se_cmd, true);
-		target_put_sess_cmd(se_cmd);
+		if (!transport_cmd_finish_abort(se_cmd, true))
+			target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %llu\n", ref_tag);
@@ -286,8 +286,8 @@ static void core_tmr_drain_tmr_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		transport_cmd_finish_abort(cmd, 1);
-		target_put_sess_cmd(cmd);
+		if (!transport_cmd_finish_abort(cmd, 1))
+			target_put_sess_cmd(cmd);
 	}
 }
 
@@ -385,8 +385,8 @@ static void core_tmr_drain_state_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		core_tmr_handle_tas_abort(cmd, tas);
-		target_put_sess_cmd(cmd);
+		if (!core_tmr_handle_tas_abort(cmd, tas))
+			target_put_sess_cmd(cmd);
 	}
 }
 
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 5fb9dd7f08bb..f69f4902dc07 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -75,9 +75,21 @@ struct se_node_acl *core_tpg_get_initiator_node_acl(
 	unsigned char *initiatorname)
 {
 	struct se_node_acl *acl;
-
+	/*
+	 * Obtain se_node_acl->acl_kref using fabric driver provided
+	 * initiatorname[] during node acl endpoint lookup driven by
+	 * new se_session login.
+	 *
+	 * The reference is held until se_session shutdown -> release
+	 * occurs via fabric driver invoked transport_deregister_session()
+	 * or transport_free_session() code.
+	 */
 	mutex_lock(&tpg->acl_node_mutex);
 	acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname);
+	if (acl) {
+		if (!kref_get_unless_zero(&acl->acl_kref))
+			acl = NULL;
+	}
 	mutex_unlock(&tpg->acl_node_mutex);
 
 	return acl;
@@ -157,28 +169,25 @@ void core_tpg_add_node_to_devs(
 	mutex_unlock(&tpg->tpg_lun_mutex);
 }
 
-/*      core_set_queue_depth_for_node():
- *
- *
- */
-static int core_set_queue_depth_for_node(
-	struct se_portal_group *tpg,
-	struct se_node_acl *acl)
+static void
+target_set_nacl_queue_depth(struct se_portal_group *tpg,
+			    struct se_node_acl *acl, u32 queue_depth)
 {
+	acl->queue_depth = queue_depth;
+
 	if (!acl->queue_depth) {
-		pr_err("Queue depth for %s Initiator Node: %s is 0,"
+		pr_warn("Queue depth for %s Initiator Node: %s is 0,"
 			"defaulting to 1.\n", tpg->se_tpg_tfo->get_fabric_name(),
 			acl->initiatorname);
 		acl->queue_depth = 1;
 	}
-
-	return 0;
 }
 
 static struct se_node_acl *target_alloc_node_acl(struct se_portal_group *tpg,
 		const unsigned char *initiatorname)
 {
 	struct se_node_acl *acl;
+	u32 queue_depth;
 
 	acl = kzalloc(max(sizeof(*acl), tpg->se_tpg_tfo->node_acl_size),
 			GFP_KERNEL);
@@ -193,24 +202,20 @@ static struct se_node_acl *target_alloc_node_acl(struct se_portal_group *tpg,
 	spin_lock_init(&acl->nacl_sess_lock);
 	mutex_init(&acl->lun_entry_mutex);
 	atomic_set(&acl->acl_pr_ref_count, 0);
+
 	if (tpg->se_tpg_tfo->tpg_get_default_depth)
-		acl->queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg);
+		queue_depth = tpg->se_tpg_tfo->tpg_get_default_depth(tpg);
 	else
-		acl->queue_depth = 1;
+		queue_depth = 1;
+	target_set_nacl_queue_depth(tpg, acl, queue_depth);
+
 	snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
 	acl->se_tpg = tpg;
 	acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
 
 	tpg->se_tpg_tfo->set_default_node_attributes(acl);
 
-	if (core_set_queue_depth_for_node(tpg, acl) < 0)
-		goto out_free_acl;
-
 	return acl;
-
-out_free_acl:
-	kfree(acl);
-	return NULL;
 }
 
 static void target_add_node_acl(struct se_node_acl *acl)
@@ -232,6 +237,25 @@ static void target_add_node_acl(struct se_node_acl *acl)
 		acl->initiatorname);
 }
 
+bool target_tpg_has_node_acl(struct se_portal_group *tpg,
+			     const char *initiatorname)
+{
+	struct se_node_acl *acl;
+	bool found = false;
+
+	mutex_lock(&tpg->acl_node_mutex);
+	list_for_each_entry(acl, &tpg->acl_node_list, acl_list) {
+		if (!strcmp(acl->initiatorname, initiatorname)) {
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&tpg->acl_node_mutex);
+
+	return found;
+}
+EXPORT_SYMBOL(target_tpg_has_node_acl);
+
 struct se_node_acl *core_tpg_check_initiator_node_acl(
 	struct se_portal_group *tpg,
 	unsigned char *initiatorname)
@@ -248,6 +272,15 @@ struct se_node_acl *core_tpg_check_initiator_node_acl(
 	acl = target_alloc_node_acl(tpg, initiatorname);
 	if (!acl)
 		return NULL;
+	/*
+	 * When allocating a dynamically generated node_acl, go ahead
+	 * and take the extra kref now before returning to the fabric
+	 * driver caller.
+	 *
+	 * Note this reference will be released at session shutdown
+	 * time within transport_free_session() code.
+	 */
+	kref_get(&acl->acl_kref);
 	acl->dynamic_node_acl = 1;
 
 	/*
@@ -329,7 +362,8 @@ void core_tpg_del_initiator_node_acl(struct se_node_acl *acl)
 		if (sess->sess_tearing_down != 0)
 			continue;
 
-		target_get_session(sess);
+		if (!target_get_session(sess))
+			continue;
 		list_move(&sess->sess_acl_list, &sess_list);
 	}
 	spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
@@ -366,108 +400,52 @@ void core_tpg_del_initiator_node_acl(struct se_node_acl *acl)
  *
  */
 int core_tpg_set_initiator_node_queue_depth(
-	struct se_portal_group *tpg,
-	unsigned char *initiatorname,
-	u32 queue_depth,
-	int force)
+	struct se_node_acl *acl,
+	u32 queue_depth)
 {
-	struct se_session *sess, *init_sess = NULL;
-	struct se_node_acl *acl;
+	LIST_HEAD(sess_list);
+	struct se_portal_group *tpg = acl->se_tpg;
+	struct se_session *sess, *sess_tmp;
 	unsigned long flags;
-	int dynamic_acl = 0;
-
-	mutex_lock(&tpg->acl_node_mutex);
-	acl = __core_tpg_get_initiator_node_acl(tpg, initiatorname);
-	if (!acl) {
-		pr_err("Access Control List entry for %s Initiator"
-			" Node %s does not exists for TPG %hu, ignoring"
-			" request.\n", tpg->se_tpg_tfo->get_fabric_name(),
-			initiatorname, tpg->se_tpg_tfo->tpg_get_tag(tpg));
-		mutex_unlock(&tpg->acl_node_mutex);
-		return -ENODEV;
-	}
-	if (acl->dynamic_node_acl) {
-		acl->dynamic_node_acl = 0;
-		dynamic_acl = 1;
-	}
-	mutex_unlock(&tpg->acl_node_mutex);
-
-	spin_lock_irqsave(&tpg->session_lock, flags);
-	list_for_each_entry(sess, &tpg->tpg_sess_list, sess_list) {
-		if (sess->se_node_acl != acl)
-			continue;
-
-		if (!force) {
-			pr_err("Unable to change queue depth for %s"
-				" Initiator Node: %s while session is"
-				" operational.  To forcefully change the queue"
-				" depth and force session reinstatement"
-				" use the \"force=1\" parameter.\n",
-				tpg->se_tpg_tfo->get_fabric_name(), initiatorname);
-			spin_unlock_irqrestore(&tpg->session_lock, flags);
-
-			mutex_lock(&tpg->acl_node_mutex);
-			if (dynamic_acl)
-				acl->dynamic_node_acl = 1;
-			mutex_unlock(&tpg->acl_node_mutex);
-			return -EEXIST;
-		}
-		/*
-		 * Determine if the session needs to be closed by our context.
-		 */
-		if (!tpg->se_tpg_tfo->shutdown_session(sess))
-			continue;
-
-		init_sess = sess;
-		break;
-	}
+	int rc;
 
 	/*
 	 * User has requested to change the queue depth for a Initiator Node.
 	 * Change the value in the Node's struct se_node_acl, and call
-	 * core_set_queue_depth_for_node() to add the requested queue depth.
-	 *
-	 * Finally call  tpg->se_tpg_tfo->close_session() to force session
-	 * reinstatement to occur if there is an active session for the
-	 * $FABRIC_MOD Initiator Node in question.
+	 * target_set_nacl_queue_depth() to set the new queue depth.
 	 */
-	acl->queue_depth = queue_depth;
+	target_set_nacl_queue_depth(tpg, acl, queue_depth);
+
+	spin_lock_irqsave(&acl->nacl_sess_lock, flags);
+	list_for_each_entry_safe(sess, sess_tmp, &acl->acl_sess_list,
+				 sess_acl_list) {
+		if (sess->sess_tearing_down != 0)
+			continue;
+		if (!target_get_session(sess))
+			continue;
+		spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
 
-	if (core_set_queue_depth_for_node(tpg, acl) < 0) {
-		spin_unlock_irqrestore(&tpg->session_lock, flags);
 		/*
-		 * Force session reinstatement if
-		 * core_set_queue_depth_for_node() failed, because we assume
-		 * the $FABRIC_MOD has already the set session reinstatement
-		 * bit from tpg->se_tpg_tfo->shutdown_session() called above.
+		 * Finally call tpg->se_tpg_tfo->close_session() to force session
+		 * reinstatement to occur if there is an active session for the
+		 * $FABRIC_MOD Initiator Node in question.
 		 */
-		if (init_sess)
-			tpg->se_tpg_tfo->close_session(init_sess);
-
-		mutex_lock(&tpg->acl_node_mutex);
-		if (dynamic_acl)
-			acl->dynamic_node_acl = 1;
-		mutex_unlock(&tpg->acl_node_mutex);
-		return -EINVAL;
+		rc = tpg->se_tpg_tfo->shutdown_session(sess);
+		target_put_session(sess);
+		if (!rc) {
+			spin_lock_irqsave(&acl->nacl_sess_lock, flags);
+			continue;
+		}
+		target_put_session(sess);
+		spin_lock_irqsave(&acl->nacl_sess_lock, flags);
 	}
-	spin_unlock_irqrestore(&tpg->session_lock, flags);
-	/*
-	 * If the $FABRIC_MOD session for the Initiator Node ACL exists,
-	 * forcefully shutdown the $FABRIC_MOD session/nexus.
-	 */
-	if (init_sess)
-		tpg->se_tpg_tfo->close_session(init_sess);
+	spin_unlock_irqrestore(&acl->nacl_sess_lock, flags);
 
 	pr_debug("Successfully changed queue depth to: %d for Initiator"
-		" Node: %s on %s Target Portal Group: %u\n", queue_depth,
-		initiatorname, tpg->se_tpg_tfo->get_fabric_name(),
+		" Node: %s on %s Target Portal Group: %u\n", acl->queue_depth,
+		acl->initiatorname, tpg->se_tpg_tfo->get_fabric_name(),
 		tpg->se_tpg_tfo->tpg_get_tag(tpg));
 
-	mutex_lock(&tpg->acl_node_mutex);
-	if (dynamic_acl)
-		acl->dynamic_node_acl = 1;
-	mutex_unlock(&tpg->acl_node_mutex);
-
 	return 0;
 }
 EXPORT_SYMBOL(core_tpg_set_initiator_node_queue_depth);
@@ -499,7 +477,7 @@ static void core_tpg_lun_ref_release(struct percpu_ref *ref)
 {
 	struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
 
-	complete(&lun->lun_ref_comp);
+	complete(&lun->lun_shutdown_comp);
 }
 
 int core_tpg_register(
@@ -626,6 +604,7 @@ struct se_lun *core_tpg_alloc_lun(
 	lun->lun_link_magic = SE_LUN_LINK_MAGIC;
 	atomic_set(&lun->lun_acl_count, 0);
 	init_completion(&lun->lun_ref_comp);
+	init_completion(&lun->lun_shutdown_comp);
 	INIT_LIST_HEAD(&lun->lun_deve_list);
 	INIT_LIST_HEAD(&lun->lun_dev_link);
 	atomic_set(&lun->lun_tg_pt_secondary_offline, 0);
@@ -694,6 +673,8 @@ void core_tpg_remove_lun(
 	 */
 	struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
 
+	lun->lun_shutdown = true;
+
 	core_clear_lun_from_tpg(lun, tpg);
 	/*
 	 * Wait for any active I/O references to percpu se_lun->lun_ref to
@@ -715,6 +696,8 @@ void core_tpg_remove_lun(
 	}
 	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		hlist_del_rcu(&lun->link);
+
+	lun->lun_shutdown = false;
 	mutex_unlock(&tpg->tpg_lun_mutex);
 
 	percpu_ref_exit(&lun->lun_ref);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 94f4ffac723f..f71bedea973a 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -341,7 +341,6 @@ void __transport_register_session(
 					&buf[0], PR_REG_ISID_LEN);
 			se_sess->sess_bin_isid = get_unaligned_be64(&buf[0]);
 		}
-		kref_get(&se_nacl->acl_kref);
 
 		spin_lock_irq(&se_nacl->nacl_sess_lock);
 		/*
@@ -384,9 +383,9 @@ static void target_release_session(struct kref *kref)
 	se_tpg->se_tpg_tfo->close_session(se_sess);
 }
 
-void target_get_session(struct se_session *se_sess)
+int target_get_session(struct se_session *se_sess)
 {
-	kref_get(&se_sess->sess_kref);
+	return kref_get_unless_zero(&se_sess->sess_kref);
 }
 EXPORT_SYMBOL(target_get_session);
 
@@ -424,14 +423,27 @@ static void target_complete_nacl(struct kref *kref)
 {
 	struct se_node_acl *nacl = container_of(kref,
 				struct se_node_acl, acl_kref);
+	struct se_portal_group *se_tpg = nacl->se_tpg;
 
-	complete(&nacl->acl_free_comp);
+	if (!nacl->dynamic_stop) {
+		complete(&nacl->acl_free_comp);
+		return;
+	}
+
+	mutex_lock(&se_tpg->acl_node_mutex);
+	list_del(&nacl->acl_list);
+	mutex_unlock(&se_tpg->acl_node_mutex);
+
+	core_tpg_wait_for_nacl_pr_ref(nacl);
+	core_free_device_list_for_node(nacl, se_tpg);
+	kfree(nacl);
 }
 
 void target_put_nacl(struct se_node_acl *nacl)
 {
 	kref_put(&nacl->acl_kref, target_complete_nacl);
 }
+EXPORT_SYMBOL(target_put_nacl);
 
 void transport_deregister_session_configfs(struct se_session *se_sess)
 {
@@ -464,6 +476,42 @@ EXPORT_SYMBOL(transport_deregister_session_configfs);
 
 void transport_free_session(struct se_session *se_sess)
 {
+	struct se_node_acl *se_nacl = se_sess->se_node_acl;
+
+	/*
+	 * Drop the se_node_acl->nacl_kref obtained from within
+	 * core_tpg_get_initiator_node_acl().
+	 */
+	if (se_nacl) {
+		struct se_portal_group *se_tpg = se_nacl->se_tpg;
+		const struct target_core_fabric_ops *se_tfo = se_tpg->se_tpg_tfo;
+		unsigned long flags;
+
+		se_sess->se_node_acl = NULL;
+
+		/*
+		 * Also determine if we need to drop the extra ->cmd_kref if
+		 * it had been previously dynamically generated, and
+		 * the endpoint is not caching dynamic ACLs.
+		 */
+		mutex_lock(&se_tpg->acl_node_mutex);
+		if (se_nacl->dynamic_node_acl &&
+		    !se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
+			spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
+			if (list_empty(&se_nacl->acl_sess_list))
+				se_nacl->dynamic_stop = true;
+			spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
+
+			if (se_nacl->dynamic_stop)
+				list_del(&se_nacl->acl_list);
+		}
+		mutex_unlock(&se_tpg->acl_node_mutex);
+
+		if (se_nacl->dynamic_stop)
+			target_put_nacl(se_nacl);
+
+		target_put_nacl(se_nacl);
+	}
 	if (se_sess->sess_cmd_map) {
 		percpu_ida_destroy(&se_sess->sess_tag_pool);
 		kvfree(se_sess->sess_cmd_map);
@@ -475,16 +523,12 @@ EXPORT_SYMBOL(transport_free_session);
 void transport_deregister_session(struct se_session *se_sess)
 {
 	struct se_portal_group *se_tpg = se_sess->se_tpg;
-	const struct target_core_fabric_ops *se_tfo;
-	struct se_node_acl *se_nacl;
 	unsigned long flags;
-	bool comp_nacl = true, drop_nacl = false;
 
 	if (!se_tpg) {
 		transport_free_session(se_sess);
 		return;
 	}
-	se_tfo = se_tpg->se_tpg_tfo;
 
 	spin_lock_irqsave(&se_tpg->session_lock, flags);
 	list_del(&se_sess->sess_list);
@@ -492,37 +536,16 @@ void transport_deregister_session(struct se_session *se_sess)
 	se_sess->fabric_sess_ptr = NULL;
 	spin_unlock_irqrestore(&se_tpg->session_lock, flags);
 
-	/*
-	 * Determine if we need to do extra work for this initiator node's
-	 * struct se_node_acl if it had been previously dynamically generated.
-	 */
-	se_nacl = se_sess->se_node_acl;
-
-	mutex_lock(&se_tpg->acl_node_mutex);
-	if (se_nacl && se_nacl->dynamic_node_acl) {
-		if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
-			list_del(&se_nacl->acl_list);
-			se_tpg->num_node_acls--;
-			drop_nacl = true;
-		}
-	}
-	mutex_unlock(&se_tpg->acl_node_mutex);
-
-	if (drop_nacl) {
-		core_tpg_wait_for_nacl_pr_ref(se_nacl);
-		core_free_device_list_for_node(se_nacl, se_tpg);
-		kfree(se_nacl);
-		comp_nacl = false;
-	}
 	pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
 		se_tpg->se_tpg_tfo->get_fabric_name());
 	/*
 	 * If last kref is dropping now for an explicit NodeACL, awake sleeping
 	 * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
-	 * removal context.
+	 * removal context from within transport_free_session() code.
+	 *
+	 * For dynamic ACL, target_put_nacl() uses target_complete_nacl()
+	 * to release all remaining generate_node_acl=1 created ACL resources.
 	 */
-	if (se_nacl && comp_nacl)
-		target_put_nacl(se_nacl);
 
 	transport_free_session(se_sess);
 }
@@ -616,9 +639,10 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 		percpu_ref_put(&lun->lun_ref);
 }
 
-void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
+int transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
 	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
+	int ret = 0;
 
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
@@ -630,9 +654,11 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 		cmd->se_tfo->aborted_task(cmd);
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
-		return;
+		return 1;
 	if (remove && ack_kref)
-		transport_put_cmd(cmd);
+		ret = transport_put_cmd(cmd);
+
+	return ret;
 }
 
 static void target_complete_failure_work(struct work_struct *work)
@@ -702,6 +728,15 @@ 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);
+		/*
+		 * If COMPARE_AND_WRITE was stopped by __transport_wait_for_tasks(),
+		 * release se_device->caw_sem obtained by sbc_compare_and_write()
+		 * since target_complete_ok_work() or target_complete_failure_work()
+		 * won't be called to invoke the normal CAW completion callbacks.
+		 */
+		if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) {
+			up(&dev->caw_sem);
+		}
 		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	} else if (!success) {
@@ -1131,15 +1166,28 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size)
 	if (cmd->unknown_data_length) {
 		cmd->data_length = size;
 	} else if (size != cmd->data_length) {
-		pr_warn("TARGET_CORE[%s]: Expected Transfer Length:"
+		pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:"
 			" %u does not match SCSI CDB Length: %u for SAM Opcode:"
 			" 0x%02x\n", cmd->se_tfo->get_fabric_name(),
 				cmd->data_length, size, cmd->t_task_cdb[0]);
 
-		if (cmd->data_direction == DMA_TO_DEVICE &&
-		    cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
-			pr_err("Rejecting underflow/overflow WRITE data\n");
-			return TCM_INVALID_CDB_FIELD;
+		if (cmd->data_direction == DMA_TO_DEVICE) {
+			if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
+				pr_err_ratelimited("Rejecting underflow/overflow"
+						   " for WRITE data CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
+			/*
+			 * Some fabric drivers like iscsi-target still expect to
+			 * always reject overflow writes.  Reject this case until
+			 * full fabric driver level support for overflow writes
+			 * is introduced tree-wide.
+			 */
+			if (size > cmd->data_length) {
+				pr_err_ratelimited("Rejecting overflow for"
+						   " WRITE control CDB\n");
+				return TCM_INVALID_CDB_FIELD;
+			}
 		}
 		/*
 		 * Reject READ_* or WRITE_* with overflow/underflow for
@@ -1270,23 +1318,6 @@ target_setup_cmd_from_cdb(struct se_cmd *cmd, unsigned char *cdb)
 
 	trace_target_sequencer_start(cmd);
 
-	/*
-	 * Check for an existing UNIT ATTENTION condition
-	 */
-	ret = target_scsi3_ua_check(cmd);
-	if (ret)
-		return ret;
-
-	ret = target_alua_state_check(cmd);
-	if (ret)
-		return ret;
-
-	ret = target_check_reservation(cmd);
-	if (ret) {
-		cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
-		return ret;
-	}
-
 	ret = dev->transport->parse_cdb(cmd);
 	if (ret == TCM_UNSUPPORTED_SCSI_OPCODE)
 		pr_warn_ratelimited("%s/%s: Unsupported SCSI Opcode 0x%02x, sending CHECK_CONDITION.\n",
@@ -1697,6 +1728,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
 	case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
 	case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
+	case TCM_COPY_TARGET_DEVICE_NOT_REACHABLE:
 		break;
 	case TCM_OUT_OF_RESOURCES:
 		sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -1749,20 +1781,45 @@ queue_full:
 }
 EXPORT_SYMBOL(transport_generic_request_failure);
 
-void __target_execute_cmd(struct se_cmd *cmd)
+void __target_execute_cmd(struct se_cmd *cmd, bool do_checks)
 {
 	sense_reason_t ret;
 
-	if (cmd->execute_cmd) {
-		ret = cmd->execute_cmd(cmd);
-		if (ret) {
-			spin_lock_irq(&cmd->t_state_lock);
-			cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
-			spin_unlock_irq(&cmd->t_state_lock);
+	if (!cmd->execute_cmd) {
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto err;
+	}
+	if (do_checks) {
+		/*
+		 * Check for an existing UNIT ATTENTION condition after
+		 * target_handle_task_attr() has done SAM task attr
+		 * checking, and possibly have already defered execution
+		 * out to target_restart_delayed_cmds() context.
+		 */
+		ret = target_scsi3_ua_check(cmd);
+		if (ret)
+			goto err;
+
+		ret = target_alua_state_check(cmd);
+		if (ret)
+			goto err;
 
-			transport_generic_request_failure(cmd, ret);
+		ret = target_check_reservation(cmd);
+		if (ret) {
+			cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT;
+			goto err;
 		}
 	}
+
+	ret = cmd->execute_cmd(cmd);
+	if (!ret)
+		return;
+err:
+	spin_lock_irq(&cmd->t_state_lock);
+	cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	transport_generic_request_failure(cmd, ret);
 }
 
 static int target_write_prot_action(struct se_cmd *cmd)
@@ -1807,6 +1864,8 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
 		return false;
 
+	cmd->se_cmd_flags |= SCF_TASK_ATTR_SET;
+
 	/*
 	 * Check for the existence of HEAD_OF_QUEUE, and if true return 1
 	 * to allow the passed struct se_cmd list of tasks to the front of the list.
@@ -1887,7 +1946,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 		return;
 	}
 
-	__target_execute_cmd(cmd);
+	__target_execute_cmd(cmd, true);
 }
 EXPORT_SYMBOL(target_execute_cmd);
 
@@ -1911,7 +1970,7 @@ static void target_restart_delayed_cmds(struct se_device *dev)
 		list_del(&cmd->se_delayed_node);
 		spin_unlock(&dev->delayed_cmd_lock);
 
-		__target_execute_cmd(cmd);
+		__target_execute_cmd(cmd, true);
 
 		if (cmd->sam_task_attr == TCM_ORDERED_TAG)
 			break;
@@ -1929,6 +1988,9 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
 		return;
 
+	if (!(cmd->se_cmd_flags & SCF_TASK_ATTR_SET))
+		goto restart;
+
 	if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
 		atomic_dec_mb(&dev->simple_cmds);
 		dev->dev_cur_ordered_id++;
@@ -1945,7 +2007,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 		pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED\n",
 			 dev->dev_cur_ordered_id);
 	}
-
+restart:
 	target_restart_delayed_cmds(dev);
 }
 
@@ -2496,8 +2558,10 @@ int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref)
 	 * fabric acknowledgement that requires two target_put_sess_cmd()
 	 * invocations before se_cmd descriptor release.
 	 */
-	if (ack_kref)
+	if (ack_kref) {
 		kref_get(&se_cmd->cmd_kref);
+		se_cmd->se_cmd_flags |= SCF_ACK_KREF;
+	}
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (se_sess->sess_tearing_down) {
@@ -2533,15 +2597,10 @@ static void target_release_cmd_kref(struct kref *kref)
 	bool fabric_stop;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-	if (list_empty(&se_cmd->se_cmd_list)) {
-		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-		target_free_cmd_mem(se_cmd);
-		se_cmd->se_tfo->release_cmd(se_cmd);
-		return;
-	}
 
 	spin_lock(&se_cmd->t_state_lock);
-	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP);
+	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
+		      (se_cmd->transport_state & CMD_T_ABORTED);
 	spin_unlock(&se_cmd->t_state_lock);
 
 	if (se_cmd->cmd_wait_set || fabric_stop) {
@@ -2618,8 +2677,6 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del_init(&se_cmd->se_cmd_list);
-
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));
@@ -2648,10 +2705,39 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
+static void target_lun_confirm(struct percpu_ref *ref)
+{
+	struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
+
+	complete(&lun->lun_ref_comp);
+}
+
 void transport_clear_lun_ref(struct se_lun *lun)
 {
-	percpu_ref_kill(&lun->lun_ref);
+	/*
+	 * Mark the percpu-ref as DEAD, switch to atomic_t mode, drop
+	 * the initial reference and schedule confirm kill to be
+	 * executed after one full RCU grace period has completed.
+	 */
+	percpu_ref_kill_and_confirm(&lun->lun_ref, target_lun_confirm);
+	/*
+	 * The first completion waits for percpu_ref_switch_to_atomic_rcu()
+	 * to call target_lun_confirm after lun->lun_ref has been marked
+	 * as __PERCPU_REF_DEAD on all CPUs, and switches to atomic_t
+	 * mode so that percpu_ref_tryget_live() lookup of lun->lun_ref
+	 * fails for all new incoming I/O.
+	 */
 	wait_for_completion(&lun->lun_ref_comp);
+	/*
+	 * The second completion waits for percpu_ref_put_many() to
+	 * invoke ->release() after lun->lun_ref has switched to
+	 * atomic_t mode, and lun->lun_ref.count has reached zero.
+	 *
+	 * At this point all target-core lun->lun_ref references have
+	 * been dropped via transport_lun_remove_cmd(), and it's safe
+	 * to proceed with the remaining LUN shutdown.
+	 */
+	wait_for_completion(&lun->lun_shutdown_comp);
 }
 
 static bool
@@ -2827,6 +2913,12 @@ static const struct sense_info sense_info_table[] = {
 		.ascq = 0x03, /* LOGICAL BLOCK REFERENCE TAG CHECK FAILED */
 		.add_sector_info = true,
 	},
+	[TCM_COPY_TARGET_DEVICE_NOT_REACHABLE] = {
+		.key = COPY_ABORTED,
+		.asc = 0x0d,
+		.ascq = 0x02, /* COPY TARGET DEVICE NOT REACHABLE */
+
+	},
 	[TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE] = {
 		/*
 		 * Returning ILLEGAL REQUEST would cause immediate IO errors on
@@ -3043,7 +3135,6 @@ static void target_tmr_work(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		goto check_stop;
 	}
-	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
 	cmd->se_tfo->queue_tm_rsp(cmd);
@@ -3056,11 +3147,25 @@ int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
 	unsigned long flags;
+	bool aborted = false;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	cmd->transport_state |= CMD_T_ACTIVE;
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		aborted = true;
+	} else {
+		cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+		cmd->transport_state |= CMD_T_ACTIVE;
+	}
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
+	if (aborted) {
+		pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d"
+			"ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function,
+			cmd->se_tmr_req->ref_task_tag, cmd->tag);
+		transport_cmd_check_stop_to_fabric(cmd);
+		return 0;
+	}
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 5e6d6cb348fc..a7d30e894cab 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -645,8 +645,6 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)
 	target_complete_cmd(cmd->se_cmd, SAM_STAT_CHECK_CONDITION);
 	cmd->se_cmd = NULL;
 
-	kmem_cache_free(tcmu_cmd_cache, cmd);
-
 	return 0;
 }
 
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 47fe94ee10b8..6415e9b09a52 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -104,7 +104,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
 	}
 	mutex_unlock(&g_device_mutex);
 
-	pr_err("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+	pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
 	return -EINVAL;
 }
 
@@ -185,7 +185,7 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op
 
 static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
 				struct xcopy_op *xop, unsigned char *p,
-				unsigned short tdll)
+				unsigned short tdll, sense_reason_t *sense_ret)
 {
 	struct se_device *local_dev = se_cmd->se_dev;
 	unsigned char *desc = p;
@@ -193,6 +193,8 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
 	unsigned short start = 0;
 	bool src = true;
 
+	*sense_ret = TCM_INVALID_PARAMETER_LIST;
+
 	if (offset != 0) {
 		pr_err("XCOPY target descriptor list length is not"
 			" multiple of %d\n", XCOPY_TARGET_DESC_LEN);
@@ -243,9 +245,16 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
 		rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true);
 	else
 		rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false);
-
-	if (rc < 0)
+	/*
+	 * If a matching IEEE NAA 0x83 descriptor for the requested device
+	 * is not located on this node, return COPY_ABORTED with ASQ/ASQC
+	 * 0x0d/0x02 - COPY_TARGET_DEVICE_NOT_REACHABLE to request the
+	 * initiator to fall back to normal copy method.
+	 */
+	if (rc < 0) {
+		*sense_ret = TCM_COPY_TARGET_DEVICE_NOT_REACHABLE;
 		goto out;
+	}
 
 	pr_debug("XCOPY TGT desc: Source dev: %p NAA IEEE WWN: 0x%16phN\n",
 		 xop->src_dev, &xop->src_tid_wwn[0]);
@@ -653,6 +662,7 @@ static int target_xcopy_read_source(
 	rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0],
 				remote_port, true);
 	if (rc < 0) {
+		ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
 		transport_generic_free_cmd(se_cmd, 0);
 		return rc;
 	}
@@ -664,6 +674,7 @@ static int target_xcopy_read_source(
 
 	rc = target_xcopy_issue_pt_cmd(xpt_cmd);
 	if (rc < 0) {
+		ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
 		transport_generic_free_cmd(se_cmd, 0);
 		return rc;
 	}
@@ -714,6 +725,7 @@ static int target_xcopy_write_destination(
 				remote_port, false);
 	if (rc < 0) {
 		struct se_cmd *src_cmd = &xop->src_pt_cmd->se_cmd;
+		ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
 		/*
 		 * If the failure happened before the t_mem_list hand-off in
 		 * target_xcopy_setup_pt_cmd(), Reset memory + clear flag so that
@@ -729,6 +741,7 @@ static int target_xcopy_write_destination(
 
 	rc = target_xcopy_issue_pt_cmd(xpt_cmd);
 	if (rc < 0) {
+		ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
 		se_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 		transport_generic_free_cmd(se_cmd, 0);
 		return rc;
@@ -815,10 +828,15 @@ static void target_xcopy_do_work(struct work_struct *work)
 out:
 	xcopy_pt_undepend_remotedev(xop);
 	kfree(xop);
-
-	pr_warn("target_xcopy_do_work: Setting X-COPY CHECK_CONDITION -> sending response\n");
-	ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
-	target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
+	/*
+	 * Don't override an error scsi status if it has already been set
+	 */
+	if (ec_cmd->scsi_status == SAM_STAT_GOOD) {
+		pr_warn_ratelimited("target_xcopy_do_work: rc: %d, Setting X-COPY"
+			" CHECK_CONDITION -> sending response\n", rc);
+		ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+	}
+	target_complete_cmd(ec_cmd, ec_cmd->scsi_status);
 }
 
 sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
@@ -875,7 +893,7 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
 		" tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage,
 		tdll, sdll, inline_dl);
 
-	rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll);
+	rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll, &ret);
 	if (rc <= 0)
 		goto out;
 
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6ceac4f2d4b2..87d87ac1c8a0 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -191,8 +191,10 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
 	mutex_lock(&cooling_list_lock);
 	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
 		if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
+			unsigned long level = get_level(cpufreq_dev, freq);
+
 			mutex_unlock(&cooling_list_lock);
-			return get_level(cpufreq_dev, freq);
+			return level;
 		}
 	}
 	mutex_unlock(&cooling_list_lock);
@@ -857,14 +859,6 @@ __cpufreq_cooling_register(struct device_node *np,
 		goto free_power_table;
 	}
 
-	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
-		 cpufreq_dev->id);
-
-	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
-						      &cpufreq_cooling_ops);
-	if (IS_ERR(cool_dev))
-		goto remove_idr;
-
 	/* Fill freq-table in descending order of frequencies */
 	for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) {
 		freq = find_next_max(table, freq);
@@ -877,6 +871,14 @@ __cpufreq_cooling_register(struct device_node *np,
 			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
 
+	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
+		 cpufreq_dev->id);
+
+	cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
+						      &cpufreq_cooling_ops);
+	if (IS_ERR(cool_dev))
+		goto remove_idr;
+
 	cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0];
 	cpufreq_dev->cool_dev = cool_dev;
 
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index e845841ab036..7106288efae3 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -545,15 +545,14 @@ static int rockchip_configure_from_dt(struct device *dev,
 			 thermal->chip->tshut_temp);
 		thermal->tshut_temp = thermal->chip->tshut_temp;
 	} else {
+		if (shut_temp > INT_MAX) {
+			dev_err(dev, "Invalid tshut temperature specified: %d\n",
+				shut_temp);
+			return -ERANGE;
+		}
 		thermal->tshut_temp = shut_temp;
 	}
 
-	if (thermal->tshut_temp > INT_MAX) {
-		dev_err(dev, "Invalid tshut temperature specified: %d\n",
-			thermal->tshut_temp);
-		return -ERANGE;
-	}
-
 	if (of_property_read_u32(np, "rockchip,hw-tshut-mode", &tshut_mode)) {
 		dev_warn(dev,
 			 "Missing tshut mode property, using default (%s)\n",
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index ba08b5521382..3d5f8f432b5b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -454,6 +454,10 @@ static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
 {
 	enum thermal_trip_type type;
 
+	/* Ignore disabled trip points */
+	if (test_bit(trip, &tz->trips_disabled))
+		return;
+
 	tz->ops->get_trip_type(tz, trip, &type);
 
 	if (type == THERMAL_TRIP_CRITICAL || type == THERMAL_TRIP_HOT)
@@ -1796,6 +1800,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 {
 	struct thermal_zone_device *tz;
 	enum thermal_trip_type trip_type;
+	int trip_temp;
 	int result;
 	int count;
 	int passive = 0;
@@ -1867,9 +1872,15 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 		goto unregister;
 
 	for (count = 0; count < trips; count++) {
-		tz->ops->get_trip_type(tz, count, &trip_type);
+		if (tz->ops->get_trip_type(tz, count, &trip_type))
+			set_bit(count, &tz->trips_disabled);
 		if (trip_type == THERMAL_TRIP_PASSIVE)
 			passive = 1;
+		if (tz->ops->get_trip_temp(tz, count, &trip_temp))
+			set_bit(count, &tz->trips_disabled);
+		/* Check for bogus trip points */
+		if (trip_temp == 0)
+			set_bit(count, &tz->trips_disabled);
 	}
 
 	if (!passive) {
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 06fd2ed9ef9d..705b0cafedbb 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -98,7 +98,7 @@ temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf)
 	int temperature;
 	int ret;
 
-	ret = tz->ops->get_trip_temp(tz, 0, &temperature);
+	ret = tz->ops->get_crit_temp(tz, &temperature);
 	if (ret)
 		return ret;
 
diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c
index 0dde34e3a7c5..545c60c826a1 100644
--- a/drivers/thunderbolt/eeprom.c
+++ b/drivers/thunderbolt/eeprom.c
@@ -444,6 +444,7 @@ int tb_drom_read(struct tb_switch *sw)
 	return tb_drom_parse_entries(sw);
 err:
 	kfree(sw->drom);
+	sw->drom = NULL;
 	return -EIO;
 
 }
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index c3fe026d3168..9aff37186246 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2045,7 +2045,9 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm)
 		}
 	}
 	spin_unlock(&gsm_mux_lock);
-	WARN_ON(i == MAX_MUX);
+	/* open failed before registering => nothing to do */
+	if (i == MAX_MUX)
+		return;
 
 	/* In theory disconnecting DLCI 0 is sufficient but for some
 	   modems this is apparently not the case. */
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index bbc4ce66c2c1..6d1e2f746ab4 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -114,7 +114,7 @@
 #define DEFAULT_TX_BUF_COUNT 3
 
 struct n_hdlc_buf {
-	struct n_hdlc_buf *link;
+	struct list_head  list_item;
 	int		  count;
 	char		  buf[1];
 };
@@ -122,8 +122,7 @@ struct n_hdlc_buf {
 #define	N_HDLC_BUF_SIZE	(sizeof(struct n_hdlc_buf) + maxframe)
 
 struct n_hdlc_buf_list {
-	struct n_hdlc_buf *head;
-	struct n_hdlc_buf *tail;
+	struct list_head  list;
 	int		  count;
 	spinlock_t	  spinlock;
 };
@@ -136,7 +135,6 @@ struct n_hdlc_buf_list {
  * @backup_tty - TTY to use if tty gets closed
  * @tbusy - reentrancy flag for tx wakeup code
  * @woke_up - FIXME: describe this field
- * @tbuf - currently transmitting tx buffer
  * @tx_buf_list - list of pending transmit frame buffers
  * @rx_buf_list - list of received frame buffers
  * @tx_free_buf_list - list unused transmit frame buffers
@@ -149,7 +147,6 @@ struct n_hdlc {
 	struct tty_struct	*backup_tty;
 	int			tbusy;
 	int			woke_up;
-	struct n_hdlc_buf	*tbuf;
 	struct n_hdlc_buf_list	tx_buf_list;
 	struct n_hdlc_buf_list	rx_buf_list;
 	struct n_hdlc_buf_list	tx_free_buf_list;
@@ -159,7 +156,8 @@ struct n_hdlc {
 /*
  * HDLC buffer list manipulation functions
  */
-static void n_hdlc_buf_list_init(struct n_hdlc_buf_list *list);
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf);
 static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
 			   struct n_hdlc_buf *buf);
 static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list);
@@ -209,16 +207,9 @@ static void flush_tx_queue(struct tty_struct *tty)
 {
 	struct n_hdlc *n_hdlc = tty2n_hdlc(tty);
 	struct n_hdlc_buf *buf;
-	unsigned long flags;
 
 	while ((buf = n_hdlc_buf_get(&n_hdlc->tx_buf_list)))
 		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, buf);
- 	spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock, flags);
-	if (n_hdlc->tbuf) {
-		n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, n_hdlc->tbuf);
-		n_hdlc->tbuf = NULL;
-	}
-	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 }
 
 static struct tty_ldisc_ops n_hdlc_ldisc = {
@@ -284,7 +275,6 @@ static void n_hdlc_release(struct n_hdlc *n_hdlc)
 		} else
 			break;
 	}
-	kfree(n_hdlc->tbuf);
 	kfree(n_hdlc);
 	
 }	/* end of n_hdlc_release() */
@@ -403,13 +393,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 	n_hdlc->woke_up = 0;
 	spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock, flags);
 
-	/* get current transmit buffer or get new transmit */
-	/* buffer from list of pending transmit buffers */
-		
-	tbuf = n_hdlc->tbuf;
-	if (!tbuf)
-		tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
-		
+	tbuf = n_hdlc_buf_get(&n_hdlc->tx_buf_list);
 	while (tbuf) {
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d)sending frame %p, count=%d\n",
@@ -421,7 +405,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 
 		/* rollback was possible and has been done */
 		if (actual == -ERESTARTSYS) {
-			n_hdlc->tbuf = tbuf;
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 		/* if transmit error, throw frame away by */
@@ -436,10 +420,7 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 					
 			/* free current transmit buffer */
 			n_hdlc_buf_put(&n_hdlc->tx_free_buf_list, tbuf);
-			
-			/* this tx buffer is done */
-			n_hdlc->tbuf = NULL;
-			
+
 			/* wait up sleeping writers */
 			wake_up_interruptible(&tty->write_wait);
 	
@@ -449,10 +430,12 @@ static void n_hdlc_send_frames(struct n_hdlc *n_hdlc, struct tty_struct *tty)
 			if (debuglevel >= DEBUG_LEVEL_INFO)	
 				printk("%s(%d)frame %p pending\n",
 					__FILE__,__LINE__,tbuf);
-					
-			/* buffer not accepted by driver */
-			/* set this buffer as pending buffer */
-			n_hdlc->tbuf = tbuf;
+
+			/*
+			 * the buffer was not accepted by driver,
+			 * return it back into tx queue
+			 */
+			n_hdlc_buf_return(&n_hdlc->tx_buf_list, tbuf);
 			break;
 		}
 	}
@@ -600,7 +583,7 @@ static ssize_t n_hdlc_tty_read(struct tty_struct *tty, struct file *file,
 	add_wait_queue(&tty->read_wait, &wait);
 
 	for (;;) {
-		if (test_bit(TTY_OTHER_DONE, &tty->flags)) {
+		if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) {
 			ret = -EIO;
 			break;
 		}
@@ -750,7 +733,8 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 	int error = 0;
 	int count;
 	unsigned long flags;
-	
+	struct n_hdlc_buf *buf = NULL;
+
 	if (debuglevel >= DEBUG_LEVEL_INFO)	
 		printk("%s(%d)n_hdlc_tty_ioctl() called %d\n",
 			__FILE__,__LINE__,cmd);
@@ -764,8 +748,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		/* report count of read data available */
 		/* in next available frame (if any) */
 		spin_lock_irqsave(&n_hdlc->rx_buf_list.spinlock,flags);
-		if (n_hdlc->rx_buf_list.head)
-			count = n_hdlc->rx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->rx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count = buf->count;
 		else
 			count = 0;
 		spin_unlock_irqrestore(&n_hdlc->rx_buf_list.spinlock,flags);
@@ -777,8 +763,10 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file,
 		count = tty_chars_in_buffer(tty);
 		/* add size of next output frame in queue */
 		spin_lock_irqsave(&n_hdlc->tx_buf_list.spinlock,flags);
-		if (n_hdlc->tx_buf_list.head)
-			count += n_hdlc->tx_buf_list.head->count;
+		buf = list_first_entry_or_null(&n_hdlc->tx_buf_list.list,
+						struct n_hdlc_buf, list_item);
+		if (buf)
+			count += buf->count;
 		spin_unlock_irqrestore(&n_hdlc->tx_buf_list.spinlock,flags);
 		error = put_user(count, (int __user *)arg);
 		break;
@@ -826,14 +814,14 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
 		poll_wait(filp, &tty->write_wait, wait);
 
 		/* set bits for operations that won't block */
-		if (n_hdlc->rx_buf_list.head)
+		if (!list_empty(&n_hdlc->rx_buf_list.list))
 			mask |= POLLIN | POLLRDNORM;	/* readable */
-		if (test_bit(TTY_OTHER_DONE, &tty->flags))
+		if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
 			mask |= POLLHUP;
 		if (tty_hung_up_p(filp))
 			mask |= POLLHUP;
 		if (!tty_is_writelocked(tty) &&
-				n_hdlc->tx_free_buf_list.head)
+				!list_empty(&n_hdlc->tx_free_buf_list.list))
 			mask |= POLLOUT | POLLWRNORM;	/* writable */
 	}
 	return mask;
@@ -853,11 +841,16 @@ static struct n_hdlc *n_hdlc_alloc(void)
 	if (!n_hdlc)
 		return NULL;
 
-	n_hdlc_buf_list_init(&n_hdlc->rx_free_buf_list);
-	n_hdlc_buf_list_init(&n_hdlc->tx_free_buf_list);
-	n_hdlc_buf_list_init(&n_hdlc->rx_buf_list);
-	n_hdlc_buf_list_init(&n_hdlc->tx_buf_list);
-	
+	spin_lock_init(&n_hdlc->rx_free_buf_list.spinlock);
+	spin_lock_init(&n_hdlc->tx_free_buf_list.spinlock);
+	spin_lock_init(&n_hdlc->rx_buf_list.spinlock);
+	spin_lock_init(&n_hdlc->tx_buf_list.spinlock);
+
+	INIT_LIST_HEAD(&n_hdlc->rx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_free_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->rx_buf_list.list);
+	INIT_LIST_HEAD(&n_hdlc->tx_buf_list.list);
+
 	/* allocate free rx buffer list */
 	for(i=0;i<DEFAULT_RX_BUF_COUNT;i++) {
 		buf = kmalloc(N_HDLC_BUF_SIZE, GFP_KERNEL);
@@ -885,63 +878,65 @@ static struct n_hdlc *n_hdlc_alloc(void)
 }	/* end of n_hdlc_alloc() */
 
 /**
- * n_hdlc_buf_list_init - initialize specified HDLC buffer list
- * @list - pointer to buffer list
+ * n_hdlc_buf_return - put the HDLC buffer after the head of the specified list
+ * @buf_list - pointer to the buffer list
+ * @buf - pointer to the buffer
  */
-static void n_hdlc_buf_list_init(struct n_hdlc_buf_list *list)
+static void n_hdlc_buf_return(struct n_hdlc_buf_list *buf_list,
+						struct n_hdlc_buf *buf)
 {
-	memset(list, 0, sizeof(*list));
-	spin_lock_init(&list->spinlock);
-}	/* end of n_hdlc_buf_list_init() */
+	unsigned long flags;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
+}
 
 /**
  * n_hdlc_buf_put - add specified HDLC buffer to tail of specified list
- * @list - pointer to buffer list
+ * @buf_list - pointer to buffer list
  * @buf	- pointer to buffer
  */
-static void n_hdlc_buf_put(struct n_hdlc_buf_list *list,
+static void n_hdlc_buf_put(struct n_hdlc_buf_list *buf_list,
 			   struct n_hdlc_buf *buf)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf->link=NULL;
-	if (list->tail)
-		list->tail->link = buf;
-	else
-		list->head = buf;
-	list->tail = buf;
-	(list->count)++;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
-	
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	list_add_tail(&buf->list_item, &buf_list->list);
+	buf_list->count++;
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 }	/* end of n_hdlc_buf_put() */
 
 /**
  * n_hdlc_buf_get - remove and return an HDLC buffer from list
- * @list - pointer to HDLC buffer list
+ * @buf_list - pointer to HDLC buffer list
  * 
  * Remove and return an HDLC buffer from the head of the specified HDLC buffer
  * list.
  * Returns a pointer to HDLC buffer if available, otherwise %NULL.
  */
-static struct n_hdlc_buf* n_hdlc_buf_get(struct n_hdlc_buf_list *list)
+static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *buf_list)
 {
 	unsigned long flags;
 	struct n_hdlc_buf *buf;
-	spin_lock_irqsave(&list->spinlock,flags);
-	
-	buf = list->head;
+
+	spin_lock_irqsave(&buf_list->spinlock, flags);
+
+	buf = list_first_entry_or_null(&buf_list->list,
+						struct n_hdlc_buf, list_item);
 	if (buf) {
-		list->head = buf->link;
-		(list->count)--;
+		list_del(&buf->list_item);
+		buf_list->count--;
 	}
-	if (!list->head)
-		list->tail = NULL;
-	
-	spin_unlock_irqrestore(&list->spinlock,flags);
+
+	spin_unlock_irqrestore(&buf_list->spinlock, flags);
 	return buf;
-	
 }	/* end of n_hdlc_buf_get() */
 
 static char hdlc_banner[] __initdata =
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index cf000b331eed..84e71bd19082 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1955,18 +1955,6 @@ static inline int input_available_p(struct tty_struct *tty, int poll)
 		return ldata->commit_head - ldata->read_tail >= amt;
 }
 
-static inline int check_other_done(struct tty_struct *tty)
-{
-	int done = test_bit(TTY_OTHER_DONE, &tty->flags);
-	if (done) {
-		/* paired with cmpxchg() in check_other_closed(); ensures
-		 * read buffer head index is not stale
-		 */
-		smp_mb__after_atomic();
-	}
-	return done;
-}
-
 /**
  *	copy_from_read_buf	-	copy read data directly
  *	@tty: terminal device
@@ -2171,7 +2159,7 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 	struct n_tty_data *ldata = tty->disc_data;
 	unsigned char __user *b = buf;
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	int c, done;
+	int c;
 	int minimum, time;
 	ssize_t retval = 0;
 	long timeout;
@@ -2239,32 +2227,35 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 		    ((minimum - (b - buf)) >= 1))
 			ldata->minimum_to_wake = (minimum - (b - buf));
 
-		done = check_other_done(tty);
-
 		if (!input_available_p(tty, 0)) {
-			if (done) {
-				retval = -EIO;
-				break;
-			}
-			if (tty_hung_up_p(file))
-				break;
-			if (!timeout)
-				break;
-			if (file->f_flags & O_NONBLOCK) {
-				retval = -EAGAIN;
-				break;
-			}
-			if (signal_pending(current)) {
-				retval = -ERESTARTSYS;
-				break;
-			}
 			up_read(&tty->termios_rwsem);
+			tty_buffer_flush_work(tty->port);
+			down_read(&tty->termios_rwsem);
+			if (!input_available_p(tty, 0)) {
+				if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) {
+					retval = -EIO;
+					break;
+				}
+				if (tty_hung_up_p(file))
+					break;
+				if (!timeout)
+					break;
+				if (file->f_flags & O_NONBLOCK) {
+					retval = -EAGAIN;
+					break;
+				}
+				if (signal_pending(current)) {
+					retval = -ERESTARTSYS;
+					break;
+				}
+				up_read(&tty->termios_rwsem);
 
-			timeout = wait_woken(&wait, TASK_INTERRUPTIBLE,
-					     timeout);
+				timeout = wait_woken(&wait, TASK_INTERRUPTIBLE,
+						timeout);
 
-			down_read(&tty->termios_rwsem);
-			continue;
+				down_read(&tty->termios_rwsem);
+				continue;
+			}
 		}
 
 		if (ldata->icanon && !L_EXTPROC(tty)) {
@@ -2446,12 +2437,17 @@ static unsigned int n_tty_poll(struct tty_struct *tty, struct file *file,
 
 	poll_wait(file, &tty->read_wait, wait);
 	poll_wait(file, &tty->write_wait, wait);
-	if (check_other_done(tty))
-		mask |= POLLHUP;
 	if (input_available_p(tty, 1))
 		mask |= POLLIN | POLLRDNORM;
+	else {
+		tty_buffer_flush_work(tty->port);
+		if (input_available_p(tty, 1))
+			mask |= POLLIN | POLLRDNORM;
+	}
 	if (tty->packet && tty->link->ctrl_status)
 		mask |= POLLPRI | POLLIN | POLLRDNORM;
+	if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
+		mask |= POLLHUP;
 	if (tty_hung_up_p(file))
 		mask |= POLLHUP;
 	if (!(mask & (POLLHUP | POLLIN | POLLRDNORM))) {
diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c
index 80f9de907563..5cc80b80c82b 100644
--- a/drivers/tty/nozomi.c
+++ b/drivers/tty/nozomi.c
@@ -823,7 +823,7 @@ static int receive_data(enum port_type index, struct nozomi *dc)
 	struct tty_struct *tty = tty_port_tty_get(&port->port);
 	int i, ret;
 
-	read_mem32((u32 *) &size, addr, 4);
+	size = __le32_to_cpu(readl(addr));
 	/*  DBG1( "%d bytes port: %d", size, index); */
 
 	if (tty && test_bit(TTY_THROTTLED, &tty->flags)) {
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 78e983677339..96aa0ad32497 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -59,7 +59,7 @@ static void pty_close(struct tty_struct *tty, struct file *filp)
 	if (!tty->link)
 		return;
 	set_bit(TTY_OTHER_CLOSED, &tty->link->flags);
-	tty_flip_buffer_push(tty->link->port);
+	wake_up_interruptible(&tty->link->read_wait);
 	wake_up_interruptible(&tty->link->write_wait);
 	if (tty->driver->subtype == PTY_TYPE_MASTER) {
 		set_bit(TTY_OTHER_CLOSED, &tty->flags);
@@ -216,16 +216,11 @@ static int pty_signal(struct tty_struct *tty, int sig)
 static void pty_flush_buffer(struct tty_struct *tty)
 {
 	struct tty_struct *to = tty->link;
-	struct tty_ldisc *ld;
 
 	if (!to)
 		return;
 
-	ld = tty_ldisc_ref(to);
-	tty_buffer_flush(to, ld);
-	if (ld)
-		tty_ldisc_deref(ld);
-
+	tty_buffer_flush(to, NULL);
 	if (to->packet) {
 		spin_lock_irq(&tty->ctrl_lock);
 		tty->ctrl_status |= TIOCPKT_FLUSHWRITE;
@@ -247,9 +242,7 @@ static int pty_open(struct tty_struct *tty, struct file *filp)
 		goto out;
 
 	clear_bit(TTY_IO_ERROR, &tty->flags);
-	/* TTY_OTHER_CLOSED must be cleared before TTY_OTHER_DONE */
 	clear_bit(TTY_OTHER_CLOSED, &tty->link->flags);
-	clear_bit(TTY_OTHER_DONE, &tty->link->flags);
 	set_bit(TTY_THROTTLED, &tty->flags);
 	return 0;
 
@@ -681,14 +674,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
 /* this is called once with whichever end is closed last */
 static void pty_unix98_shutdown(struct tty_struct *tty)
 {
-	struct inode *ptmx_inode;
+	struct pts_fs_info *fsi;
 
 	if (tty->driver->subtype == PTY_TYPE_MASTER)
-		ptmx_inode = tty->driver_data;
+		fsi = tty->driver_data;
 	else
-		ptmx_inode = tty->link->driver_data;
-	devpts_kill_index(ptmx_inode, tty->index);
-	devpts_del_ref(ptmx_inode);
+		fsi = tty->link->driver_data;
+	devpts_kill_index(fsi, tty->index);
+	devpts_put_ref(fsi);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -740,6 +733,7 @@ static const struct tty_operations pty_unix98_ops = {
 
 static int ptmx_open(struct inode *inode, struct file *filp)
 {
+	struct pts_fs_info *fsi;
 	struct tty_struct *tty;
 	struct inode *slave_inode;
 	int retval;
@@ -754,47 +748,41 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	if (retval)
 		return retval;
 
+	fsi = devpts_get_ref(inode, filp);
+	retval = -ENODEV;
+	if (!fsi)
+		goto out_free_file;
+
 	/* find a device that is not in use. */
 	mutex_lock(&devpts_mutex);
-	index = devpts_new_index(inode);
-	if (index < 0) {
-		retval = index;
-		mutex_unlock(&devpts_mutex);
-		goto err_file;
-	}
-
+	index = devpts_new_index(fsi);
 	mutex_unlock(&devpts_mutex);
 
-	mutex_lock(&tty_mutex);
-	tty = tty_init_dev(ptm_driver, index);
+	retval = index;
+	if (index < 0)
+		goto out_put_ref;
 
-	if (IS_ERR(tty)) {
-		retval = PTR_ERR(tty);
-		goto out;
-	}
 
+	mutex_lock(&tty_mutex);
+	tty = tty_init_dev(ptm_driver, index);
 	/* The tty returned here is locked so we can safely
 	   drop the mutex */
 	mutex_unlock(&tty_mutex);
 
-	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
-	tty->driver_data = inode;
+	retval = PTR_ERR(tty);
+	if (IS_ERR(tty))
+		goto out;
 
 	/*
-	 * In the case where all references to ptmx inode are dropped and we
-	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
-	 * is closed/released before /dev/tty), we must make sure that the inode
-	 * is still valid when we call the final pty_unix98_shutdown, thus we
-	 * hold an additional reference to the ptmx inode. For the same /dev/tty
-	 * last close case, we also need to make sure the super_block isn't
-	 * destroyed (devpts instance unmounted), before /dev/tty is closed and
-	 * on its release devpts_kill_index is called.
+	 * From here on out, the tty is "live", and the index and
+	 * fsi will be killed/put by the tty_release()
 	 */
-	devpts_add_ref(inode);
+	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+	tty->driver_data = fsi;
 
 	tty_add_file(tty, filp);
 
-	slave_inode = devpts_pty_new(inode,
+	slave_inode = devpts_pty_new(fsi,
 			MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index,
 			tty->link);
 	if (IS_ERR(slave_inode)) {
@@ -813,12 +801,14 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	return 0;
 err_release:
 	tty_unlock(tty);
+	// This will also put-ref the fsi
 	tty_release(inode, filp);
 	return retval;
 out:
-	mutex_unlock(&tty_mutex);
-	devpts_kill_index(inode, index);
-err_file:
+	devpts_kill_index(fsi, index);
+out_put_ref:
+	devpts_put_ref(fsi);
+out_free_file:
 	tty_free_file(filp);
 	return retval;
 }
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index a5d319e4aae6..8435c3f204c1 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -440,7 +440,7 @@ static int dw8250_probe(struct platform_device *pdev)
 	}
 
 	data->pclk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(data->clk) && PTR_ERR(data->clk) == -EPROBE_DEFER) {
+	if (IS_ERR(data->pclk) && PTR_ERR(data->pclk) == -EPROBE_DEFER) {
 		err = -EPROBE_DEFER;
 		goto err_clk;
 	}
diff --git a/drivers/tty/serial/8250/8250_mid.c b/drivers/tty/serial/8250/8250_mid.c
index 88531a36b69c..83b3988eb6b2 100644
--- a/drivers/tty/serial/8250/8250_mid.c
+++ b/drivers/tty/serial/8250/8250_mid.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 
 #include <linux/dma/hsu.h>
+#include <linux/8250_pci.h>
 
 #include "8250.h"
 
@@ -24,6 +25,7 @@
 #define PCI_DEVICE_ID_INTEL_DNV_UART	0x19d8
 
 /* Intel MID Specific registers */
+#define INTEL_MID_UART_DNV_FISR		0x08
 #define INTEL_MID_UART_PS		0x30
 #define INTEL_MID_UART_MUL		0x34
 #define INTEL_MID_UART_DIV		0x38
@@ -31,6 +33,7 @@
 struct mid8250;
 
 struct mid8250_board {
+	unsigned int flags;
 	unsigned long freq;
 	unsigned int base_baud;
 	int (*setup)(struct mid8250 *, struct uart_port *p);
@@ -88,16 +91,16 @@ static int tng_setup(struct mid8250 *mid, struct uart_port *p)
 static int dnv_handle_irq(struct uart_port *p)
 {
 	struct mid8250 *mid = p->private_data;
-	int ret;
-
-	ret = hsu_dma_irq(&mid->dma_chip, 0);
-	ret |= hsu_dma_irq(&mid->dma_chip, 1);
-
-	/* For now, letting the HW generate separate interrupt for the UART */
-	if (ret)
-		return ret;
-
-	return serial8250_handle_irq(p, serial_port_in(p, UART_IIR));
+	unsigned int fisr = serial_port_in(p, INTEL_MID_UART_DNV_FISR);
+	int ret = IRQ_NONE;
+
+	if (fisr & BIT(2))
+		ret |= hsu_dma_irq(&mid->dma_chip, 1);
+	if (fisr & BIT(1))
+		ret |= hsu_dma_irq(&mid->dma_chip, 0);
+	if (fisr & BIT(0))
+		ret |= serial8250_handle_irq(p, serial_port_in(p, UART_IIR));
+	return ret;
 }
 
 #define DNV_DMA_CHAN_OFFSET 0x80
@@ -106,12 +109,13 @@ static int dnv_setup(struct mid8250 *mid, struct uart_port *p)
 {
 	struct hsu_dma_chip *chip = &mid->dma_chip;
 	struct pci_dev *pdev = to_pci_dev(p->dev);
+	unsigned int bar = FL_GET_BASE(mid->board->flags);
 	int ret;
 
 	chip->dev = &pdev->dev;
 	chip->irq = pdev->irq;
 	chip->regs = p->membase;
-	chip->length = pci_resource_len(pdev, 0);
+	chip->length = pci_resource_len(pdev, bar);
 	chip->offset = DNV_DMA_CHAN_OFFSET;
 
 	/* Falling back to PIO mode if DMA probing fails */
@@ -145,6 +149,9 @@ static void mid8250_set_termios(struct uart_port *p,
 	unsigned long w = BIT(24) - 1;
 	unsigned long mul, div;
 
+	/* Gracefully handle the B0 case: fall back to B9600 */
+	fuart = fuart ? fuart : 9600 * 16;
+
 	if (mid->board->freq < fuart) {
 		/* Find prescaler value that satisfies Fuart < Fref */
 		if (mid->board->freq > baud)
@@ -217,6 +224,7 @@ static int mid8250_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct uart_8250_port uart;
 	struct mid8250 *mid;
+	unsigned int bar;
 	int ret;
 
 	ret = pcim_enable_device(pdev);
@@ -230,6 +238,7 @@ static int mid8250_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	mid->board = (struct mid8250_board *)id->driver_data;
+	bar = FL_GET_BASE(mid->board->flags);
 
 	memset(&uart, 0, sizeof(struct uart_8250_port));
 
@@ -242,8 +251,8 @@ static int mid8250_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	uart.port.flags = UPF_SHARE_IRQ | UPF_FIXED_PORT | UPF_FIXED_TYPE;
 	uart.port.set_termios = mid8250_set_termios;
 
-	uart.port.mapbase = pci_resource_start(pdev, 0);
-	uart.port.membase = pcim_iomap(pdev, 0, 0);
+	uart.port.mapbase = pci_resource_start(pdev, bar);
+	uart.port.membase = pcim_iomap(pdev, bar, 0);
 	if (!uart.port.membase)
 		return -ENOMEM;
 
@@ -282,18 +291,21 @@ static void mid8250_remove(struct pci_dev *pdev)
 }
 
 static const struct mid8250_board pnw_board = {
+	.flags = FL_BASE0,
 	.freq = 50000000,
 	.base_baud = 115200,
 	.setup = pnw_setup,
 };
 
 static const struct mid8250_board tng_board = {
+	.flags = FL_BASE0,
 	.freq = 38400000,
 	.base_baud = 1843200,
 	.setup = tng_setup,
 };
 
 static const struct mid8250_board dnv_board = {
+	.flags = FL_BASE1,
 	.freq = 133333333,
 	.base_baud = 115200,
 	.setup = dnv_setup,
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index a2c0734c76e2..e8dd296fb25b 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1235,7 +1235,8 @@ static int omap8250_probe(struct platform_device *pdev)
 	pm_runtime_put_autosuspend(&pdev->dev);
 	return 0;
 err:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
@@ -1244,6 +1245,7 @@ static int omap8250_remove(struct platform_device *pdev)
 {
 	struct omap8250_priv *priv = platform_get_drvdata(pdev);
 
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	serial8250_unregister_port(priv->line);
@@ -1343,6 +1345,10 @@ static int omap8250_runtime_suspend(struct device *dev)
 	struct omap8250_priv *priv = dev_get_drvdata(dev);
 	struct uart_8250_port *up;
 
+	/* In case runtime-pm tries this before we are setup */
+	if (!priv)
+		return 0;
+
 	up = serial8250_get_port(priv->line);
 	/*
 	 * When using 'no_console_suspend', the console UART must not be
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 7cd6f9a90542..cf3da51a3536 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -57,6 +57,7 @@ struct serial_private {
 	unsigned int		nr;
 	void __iomem		*remapped_bar[PCI_NUM_BAR_RESOURCES];
 	struct pci_serial_quirk	*quirk;
+	const struct pciserial_board *board;
 	int			line[0];
 };
 
@@ -1401,6 +1402,9 @@ byt_set_termios(struct uart_port *p, struct ktermios *termios,
 	unsigned long m, n;
 	u32 reg;
 
+	/* Gracefully handle the B0 case: fall back to B9600 */
+	fuart = fuart ? fuart : 9600 * 16;
+
 	/* Get Fuart closer to Fref */
 	fuart *= rounddown_pow_of_two(fref / fuart);
 
@@ -1949,6 +1953,43 @@ pci_wch_ch38x_setup(struct serial_private *priv,
 #define PCI_DEVICE_ID_PERICOM_PI7C9X7954	0x7954
 #define PCI_DEVICE_ID_PERICOM_PI7C9X7958	0x7958
 
+#define PCI_VENDOR_ID_ACCESIO			0x494f
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB	0x1051
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S	0x1053
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB	0x105C
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S	0x105E
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB	0x1091
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2	0x1093
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB	0x1099
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4	0x109B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB	0x10D1
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM	0x10D3
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB	0x10DA
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM	0x10DC
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1	0x1108
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2	0x1110
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2	0x1111
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4	0x1118
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4	0x1119
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S	0x1152
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S	0x115A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2	0x1190
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2	0x1191
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4	0x1198
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4	0x1199
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM	0x11D0
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4	0x105A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4	0x105B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8	0x106A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8	0x106B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4	0x1098
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8	0x10A9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM	0x10D9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM	0x10E9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM	0x11D8
+
+
+
 /* Unknown vendors/cards - this should not be in linux/pci_ids.h */
 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584	0x1584
 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1588	0x1588
@@ -2840,6 +2881,8 @@ enum pci_board_num_t {
 	pbn_b0_4_1152000_200,
 	pbn_b0_8_1152000_200,
 
+	pbn_b0_4_1250000,
+
 	pbn_b0_2_1843200,
 	pbn_b0_4_1843200,
 
@@ -3073,6 +3116,13 @@ static struct pciserial_board pci_boards[] = {
 		.uart_offset	= 0x200,
 	},
 
+	[pbn_b0_4_1250000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 4,
+		.base_baud	= 1250000,
+		.uart_offset	= 8,
+	},
+
 	[pbn_b0_2_1843200] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 2,
@@ -4009,6 +4059,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
 		}
 	}
 	priv->nr = i;
+	priv->board = board;
 	return priv;
 
 err_deinit:
@@ -4019,7 +4070,7 @@ err_out:
 }
 EXPORT_SYMBOL_GPL(pciserial_init_ports);
 
-void pciserial_remove_ports(struct serial_private *priv)
+void pciserial_detach_ports(struct serial_private *priv)
 {
 	struct pci_serial_quirk *quirk;
 	int i;
@@ -4039,7 +4090,11 @@ void pciserial_remove_ports(struct serial_private *priv)
 	quirk = find_quirk(priv->dev);
 	if (quirk->exit)
 		quirk->exit(priv->dev);
+}
 
+void pciserial_remove_ports(struct serial_private *priv)
+{
+	pciserial_detach_ports(priv);
 	kfree(priv);
 }
 EXPORT_SYMBOL_GPL(pciserial_remove_ports);
@@ -5117,6 +5172,108 @@ static struct pci_device_id serial_pci_tbl[] = {
 		0,
 		0, pbn_pericom_PI7C9X7958 },
 	/*
+	 * ACCES I/O Products quad
+	 */
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7954 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	{	PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_pericom_PI7C9X7958 },
+	/*
 	 * Topic TP560 Data/Fax/Voice 56k modem (reported by Evan Clarke)
 	 */
 	{	PCI_VENDOR_ID_TOPIC, PCI_DEVICE_ID_TOPIC_TP560,
@@ -5636,6 +5793,10 @@ static struct pci_device_id serial_pci_tbl[] = {
 	{ PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 },
 	{ PCI_DEVICE(0x1c29, 0x1112), .driver_data = pbn_fintek_12 },
 
+	/* MKS Tenta SCOM-080x serial cards */
+	{ PCI_DEVICE(0x1601, 0x0800), .driver_data = pbn_b0_4_1250000 },
+	{ PCI_DEVICE(0x1601, 0xa801), .driver_data = pbn_b0_4_1250000 },
+
 	/*
 	 * These entries match devices with class COMMUNICATION_SERIAL,
 	 * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL
@@ -5664,7 +5825,7 @@ static pci_ers_result_t serial8250_io_error_detected(struct pci_dev *dev,
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	if (priv)
-		pciserial_suspend_ports(priv);
+		pciserial_detach_ports(priv);
 
 	pci_disable_device(dev);
 
@@ -5689,9 +5850,16 @@ static pci_ers_result_t serial8250_io_slot_reset(struct pci_dev *dev)
 static void serial8250_io_resume(struct pci_dev *dev)
 {
 	struct serial_private *priv = pci_get_drvdata(dev);
+	struct serial_private *new;
 
-	if (priv)
-		pciserial_resume_ports(priv);
+	if (!priv)
+		return;
+
+	new = pciserial_init_ports(dev, priv->board);
+	if (!IS_ERR(new)) {
+		pci_set_drvdata(dev, new);
+		kfree(priv);
+	}
 }
 
 static const struct pci_error_handlers serial8250_err_handler = {
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 52d82d2ac726..56ccbcefdd85 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -713,22 +713,16 @@ static int size_fifo(struct uart_8250_port *up)
  */
 static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p)
 {
-	unsigned char old_dll, old_dlm, old_lcr;
-	unsigned int id;
+	unsigned char old_lcr;
+	unsigned int id, old_dl;
 
 	old_lcr = serial_in(p, UART_LCR);
 	serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A);
+	old_dl = serial_dl_read(p);
+	serial_dl_write(p, 0);
+	id = serial_dl_read(p);
+	serial_dl_write(p, old_dl);
 
-	old_dll = serial_in(p, UART_DLL);
-	old_dlm = serial_in(p, UART_DLM);
-
-	serial_out(p, UART_DLL, 0);
-	serial_out(p, UART_DLM, 0);
-
-	id = serial_in(p, UART_DLL) | serial_in(p, UART_DLM) << 8;
-
-	serial_out(p, UART_DLL, old_dll);
-	serial_out(p, UART_DLM, old_dlm);
 	serial_out(p, UART_LCR, old_lcr);
 
 	return id;
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 94294558943c..53e4d5056db7 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -277,6 +277,13 @@ static bool atmel_use_dma_rx(struct uart_port *port)
 	return atmel_port->use_dma_rx;
 }
 
+static bool atmel_use_fifo(struct uart_port *port)
+{
+	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
+
+	return atmel_port->fifo_size;
+}
+
 static unsigned int atmel_get_lines_status(struct uart_port *port)
 {
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
@@ -463,6 +470,14 @@ static void atmel_stop_tx(struct uart_port *port)
 		/* disable PDC transmit */
 		atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS);
 	}
+
+	/*
+	 * Disable the transmitter.
+	 * This is mandatory when DMA is used, otherwise the DMA buffer
+	 * is fully transmitted.
+	 */
+	atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXDIS);
+
 	/* Disable interrupts */
 	atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
 
@@ -478,21 +493,26 @@ static void atmel_start_tx(struct uart_port *port)
 {
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
 
-	if (atmel_use_pdc_tx(port)) {
-		if (atmel_uart_readl(port, ATMEL_PDC_PTSR) & ATMEL_PDC_TXTEN)
-			/* The transmitter is already running.  Yes, we
-			   really need this.*/
-			return;
+	if (atmel_use_pdc_tx(port) && (atmel_uart_readl(port, ATMEL_PDC_PTSR)
+				       & ATMEL_PDC_TXTEN))
+		/* The transmitter is already running.  Yes, we
+		   really need this.*/
+		return;
 
+	if (atmel_use_pdc_tx(port) || atmel_use_dma_tx(port))
 		if ((port->rs485.flags & SER_RS485_ENABLED) &&
 		    !(port->rs485.flags & SER_RS485_RX_DURING_TX))
 			atmel_stop_rx(port);
 
+	if (atmel_use_pdc_tx(port))
 		/* re-enable PDC transmit */
 		atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTEN);
-	}
+
 	/* Enable interrupts */
 	atmel_uart_writel(port, ATMEL_US_IER, atmel_port->tx_done_mask);
+
+	/* re-enable the transmitter */
+	atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN);
 }
 
 /*
@@ -790,6 +810,11 @@ static void atmel_complete_tx_dma(void *arg)
 	 */
 	if (!uart_circ_empty(xmit))
 		tasklet_schedule(&atmel_port->tasklet);
+	else if ((port->rs485.flags & SER_RS485_ENABLED) &&
+		 !(port->rs485.flags & SER_RS485_RX_DURING_TX)) {
+		/* DMA done, stop TX, start RX for RS485 */
+		atmel_start_rx(port);
+	}
 
 	spin_unlock_irqrestore(&port->lock, flags);
 }
@@ -892,12 +917,6 @@ static void atmel_tx_dma(struct uart_port *port)
 		desc->callback = atmel_complete_tx_dma;
 		desc->callback_param = atmel_port;
 		atmel_port->cookie_tx = dmaengine_submit(desc);
-
-	} else {
-		if (port->rs485.flags & SER_RS485_ENABLED) {
-			/* DMA done, stop TX, start RX for RS485 */
-			atmel_start_rx(port);
-		}
 	}
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
@@ -1967,6 +1986,11 @@ static void atmel_flush_buffer(struct uart_port *port)
 		atmel_uart_writel(port, ATMEL_PDC_TCR, 0);
 		atmel_port->pdc_tx.ofs = 0;
 	}
+	/*
+	 * in uart_flush_buffer(), the xmit circular buffer has just
+	 * been cleared, so we have to reset tx_len accordingly.
+	 */
+	atmel_port->tx_len = 0;
 }
 
 /*
@@ -2066,6 +2090,7 @@ static void atmel_serial_pm(struct uart_port *port, unsigned int state,
 static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 			      struct ktermios *old)
 {
+	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
 	unsigned long flags;
 	unsigned int old_mode, mode, imr, quot, baud;
 
@@ -2169,7 +2194,30 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 		mode |= ATMEL_US_USMODE_RS485;
 	} else if (termios->c_cflag & CRTSCTS) {
 		/* RS232 with hardware handshake (RTS/CTS) */
-		mode |= ATMEL_US_USMODE_HWHS;
+		if (atmel_use_fifo(port) &&
+		    !mctrl_gpio_to_gpiod(atmel_port->gpios, UART_GPIO_CTS)) {
+			/*
+			 * with ATMEL_US_USMODE_HWHS set, the controller will
+			 * be able to drive the RTS pin high/low when the RX
+			 * FIFO is above RXFTHRES/below RXFTHRES2.
+			 * It will also disable the transmitter when the CTS
+			 * pin is high.
+			 * This mode is not activated if CTS pin is a GPIO
+			 * because in this case, the transmitter is always
+			 * disabled (there must be an internal pull-up
+			 * responsible for this behaviour).
+			 * If the RTS pin is a GPIO, the controller won't be
+			 * able to drive it according to the FIFO thresholds,
+			 * but it will be handled by the driver.
+			 */
+			mode |= ATMEL_US_USMODE_HWHS;
+		} else {
+			/*
+			 * For platforms without FIFO, the flow control is
+			 * handled by the driver.
+			 */
+			mode |= ATMEL_US_USMODE_NORMAL;
+		}
 	} else {
 		/* RS232 without hadware handshake */
 		mode |= ATMEL_US_USMODE_NORMAL;
@@ -2455,6 +2503,9 @@ static void atmel_console_write(struct console *co, const char *s, u_int count)
 	pdc_tx = atmel_uart_readl(port, ATMEL_PDC_PTSR) & ATMEL_PDC_TXTEN;
 	atmel_uart_writel(port, ATMEL_PDC_PTCR, ATMEL_PDC_TXTDIS);
 
+	/* Make sure that tx path is actually able to send characters */
+	atmel_uart_writel(port, ATMEL_US_CR, ATMEL_US_TXEN);
+
 	uart_console_write(port, s, count, atmel_console_putchar);
 
 	/*
diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c
index 195acc868763..5d476916191b 100644
--- a/drivers/tty/serial/efm32-uart.c
+++ b/drivers/tty/serial/efm32-uart.c
@@ -27,6 +27,7 @@
 #define UARTn_FRAME		0x04
 #define UARTn_FRAME_DATABITS__MASK	0x000f
 #define UARTn_FRAME_DATABITS(n)		((n) - 3)
+#define UARTn_FRAME_PARITY__MASK	0x0300
 #define UARTn_FRAME_PARITY_NONE		0x0000
 #define UARTn_FRAME_PARITY_EVEN		0x0200
 #define UARTn_FRAME_PARITY_ODD		0x0300
@@ -572,12 +573,16 @@ static void efm32_uart_console_get_options(struct efm32_uart_port *efm_port,
 			16 * (4 + (clkdiv >> 6)));
 
 	frame = efm32_uart_read32(efm_port, UARTn_FRAME);
-	if (frame & UARTn_FRAME_PARITY_ODD)
+	switch (frame & UARTn_FRAME_PARITY__MASK) {
+	case UARTn_FRAME_PARITY_ODD:
 		*parity = 'o';
-	else if (frame & UARTn_FRAME_PARITY_EVEN)
+		break;
+	case UARTn_FRAME_PARITY_EVEN:
 		*parity = 'e';
-	else
+		break;
+	default:
 		*parity = 'n';
+	}
 
 	*bits = (frame & UARTn_FRAME_DATABITS__MASK) -
 			UARTn_FRAME_DATABITS(4) + 4;
diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c
index 88246f7e435a..0f23dda60011 100644
--- a/drivers/tty/serial/ifx6x60.c
+++ b/drivers/tty/serial/ifx6x60.c
@@ -1378,9 +1378,9 @@ static struct spi_driver ifx_spi_driver = {
 static void __exit ifx_spi_exit(void)
 {
 	/* unregister */
+	spi_unregister_driver(&ifx_spi_driver);
 	tty_unregister_driver(tty_drv);
 	put_tty_driver(tty_drv);
-	spi_unregister_driver(&ifx_spi_driver);
 	unregister_reboot_notifier(&ifx_modem_reboot_notifier_block);
 }
 
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index dcde955475dc..8c4707d5778e 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -726,7 +726,7 @@ static void msm_handle_tx(struct uart_port *port)
 		return;
 	}
 
-	pio_count = CIRC_CNT(xmit->head, xmit->tail, UART_XMIT_SIZE);
+	pio_count = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
 	dma_count = CIRC_CNT_TO_END(xmit->head, xmit->tail, UART_XMIT_SIZE);
 
 	dma_min = 1;	/* Always DMA */
@@ -1615,6 +1615,7 @@ static const struct of_device_id msm_match_table[] = {
 	{ .compatible = "qcom,msm-uartdm" },
 	{}
 };
+MODULE_DEVICE_TABLE(of, msm_match_table);
 
 static struct platform_driver msm_platform_driver = {
 	.remove = msm_serial_remove,
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 24280d9a05e9..de1c143b475f 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1712,7 +1712,8 @@ static int serial_omap_probe(struct platform_device *pdev)
 	return 0;
 
 err_add_port:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	pm_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(up->dev, false);
@@ -1725,9 +1726,13 @@ static int serial_omap_remove(struct platform_device *dev)
 {
 	struct uart_omap_port *up = platform_get_drvdata(dev);
 
+	pm_runtime_get_sync(up->dev);
+
+	uart_remove_one_port(&serial_omap_reg, &up->port);
+
+	pm_runtime_dont_use_autosuspend(up->dev);
 	pm_runtime_put_sync(up->dev);
 	pm_runtime_disable(up->dev);
-	uart_remove_one_port(&serial_omap_reg, &up->port);
 	pm_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(&dev->dev, false);
 
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index d72cd736bdc6..e6bc1a6be4a4 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -900,14 +900,13 @@ static int s3c24xx_serial_request_dma(struct s3c24xx_uart_port *p)
 		return -ENOMEM;
 	}
 
-	dma->rx_addr = dma_map_single(dma->rx_chan->device->dev, dma->rx_buf,
+	dma->rx_addr = dma_map_single(p->port.dev, dma->rx_buf,
 				dma->rx_size, DMA_FROM_DEVICE);
 
 	spin_lock_irqsave(&p->port.lock, flags);
 
 	/* TX buffer */
-	dma->tx_addr = dma_map_single(dma->tx_chan->device->dev,
-				p->port.state->xmit.buf,
+	dma->tx_addr = dma_map_single(p->port.dev, p->port.state->xmit.buf,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 
 	spin_unlock_irqrestore(&p->port.lock, flags);
@@ -921,7 +920,7 @@ static void s3c24xx_serial_release_dma(struct s3c24xx_uart_port *p)
 
 	if (dma->rx_chan) {
 		dmaengine_terminate_all(dma->rx_chan);
-		dma_unmap_single(dma->rx_chan->device->dev, dma->rx_addr,
+		dma_unmap_single(p->port.dev, dma->rx_addr,
 				dma->rx_size, DMA_FROM_DEVICE);
 		kfree(dma->rx_buf);
 		dma_release_channel(dma->rx_chan);
@@ -930,7 +929,7 @@ static void s3c24xx_serial_release_dma(struct s3c24xx_uart_port *p)
 
 	if (dma->tx_chan) {
 		dmaengine_terminate_all(dma->tx_chan);
-		dma_unmap_single(dma->tx_chan->device->dev, dma->tx_addr,
+		dma_unmap_single(p->port.dev, dma->tx_addr,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 		dma_release_channel(dma->tx_chan);
 		dma->tx_chan = NULL;
@@ -1030,8 +1029,10 @@ static int s3c64xx_serial_startup(struct uart_port *port)
 	if (ourport->dma) {
 		ret = s3c24xx_serial_request_dma(ourport);
 		if (ret < 0) {
-			dev_warn(port->dev, "DMA request failed\n");
-			return ret;
+			dev_warn(port->dev,
+				 "DMA request failed, DMA will not be used\n");
+			devm_kfree(port->dev, ourport->dma);
+			ourport->dma = NULL;
 		}
 	}
 
@@ -1263,6 +1264,8 @@ static void s3c24xx_serial_set_termios(struct uart_port *port,
 	/* check to see if we need  to change clock source */
 
 	if (ourport->baudclk != clk) {
+		clk_prepare_enable(clk);
+
 		s3c24xx_serial_setsource(port, clk_sel);
 
 		if (!IS_ERR(ourport->baudclk)) {
@@ -1270,8 +1273,6 @@ static void s3c24xx_serial_set_termios(struct uart_port *port,
 			ourport->baudclk = ERR_PTR(-EINVAL);
 		}
 
-		clk_prepare_enable(clk);
-
 		ourport->baudclk = clk;
 		ourport->baudclk_rate = clk ? clk_get_rate(clk) : 0;
 	}
@@ -1676,7 +1677,7 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport,
 		return -ENODEV;
 
 	if (port->mapbase != 0)
-		return 0;
+		return -EINVAL;
 
 	/* setup info for port */
 	port->dev	= &platdev->dev;
@@ -1730,22 +1731,25 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport,
 		ourport->dma = devm_kzalloc(port->dev,
 					    sizeof(*ourport->dma),
 					    GFP_KERNEL);
-		if (!ourport->dma)
-			return -ENOMEM;
+		if (!ourport->dma) {
+			ret = -ENOMEM;
+			goto err;
+		}
 	}
 
 	ourport->clk	= clk_get(&platdev->dev, "uart");
 	if (IS_ERR(ourport->clk)) {
 		pr_err("%s: Controller clock not found\n",
 				dev_name(&platdev->dev));
-		return PTR_ERR(ourport->clk);
+		ret = PTR_ERR(ourport->clk);
+		goto err;
 	}
 
 	ret = clk_prepare_enable(ourport->clk);
 	if (ret) {
 		pr_err("uart: clock failed to prepare+enable: %d\n", ret);
 		clk_put(ourport->clk);
-		return ret;
+		goto err;
 	}
 
 	/* Keep all interrupts masked and cleared */
@@ -1761,7 +1765,12 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport,
 
 	/* reset the fifos (and setup the uart) */
 	s3c24xx_serial_resetport(port, cfg);
+
 	return 0;
+
+err:
+	port->mapbase = 0;
+	return ret;
 }
 
 /* Device driver serial port probe */
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index edb5305b9d4d..7d5ee8a13ac6 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1230,7 +1230,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 	/* Setup interrupt */
 	ret = devm_request_irq(dev, irq, sc16is7xx_irq,
-			       IRQF_ONESHOT | flags, dev_name(dev), s);
+			       flags, dev_name(dev), s);
 	if (!ret)
 		return 0;
 
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 51c7507b0444..235e150d7b81 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -38,7 +38,6 @@
 #include <linux/major.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -116,8 +115,6 @@ struct sci_port {
 	struct timer_list		rx_timer;
 	unsigned int			rx_timeout;
 #endif
-
-	struct notifier_block		freq_transition;
 };
 
 #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS
@@ -1606,29 +1603,6 @@ static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr)
 	return ret;
 }
 
-/*
- * Here we define a transition notifier so that we can update all of our
- * ports' baud rate when the peripheral clock changes.
- */
-static int sci_notifier(struct notifier_block *self,
-			unsigned long phase, void *p)
-{
-	struct sci_port *sci_port;
-	unsigned long flags;
-
-	sci_port = container_of(self, struct sci_port, freq_transition);
-
-	if (phase == CPUFREQ_POSTCHANGE) {
-		struct uart_port *port = &sci_port->port;
-
-		spin_lock_irqsave(&port->lock, flags);
-		port->uartclk = clk_get_rate(sci_port->iclk);
-		spin_unlock_irqrestore(&port->lock, flags);
-	}
-
-	return NOTIFY_OK;
-}
-
 static const struct sci_irq_desc {
 	const char	*desc;
 	irq_handler_t	handler;
@@ -1826,11 +1800,13 @@ static int sci_startup(struct uart_port *port)
 
 	dev_dbg(port->dev, "%s(%d)\n", __func__, port->line);
 
+	sci_request_dma(port);
+
 	ret = sci_request_irq(s);
-	if (unlikely(ret < 0))
+	if (unlikely(ret < 0)) {
+		sci_free_dma(port);
 		return ret;
-
-	sci_request_dma(port);
+	}
 
 	spin_lock_irqsave(&port->lock, flags);
 	sci_start_tx(port);
@@ -1860,8 +1836,8 @@ static void sci_shutdown(struct uart_port *port)
 	}
 #endif
 
-	sci_free_dma(port);
 	sci_free_irq(s);
+	sci_free_dma(port);
 }
 
 static unsigned int sci_scbrr_calc(struct sci_port *s, unsigned int bps,
@@ -2559,9 +2535,6 @@ static int sci_remove(struct platform_device *dev)
 {
 	struct sci_port *port = platform_get_drvdata(dev);
 
-	cpufreq_unregister_notifier(&port->freq_transition,
-				    CPUFREQ_TRANSITION_NOTIFIER);
-
 	uart_remove_one_port(&sci_uart_driver, &port->port);
 
 	sci_cleanup_single(port);
@@ -2714,16 +2687,6 @@ static int sci_probe(struct platform_device *dev)
 	if (ret)
 		return ret;
 
-	sp->freq_transition.notifier_call = sci_notifier;
-
-	ret = cpufreq_register_notifier(&sp->freq_transition,
-					CPUFREQ_TRANSITION_NOTIFIER);
-	if (unlikely(ret < 0)) {
-		uart_remove_one_port(&sci_uart_driver, &sp->port);
-		sci_cleanup_single(sp);
-		return ret;
-	}
-
 #ifdef CONFIG_SH_STANDARD_BIOS
 	sh_bios_gdb_detach();
 #endif
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index ca0d3802f2af..4e603d060e80 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -490,12 +490,6 @@ static void sunhv_console_write_bychar(struct console *con, const char *s, unsig
 		locked = spin_trylock_irqsave(&port->lock, flags);
 	else
 		spin_lock_irqsave(&port->lock, flags);
-	if (port->sysrq) {
-		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&port->lock);
-	} else
-		spin_lock(&port->lock);
 
 	for (i = 0; i < n; i++) {
 		if (*s == '\n')
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index 73190f5d2832..71d26c8e1b8f 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -1478,6 +1478,9 @@ static const struct of_device_id ucc_uart_match[] = {
 		.type = "serial",
 		.compatible = "ucc_uart",
 	},
+	{
+		.compatible = "fsl,t1040-ucc-uart",
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, ucc_uart_match);
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 5381a728d23e..1fa4128eb88e 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -939,8 +939,8 @@ static const struct input_device_id sysrq_ids[] = {
 	{
 		.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
 				INPUT_DEVICE_ID_MATCH_KEYBIT,
-		.evbit = { BIT_MASK(EV_KEY) },
-		.keybit = { BIT_MASK(KEY_LEFTALT) },
+		.evbit = { [BIT_WORD(EV_KEY)] = BIT_MASK(EV_KEY) },
+		.keybit = { [BIT_WORD(KEY_LEFTALT)] = BIT_MASK(KEY_LEFTALT) },
 	},
 	{ },
 };
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 3cd31e0d4bd9..fb31eecb708d 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -37,29 +37,6 @@
 
 #define TTY_BUFFER_PAGE	(((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF)
 
-/*
- * If all tty flip buffers have been processed by flush_to_ldisc() or
- * dropped by tty_buffer_flush(), check if the linked pty has been closed.
- * If so, wake the reader/poll to process
- */
-static inline void check_other_closed(struct tty_struct *tty)
-{
-	unsigned long flags, old;
-
-	/* transition from TTY_OTHER_CLOSED => TTY_OTHER_DONE must be atomic */
-	for (flags = ACCESS_ONCE(tty->flags);
-	     test_bit(TTY_OTHER_CLOSED, &flags);
-	     ) {
-		old = flags;
-		__set_bit(TTY_OTHER_DONE, &flags);
-		flags = cmpxchg(&tty->flags, old, flags);
-		if (old == flags) {
-			wake_up_interruptible(&tty->read_wait);
-			break;
-		}
-	}
-}
-
 /**
  *	tty_buffer_lock_exclusive	-	gain exclusive access to buffer
  *	tty_buffer_unlock_exclusive	-	release exclusive access
@@ -254,8 +231,6 @@ void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld)
 	if (ld && ld->ops->flush_buffer)
 		ld->ops->flush_buffer(tty);
 
-	check_other_closed(tty);
-
 	atomic_dec(&buf->priority);
 	mutex_unlock(&buf->lock);
 }
@@ -505,10 +480,8 @@ static void flush_to_ldisc(struct work_struct *work)
 		 */
 		count = smp_load_acquire(&head->commit) - head->read;
 		if (!count) {
-			if (next == NULL) {
-				check_other_closed(tty);
+			if (next == NULL)
 				break;
-			}
 			buf->head = next;
 			tty_buffer_free(port, head);
 			continue;
@@ -597,3 +570,8 @@ bool tty_buffer_cancel_work(struct tty_port *port)
 {
 	return cancel_work_sync(&port->buf.work);
 }
+
+void tty_buffer_flush_work(struct tty_port *port)
+{
+	flush_work(&port->buf.work);
+}
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 7cef54334b12..1bb629ab8ecc 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2070,13 +2070,12 @@ retry_open:
 		if (tty) {
 			mutex_unlock(&tty_mutex);
 			retval = tty_lock_interruptible(tty);
+			tty_kref_put(tty);  /* drop kref from tty_driver_lookup_tty() */
 			if (retval) {
 				if (retval == -EINTR)
 					retval = -ERESTARTSYS;
 				goto err_unref;
 			}
-			/* safe to drop the kref from tty_driver_lookup_tty() */
-			tty_kref_put(tty);
 			retval = tty_reopen(tty);
 			if (retval < 0) {
 				tty_unlock(tty);
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 629e3c865072..9bee25cfa0be 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -417,6 +417,10 @@ EXPORT_SYMBOL_GPL(tty_ldisc_flush);
  *	they are not on hot paths so a little discipline won't do
  *	any harm.
  *
+ *	The line discipline-related tty_struct fields are reset to
+ *	prevent the ldisc driver from re-using stale information for
+ *	the new ldisc instance.
+ *
  *	Locking: takes termios_rwsem
  */
 
@@ -425,6 +429,9 @@ static void tty_set_termios_ldisc(struct tty_struct *tty, int num)
 	down_write(&tty->termios_rwsem);
 	tty->termios.c_line = num;
 	up_write(&tty->termios_rwsem);
+
+	tty->disc_data = NULL;
+	tty->receive_room = 0;
 }
 
 /**
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index d09293bc0e04..cff304abb619 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -24,10 +24,15 @@ EXPORT_SYMBOL(tty_lock);
 
 int tty_lock_interruptible(struct tty_struct *tty)
 {
+	int ret;
+
 	if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty))
 		return -EIO;
 	tty_kref_get(tty);
-	return mutex_lock_interruptible(&tty->legacy_mutex);
+	ret = mutex_lock_interruptible(&tty->legacy_mutex);
+	if (ret)
+		tty_kref_put(tty);
+	return ret;
 }
 
 void __lockfunc tty_unlock(struct tty_struct *tty)
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 6f0336fff501..988c564b61a8 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -366,34 +366,22 @@ static void to_utf8(struct vc_data *vc, uint c)
 
 static void do_compute_shiftstate(void)
 {
-	unsigned int i, j, k, sym, val;
+	unsigned int k, sym, val;
 
 	shift_state = 0;
 	memset(shift_down, 0, sizeof(shift_down));
 
-	for (i = 0; i < ARRAY_SIZE(key_down); i++) {
-
-		if (!key_down[i])
+	for_each_set_bit(k, key_down, min(NR_KEYS, KEY_CNT)) {
+		sym = U(key_maps[0][k]);
+		if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK)
 			continue;
 
-		k = i * BITS_PER_LONG;
-
-		for (j = 0; j < BITS_PER_LONG; j++, k++) {
-
-			if (!test_bit(k, key_down))
-				continue;
+		val = KVAL(sym);
+		if (val == KVAL(K_CAPSSHIFT))
+			val = KVAL(K_SHIFT);
 
-			sym = U(key_maps[0][k]);
-			if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK)
-				continue;
-
-			val = KVAL(sym);
-			if (val == KVAL(K_CAPSSHIFT))
-				val = KVAL(K_SHIFT);
-
-			shift_down[val]++;
-			shift_state |= (1 << val);
-		}
+		shift_down[val]++;
+		shift_state |= BIT(val);
 	}
 }
 
@@ -994,7 +982,7 @@ static void kbd_led_trigger_activate(struct led_classdev *cdev)
 	KBD_LED_TRIGGER((_led_bit) + 8, _name)
 
 static struct kbd_led_trigger kbd_led_triggers[] = {
-	KBD_LED_TRIGGER(VC_SCROLLOCK, "kbd-scrollock"),
+	KBD_LED_TRIGGER(VC_SCROLLOCK, "kbd-scrolllock"),
 	KBD_LED_TRIGGER(VC_NUMLOCK,   "kbd-numlock"),
 	KBD_LED_TRIGGER(VC_CAPSLOCK,  "kbd-capslock"),
 	KBD_LED_TRIGGER(VC_KANALOCK,  "kbd-kanalock"),
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 4462d167900c..e4f69bddcfb1 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -750,6 +750,7 @@ static void visual_init(struct vc_data *vc, int num, int init)
 	vc->vc_complement_mask = 0;
 	vc->vc_can_do_color = 0;
 	vc->vc_panic_force_write = false;
+	vc->vc_cur_blink_ms = DEFAULT_CURSOR_BLINK_MS;
 	vc->vc_sw->con_init(vc, init);
 	if (!vc->vc_complement_mask)
 		vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800;
@@ -871,10 +872,15 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
+	if (new_screen_size > (4 << 20))
+		return -EINVAL;
 	newscreen = kmalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
 		return -ENOMEM;
 
+	if (vc == sel_cons)
+		clear_selection();
+
 	old_rows = vc->vc_rows;
 	old_row_size = vc->vc_size_row;
 
@@ -1172,7 +1178,7 @@ static void csi_J(struct vc_data *vc, int vpar)
 			break;
 		case 3: /* erase scroll-back buffer (and whole display) */
 			scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
-				    vc->vc_screenbuf_size >> 1);
+				    vc->vc_screenbuf_size);
 			set_origin(vc);
 			if (CON_IS_VISIBLE(vc))
 				update_screen(vc);
@@ -2702,13 +2708,13 @@ int tioclinux(struct tty_struct *tty, unsigned long arg)
 	 * related to the kernel should not use this.
 	 */
 			data = vt_get_shift_state();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_GETMOUSEREPORTING:
 			console_lock();	/* May be overkill */
 			data = mouse_reporting();
 			console_unlock();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_SETVESABLANK:
 			console_lock();
@@ -2717,7 +2723,7 @@ int tioclinux(struct tty_struct *tty, unsigned long arg)
 			break;
 		case TIOCL_GETKMSGREDIRECT:
 			data = vt_get_kmsg_redirect();
-			ret = __put_user(data, p);
+			ret = put_user(data, p);
 			break;
 		case TIOCL_SETKMSGREDIRECT:
 			if (!capable(CAP_SYS_ADMIN)) {
@@ -3583,9 +3589,10 @@ static int do_register_con_driver(const struct consw *csw, int first, int last)
 		goto err;
 
 	desc = csw->con_startup();
-
-	if (!desc)
+	if (!desc) {
+		retval = -ENODEV;
 		goto err;
+	}
 
 	retval = -EINVAL;
 
diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c
index 915facbf552e..e1134a4d97f3 100644
--- a/drivers/uio/uio_dmem_genirq.c
+++ b/drivers/uio/uio_dmem_genirq.c
@@ -229,7 +229,7 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev)
 		++uiomem;
 	}
 
-	priv->dmem_region_start = i;
+	priv->dmem_region_start = uiomem - &uioinfo->mem[0];
 	priv->num_dmem_regions = pdata->num_dynamic_regions;
 
 	for (i = 0; i < pdata->num_dynamic_regions; ++i) {
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index 41d7cf6d63ba..858c30814497 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -428,9 +428,6 @@ int hw_port_test_set(struct ci_hdrc *ci, u8 mode);
 
 u8 hw_port_test_get(struct ci_hdrc *ci);
 
-int hw_wait_reg(struct ci_hdrc *ci, enum ci_hw_regs reg, u32 mask,
-				u32 value, unsigned int timeout_ms);
-
 void ci_platform_configure(struct ci_hdrc *ci);
 
 #endif	/* __DRIVERS_USB_CHIPIDEA_CI_H */
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 5a048b7b92e8..2949289bb3c5 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -244,7 +244,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	struct ci_hdrc_platform_data pdata = {
 		.name		= dev_name(&pdev->dev),
 		.capoffset	= DEF_CAPOFFSET,
-		.flags		= CI_HDRC_SET_NON_ZERO_TTHA,
 	};
 	int ret;
 	const struct of_device_id *of_id;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 965d0e240dcb..939c6ad71068 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -518,38 +518,6 @@ int hw_device_reset(struct ci_hdrc *ci)
 	return 0;
 }
 
-/**
- * hw_wait_reg: wait the register value
- *
- * Sometimes, it needs to wait register value before going on.
- * Eg, when switch to device mode, the vbus value should be lower
- * than OTGSC_BSV before connects to host.
- *
- * @ci: the controller
- * @reg: register index
- * @mask: mast bit
- * @value: the bit value to wait
- * @timeout_ms: timeout in millisecond
- *
- * This function returns an error code if timeout
- */
-int hw_wait_reg(struct ci_hdrc *ci, enum ci_hw_regs reg, u32 mask,
-				u32 value, unsigned int timeout_ms)
-{
-	unsigned long elapse = jiffies + msecs_to_jiffies(timeout_ms);
-
-	while (hw_read(ci, reg, mask) != value) {
-		if (time_after(jiffies, elapse)) {
-			dev_err(ci->dev, "timeout waiting for %08x in %d\n",
-					mask, reg);
-			return -ETIMEDOUT;
-		}
-		msleep(20);
-	}
-
-	return 0;
-}
-
 static irqreturn_t ci_irq(int irq, void *data)
 {
 	struct ci_hdrc *ci = data;
@@ -926,6 +894,7 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 	if (!ci)
 		return -ENOMEM;
 
+	spin_lock_init(&ci->lock);
 	ci->dev = dev;
 	ci->platdata = dev_get_platdata(dev);
 	ci->imx28_write_fix = !!(ci->platdata->flags &
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index 58c8485a0715..923379972707 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -295,7 +295,8 @@ static int ci_role_show(struct seq_file *s, void *data)
 {
 	struct ci_hdrc *ci = s->private;
 
-	seq_printf(s, "%s\n", ci_role(ci)->name);
+	if (ci->role != CI_ROLE_END)
+		seq_printf(s, "%s\n", ci_role(ci)->name);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c
index 03b6743461d1..0cf149edddd8 100644
--- a/drivers/usb/chipidea/otg.c
+++ b/drivers/usb/chipidea/otg.c
@@ -44,12 +44,15 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask)
 		else
 			val &= ~OTGSC_BSVIS;
 
-		cable->changed = false;
-
 		if (cable->state)
 			val |= OTGSC_BSV;
 		else
 			val &= ~OTGSC_BSV;
+
+		if (cable->enabled)
+			val |= OTGSC_BSVIE;
+		else
+			val &= ~OTGSC_BSVIE;
 	}
 
 	cable = &ci->platdata->id_extcon;
@@ -59,15 +62,18 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask)
 		else
 			val &= ~OTGSC_IDIS;
 
-		cable->changed = false;
-
 		if (cable->state)
 			val |= OTGSC_ID;
 		else
 			val &= ~OTGSC_ID;
+
+		if (cable->enabled)
+			val |= OTGSC_IDIE;
+		else
+			val &= ~OTGSC_IDIE;
 	}
 
-	return val;
+	return val & mask;
 }
 
 /**
@@ -77,6 +83,36 @@ u32 hw_read_otgsc(struct ci_hdrc *ci, u32 mask)
  */
 void hw_write_otgsc(struct ci_hdrc *ci, u32 mask, u32 data)
 {
+	struct ci_hdrc_cable *cable;
+
+	cable = &ci->platdata->vbus_extcon;
+	if (!IS_ERR(cable->edev)) {
+		if (data & mask & OTGSC_BSVIS)
+			cable->changed = false;
+
+		/* Don't enable vbus interrupt if using external notifier */
+		if (data & mask & OTGSC_BSVIE) {
+			cable->enabled = true;
+			data &= ~OTGSC_BSVIE;
+		} else if (mask & OTGSC_BSVIE) {
+			cable->enabled = false;
+		}
+	}
+
+	cable = &ci->platdata->id_extcon;
+	if (!IS_ERR(cable->edev)) {
+		if (data & mask & OTGSC_IDIS)
+			cable->changed = false;
+
+		/* Don't enable id interrupt if using external notifier */
+		if (data & mask & OTGSC_IDIE) {
+			cable->enabled = true;
+			data &= ~OTGSC_IDIE;
+		} else if (mask & OTGSC_IDIE) {
+			cable->enabled = false;
+		}
+	}
+
 	hw_write(ci, OP_OTGSC, mask | OTGSC_INT_STATUS_BITS, data);
 }
 
@@ -104,7 +140,31 @@ void ci_handle_vbus_change(struct ci_hdrc *ci)
 		usb_gadget_vbus_disconnect(&ci->gadget);
 }
 
-#define CI_VBUS_STABLE_TIMEOUT_MS 5000
+/**
+ * When we switch to device mode, the vbus value should be lower
+ * than OTGSC_BSV before connecting to host.
+ *
+ * @ci: the controller
+ *
+ * This function returns an error code if timeout
+ */
+static int hw_wait_vbus_lower_bsv(struct ci_hdrc *ci)
+{
+	unsigned long elapse = jiffies + msecs_to_jiffies(5000);
+	u32 mask = OTGSC_BSV;
+
+	while (hw_read_otgsc(ci, mask)) {
+		if (time_after(jiffies, elapse)) {
+			dev_err(ci->dev, "timeout waiting for %08x in OTGSC\n",
+					mask);
+			return -ETIMEDOUT;
+		}
+		msleep(20);
+	}
+
+	return 0;
+}
+
 static void ci_handle_id_switch(struct ci_hdrc *ci)
 {
 	enum ci_role role = ci_otg_role(ci);
@@ -116,9 +176,11 @@ static void ci_handle_id_switch(struct ci_hdrc *ci)
 		ci_role_stop(ci);
 
 		if (role == CI_ROLE_GADGET)
-			/* wait vbus lower than OTGSC_BSV */
-			hw_wait_reg(ci, OP_OTGSC, OTGSC_BSV, 0,
-					CI_VBUS_STABLE_TIMEOUT_MS);
+			/*
+			 * wait vbus lower than OTGSC_BSV before connecting
+			 * to host
+			 */
+			hw_wait_vbus_lower_bsv(ci);
 
 		ci_role_start(ci, role);
 	}
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 391a1225b0ba..aff086ca97e4 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -939,6 +939,15 @@ static int isr_setup_status_phase(struct ci_hdrc *ci)
 	int retval;
 	struct ci_hw_ep *hwep;
 
+	/*
+	 * Unexpected USB controller behavior, caused by bad signal integrity
+	 * or ground reference problems, can lead to isr_setup_status_phase
+	 * being called with ci->status equal to NULL.
+	 * If this situation occurs, you should review your USB hardware design.
+	 */
+	if (WARN_ON_ONCE(!ci->status))
+		return -EPIPE;
+
 	hwep = (ci->ep0_dir == TX) ? ci->ep0out : ci->ep0in;
 	ci->status->context = ci;
 	ci->status->complete = isr_setup_status_complete;
@@ -1585,8 +1594,11 @@ static int ci_udc_pullup(struct usb_gadget *_gadget, int is_on)
 {
 	struct ci_hdrc *ci = container_of(_gadget, struct ci_hdrc, gadget);
 
-	/* Data+ pullup controlled by OTG state machine in OTG fsm mode */
-	if (ci_otg_is_fsm_mode(ci))
+	/*
+	 * Data+ pullup controlled by OTG state machine in OTG fsm mode;
+	 * and don't touch Data+ in host mode for dual role config.
+	 */
+	if (ci_otg_is_fsm_mode(ci) || ci->role == CI_ROLE_HOST)
 		return 0;
 
 	pm_runtime_get_sync(&ci->gadget.dev);
@@ -1872,8 +1884,6 @@ static int udc_start(struct ci_hdrc *ci)
 	struct usb_otg_caps *otg_caps = &ci->platdata->ci_otg_caps;
 	int retval = 0;
 
-	spin_lock_init(&ci->lock);
-
 	ci->gadget.ops          = &usb_gadget_ops;
 	ci->gadget.speed        = USB_SPEED_UNKNOWN;
 	ci->gadget.max_speed    = USB_SPEED_HIGH;
@@ -1972,6 +1982,7 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci)
 int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 {
 	struct ci_role_driver *rdrv;
+	int ret;
 
 	if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC))
 		return -ENXIO;
@@ -1984,7 +1995,10 @@ int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 	rdrv->stop	= udc_id_switch_for_host;
 	rdrv->irq	= udc_irq;
 	rdrv->name	= "gadget";
-	ci->roles[CI_ROLE_GADGET] = rdrv;
 
-	return udc_start(ci);
+	ret = udc_start(ci);
+	if (!ret)
+		ci->roles[CI_ROLE_GADGET] = rdrv;
+
+	return ret;
 }
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index fa4e23930614..df96f5f88c15 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -311,6 +311,12 @@ static void acm_ctrl_irq(struct urb *urb)
 		break;
 
 	case USB_CDC_NOTIFY_SERIAL_STATE:
+		if (le16_to_cpu(dr->wLength) != 2) {
+			dev_dbg(&acm->control->dev,
+				"%s - malformed serial state\n", __func__);
+			break;
+		}
+
 		newctrl = get_unaligned_le16(data);
 
 		if (!acm->clocal && (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
@@ -347,11 +353,10 @@ static void acm_ctrl_irq(struct urb *urb)
 
 	default:
 		dev_dbg(&acm->control->dev,
-			"%s - unknown notification %d received: index %d "
-			"len %d data0 %d data1 %d\n",
+			"%s - unknown notification %d received: index %d len %d\n",
 			__func__,
-			dr->bNotificationType, dr->wIndex,
-			dr->wLength, data[0], data[1]);
+			dr->bNotificationType, dr->wIndex, dr->wLength);
+
 		break;
 	}
 exit:
@@ -877,8 +882,6 @@ static int wait_serial_change(struct acm *acm, unsigned long arg)
 	DECLARE_WAITQUEUE(wait, current);
 	struct async_icount old, new;
 
-	if (arg & (TIOCM_DSR | TIOCM_RI | TIOCM_CD ))
-		return -EINVAL;
 	do {
 		spin_lock_irq(&acm->read_lock);
 		old = acm->oldcount;
@@ -1114,6 +1117,9 @@ static int acm_probe(struct usb_interface *intf,
 	if (quirks == NO_UNION_NORMAL) {
 		data_interface = usb_ifnum_to_if(usb_dev, 1);
 		control_interface = usb_ifnum_to_if(usb_dev, 0);
+		/* we would crash */
+		if (!data_interface || !control_interface)
+			return -ENODEV;
 		goto skip_normal_probe;
 	}
 
@@ -1333,7 +1339,6 @@ made_compressed_probe:
 	spin_lock_init(&acm->write_lock);
 	spin_lock_init(&acm->read_lock);
 	mutex_init(&acm->mutex);
-	acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress);
 	acm->is_int_ep = usb_endpoint_xfer_int(epread);
 	if (acm->is_int_ep)
 		acm->bInterval = epread->bInterval;
@@ -1373,14 +1378,14 @@ made_compressed_probe:
 		urb->transfer_dma = rb->dma;
 		if (acm->is_int_ep) {
 			usb_fill_int_urb(urb, acm->dev,
-					 acm->rx_endpoint,
+					 usb_rcvintpipe(usb_dev, epread->bEndpointAddress),
 					 rb->base,
 					 acm->readsize,
 					 acm_read_bulk_callback, rb,
 					 acm->bInterval);
 		} else {
 			usb_fill_bulk_urb(urb, acm->dev,
-					  acm->rx_endpoint,
+					  usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress),
 					  rb->base,
 					  acm->readsize,
 					  acm_read_bulk_callback, rb);
@@ -1708,6 +1713,7 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x20df, 0x0001), /* Simtec Electronics Entropy Key */
 	.driver_info = QUIRK_CONTROL_LINE_STATE, },
 	{ USB_DEVICE(0x2184, 0x001c) },	/* GW Instek AFG-2225 */
+	{ USB_DEVICE(0x2184, 0x0036) },	/* GW Instek AFG-125 */
 	{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
 	},
 	/* Motorola H24 HSPA module: */
@@ -1753,6 +1759,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x1576, 0x03b1), /* Maretron USB100 */
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
+	{ USB_DEVICE(0xfff0, 0x0100), /* DATECS FP-2000 */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 
 	{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
 	.driver_info = CLEAR_HALT_CONDITIONS,
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ccfaba9ab4e4..b30ac5fcde68 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -95,7 +95,6 @@ struct acm {
 	struct urb *read_urbs[ACM_NR];
 	struct acm_rb read_buffers[ACM_NR];
 	int rx_buflimit;
-	int rx_endpoint;
 	spinlock_t read_lock;
 	int write_used;					/* number of non-empty write buffers */
 	int transmitting;
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 7a11a8263171..24337ac3323f 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -121,6 +121,7 @@ static void usbtmc_delete(struct kref *kref)
 	struct usbtmc_device_data *data = to_usbtmc_data(kref);
 
 	usb_put_dev(data->usb_dev);
+	kfree(data);
 }
 
 static int usbtmc_open(struct inode *inode, struct file *filp)
@@ -1104,7 +1105,7 @@ static int usbtmc_probe(struct usb_interface *intf,
 
 	dev_dbg(&intf->dev, "%s called\n", __func__);
 
-	data = devm_kzalloc(&intf->dev, sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -1162,6 +1163,12 @@ static int usbtmc_probe(struct usb_interface *intf,
 		}
 	}
 
+	if (!data->bulk_out || !data->bulk_in) {
+		dev_err(&intf->dev, "bulk endpoints not found\n");
+		retcode = -ENODEV;
+		goto err_put;
+	}
+
 	retcode = get_capabilities(data);
 	if (retcode)
 		dev_err(&intf->dev, "can't read capabilities\n");
@@ -1185,6 +1192,7 @@ static int usbtmc_probe(struct usb_interface *intf,
 error_register:
 	sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp);
 	sysfs_remove_group(&intf->dev.kobj, &data_attr_grp);
+err_put:
 	kref_put(&data->kref, usbtmc_delete);
 	return retcode;
 }
diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c
index 673d53038ed2..a00bfb93acc3 100644
--- a/drivers/usb/common/common.c
+++ b/drivers/usb/common/common.c
@@ -50,6 +50,7 @@ static const char *const speed_names[] = {
 	[USB_SPEED_HIGH] = "high-speed",
 	[USB_SPEED_WIRELESS] = "wireless",
 	[USB_SPEED_SUPER] = "super-speed",
+	[USB_SPEED_SUPER_PLUS] = "super-speed-plus",
 };
 
 const char *usb_speed_string(enum usb_device_speed speed)
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 61d538aa2346..4f4f06a5889f 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -21,6 +21,7 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
@@ -365,3 +366,4 @@ int otg_statemachine(struct otg_fsm *fsm)
 	return state_changed;
 }
 EXPORT_SYMBOL_GPL(otg_statemachine);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 5050760f5e17..325cbc9c35d8 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -142,6 +142,31 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	}
 }
 
+static const unsigned short low_speed_maxpacket_maxes[4] = {
+	[USB_ENDPOINT_XFER_CONTROL] = 8,
+	[USB_ENDPOINT_XFER_ISOC] = 0,
+	[USB_ENDPOINT_XFER_BULK] = 0,
+	[USB_ENDPOINT_XFER_INT] = 8,
+};
+static const unsigned short full_speed_maxpacket_maxes[4] = {
+	[USB_ENDPOINT_XFER_CONTROL] = 64,
+	[USB_ENDPOINT_XFER_ISOC] = 1023,
+	[USB_ENDPOINT_XFER_BULK] = 64,
+	[USB_ENDPOINT_XFER_INT] = 64,
+};
+static const unsigned short high_speed_maxpacket_maxes[4] = {
+	[USB_ENDPOINT_XFER_CONTROL] = 64,
+	[USB_ENDPOINT_XFER_ISOC] = 1024,
+	[USB_ENDPOINT_XFER_BULK] = 512,
+	[USB_ENDPOINT_XFER_INT] = 1024,
+};
+static const unsigned short super_speed_maxpacket_maxes[4] = {
+	[USB_ENDPOINT_XFER_CONTROL] = 512,
+	[USB_ENDPOINT_XFER_ISOC] = 1024,
+	[USB_ENDPOINT_XFER_BULK] = 1024,
+	[USB_ENDPOINT_XFER_INT] = 1024,
+};
+
 static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
     int asnum, struct usb_host_interface *ifp, int num_ep,
     unsigned char *buffer, int size)
@@ -150,6 +175,8 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 	struct usb_endpoint_descriptor *d;
 	struct usb_host_endpoint *endpoint;
 	int n, i, j, retval;
+	unsigned int maxp;
+	const unsigned short *maxpacket_maxes;
 
 	d = (struct usb_endpoint_descriptor *) buffer;
 	buffer += d->bLength;
@@ -178,32 +205,57 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 	if (ifp->desc.bNumEndpoints >= num_ep)
 		goto skip_to_next_endpoint_or_interface_descriptor;
 
+	/* Check for duplicate endpoint addresses */
+	for (i = 0; i < ifp->desc.bNumEndpoints; ++i) {
+		if (ifp->endpoint[i].desc.bEndpointAddress ==
+		    d->bEndpointAddress) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n",
+			    cfgno, inum, asnum, d->bEndpointAddress);
+			goto skip_to_next_endpoint_or_interface_descriptor;
+		}
+	}
+
 	endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
 	++ifp->desc.bNumEndpoints;
 
 	memcpy(&endpoint->desc, d, n);
 	INIT_LIST_HEAD(&endpoint->urb_list);
 
-	/* Fix up bInterval values outside the legal range. Use 32 ms if no
-	 * proper value can be guessed. */
+	/*
+	 * Fix up bInterval values outside the legal range.
+	 * Use 10 or 8 ms if no proper value can be guessed.
+	 */
 	i = 0;		/* i = min, j = max, n = default */
 	j = 255;
 	if (usb_endpoint_xfer_int(d)) {
 		i = 1;
 		switch (to_usb_device(ddev)->speed) {
+		case USB_SPEED_SUPER_PLUS:
 		case USB_SPEED_SUPER:
 		case USB_SPEED_HIGH:
-			/* Many device manufacturers are using full-speed
+			/*
+			 * Many device manufacturers are using full-speed
 			 * bInterval values in high-speed interrupt endpoint
-			 * descriptors. Try to fix those and fall back to a
-			 * 32 ms default value otherwise. */
+			 * descriptors. Try to fix those and fall back to an
+			 * 8-ms default value otherwise.
+			 */
 			n = fls(d->bInterval*8);
 			if (n == 0)
-				n = 9;	/* 32 ms = 2^(9-1) uframes */
+				n = 7;	/* 8 ms = 2^(7-1) uframes */
 			j = 16;
 
 			/*
 			 * Adjust bInterval for quirked devices.
+			 */
+			/*
+			 * This quirk fixes bIntervals reported in ms.
+			 */
+			if (to_usb_device(ddev)->quirks &
+				USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) {
+				n = clamp(fls(d->bInterval) + 3, i, j);
+				i = j = n;
+			}
+			/*
 			 * This quirk fixes bIntervals reported in
 			 * linear microframes.
 			 */
@@ -214,10 +266,12 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 			}
 			break;
 		default:		/* USB_SPEED_FULL or _LOW */
-			/* For low-speed, 10 ms is the official minimum.
+			/*
+			 * For low-speed, 10 ms is the official minimum.
 			 * But some "overclocked" devices might want faster
-			 * polling so we'll allow it. */
-			n = 32;
+			 * polling so we'll allow it.
+			 */
+			n = 10;
 			break;
 		}
 	} else if (usb_endpoint_xfer_isoc(d)) {
@@ -225,10 +279,10 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 		j = 16;
 		switch (to_usb_device(ddev)->speed) {
 		case USB_SPEED_HIGH:
-			n = 9;		/* 32 ms = 2^(9-1) uframes */
+			n = 7;		/* 8 ms = 2^(7-1) uframes */
 			break;
 		default:		/* USB_SPEED_FULL */
-			n = 6;		/* 32 ms = 2^(6-1) frames */
+			n = 4;		/* 8 ms = 2^(4-1) frames */
 			break;
 		}
 	}
@@ -256,6 +310,42 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 			endpoint->desc.wMaxPacketSize = cpu_to_le16(8);
 	}
 
+	/* Validate the wMaxPacketSize field */
+	maxp = usb_endpoint_maxp(&endpoint->desc);
+
+	/* Find the highest legal maxpacket size for this endpoint */
+	i = 0;		/* additional transactions per microframe */
+	switch (to_usb_device(ddev)->speed) {
+	case USB_SPEED_LOW:
+		maxpacket_maxes = low_speed_maxpacket_maxes;
+		break;
+	case USB_SPEED_FULL:
+		maxpacket_maxes = full_speed_maxpacket_maxes;
+		break;
+	case USB_SPEED_HIGH:
+		/* Bits 12..11 are allowed only for HS periodic endpoints */
+		if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) {
+			i = maxp & (BIT(12) | BIT(11));
+			maxp &= ~i;
+		}
+		/* fallthrough */
+	default:
+		maxpacket_maxes = high_speed_maxpacket_maxes;
+		break;
+	case USB_SPEED_SUPER:
+	case USB_SPEED_SUPER_PLUS:
+		maxpacket_maxes = super_speed_maxpacket_maxes;
+		break;
+	}
+	j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)];
+
+	if (maxp > j) {
+		dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n",
+		    cfgno, inum, asnum, d->bEndpointAddress, maxp, j);
+		maxp = j;
+		endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp);
+	}
+
 	/*
 	 * Some buggy high speed devices have bulk endpoints using
 	 * maxpacket sizes other than 512.  High speed HCDs may not
@@ -263,9 +353,6 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 	 */
 	if (to_usb_device(ddev)->speed == USB_SPEED_HIGH
 			&& usb_endpoint_xfer_bulk(d)) {
-		unsigned maxp;
-
-		maxp = usb_endpoint_maxp(&endpoint->desc) & 0x07ff;
 		if (maxp != 512)
 			dev_warn(ddev, "config %d interface %d altsetting %d "
 				"bulk endpoint 0x%X has invalid maxpacket %d\n",
@@ -274,7 +361,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 	}
 
 	/* Parse a possible SuperSpeed endpoint companion descriptor */
-	if (to_usb_device(ddev)->speed == USB_SPEED_SUPER)
+	if (to_usb_device(ddev)->speed >= USB_SPEED_SUPER)
 		usb_parse_ss_endpoint_companion(ddev, cfgno,
 				inum, asnum, endpoint, buffer, size);
 
diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c
index 2a3bbdf7eb94..332ed277a06c 100644
--- a/drivers/usb/core/devices.c
+++ b/drivers/usb/core/devices.c
@@ -221,7 +221,7 @@ static char *usb_dump_endpoint_descriptor(int speed, char *start, char *end,
 		break;
 	case USB_ENDPOINT_XFER_INT:
 		type = "Int.";
-		if (speed == USB_SPEED_HIGH || speed == USB_SPEED_SUPER)
+		if (speed == USB_SPEED_HIGH || speed >= USB_SPEED_SUPER)
 			interval = 1 << (desc->bInterval - 1);
 		else
 			interval = desc->bInterval;
@@ -230,7 +230,7 @@ static char *usb_dump_endpoint_descriptor(int speed, char *start, char *end,
 		return start;
 	}
 	interval *= (speed == USB_SPEED_HIGH ||
-		     speed == USB_SPEED_SUPER) ? 125 : 1000;
+		     speed >= USB_SPEED_SUPER) ? 125 : 1000;
 	if (interval % 1000)
 		unit = 'u';
 	else {
@@ -322,7 +322,7 @@ static char *usb_dump_config_descriptor(char *start, char *end,
 
 	if (start > end)
 		return start;
-	if (speed == USB_SPEED_SUPER)
+	if (speed >= USB_SPEED_SUPER)
 		mul = 8;
 	else
 		mul = 2;
@@ -534,6 +534,8 @@ static ssize_t usb_device_dump(char __user **buffer, size_t *nbytes,
 		speed = "480"; break;
 	case USB_SPEED_SUPER:
 		speed = "5000"; break;
+	case USB_SPEED_SUPER_PLUS:
+		speed = "10000"; break;
 	default:
 		speed = "??";
 	}
@@ -553,7 +555,7 @@ static ssize_t usb_device_dump(char __user **buffer, size_t *nbytes,
 
 		/* super/high speed reserves 80%, full/low reserves 90% */
 		if (usbdev->speed == USB_SPEED_HIGH ||
-		    usbdev->speed == USB_SPEED_SUPER)
+		    usbdev->speed >= USB_SPEED_SUPER)
 			max = 800;
 		else
 			max = FRAME_TIME_MAX_USECS_ALLOC;
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 38ae877c46e3..873ba02d59e6 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -373,11 +373,11 @@ static void snoop_urb(struct usb_device *udev,
 
 	if (userurb) {		/* Async */
 		if (when == SUBMIT)
-			dev_info(&udev->dev, "userurb %p, ep%d %s-%s, "
+			dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
 					"length %u\n",
 					userurb, ep, t, d, length);
 		else
-			dev_info(&udev->dev, "userurb %p, ep%d %s-%s, "
+			dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
 					"actual_length %u status %d\n",
 					userurb, ep, t, d, length,
 					timeout_or_status);
@@ -519,6 +519,8 @@ static void async_completed(struct urb *urb)
 	if (as->status < 0 && as->bulk_addr && as->status != -ECONNRESET &&
 			as->status != -ENOENT)
 		cancel_bulk_urbs(ps, as->bulk_addr);
+
+	wake_up(&ps->wait);
 	spin_unlock(&ps->lock);
 
 	if (signr) {
@@ -526,8 +528,6 @@ static void async_completed(struct urb *urb)
 		put_pid(pid);
 		put_cred(cred);
 	}
-
-	wake_up(&ps->wait);
 }
 
 static void destroy_async(struct usb_dev_state *ps, struct list_head *list)
@@ -1203,10 +1203,11 @@ static int proc_getdriver(struct usb_dev_state *ps, void __user *arg)
 
 static int proc_connectinfo(struct usb_dev_state *ps, void __user *arg)
 {
-	struct usbdevfs_connectinfo ci = {
-		.devnum = ps->dev->devnum,
-		.slow = ps->dev->speed == USB_SPEED_LOW
-	};
+	struct usbdevfs_connectinfo ci;
+
+	memset(&ci, 0, sizeof(ci));
+	ci.devnum = ps->dev->devnum;
+	ci.slow = ps->dev->speed == USB_SPEED_LOW;
 
 	if (copy_to_user(arg, &ci, sizeof(ci)))
 		return -EFAULT;
@@ -1529,11 +1530,17 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb
 	as->urb->start_frame = uurb->start_frame;
 	as->urb->number_of_packets = number_of_packets;
 	as->urb->stream_id = stream_id;
-	if (uurb->type == USBDEVFS_URB_TYPE_ISO ||
-			ps->dev->speed == USB_SPEED_HIGH)
-		as->urb->interval = 1 << min(15, ep->desc.bInterval - 1);
-	else
-		as->urb->interval = ep->desc.bInterval;
+
+	if (ep->desc.bInterval) {
+		if (uurb->type == USBDEVFS_URB_TYPE_ISO ||
+				ps->dev->speed == USB_SPEED_HIGH ||
+				ps->dev->speed >= USB_SPEED_SUPER)
+			as->urb->interval = 1 <<
+					min(15, ep->desc.bInterval - 1);
+		else
+			as->urb->interval = ep->desc.bInterval;
+	}
+
 	as->urb->context = as;
 	as->urb->complete = async_completed;
 	for (totlen = u = 0; u < number_of_packets; u++) {
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 56593a9a8726..0bb380a9fcf7 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -284,7 +284,7 @@ static int usb_probe_interface(struct device *dev)
 	struct usb_device *udev = interface_to_usbdev(intf);
 	const struct usb_device_id *id;
 	int error = -ENODEV;
-	int lpm_disable_error;
+	int lpm_disable_error = -ENODEV;
 
 	dev_dbg(dev, "%s\n", __func__);
 
@@ -336,12 +336,14 @@ static int usb_probe_interface(struct device *dev)
 	 * setting during probe, that should also be fine.  usb_set_interface()
 	 * will attempt to disable LPM, and fail if it can't disable it.
 	 */
-	lpm_disable_error = usb_unlocked_disable_lpm(udev);
-	if (lpm_disable_error && driver->disable_hub_initiated_lpm) {
-		dev_err(&intf->dev, "%s Failed to disable LPM for driver %s\n.",
-				__func__, driver->name);
-		error = lpm_disable_error;
-		goto err;
+	if (driver->disable_hub_initiated_lpm) {
+		lpm_disable_error = usb_unlocked_disable_lpm(udev);
+		if (lpm_disable_error) {
+			dev_err(&intf->dev, "%s Failed to disable LPM for driver %s\n.",
+					__func__, driver->name);
+			error = lpm_disable_error;
+			goto err;
+		}
 	}
 
 	/* Carry out a deferred switch to altsetting 0 */
@@ -391,7 +393,8 @@ static int usb_unbind_interface(struct device *dev)
 	struct usb_interface *intf = to_usb_interface(dev);
 	struct usb_host_endpoint *ep, **eps = NULL;
 	struct usb_device *udev;
-	int i, j, error, r, lpm_disable_error;
+	int i, j, error, r;
+	int lpm_disable_error = -ENODEV;
 
 	intf->condition = USB_INTERFACE_UNBINDING;
 
@@ -399,12 +402,13 @@ static int usb_unbind_interface(struct device *dev)
 	udev = interface_to_usbdev(intf);
 	error = usb_autoresume_device(udev);
 
-	/* Hub-initiated LPM policy may change, so attempt to disable LPM until
+	/* If hub-initiated LPM policy may change, attempt to disable LPM until
 	 * the driver is unbound.  If LPM isn't disabled, that's fine because it
 	 * wouldn't be enabled unless all the bound interfaces supported
 	 * hub-initiated LPM.
 	 */
-	lpm_disable_error = usb_unlocked_disable_lpm(udev);
+	if (driver->disable_hub_initiated_lpm)
+		lpm_disable_error = usb_unlocked_disable_lpm(udev);
 
 	/*
 	 * Terminate all URBs for this interface unless the driver
@@ -502,11 +506,15 @@ static int usb_unbind_interface(struct device *dev)
 int usb_driver_claim_interface(struct usb_driver *driver,
 				struct usb_interface *iface, void *priv)
 {
-	struct device *dev = &iface->dev;
+	struct device *dev;
 	struct usb_device *udev;
 	int retval = 0;
-	int lpm_disable_error;
+	int lpm_disable_error = -ENODEV;
 
+	if (!iface)
+		return -ENODEV;
+
+	dev = &iface->dev;
 	if (dev->driver)
 		return -EBUSY;
 
@@ -522,12 +530,14 @@ int usb_driver_claim_interface(struct usb_driver *driver,
 
 	iface->condition = USB_INTERFACE_BOUND;
 
-	/* Disable LPM until this driver is bound. */
-	lpm_disable_error = usb_unlocked_disable_lpm(udev);
-	if (lpm_disable_error && driver->disable_hub_initiated_lpm) {
-		dev_err(&iface->dev, "%s Failed to disable LPM for driver %s\n.",
-				__func__, driver->name);
-		return -ENOMEM;
+	/* See the comment about disabling LPM in usb_probe_interface(). */
+	if (driver->disable_hub_initiated_lpm) {
+		lpm_disable_error = usb_unlocked_disable_lpm(udev);
+		if (lpm_disable_error) {
+			dev_err(&iface->dev, "%s Failed to disable LPM for driver %s\n.",
+					__func__, driver->name);
+			return -ENOMEM;
+		}
 	}
 
 	/* Claimed interfaces are initially inactive (suspended) and
@@ -1318,6 +1328,24 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 		 */
 		if (udev->parent && !PMSG_IS_AUTO(msg))
 			status = 0;
+
+		/*
+		 * If the device is inaccessible, don't try to resume
+		 * suspended interfaces and just return the error.
+		 */
+		if (status && status != -EBUSY) {
+			int err;
+			u16 devstat;
+
+			err = usb_get_status(udev, USB_RECIP_DEVICE, 0,
+					     &devstat);
+			if (err) {
+				dev_err(&udev->dev,
+					"Failed to suspend device, error %d\n",
+					status);
+				goto done;
+			}
+		}
 	}
 
 	/* If the suspend failed, resume interfaces that did get suspended */
@@ -1750,6 +1778,9 @@ static int autosuspend_check(struct usb_device *udev)
 	int			w, i;
 	struct usb_interface	*intf;
 
+	if (udev->state == USB_STATE_NOTATTACHED)
+		return -ENODEV;
+
 	/* Fail if autosuspend is disabled, or any interfaces are in use, or
 	 * any interface drivers require remote wakeup but it isn't available.
 	 */
diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c
index ea337a718cc1..b3de806085f0 100644
--- a/drivers/usb/core/file.c
+++ b/drivers/usb/core/file.c
@@ -26,6 +26,7 @@
 #define MAX_USB_MINORS	256
 static const struct file_operations *usb_minors[MAX_USB_MINORS];
 static DECLARE_RWSEM(minor_rwsem);
+static DEFINE_MUTEX(init_usb_class_mutex);
 
 static int usb_open(struct inode *inode, struct file *file)
 {
@@ -108,8 +109,9 @@ static void release_usb_class(struct kref *kref)
 
 static void destroy_usb_class(void)
 {
-	if (usb_class)
-		kref_put(&usb_class->kref, release_usb_class);
+	mutex_lock(&init_usb_class_mutex);
+	kref_put(&usb_class->kref, release_usb_class);
+	mutex_unlock(&init_usb_class_mutex);
 }
 
 int usb_major_init(void)
@@ -171,7 +173,10 @@ int usb_register_dev(struct usb_interface *intf,
 	if (intf->minor >= 0)
 		return -EADDRINUSE;
 
+	mutex_lock(&init_usb_class_mutex);
 	retval = init_usb_class();
+	mutex_unlock(&init_usb_class_mutex);
+
 	if (retval)
 		return retval;
 
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index 9eb1cff28bd4..40378487e023 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -74,6 +74,15 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd,
 		if (companion->bus != pdev->bus ||
 				PCI_SLOT(companion->devfn) != slot)
 			continue;
+
+		/*
+		 * Companion device should be either UHCI,OHCI or EHCI host
+		 * controller, otherwise skip.
+		 */
+		if (companion->class != CL_UHCI && companion->class != CL_OHCI &&
+				companion->class != CL_EHCI)
+			continue;
+
 		companion_hcd = pci_get_drvdata(companion);
 		if (!companion_hcd || !companion_hcd->self.root_hub)
 			continue;
@@ -197,7 +206,7 @@ int usb_hcd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	 * The xHCI driver has its own irq management
 	 * make sure irq setup is not touched for xhci in generic hcd code
 	 */
-	if ((driver->flags & HCD_MASK) != HCD_USB3) {
+	if ((driver->flags & HCD_MASK) < HCD_USB3) {
 		if (!dev->irq) {
 			dev_err(&dev->dev,
 			"Found HC with no IRQ. Check BIOS/PCI %s setup!\n",
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 1c102d60cd9f..5c0952995280 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -499,8 +499,10 @@ static int rh_call_control (struct usb_hcd *hcd, struct urb *urb)
 	 */
 	tbuf_size =  max_t(u16, sizeof(struct usb_hub_descriptor), wLength);
 	tbuf = kzalloc(tbuf_size, GFP_KERNEL);
-	if (!tbuf)
-		return -ENOMEM;
+	if (!tbuf) {
+		status = -ENOMEM;
+		goto err_alloc;
+	}
 
 	bufp = tbuf;
 
@@ -705,6 +707,7 @@ error:
 	}
 
 	kfree(tbuf);
+ err_alloc:
 
 	/* any errors get returned through the urb completion */
 	spin_lock_irq(&hcd_root_hub_lock);
@@ -966,7 +969,7 @@ static void usb_bus_init (struct usb_bus *bus)
 	bus->bandwidth_allocated = 0;
 	bus->bandwidth_int_reqs  = 0;
 	bus->bandwidth_isoc_reqs = 0;
-	mutex_init(&bus->usb_address0_mutex);
+	mutex_init(&bus->devnum_next_mutex);
 
 	INIT_LIST_HEAD (&bus->bus_list);
 }
@@ -1078,7 +1081,7 @@ static int register_root_hub(struct usb_hcd *hcd)
 		retval = usb_get_bos_descriptor(usb_dev);
 		if (!retval) {
 			usb_dev->lpm_capable = usb_device_supports_lpm(usb_dev);
-		} else if (usb_dev->speed == USB_SPEED_SUPER) {
+		} else if (usb_dev->speed >= USB_SPEED_SUPER) {
 			mutex_unlock(&usb_bus_list_lock);
 			dev_dbg(parent_dev, "can't read %s bos descriptor %d\n",
 					dev_name(&usb_dev->dev), retval);
@@ -1693,7 +1696,7 @@ int usb_hcd_unlink_urb (struct urb *urb, int status)
 		if (retval == 0)
 			retval = -EINPROGRESS;
 		else if (retval != -EIDRM && retval != -EBUSY)
-			dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n",
+			dev_dbg(&udev->dev, "hcd_unlink_urb %pK fail %d\n",
 					urb, retval);
 		usb_put_dev(udev);
 	}
@@ -1848,7 +1851,7 @@ void usb_hcd_flush_endpoint(struct usb_device *udev,
 	/* No more submits can occur */
 	spin_lock_irq(&hcd_urb_list_lock);
 rescan:
-	list_for_each_entry (urb, &ep->urb_list, urb_list) {
+	list_for_each_entry_reverse(urb, &ep->urb_list, urb_list) {
 		int	is_in;
 
 		if (urb->unlinked)
@@ -1860,7 +1863,7 @@ rescan:
 		/* kick hcd */
 		unlink1(hcd, urb, -ESHUTDOWN);
 		dev_dbg (hcd->self.controller,
-			"shutdown urb %p ep%d%s%s\n",
+			"shutdown urb %pK ep%d%s%s\n",
 			urb, usb_endpoint_num(&ep->desc),
 			is_in ? "in" : "out",
 			({	char *s;
@@ -2112,7 +2115,7 @@ int usb_alloc_streams(struct usb_interface *interface,
 	hcd = bus_to_hcd(dev->bus);
 	if (!hcd->driver->alloc_streams || !hcd->driver->free_streams)
 		return -EINVAL;
-	if (dev->speed != USB_SPEED_SUPER)
+	if (dev->speed < USB_SPEED_SUPER)
 		return -EINVAL;
 	if (dev->state < USB_STATE_CONFIGURED)
 		return -ENODEV;
@@ -2160,7 +2163,7 @@ int usb_free_streams(struct usb_interface *interface,
 
 	dev = interface_to_usbdev(interface);
 	hcd = bus_to_hcd(dev->bus);
-	if (dev->speed != USB_SPEED_SUPER)
+	if (dev->speed < USB_SPEED_SUPER)
 		return -EINVAL;
 
 	/* Double-free is not allowed */
@@ -2445,6 +2448,8 @@ void usb_hc_died (struct usb_hcd *hcd)
 	}
 	if (usb_hcd_is_primary_hcd(hcd) && hcd->shared_hcd) {
 		hcd = hcd->shared_hcd;
+		clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
+		set_bit(HCD_FLAG_DEAD, &hcd->flags);
 		if (hcd->rh_registered) {
 			clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 
@@ -2497,9 +2502,18 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
 		return NULL;
 	}
 	if (primary_hcd == NULL) {
+		hcd->address0_mutex = kmalloc(sizeof(*hcd->address0_mutex),
+				GFP_KERNEL);
+		if (!hcd->address0_mutex) {
+			kfree(hcd);
+			dev_dbg(dev, "hcd address0 mutex alloc failed\n");
+			return NULL;
+		}
+		mutex_init(hcd->address0_mutex);
 		hcd->bandwidth_mutex = kmalloc(sizeof(*hcd->bandwidth_mutex),
 				GFP_KERNEL);
 		if (!hcd->bandwidth_mutex) {
+			kfree(hcd->address0_mutex);
 			kfree(hcd);
 			dev_dbg(dev, "hcd bandwidth mutex alloc failed\n");
 			return NULL;
@@ -2508,6 +2522,7 @@ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver,
 		dev_set_drvdata(dev, hcd);
 	} else {
 		mutex_lock(&usb_port_peer_mutex);
+		hcd->address0_mutex = primary_hcd->address0_mutex;
 		hcd->bandwidth_mutex = primary_hcd->bandwidth_mutex;
 		hcd->primary_hcd = primary_hcd;
 		primary_hcd->primary_hcd = primary_hcd;
@@ -2564,24 +2579,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd);
  * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
  * deallocated.
  *
- * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
- * freed.  When hcd_release() is called for either hcd in a peer set
- * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to
- * block new peering attempts
+ * Make sure to deallocate the bandwidth_mutex only when the last HCD is
+ * freed.  When hcd_release() is called for either hcd in a peer set,
+ * invalidate the peer's ->shared_hcd and ->primary_hcd pointers.
  */
 static void hcd_release(struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
 	mutex_lock(&usb_port_peer_mutex);
-	if (usb_hcd_is_primary_hcd(hcd))
-		kfree(hcd->bandwidth_mutex);
 	if (hcd->shared_hcd) {
 		struct usb_hcd *peer = hcd->shared_hcd;
 
 		peer->shared_hcd = NULL;
-		if (peer->primary_hcd == hcd)
-			peer->primary_hcd = NULL;
+		peer->primary_hcd = NULL;
+	} else {
+		kfree(hcd->address0_mutex);
+		kfree(hcd->bandwidth_mutex);
 	}
 	mutex_unlock(&usb_port_peer_mutex);
 	kfree(hcd);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 1560f3f3e756..cdf4be3939f5 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -101,6 +101,7 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem);
 
 static void hub_release(struct kref *kref);
 static int usb_reset_and_verify_device(struct usb_device *udev);
+static int hub_port_disable(struct usb_hub *hub, int port1, int set_state);
 
 static inline char *portspeed(struct usb_hub *hub, int portstatus)
 {
@@ -298,7 +299,7 @@ static void usb_set_lpm_parameters(struct usb_device *udev)
 	unsigned int hub_u1_del;
 	unsigned int hub_u2_del;
 
-	if (!udev->lpm_capable || udev->speed != USB_SPEED_SUPER)
+	if (!udev->lpm_capable || udev->speed < USB_SPEED_SUPER)
 		return;
 
 	hub = usb_hub_to_struct_hub(udev->parent);
@@ -357,7 +358,8 @@ static void usb_set_lpm_parameters(struct usb_device *udev)
 }
 
 /* USB 2.0 spec Section 11.24.4.5 */
-static int get_hub_descriptor(struct usb_device *hdev, void *data)
+static int get_hub_descriptor(struct usb_device *hdev,
+		struct usb_hub_descriptor *desc)
 {
 	int i, ret, size;
 	unsigned dtype;
@@ -373,10 +375,18 @@ static int get_hub_descriptor(struct usb_device *hdev, void *data)
 	for (i = 0; i < 3; i++) {
 		ret = usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0),
 			USB_REQ_GET_DESCRIPTOR, USB_DIR_IN | USB_RT_HUB,
-			dtype << 8, 0, data, size,
+			dtype << 8, 0, desc, size,
 			USB_CTRL_GET_TIMEOUT);
-		if (ret >= (USB_DT_HUB_NONVAR_SIZE + 2))
+		if (hub_is_superspeed(hdev)) {
+			if (ret == size)
+				return ret;
+		} else if (ret >= USB_DT_HUB_NONVAR_SIZE + 2) {
+			/* Make sure we have the DeviceRemovable field. */
+			size = USB_DT_HUB_NONVAR_SIZE + desc->bNbrPorts / 8 + 1;
+			if (ret < size)
+				return -EMSGSIZE;
 			return ret;
+		}
 	}
 	return -EINVAL;
 }
@@ -883,88 +893,6 @@ static int hub_set_port_link_state(struct usb_hub *hub, int port1,
 }
 
 /*
- * If USB 3.0 ports are placed into the Disabled state, they will no longer
- * detect any device connects or disconnects.  This is generally not what the
- * USB core wants, since it expects a disabled port to produce a port status
- * change event when a new device connects.
- *
- * Instead, set the link state to Disabled, wait for the link to settle into
- * that state, clear any change bits, and then put the port into the RxDetect
- * state.
- */
-static int hub_usb3_port_disable(struct usb_hub *hub, int port1)
-{
-	int ret;
-	int total_time;
-	u16 portchange, portstatus;
-
-	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;
-
-	/* Wait for the link to enter the disabled state. */
-	for (total_time = 0; ; total_time += HUB_DEBOUNCE_STEP) {
-		ret = hub_port_status(hub, port1, &portstatus, &portchange);
-		if (ret < 0)
-			return ret;
-
-		if ((portstatus & USB_PORT_STAT_LINK_STATE) ==
-				USB_SS_PORT_LS_SS_DISABLED)
-			break;
-		if (total_time >= HUB_DEBOUNCE_TIMEOUT)
-			break;
-		msleep(HUB_DEBOUNCE_STEP);
-	}
-	if (total_time >= HUB_DEBOUNCE_TIMEOUT)
-		dev_warn(&hub->ports[port1 - 1]->dev,
-				"Could not disable after %d ms\n", total_time);
-
-	return hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_RX_DETECT);
-}
-
-static int hub_port_disable(struct usb_hub *hub, int port1, int set_state)
-{
-	struct usb_port *port_dev = hub->ports[port1 - 1];
-	struct usb_device *hdev = hub->hdev;
-	int ret = 0;
-
-	if (port_dev->child && set_state)
-		usb_set_device_state(port_dev->child, USB_STATE_NOTATTACHED);
-	if (!hub->error) {
-		if (hub_is_superspeed(hub->hdev))
-			ret = hub_usb3_port_disable(hub, port1);
-		else
-			ret = usb_clear_port_feature(hdev, port1,
-					USB_PORT_FEAT_ENABLE);
-	}
-	if (ret && ret != -ENODEV)
-		dev_err(&port_dev->dev, "cannot disable (err = %d)\n", ret);
-	return ret;
-}
-
-/*
  * Disable a port and mark a logical connect-change event, so that some
  * time later hub_wq will disconnect() any existing usb_device on the port
  * and will re-enumerate if there actually is a device attached.
@@ -1036,14 +964,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 	/* Continue a partial initialization */
 	if (type == HUB_INIT2 || type == HUB_INIT3) {
-		device_lock(hub->intfdev);
+		device_lock(&hdev->dev);
 
 		/* Was the hub disconnected while we were waiting? */
-		if (hub->disconnected) {
-			device_unlock(hub->intfdev);
-			kref_put(&hub->kref, hub_release);
-			return;
-		}
+		if (hub->disconnected)
+			goto disconnected;
 		if (type == HUB_INIT2)
 			goto init2;
 		goto init3;
@@ -1132,6 +1057,9 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 		portstatus = portchange = 0;
 		status = hub_port_status(hub, port1, &portstatus, &portchange);
+		if (status)
+			goto abort;
+
 		if (udev || (portstatus & USB_PORT_STAT_CONNECTION))
 			dev_dbg(&port_dev->dev, "status %04x change %04x\n",
 					portstatus, portchange);
@@ -1246,7 +1174,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			queue_delayed_work(system_power_efficient_wq,
 					&hub->init_work,
 					msecs_to_jiffies(delay));
-			device_unlock(hub->intfdev);
+			device_unlock(&hdev->dev);
 			return;		/* Continues at init3: below */
 		} else {
 			msleep(delay);
@@ -1264,13 +1192,13 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 	/* Scan all ports that need attention */
 	kick_hub_wq(hub);
-
-	/* Allow autosuspend if it was suppressed */
-	if (type <= HUB_INIT3)
+ abort:
+	if (type == HUB_INIT2 || type == HUB_INIT3) {
+		/* Allow autosuspend if it was suppressed */
+ disconnected:
 		usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
-
-	if (type == HUB_INIT2 || type == HUB_INIT3)
-		device_unlock(hub->intfdev);
+		device_unlock(&hdev->dev);
+	}
 
 	kref_put(&hub->kref, hub_release);
 }
@@ -1299,8 +1227,6 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type)
 	struct usb_device *hdev = hub->hdev;
 	int i;
 
-	cancel_delayed_work_sync(&hub->init_work);
-
 	/* hub_wq and related activity won't re-trigger */
 	hub->quiescing = 1;
 
@@ -1378,7 +1304,7 @@ static int hub_configure(struct usb_hub *hub,
 	}
 	mutex_init(&hub->status_mutex);
 
-	hub->descriptor = kmalloc(sizeof(*hub->descriptor), GFP_KERNEL);
+	hub->descriptor = kzalloc(sizeof(*hub->descriptor), GFP_KERNEL);
 	if (!hub->descriptor) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1386,13 +1312,19 @@ static int hub_configure(struct usb_hub *hub,
 
 	/* Request the entire hub descriptor.
 	 * hub->descriptor can handle USB_MAXCHILDREN ports,
-	 * but the hub can/will return fewer bytes here.
+	 * but a (non-SS) hub can/will return fewer bytes here.
 	 */
 	ret = get_hub_descriptor(hdev, hub->descriptor);
 	if (ret < 0) {
 		message = "can't read hub descriptor";
 		goto fail;
-	} else if (hub->descriptor->bNbrPorts > USB_MAXCHILDREN) {
+	}
+
+	maxchild = USB_MAXCHILDREN;
+	if (hub_is_superspeed(hdev))
+		maxchild = min_t(unsigned, maxchild, USB_SS_MAXPORTS);
+
+	if (hub->descriptor->bNbrPorts > maxchild) {
 		message = "hub has too many ports!";
 		ret = -ENODEV;
 		goto fail;
@@ -2066,7 +1998,7 @@ static void choose_devnum(struct usb_device *udev)
 	struct usb_bus	*bus = udev->bus;
 
 	/* be safe when more hub events are proceed in parallel */
-	mutex_lock(&bus->usb_address0_mutex);
+	mutex_lock(&bus->devnum_next_mutex);
 	if (udev->wusb) {
 		devnum = udev->portnum + 1;
 		BUG_ON(test_bit(devnum, bus->devmap.devicemap));
@@ -2084,7 +2016,7 @@ static void choose_devnum(struct usb_device *udev)
 		set_bit(devnum, bus->devmap.devicemap);
 		udev->devnum = devnum;
 	}
-	mutex_unlock(&bus->usb_address0_mutex);
+	mutex_unlock(&bus->devnum_next_mutex);
 }
 
 static void release_devnum(struct usb_device *udev)
@@ -2154,6 +2086,12 @@ void usb_disconnect(struct usb_device **pdev)
 	dev_info(&udev->dev, "USB disconnect, device number %d\n",
 			udev->devnum);
 
+	/*
+	 * Ensure that the pm runtime code knows that the USB device
+	 * is in the process of being disconnected.
+	 */
+	pm_runtime_barrier(&udev->dev);
+
 	usb_lock_device(udev);
 
 	hub_disconnect_children(udev);
@@ -2645,7 +2583,7 @@ static unsigned hub_is_wusb(struct usb_hub *hub)
  */
 static bool use_new_scheme(struct usb_device *udev, int retry)
 {
-	if (udev->speed == USB_SPEED_SUPER)
+	if (udev->speed >= USB_SPEED_SUPER)
 		return false;
 
 	return USE_NEW_SCHEME(retry);
@@ -2688,8 +2626,15 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1,
 		if (ret < 0)
 			return ret;
 
-		/* The port state is unknown until the reset completes. */
-		if (!(portstatus & USB_PORT_STAT_RESET))
+		/*
+		 * The port state is unknown until the reset completes.
+		 *
+		 * On top of that, some chips may require additional time
+		 * to re-establish a connection after the reset is complete,
+		 * so also wait for the connection to be re-established.
+		 */
+		if (!(portstatus & USB_PORT_STAT_RESET) &&
+		    (portstatus & USB_PORT_STAT_CONNECTION))
 			break;
 
 		/* switch to the long delay after two short delay failures */
@@ -3985,7 +3930,7 @@ int usb_disable_lpm(struct usb_device *udev)
 	struct usb_hcd *hcd;
 
 	if (!udev || !udev->parent ||
-			udev->speed != USB_SPEED_SUPER ||
+			udev->speed < USB_SPEED_SUPER ||
 			!udev->lpm_capable ||
 			udev->state < USB_STATE_DEFAULT)
 		return 0;
@@ -4042,7 +3987,7 @@ void usb_enable_lpm(struct usb_device *udev)
 	struct usb_hcd *hcd;
 
 	if (!udev || !udev->parent ||
-			udev->speed != USB_SPEED_SUPER ||
+			udev->speed < USB_SPEED_SUPER ||
 			!udev->lpm_capable ||
 			udev->state < USB_STATE_DEFAULT)
 		return;
@@ -4078,6 +4023,26 @@ void usb_unlocked_enable_lpm(struct usb_device *udev)
 }
 EXPORT_SYMBOL_GPL(usb_unlocked_enable_lpm);
 
+/* usb3 devices use U3 for disabled, make sure remote wakeup is disabled */
+static void hub_usb3_port_prepare_disable(struct usb_hub *hub,
+					  struct usb_port *port_dev)
+{
+	struct usb_device *udev = port_dev->child;
+	int ret;
+
+	if (udev && udev->port_is_suspended && udev->do_remote_wakeup) {
+		ret = hub_set_port_link_state(hub, port_dev->portnum,
+					      USB_SS_PORT_LS_U0);
+		if (!ret) {
+			msleep(USB_RESUME_TIMEOUT);
+			ret = usb_disable_remote_wakeup(udev);
+		}
+		if (ret)
+			dev_warn(&udev->dev,
+				 "Port disable: can't disable remote wake\n");
+		udev->do_remote_wakeup = 0;
+	}
+}
 
 #else	/* CONFIG_PM */
 
@@ -4085,6 +4050,9 @@ EXPORT_SYMBOL_GPL(usb_unlocked_enable_lpm);
 #define hub_resume		NULL
 #define hub_reset_resume	NULL
 
+static inline void hub_usb3_port_prepare_disable(struct usb_hub *hub,
+						 struct usb_port *port_dev) { }
+
 int usb_disable_lpm(struct usb_device *udev)
 {
 	return 0;
@@ -4120,6 +4088,34 @@ static int hub_handle_remote_wakeup(struct usb_hub *hub, unsigned int port,
 
 #endif	/* CONFIG_PM */
 
+/*
+ * USB-3 does not have a similar link state as USB-2 that will avoid negotiating
+ * a connection with a plugged-in cable but will signal the host when the cable
+ * is unplugged. Disable remote wake and set link state to U3 for USB-3 devices
+ */
+static int hub_port_disable(struct usb_hub *hub, int port1, int set_state)
+{
+	struct usb_port *port_dev = hub->ports[port1 - 1];
+	struct usb_device *hdev = hub->hdev;
+	int ret = 0;
+
+	if (!hub->error) {
+		if (hub_is_superspeed(hub->hdev)) {
+			hub_usb3_port_prepare_disable(hub, port_dev);
+			ret = hub_set_port_link_state(hub, port_dev->portnum,
+						      USB_SS_PORT_LS_U3);
+		} else {
+			ret = usb_clear_port_feature(hdev, port1,
+					USB_PORT_FEAT_ENABLE);
+		}
+	}
+	if (port_dev->child && set_state)
+		usb_set_device_state(port_dev->child, USB_STATE_NOTATTACHED);
+	if (ret && ret != -ENODEV)
+		dev_err(&port_dev->dev, "cannot disable (err = %d)\n", ret);
+	return ret;
+}
+
 
 /* USB 2.0 spec, 7.1.7.3 / fig 7-29:
  *
@@ -4234,7 +4230,7 @@ static void hub_set_initial_usb2_lpm_policy(struct usb_device *udev)
 	struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
 	int connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN;
 
-	if (!udev->usb2_hw_lpm_capable)
+	if (!udev->usb2_hw_lpm_capable || !udev->bos)
 		return;
 
 	if (hub)
@@ -4277,7 +4273,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 {
 	struct usb_device	*hdev = hub->hdev;
 	struct usb_hcd		*hcd = bus_to_hcd(hdev->bus);
-	int			i, j, retval;
+	int			retries, operations, retval, i;
 	unsigned		delay = HUB_SHORT_RESET_TIME;
 	enum usb_device_speed	oldspeed = udev->speed;
 	const char		*speed;
@@ -4297,7 +4293,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	if (oldspeed == USB_SPEED_LOW)
 		delay = HUB_LONG_RESET_TIME;
 
-	mutex_lock(&hdev->bus->usb_address0_mutex);
+	mutex_lock(hcd->address0_mutex);
 
 	/* Reset the device; full speed may morph to high speed */
 	/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
@@ -4308,7 +4304,9 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 
 	retval = -ENODEV;
 
-	if (oldspeed != USB_SPEED_UNKNOWN && oldspeed != udev->speed) {
+	/* Don't allow speed changes at reset, except usb 3.0 to faster */
+	if (oldspeed != USB_SPEED_UNKNOWN && oldspeed != udev->speed &&
+	    !(oldspeed == USB_SPEED_SUPER && udev->speed > oldspeed)) {
 		dev_dbg(&udev->dev, "device reset changed speed!\n");
 		goto fail;
 	}
@@ -4320,6 +4318,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	 * reported as 0xff in the device descriptor). WUSB1.0[4.8.1].
 	 */
 	switch (udev->speed) {
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
 	case USB_SPEED_WIRELESS:	/* fixed at 512 */
 		udev->ep0.desc.wMaxPacketSize = cpu_to_le16(512);
@@ -4346,7 +4345,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	else
 		speed = usb_speed_string(udev->speed);
 
-	if (udev->speed != USB_SPEED_SUPER)
+	if (udev->speed < USB_SPEED_SUPER)
 		dev_info(&udev->dev,
 				"%s %s USB device number %d using %s\n",
 				(udev->config) ? "reset" : "new", speed,
@@ -4379,7 +4378,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	 * first 8 bytes of the device descriptor to get the ep0 maxpacket
 	 * value.
 	 */
-	for (i = 0; i < GET_DESCRIPTOR_TRIES; (++i, msleep(100))) {
+	for (retries = 0; retries < GET_DESCRIPTOR_TRIES; (++retries, msleep(100))) {
 		bool did_new_scheme = false;
 
 		if (use_new_scheme(udev, retry_counter)) {
@@ -4406,7 +4405,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 			 * 255 is for WUSB devices, we actually need to use
 			 * 512 (WUSB1.0[4.8.1]).
 			 */
-			for (j = 0; j < 3; ++j) {
+			for (operations = 0; operations < 3; ++operations) {
 				buf->bMaxPacketSize0 = 0;
 				r = usb_control_msg(udev, usb_rcvaddr0pipe(),
 					USB_REQ_GET_DESCRIPTOR, USB_DIR_IN,
@@ -4426,7 +4425,13 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 						r = -EPROTO;
 					break;
 				}
-				if (r == 0)
+				/*
+				 * Some devices time out if they are powered on
+				 * when already connected. They need a second
+				 * reset. But only on the first attempt,
+				 * lest we get into a time out/reset loop
+				 */
+				if (r == 0  || (r == -ETIMEDOUT && retries == 0))
 					break;
 			}
 			udev->descriptor.bMaxPacketSize0 =
@@ -4458,7 +4463,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 		 * authorization will assign the final address.
 		 */
 		if (udev->wusb == 0) {
-			for (j = 0; j < SET_ADDRESS_TRIES; ++j) {
+			for (operations = 0; operations < SET_ADDRESS_TRIES; ++operations) {
 				retval = hub_set_address(udev, devnum);
 				if (retval >= 0)
 					break;
@@ -4470,11 +4475,12 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 							devnum, retval);
 				goto fail;
 			}
-			if (udev->speed == USB_SPEED_SUPER) {
+			if (udev->speed >= USB_SPEED_SUPER) {
 				devnum = udev->devnum;
 				dev_info(&udev->dev,
-						"%s SuperSpeed USB device number %d using %s\n",
+						"%s SuperSpeed%s USB device number %d using %s\n",
 						(udev->config) ? "reset" : "new",
+					 (udev->speed == USB_SPEED_SUPER_PLUS) ? "Plus" : "",
 						devnum, udev->bus->controller->driver->name);
 			}
 
@@ -4513,7 +4519,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	 * got from those devices show they aren't superspeed devices. Warm
 	 * reset the port attached by the devices can fix them.
 	 */
-	if ((udev->speed == USB_SPEED_SUPER) &&
+	if ((udev->speed >= USB_SPEED_SUPER) &&
 			(le16_to_cpu(udev->descriptor.bcdUSB) < 0x0300)) {
 		dev_err(&udev->dev, "got a wrong device descriptor, "
 				"warm reset device\n");
@@ -4524,7 +4530,7 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	}
 
 	if (udev->descriptor.bMaxPacketSize0 == 0xff ||
-			udev->speed == USB_SPEED_SUPER)
+			udev->speed >= USB_SPEED_SUPER)
 		i = 512;
 	else
 		i = udev->descriptor.bMaxPacketSize0;
@@ -4573,7 +4579,7 @@ fail:
 		hub_port_disable(hub, port1, 0);
 		update_devnum(udev, devnum);	/* for disconnect processing */
 	}
-	mutex_unlock(&hdev->bus->usb_address0_mutex);
+	mutex_unlock(hcd->address0_mutex);
 	return retval;
 }
 
@@ -4655,7 +4661,8 @@ hub_power_remaining(struct usb_hub *hub)
 static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		u16 portchange)
 {
-	int status, i;
+	int status = -ENODEV;
+	int i;
 	unsigned unit_load;
 	struct usb_device *hdev = hub->hdev;
 	struct usb_hcd *hcd = bus_to_hcd(hdev->bus);
@@ -4734,7 +4741,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		udev->level = hdev->level + 1;
 		udev->wusb = hub_is_wusb(hub);
 
-		/* Only USB 3.0 devices are connected to SuperSpeed hubs. */
+		/* Devices connected to SuperSpeed hubs are USB 3.0 or later */
 		if (hub_is_superspeed(hub->hdev))
 			udev->speed = USB_SPEED_SUPER;
 		else
@@ -4859,9 +4866,10 @@ loop:
 
 done:
 	hub_port_disable(hub, port1, 1);
-	if (hcd->driver->relinquish_port && !hub->hdev->parent)
-		hcd->driver->relinquish_port(hcd, port1);
-
+	if (hcd->driver->relinquish_port && !hub->hdev->parent) {
+		if (status != -ENOTCONN && status != -ENODEV)
+			hcd->driver->relinquish_port(hcd, port1);
+	}
 }
 
 /* Handle physical or logical connection change events.
@@ -5386,6 +5394,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	}
 
 	bos = udev->bos;
+	udev->bos = NULL;
 
 	for (i = 0; i < SET_CONFIG_TRIES; ++i) {
 
@@ -5478,11 +5487,8 @@ done:
 	usb_set_usb2_hardware_lpm(udev, 1);
 	usb_unlocked_enable_lpm(udev);
 	usb_enable_ltm(udev);
-	/* release the new BOS descriptor allocated  by hub_port_init() */
-	if (udev->bos != bos) {
-		usb_release_bos_descriptor(udev);
-		udev->bos = bos;
-	}
+	usb_release_bos_descriptor(udev);
+	udev->bos = bos;
 	return 0;
 
 re_enumerate:
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6dc810bce295..82806e311202 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -37,6 +37,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* CBM - Flash disk */
 	{ USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* WORLDE easy key (easykey.25) MIDI controller  */
+	{ USB_DEVICE(0x0218, 0x0401), .driver_info =
+			USB_QUIRK_CONFIG_INTF_STRINGS },
+
 	/* HP 5300/5370C scanner */
 	{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -44,14 +48,18 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* USB3503 */
+	{ USB_DEVICE(0x0424, 0x3503), .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 */
+	/* Logitech HD Pro Webcams C920, C920-C and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Logitech ConferenceCam CC3000e */
@@ -125,6 +133,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x04f3, 0x016f), .driver_info =
 			USB_QUIRK_DEVICE_QUALIFIER },
 
+	{ USB_DEVICE(0x04f3, 0x0381), .driver_info =
+			USB_QUIRK_NO_LPM },
+
 	{ USB_DEVICE(0x04f3, 0x21b8), .driver_info =
 			USB_QUIRK_DEVICE_QUALIFIER },
 
@@ -140,6 +151,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* appletouch */
 	{ USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
+	{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Avision AV600U */
 	{ USB_DEVICE(0x0638, 0x0a13), .driver_info =
 	  USB_QUIRK_STRING_FETCH_255 },
@@ -160,6 +174,14 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* M-Systems Flash Disk Pioneers */
 	{ USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Baum Vario Ultra */
+	{ USB_DEVICE(0x0904, 0x6101), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+	{ USB_DEVICE(0x0904, 0x6102), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
+			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -173,6 +195,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* MAYA44USB sound device */
 	{ USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
@@ -188,26 +214,29 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1908, 0x1315), .driver_info =
 			USB_QUIRK_HONOR_BNUMINTERFACES },
 
-	/* INTEL VALUE SSD */
-	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* USB3503 */
-	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
-
-	/* ASUS Base Station(T100) */
-	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
-			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
-
 	/* Protocol and OTG Electrical Test Device */
 	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Corsair Strafe RGB */
+	{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT },
+
+	/* Acer C120 LED Projector */
+	{ USB_DEVICE(0x1de1, 0xc102), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Blackmagic Design Intensity Shuttle */
 	{ USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
 
 	/* Blackmagic Design UltraStudio SDI */
 	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Hauppauge HVR-950q */
+	{ USB_DEVICE(0x2040, 0x7200), .driver_info =
+			USB_QUIRK_CONFIG_INTF_STRINGS },
+
+	/* INTEL VALUE SSD */
+	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };
 
@@ -227,6 +256,7 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = {
 	{ USB_DEVICE(0x093a, 0x2500), .driver_info = USB_QUIRK_RESET_RESUME },
 	{ USB_DEVICE(0x093a, 0x2510), .driver_info = USB_QUIRK_RESET_RESUME },
 	{ USB_DEVICE(0x093a, 0x2521), .driver_info = USB_QUIRK_RESET_RESUME },
+	{ USB_DEVICE(0x03f0, 0x2b4a), .driver_info = USB_QUIRK_RESET_RESUME },
 
 	/* Logitech Optical Mouse M90/M100 */
 	{ USB_DEVICE(0x046d, 0xc05a), .driver_info = USB_QUIRK_RESET_RESUME },
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 3d274778caaf..e43ef7d2d00e 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -335,7 +335,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 	if (!urb || !urb->complete)
 		return -EINVAL;
 	if (urb->hcpriv) {
-		WARN_ONCE(1, "URB %p submitted while active\n", urb);
+		WARN_ONCE(1, "URB %pK submitted while active\n", urb);
 		return -EBUSY;
 	}
 
@@ -401,7 +401,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 		/* SuperSpeed isoc endpoints have up to 16 bursts of up to
 		 * 3 packets each
 		 */
-		if (dev->speed == USB_SPEED_SUPER) {
+		if (dev->speed >= USB_SPEED_SUPER) {
 			int     burst = 1 + ep->ss_ep_comp.bMaxBurst;
 			int     mult = USB_SS_MULT(ep->ss_ep_comp.bmAttributes);
 			max *= burst;
@@ -499,6 +499,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 		}
 		/* too big? */
 		switch (dev->speed) {
+		case USB_SPEED_SUPER_PLUS:
 		case USB_SPEED_SUPER:	/* units are 125us */
 			/* Handle up to 2^(16-1) microframes */
 			if (urb->interval > (1 << 15))
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index 2776cfe64c09..ef9cf4a21afe 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -127,6 +127,22 @@ out:
  */
 #define USB_ACPI_LOCATION_VALID (1 << 31)
 
+static struct acpi_device *usb_acpi_find_port(struct acpi_device *parent,
+					      int raw)
+{
+	struct acpi_device *adev;
+
+	if (!parent)
+		return NULL;
+
+	list_for_each_entry(adev, &parent->children, node) {
+		if (acpi_device_adr(adev) == raw)
+			return adev;
+	}
+
+	return acpi_find_child_device(parent, raw, false);
+}
+
 static struct acpi_device *usb_acpi_find_companion(struct device *dev)
 {
 	struct usb_device *udev;
@@ -174,8 +190,10 @@ static struct acpi_device *usb_acpi_find_companion(struct device *dev)
 			int raw;
 
 			raw = usb_hcd_find_raw_port_number(hcd, port1);
-			adev = acpi_find_child_device(ACPI_COMPANION(&udev->dev),
-					raw, false);
+
+			adev = usb_acpi_find_port(ACPI_COMPANION(&udev->dev),
+						  raw);
+
 			if (!adev)
 				return NULL;
 		} else {
@@ -186,7 +204,9 @@ static struct acpi_device *usb_acpi_find_companion(struct device *dev)
 				return NULL;
 
 			acpi_bus_get_device(parent_handle, &adev);
-			adev = acpi_find_child_device(adev, port1, false);
+
+			adev = usb_acpi_find_port(adev, port1);
+
 			if (!adev)
 				return NULL;
 		}
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 05b5e17abf92..53318126ed91 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -45,7 +45,7 @@ static inline unsigned usb_get_max_power(struct usb_device *udev,
 		struct usb_host_config *c)
 {
 	/* SuperSpeed power is in 8 mA units; others are in 2 mA units */
-	unsigned mul = (udev->speed == USB_SPEED_SUPER ? 8 : 2);
+	unsigned mul = (udev->speed >= USB_SPEED_SUPER ? 8 : 2);
 
 	return c->desc.bMaxPower * mul;
 }
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index a66d3cb62b65..a738a68d2292 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -44,6 +44,17 @@
 #include <linux/usb/phy.h>
 #include "hw.h"
 
+#ifdef CONFIG_MIPS
+/*
+ * There are some MIPS machines that can run in either big-endian
+ * or little-endian mode and that use the dwc2 register without
+ * a byteswap in both ways.
+ * Unlike other architectures, MIPS apparently does not require a
+ * barrier before the __raw_writel() to synchronize with DMA but does
+ * require the barrier after the __raw_writel() to serialize a set of
+ * writes. This set of operations was added specifically for MIPS and
+ * should only be used there.
+ */
 static inline u32 dwc2_readl(const void __iomem *addr)
 {
 	u32 value = __raw_readl(addr);
@@ -70,6 +81,22 @@ static inline void dwc2_writel(u32 value, void __iomem *addr)
 	pr_info("INFO:: wrote %08x to %p\n", value, addr);
 #endif
 }
+#else
+/* Normal architectures just use readl/write */
+static inline u32 dwc2_readl(const void __iomem *addr)
+{
+	return readl(addr);
+}
+
+static inline void dwc2_writel(u32 value, void __iomem *addr)
+{
+	writel(value, addr);
+
+#ifdef DWC2_LOG_WRITES
+	pr_info("info:: wrote %08x to %p\n", value, addr);
+#endif
+}
+#endif
 
 /* Maximum number of Endpoints/HostChannels */
 #define MAX_EPS_CHANNELS	16
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 78be201d81f4..68d11d7d4028 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -42,9 +42,7 @@
 #define DWC3_XHCI_RESOURCES_NUM	2
 
 #define DWC3_SCRATCHBUF_SIZE	4096	/* each buffer is assumed to be 4KiB */
-#define DWC3_EVENT_SIZE		4	/* bytes */
-#define DWC3_EVENT_MAX_NUM	64	/* 2 events/endpoint */
-#define DWC3_EVENT_BUFFERS_SIZE	(DWC3_EVENT_SIZE * DWC3_EVENT_MAX_NUM)
+#define DWC3_EVENT_BUFFERS_SIZE	4096
 #define DWC3_EVENT_TYPE_MASK	0xfe
 
 #define DWC3_EVENT_TYPE_DEV	0
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index dd5cb5577dca..9eba51b92f72 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -128,12 +128,6 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, exynos);
 
-	ret = dwc3_exynos_register_phys(exynos);
-	if (ret) {
-		dev_err(dev, "couldn't register PHYs\n");
-		return ret;
-	}
-
 	exynos->dev	= dev;
 
 	exynos->clk = devm_clk_get(dev, "usbdrd30");
@@ -154,7 +148,8 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 		exynos->axius_clk = devm_clk_get(dev, "usbdrd30_axius_clk");
 		if (IS_ERR(exynos->axius_clk)) {
 			dev_err(dev, "no AXI UpScaler clk specified\n");
-			return -ENODEV;
+			ret = -ENODEV;
+			goto axius_clk_err;
 		}
 		clk_prepare_enable(exynos->axius_clk);
 	} else {
@@ -183,26 +178,36 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	ret = dwc3_exynos_register_phys(exynos);
+	if (ret) {
+		dev_err(dev, "couldn't register PHYs\n");
+		goto err4;
+	}
+
 	if (node) {
 		ret = of_platform_populate(node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to add dwc3 core\n");
-			goto err4;
+			goto err5;
 		}
 	} else {
 		dev_err(dev, "no device node, failed to add dwc3 core\n");
 		ret = -ENODEV;
-		goto err4;
+		goto err5;
 	}
 
 	return 0;
 
+err5:
+	platform_device_unregister(exynos->usb2_phy);
+	platform_device_unregister(exynos->usb3_phy);
 err4:
 	regulator_disable(exynos->vdd10);
 err3:
 	regulator_disable(exynos->vdd33);
 err2:
 	clk_disable_unprepare(exynos->axius_clk);
+axius_clk_err:
 	clk_disable_unprepare(exynos->susp_clk);
 	clk_disable_unprepare(exynos->clk);
 	return ret;
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 009d83048c8c..d2c0c1a8d979 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -36,6 +36,8 @@
 #define PCI_DEVICE_ID_INTEL_SPTH		0xa130
 #define PCI_DEVICE_ID_INTEL_BXT			0x0aaa
 #define PCI_DEVICE_ID_INTEL_APL			0x5aaa
+#define PCI_DEVICE_ID_INTEL_KBP			0xa2b0
+#define PCI_DEVICE_ID_INTEL_GLK			0x31aa
 
 static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
 static const struct acpi_gpio_params cs_gpios = { 1, 0, false };
@@ -214,6 +216,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SPTH), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_GLK), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
 	{  }	/* Terminating Entry */
 };
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 5c0adb9c6fb2..81db2fa08cad 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -224,7 +224,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
 
 	dwc3_data->syscfg_reg_off = res->start;
 
-	dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n",
+	dev_vdbg(&pdev->dev, "glue-logic addr 0x%pK, syscfg-reg offset 0x%x\n",
 		 dwc3_data->glue_base, dwc3_data->syscfg_reg_off);
 
 	dwc3_data->rstc_pwrdn = devm_reset_control_get(dev, "powerdown");
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index b13912d5fa99..f13e9e9fb834 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -55,20 +55,13 @@ static const char *dwc3_ep0_state_string(enum dwc3_ep0_state state)
 	}
 }
 
-static int dwc3_ep0_start_trans(struct dwc3 *dwc, u8 epnum, dma_addr_t buf_dma,
-		u32 len, u32 type, bool chain)
+static void dwc3_ep0_prepare_one_trb(struct dwc3 *dwc, u8 epnum,
+		dma_addr_t buf_dma, u32 len, u32 type, bool chain)
 {
-	struct dwc3_gadget_ep_cmd_params params;
 	struct dwc3_trb			*trb;
 	struct dwc3_ep			*dep;
 
-	int				ret;
-
 	dep = dwc->eps[epnum];
-	if (dep->flags & DWC3_EP_BUSY) {
-		dwc3_trace(trace_dwc3_ep0, "%s still busy", dep->name);
-		return 0;
-	}
 
 	trb = &dwc->ep0_trb[dep->free_slot];
 
@@ -89,15 +82,25 @@ static int dwc3_ep0_start_trans(struct dwc3 *dwc, u8 epnum, dma_addr_t buf_dma,
 		trb->ctrl |= (DWC3_TRB_CTRL_IOC
 				| DWC3_TRB_CTRL_LST);
 
-	if (chain)
+	trace_dwc3_prepare_trb(dep, trb);
+}
+
+static int dwc3_ep0_start_trans(struct dwc3 *dwc, u8 epnum)
+{
+	struct dwc3_gadget_ep_cmd_params params;
+	struct dwc3_ep			*dep;
+	int				ret;
+
+	dep = dwc->eps[epnum];
+	if (dep->flags & DWC3_EP_BUSY) {
+		dwc3_trace(trace_dwc3_ep0, "%s still busy", dep->name);
 		return 0;
+	}
 
 	memset(&params, 0, sizeof(params));
 	params.param0 = upper_32_bits(dwc->ep0_trb_addr);
 	params.param1 = lower_32_bits(dwc->ep0_trb_addr);
 
-	trace_dwc3_prepare_trb(dep, trb);
-
 	ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
 			DWC3_DEPCMD_STARTTRANSFER, &params);
 	if (ret < 0) {
@@ -311,8 +314,9 @@ void dwc3_ep0_out_start(struct dwc3 *dwc)
 {
 	int				ret;
 
-	ret = dwc3_ep0_start_trans(dwc, 0, dwc->ctrl_req_addr, 8,
+	dwc3_ep0_prepare_one_trb(dwc, 0, dwc->ctrl_req_addr, 8,
 			DWC3_TRBCTL_CONTROL_SETUP, false);
+	ret = dwc3_ep0_start_trans(dwc, 0);
 	WARN_ON(ret < 0);
 }
 
@@ -871,9 +875,9 @@ static void dwc3_ep0_complete_data(struct dwc3 *dwc,
 
 			dwc->ep0_next_event = DWC3_EP0_COMPLETE;
 
-			ret = dwc3_ep0_start_trans(dwc, epnum,
-					dwc->ctrl_req_addr, 0,
-					DWC3_TRBCTL_CONTROL_DATA, false);
+			dwc3_ep0_prepare_one_trb(dwc, epnum, dwc->ctrl_req_addr,
+					0, DWC3_TRBCTL_CONTROL_DATA, false);
+			ret = dwc3_ep0_start_trans(dwc, epnum);
 			WARN_ON(ret < 0);
 		}
 	}
@@ -955,9 +959,10 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 	req->direction = !!dep->number;
 
 	if (req->request.length == 0) {
-		ret = dwc3_ep0_start_trans(dwc, dep->number,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number,
 				dwc->ctrl_req_addr, 0,
 				DWC3_TRBCTL_CONTROL_DATA, false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	} else if (!IS_ALIGNED(req->request.length, dep->endpoint.maxpacket)
 			&& (dep->number == 0)) {
 		u32	transfer_size = 0;
@@ -975,7 +980,7 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		if (req->request.length > DWC3_EP0_BOUNCE_SIZE) {
 			transfer_size = ALIGN(req->request.length - maxpacket,
 					      maxpacket);
-			ret = dwc3_ep0_start_trans(dwc, dep->number,
+			dwc3_ep0_prepare_one_trb(dwc, dep->number,
 						   req->request.dma,
 						   transfer_size,
 						   DWC3_TRBCTL_CONTROL_DATA,
@@ -987,9 +992,10 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 
 		dwc->ep0_bounced = true;
 
-		ret = dwc3_ep0_start_trans(dwc, dep->number,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number,
 				dwc->ep0_bounce_addr, transfer_size,
 				DWC3_TRBCTL_CONTROL_DATA, false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	} else {
 		ret = usb_gadget_map_request(&dwc->gadget, &req->request,
 				dep->number);
@@ -998,9 +1004,10 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 			return;
 		}
 
-		ret = dwc3_ep0_start_trans(dwc, dep->number, req->request.dma,
+		dwc3_ep0_prepare_one_trb(dwc, dep->number, req->request.dma,
 				req->request.length, DWC3_TRBCTL_CONTROL_DATA,
 				false);
+		ret = dwc3_ep0_start_trans(dwc, dep->number);
 	}
 
 	WARN_ON(ret < 0);
@@ -1014,8 +1021,9 @@ static int dwc3_ep0_start_control_status(struct dwc3_ep *dep)
 	type = dwc->three_stage_setup ? DWC3_TRBCTL_CONTROL_STATUS3
 		: DWC3_TRBCTL_CONTROL_STATUS2;
 
-	return dwc3_ep0_start_trans(dwc, dep->number,
+	dwc3_ep0_prepare_one_trb(dwc, dep->number,
 			dwc->ctrl_req_addr, 0, type, false);
+	return dwc3_ep0_start_trans(dwc, dep->number);
 }
 
 static void __dwc3_ep0_do_control_status(struct dwc3 *dwc, struct dwc3_ep *dep)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 69ffe6e8d77f..d3bd1afd6302 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -235,6 +235,7 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 		int status)
 {
 	struct dwc3			*dwc = dep->dwc;
+	unsigned int			unmap_after_complete = false;
 	int				i;
 
 	if (req->queued) {
@@ -259,11 +260,19 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 	if (req->request.status == -EINPROGRESS)
 		req->request.status = status;
 
-	if (dwc->ep0_bounced && dep->number == 0)
+	/*
+	 * NOTICE we don't want to unmap before calling ->complete() if we're
+	 * dealing with a bounced ep0 request. If we unmap it here, we would end
+	 * up overwritting the contents of req->buf and this could confuse the
+	 * gadget driver.
+	 */
+	if (dwc->ep0_bounced && dep->number <= 1) {
 		dwc->ep0_bounced = false;
-	else
-		usb_gadget_unmap_request(&dwc->gadget, &req->request,
-				req->direction);
+		unmap_after_complete = true;
+	} else {
+		usb_gadget_unmap_request(&dwc->gadget,
+				&req->request, req->direction);
+	}
 
 	dev_dbg(dwc->dev, "request %p from %s completed %d/%d ===> %d\n",
 			req, dep->name, req->request.actual,
@@ -273,6 +282,10 @@ void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 	spin_unlock(&dwc->lock);
 	usb_gadget_giveback_request(&dep->endpoint, &req->request);
 	spin_lock(&dwc->lock);
+
+	if (unmap_after_complete)
+		usb_gadget_unmap_request(&dwc->gadget,
+				&req->request, req->direction);
 }
 
 int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned cmd, u32 param)
@@ -1206,7 +1219,7 @@ static int dwc3_gadget_ep_queue(struct usb_ep *ep, struct usb_request *request,
 		goto out;
 	}
 
-	if (WARN(req->dep != dep, "request %p belongs to '%s'\n",
+	if (WARN(req->dep != dep, "request %pK belongs to '%s'\n",
 				request, req->dep->name)) {
 		ret = -EINVAL;
 		goto out;
@@ -1251,7 +1264,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 			dwc3_stop_active_transfer(dwc, dep->number, true);
 			goto out1;
 		}
-		dev_err(dwc->dev, "request %p was not queued to %s\n",
+		dev_err(dwc->dev, "request %pK was not queued to %s\n",
 				request, ep->name);
 		ret = -EINVAL;
 		goto out0;
@@ -1853,7 +1866,7 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 		 * would help. Lets hope that if this occurs, someone
 		 * fixes the root cause instead of looking away :)
 		 */
-		dev_err(dwc->dev, "%s's TRB (%p) still owned by HW\n",
+		dev_err(dwc->dev, "%s's TRB (%pK) still owned by HW\n",
 				dep->name, trb);
 	count = trb->size & DWC3_TRB_SIZE_MASK;
 
@@ -1892,14 +1905,6 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 			s_pkt = 1;
 	}
 
-	/*
-	 * We assume here we will always receive the entire data block
-	 * which we should receive. Meaning, if we program RX to
-	 * receive 4K but we receive only 2K, we assume that's all we
-	 * should receive and we simply bounce the request back to the
-	 * gadget driver for further processing.
-	 */
-	req->request.actual += req->request.length - count;
 	if (s_pkt)
 		return 1;
 	if ((event->status & DEPEVT_STATUS_LST) &&
@@ -1919,6 +1924,7 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep,
 	struct dwc3_trb		*trb;
 	unsigned int		slot;
 	unsigned int		i;
+	int			count = 0;
 	int			ret;
 
 	do {
@@ -1935,6 +1941,8 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep,
 				slot++;
 			slot %= DWC3_TRB_NUM;
 			trb = &dep->trb_pool[slot];
+			count += trb->size & DWC3_TRB_SIZE_MASK;
+
 
 			ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb,
 					event, status);
@@ -1942,6 +1950,14 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep,
 				break;
 		} while (++i < req->request.num_mapped_sgs);
 
+		/*
+		 * We assume here we will always receive the entire data block
+		 * which we should receive. Meaning, if we program RX to
+		 * receive 4K but we receive only 2K, we assume that's all we
+		 * should receive and we simply bounce the request back to the
+		 * gadget driver for further processing.
+		 */
+		req->request.actual += req->request.length - count;
 		dwc3_gadget_giveback(dep, req, status);
 
 		if (ret)
@@ -1965,6 +1981,10 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep,
 		return 1;
 	}
 
+	if (usb_endpoint_xfer_isoc(dep->endpoint.desc))
+		if ((event->status & DEPEVT_STATUS_IOC) &&
+				(trb->ctrl & DWC3_TRB_CTRL_IOC))
+			return 0;
 	return 1;
 }
 
@@ -2838,7 +2858,7 @@ err3:
 	kfree(dwc->setup_buf);
 
 err2:
-	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
 			dwc->ep0_trb, dwc->ep0_trb_addr);
 
 err1:
@@ -2862,7 +2882,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
 
 	kfree(dwc->setup_buf);
 
-	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
 			dwc->ep0_trb, dwc->ep0_trb_addr);
 
 	dma_free_coherent(dwc->dev, sizeof(*dwc->ctrl_req),
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 18ae3eaa8b6f..ccd9694f8e36 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -28,23 +28,23 @@ struct dwc3;
 #define gadget_to_dwc(g)	(container_of(g, struct dwc3, gadget))
 
 /* DEPCFG parameter 1 */
-#define DWC3_DEPCFG_INT_NUM(n)		((n) << 0)
+#define DWC3_DEPCFG_INT_NUM(n)		(((n) & 0x1f) << 0)
 #define DWC3_DEPCFG_XFER_COMPLETE_EN	(1 << 8)
 #define DWC3_DEPCFG_XFER_IN_PROGRESS_EN	(1 << 9)
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	(1 << 10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	(1 << 11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	(1 << 13)
-#define DWC3_DEPCFG_BINTERVAL_M1(n)	((n) << 16)
+#define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	(1 << 24)
-#define DWC3_DEPCFG_EP_NUMBER(n)	((n) << 25)
+#define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
 #define DWC3_DEPCFG_BULK_BASED		(1 << 30)
 #define DWC3_DEPCFG_FIFO_BASED		(1 << 31)
 
 /* DEPCFG parameter 0 */
-#define DWC3_DEPCFG_EP_TYPE(n)		((n) << 1)
-#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	((n) << 3)
-#define DWC3_DEPCFG_FIFO_NUMBER(n)	((n) << 17)
-#define DWC3_DEPCFG_BURST_SIZE(n)	((n) << 22)
+#define DWC3_DEPCFG_EP_TYPE(n)		(((n) & 0x3) << 1)
+#define DWC3_DEPCFG_MAX_PACKET_SIZE(n)	(((n) & 0x7ff) << 3)
+#define DWC3_DEPCFG_FIFO_NUMBER(n)	(((n) & 0x1f) << 17)
+#define DWC3_DEPCFG_BURST_SIZE(n)	(((n) & 0xf) << 22)
 #define DWC3_DEPCFG_DATA_SEQ_NUM(n)	((n) << 26)
 /* This applies for core versions earlier than 1.94a */
 #define DWC3_DEPCFG_IGN_SEQ_NUM		(1 << 31)
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 8b14c2a13ac5..e2641d4dfdd6 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -144,11 +144,16 @@ int config_ep_by_speed(struct usb_gadget *g,
 
 ep_found:
 	/* commit results */
-	_ep->maxpacket = usb_endpoint_maxp(chosen_desc);
+	_ep->maxpacket = usb_endpoint_maxp(chosen_desc) & 0x7ff;
 	_ep->desc = chosen_desc;
 	_ep->comp_desc = NULL;
 	_ep->maxburst = 0;
-	_ep->mult = 0;
+	_ep->mult = 1;
+
+	if (g->speed == USB_SPEED_HIGH && (usb_endpoint_xfer_isoc(_ep->desc) ||
+				usb_endpoint_xfer_int(_ep->desc)))
+		_ep->mult = ((usb_endpoint_maxp(_ep->desc) & 0x1800) >> 11) + 1;
+
 	if (!want_comp_desc)
 		return 0;
 
@@ -165,7 +170,7 @@ ep_found:
 		switch (usb_endpoint_type(_ep->desc)) {
 		case USB_ENDPOINT_XFER_ISOC:
 			/* mult: bits 1:0 of bmAttributes */
-			_ep->mult = comp_desc->bmAttributes & 0x3;
+			_ep->mult = (comp_desc->bmAttributes & 0x3) + 1;
 		case USB_ENDPOINT_XFER_BULK:
 		case USB_ENDPOINT_XFER_INT:
 			_ep->maxburst = comp_desc->bMaxBurst + 1;
@@ -1596,9 +1601,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		value = min(w_length, (u16) 1);
 		break;
 
-	/* function drivers must handle get/set altsetting; if there's
-	 * no get() method, we know only altsetting zero works.
-	 */
+	/* function drivers must handle get/set altsetting */
 	case USB_REQ_SET_INTERFACE:
 		if (ctrl->bRequestType != USB_RECIP_INTERFACE)
 			goto unknown;
@@ -1607,7 +1610,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		f = cdev->config->interface[intf];
 		if (!f)
 			break;
-		if (w_value && !f->set_alt)
+
+		/*
+		 * If there's no get_alt() method, we know only altsetting zero
+		 * works. There is no need to check if set_alt() is not NULL
+		 * as we check this in usb_add_function().
+		 */
+		if (w_value && !f->get_alt)
 			break;
 		value = f->set_alt(f, w_index, w_value);
 		if (value == USB_GADGET_DELAYED_STATUS) {
diff --git a/drivers/usb/gadget/function/f_acm.c b/drivers/usb/gadget/function/f_acm.c
index 2fa1e80a3ce7..67e474b13fca 100644
--- a/drivers/usb/gadget/function/f_acm.c
+++ b/drivers/usb/gadget/function/f_acm.c
@@ -535,13 +535,15 @@ static int acm_notify_serial_state(struct f_acm *acm)
 {
 	struct usb_composite_dev *cdev = acm->port.func.config->cdev;
 	int			status;
+	__le16			serial_state;
 
 	spin_lock(&acm->lock);
 	if (acm->notify_req) {
 		dev_dbg(&cdev->gadget->dev, "acm ttyGS%d serial state %04x\n",
 			acm->port_num, acm->serial_state);
+		serial_state = cpu_to_le16(acm->serial_state);
 		status = acm_cdc_notify(acm, USB_CDC_NOTIFY_SERIAL_STATE,
-				0, &acm->serial_state, sizeof(acm->serial_state));
+				0, &serial_state, sizeof(acm->serial_state));
 	} else {
 		acm->pending = true;
 		status = 0;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index cf43e9e18368..732e6ed5d7b4 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -646,24 +646,23 @@ static void ffs_user_copy_worker(struct work_struct *work)
 						   work);
 	int ret = io_data->req->status ? io_data->req->status :
 					 io_data->req->actual;
+	bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD;
 
 	if (io_data->read && ret > 0) {
 		use_mm(io_data->mm);
 		ret = copy_to_iter(io_data->buf, ret, &io_data->data);
-		if (iov_iter_count(&io_data->data))
+		if (ret != io_data->req->actual && iov_iter_count(&io_data->data))
 			ret = -EFAULT;
 		unuse_mm(io_data->mm);
 	}
 
 	io_data->kiocb->ki_complete(io_data->kiocb, ret, ret);
 
-	if (io_data->ffs->ffs_eventfd &&
-	    !(io_data->kiocb->ki_flags & IOCB_EVENTFD))
+	if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
 		eventfd_signal(io_data->ffs->ffs_eventfd, 1);
 
 	usb_ep_free_request(io_data->ep, io_data->req);
 
-	io_data->kiocb->private = NULL;
 	if (io_data->read)
 		kfree(io_data->to_free);
 	kfree(io_data->buf);
@@ -1644,11 +1643,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 	spin_lock_irqsave(&func->ffs->eps_lock, flags);
 	do {
 		struct usb_endpoint_descriptor *ds;
+		struct usb_ss_ep_comp_descriptor *comp_desc = NULL;
+		int needs_comp_desc = false;
 		int desc_idx;
 
-		if (ffs->gadget->speed == USB_SPEED_SUPER)
+		if (ffs->gadget->speed == USB_SPEED_SUPER) {
 			desc_idx = 2;
-		else if (ffs->gadget->speed == USB_SPEED_HIGH)
+			needs_comp_desc = true;
+		} else if (ffs->gadget->speed == USB_SPEED_HIGH)
 			desc_idx = 1;
 		else
 			desc_idx = 0;
@@ -1665,6 +1667,14 @@ static int ffs_func_eps_enable(struct ffs_function *func)
 
 		ep->ep->driver_data = ep;
 		ep->ep->desc = ds;
+
+		if (needs_comp_desc) {
+			comp_desc = (struct usb_ss_ep_comp_descriptor *)(ds +
+					USB_DT_ENDPOINT_SIZE);
+			ep->ep->maxburst = comp_desc->bMaxBurst + 1;
+			ep->ep->comp_desc = comp_desc;
+		}
+
 		ret = usb_ep_enable(ep->ep);
 		if (likely(!ret)) {
 			epfile->ep = ep;
@@ -2080,6 +2090,8 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 		if (len < sizeof(*d) || h->interface >= ffs->interfaces_count)
 			return -EINVAL;
 		length = le32_to_cpu(d->dwSize);
+		if (len < length)
+			return -EINVAL;
 		type = le32_to_cpu(d->dwPropertyDataType);
 		if (type < USB_EXT_PROP_UNICODE ||
 		    type > USB_EXT_PROP_UNICODE_MULTI) {
@@ -2088,6 +2100,11 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 			return -EINVAL;
 		}
 		pnl = le16_to_cpu(d->wPropertyNameLength);
+		if (length < 14 + pnl) {
+			pr_vdebug("invalid os descriptor length: %d pnl:%d (descriptor %d)\n",
+				  length, pnl, type);
+			return -EINVAL;
+		}
 		pdl = le32_to_cpu(*(u32 *)((u8 *)data + 10 + pnl));
 		if (length != 14 + pnl + pdl) {
 			pr_vdebug("invalid os descriptor length: %d pnl:%d pdl:%d (descriptor %d)\n",
@@ -2172,6 +2189,9 @@ static int __ffs_data_got_descs(struct ffs_data *ffs,
 		}
 	}
 	if (flags & (1 << i)) {
+		if (len < 4) {
+			goto error;
+		}
 		os_descs_count = get_unaligned_le32(data);
 		data += 4;
 		len -= 4;
@@ -2244,7 +2264,8 @@ static int __ffs_data_got_strings(struct ffs_data *ffs,
 
 	ENTER();
 
-	if (unlikely(get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
+	if (unlikely(len < 16 ||
+		     get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
 		     get_unaligned_le32(data + 4) != len))
 		goto error;
 	str_count  = get_unaligned_le32(data + 8);
@@ -2741,6 +2762,7 @@ static int _ffs_func_bind(struct usb_configuration *c,
 		func->ffs->ss_descs_count;
 
 	int fs_len, hs_len, ss_len, ret, i;
+	struct ffs_ep *eps_ptr;
 
 	/* Make it a single chunk, less management later on */
 	vla_group(d);
@@ -2789,12 +2811,9 @@ static int _ffs_func_bind(struct usb_configuration *c,
 	       ffs->raw_descs_length);
 
 	memset(vla_ptr(vlabuf, d, inums), 0xff, d_inums__sz);
-	for (ret = ffs->eps_count; ret; --ret) {
-		struct ffs_ep *ptr;
-
-		ptr = vla_ptr(vlabuf, d, eps);
-		ptr[ret].num = -1;
-	}
+	eps_ptr = vla_ptr(vlabuf, d, eps);
+	for (i = 0; i < ffs->eps_count; i++)
+		eps_ptr[i].num = -1;
 
 	/* Save pointers
 	 * d_eps == vlabuf, func->eps used to kfree vlabuf later
@@ -3444,6 +3463,7 @@ static void ffs_closed(struct ffs_data *ffs)
 {
 	struct ffs_dev *ffs_obj;
 	struct f_fs_opts *opts;
+	struct config_item *ci;
 
 	ENTER();
 	ffs_dev_lock();
@@ -3467,8 +3487,11 @@ static void ffs_closed(struct ffs_data *ffs)
 	    || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount))
 		goto done;
 
-	unregister_gadget_item(ffs_obj->opts->
-			       func_inst.group.cg_item.ci_parent->ci_parent);
+	ci = opts->func_inst.group.cg_item.ci_parent->ci_parent;
+	ffs_dev_unlock();
+
+	unregister_gadget_item(ci);
+	return;
 done:
 	ffs_dev_unlock();
 }
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 99285b416308..ee579ba2b59e 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -539,7 +539,7 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		}
 		status = usb_ep_enable(hidg->out_ep);
 		if (status < 0) {
-			ERROR(cdev, "Enable IN endpoint FAILED!\n");
+			ERROR(cdev, "Enable OUT endpoint FAILED!\n");
 			goto fail;
 		}
 		hidg->out_ep->driver_data = hidg;
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 223ccf89d226..a069726da72a 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -399,7 +399,11 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep)
 /* Caller must hold fsg->lock */
 static void wakeup_thread(struct fsg_common *common)
 {
-	smp_wmb();	/* ensure the write of bh->state is complete */
+	/*
+	 * Ensure the reading of thread_wakeup_needed
+	 * and the writing of bh->state are completed
+	 */
+	smp_mb();
 	/* Tell the main thread that something has happened */
 	common->thread_wakeup_needed = 1;
 	if (common->thread_task)
@@ -630,7 +634,12 @@ static int sleep_thread(struct fsg_common *common, bool can_freeze)
 	}
 	__set_current_state(TASK_RUNNING);
 	common->thread_wakeup_needed = 0;
-	smp_rmb();	/* ensure the latest bh->state is visible */
+
+	/*
+	 * Ensure the writing of thread_wakeup_needed
+	 * and the reading of bh->state are completed
+	 */
+	smp_mb();
 	return rc;
 }
 
@@ -2977,25 +2986,6 @@ void fsg_common_set_inquiry_string(struct fsg_common *common, const char *vn,
 }
 EXPORT_SYMBOL_GPL(fsg_common_set_inquiry_string);
 
-int fsg_common_run_thread(struct fsg_common *common)
-{
-	common->state = FSG_STATE_IDLE;
-	/* Tell the thread to start working */
-	common->thread_task =
-		kthread_create(fsg_main_thread, common, "file-storage");
-	if (IS_ERR(common->thread_task)) {
-		common->state = FSG_STATE_TERMINATED;
-		return PTR_ERR(common->thread_task);
-	}
-
-	DBG(common, "I/O thread pid: %d\n", task_pid_nr(common->thread_task));
-
-	wake_up_process(common->thread_task);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(fsg_common_run_thread);
-
 static void fsg_common_release(struct kref *ref)
 {
 	struct fsg_common *common = container_of(ref, struct fsg_common, ref);
@@ -3005,6 +2995,7 @@ static void fsg_common_release(struct kref *ref)
 	if (common->state != FSG_STATE_TERMINATED) {
 		raise_exception(common, FSG_STATE_EXIT);
 		wait_for_completion(&common->thread_notifier);
+		common->thread_task = NULL;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(common->luns); ++i) {
@@ -3050,9 +3041,21 @@ static int fsg_bind(struct usb_configuration *c, struct usb_function *f)
 		if (ret)
 			return ret;
 		fsg_common_set_inquiry_string(fsg->common, NULL, NULL);
-		ret = fsg_common_run_thread(fsg->common);
-		if (ret)
+	}
+
+	if (!common->thread_task) {
+		common->state = FSG_STATE_IDLE;
+		common->thread_task =
+			kthread_create(fsg_main_thread, common, "file-storage");
+		if (IS_ERR(common->thread_task)) {
+			int ret = PTR_ERR(common->thread_task);
+			common->thread_task = NULL;
+			common->state = FSG_STATE_TERMINATED;
 			return ret;
+		}
+		DBG(common, "I/O thread pid: %d\n",
+		    task_pid_nr(common->thread_task));
+		wake_up_process(common->thread_task);
 	}
 
 	fsg->gadget = gadget;
diff --git a/drivers/usb/gadget/function/f_mass_storage.h b/drivers/usb/gadget/function/f_mass_storage.h
index 445df6775609..b6a9918eaefb 100644
--- a/drivers/usb/gadget/function/f_mass_storage.h
+++ b/drivers/usb/gadget/function/f_mass_storage.h
@@ -153,8 +153,6 @@ int fsg_common_create_luns(struct fsg_common *common, struct fsg_config *cfg);
 void fsg_common_set_inquiry_string(struct fsg_common *common, const char *vn,
 				   const char *pn);
 
-int fsg_common_run_thread(struct fsg_common *common);
-
 void fsg_config_from_params(struct fsg_config *cfg,
 			    const struct fsg_module_parameters *params,
 			    unsigned int fsg_num_buffers);
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 898a570319f1..af60cc3714c1 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -361,7 +361,9 @@ static int f_midi_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 	/* allocate a bunch of read buffers and queue them all at once. */
 	for (i = 0; i < midi->qlen && err == 0; i++) {
 		struct usb_request *req =
-			midi_alloc_ep_req(midi->out_ep, midi->buflen);
+			midi_alloc_ep_req(midi->out_ep,
+				max_t(unsigned, midi->buflen,
+					bulk_out_desc.wMaxPacketSize));
 		if (req == NULL)
 			return -ENOMEM;
 
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 044ca79d3cb5..12064d3bddf6 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -1079,13 +1079,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
 	if (!agdev->out_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		goto err;
+		return ret;
 	}
 
 	agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc);
 	if (!agdev->in_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		goto err;
+		return ret;
 	}
 
 	uac2->p_prm.uac2 = uac2;
@@ -1102,7 +1102,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 
 	ret = usb_assign_descriptors(fn, fs_audio_desc, hs_audio_desc, NULL);
 	if (ret)
-		goto err;
+		return ret;
 
 	prm = &agdev->uac2.c_prm;
 	prm->max_psize = hs_epout_desc.wMaxPacketSize;
@@ -1117,19 +1117,19 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	prm->rbuf = kzalloc(prm->max_psize * USB_XFERS, GFP_KERNEL);
 	if (!prm->rbuf) {
 		prm->max_psize = 0;
-		goto err_free_descs;
+		goto err;
 	}
 
 	ret = alsa_uac2_init(agdev);
 	if (ret)
-		goto err_free_descs;
+		goto err;
 	return 0;
 
-err_free_descs:
-	usb_free_all_descriptors(fn);
 err:
 	kfree(agdev->uac2.p_prm.rbuf);
 	kfree(agdev->uac2.c_prm.rbuf);
+err_free_descs:
+	usb_free_all_descriptors(fn);
 	return -EINVAL;
 }
 
@@ -1291,6 +1291,7 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 
 	if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
 		struct cntrl_cur_lay3 c;
+		memset(&c, 0, sizeof(struct cntrl_cur_lay3));
 
 		if (entity_id == USB_IN_CLK_ID)
 			c.dCUR = p_srate;
diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 29b41b5dee04..c7689d05356c 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -625,7 +625,7 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	uvc_ss_streaming_comp.bMaxBurst = opts->streaming_maxburst;
 	uvc_ss_streaming_comp.wBytesPerInterval =
 		cpu_to_le16(max_packet_size * max_packet_mult *
-			    opts->streaming_maxburst);
+			    (opts->streaming_maxburst + 1));
 
 	/* Allocate endpoints. */
 	ep = usb_ep_autoconfig(cdev->gadget, &uvc_control_ep);
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 6554322af2c1..7413f89660f7 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -594,13 +594,6 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 
 	req->length = length;
 
-	/* throttle high/super speed IRQ rate back slightly */
-	if (gadget_is_dualspeed(dev->gadget))
-		req->no_interrupt = (dev->gadget->speed == USB_SPEED_HIGH ||
-				     dev->gadget->speed == USB_SPEED_SUPER)
-			? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
-			: 0;
-
 	retval = usb_ep_queue(in, req, GFP_ATOMIC);
 	switch (retval) {
 	default:
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 3d0d5d94a62f..0f01c04d7cbd 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -243,7 +243,7 @@ uvc_video_alloc_requests(struct uvc_video *video)
 
 	req_size = video->ep->maxpacket
 		 * max_t(unsigned int, video->ep->maxburst, 1)
-		 * (video->ep->mult + 1);
+		 * (video->ep->mult);
 
 	for (i = 0; i < UVC_NUM_REQUESTS; ++i) {
 		video->req_buffer[i] = kmalloc(req_size, GFP_KERNEL);
diff --git a/drivers/usb/gadget/legacy/acm_ms.c b/drivers/usb/gadget/legacy/acm_ms.c
index 4b158e2d1e57..64b2cbb0bc6b 100644
--- a/drivers/usb/gadget/legacy/acm_ms.c
+++ b/drivers/usb/gadget/legacy/acm_ms.c
@@ -133,10 +133,6 @@ static int acm_ms_do_config(struct usb_configuration *c)
 	if (status < 0)
 		goto put_msg;
 
-	status = fsg_common_run_thread(opts->common);
-	if (status)
-		goto remove_acm;
-
 	status = usb_add_function(c, f_msg);
 	if (status)
 		goto remove_acm;
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index f454c7af489c..43ce2cfcdb4d 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -541,7 +541,7 @@ static ssize_t ep_aio(struct kiocb *iocb,
 	 */
 	spin_lock_irq(&epdata->dev->lock);
 	value = -ENODEV;
-	if (unlikely(epdata->ep))
+	if (unlikely(epdata->ep == NULL))
 		goto fail;
 
 	req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC);
@@ -937,8 +937,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr)
 			struct usb_ep		*ep = dev->gadget->ep0;
 			struct usb_request	*req = dev->req;
 
-			if ((retval = setup_req (ep, req, 0)) == 0)
-				retval = usb_ep_queue (ep, req, GFP_ATOMIC);
+			if ((retval = setup_req (ep, req, 0)) == 0) {
+				spin_unlock_irq (&dev->lock);
+				retval = usb_ep_queue (ep, req, GFP_KERNEL);
+				spin_lock_irq (&dev->lock);
+			}
 			dev->state = STATE_DEV_CONNECTED;
 
 			/* assume that was SET_CONFIGURATION */
@@ -1122,7 +1125,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 	/* data and/or status stage for control request */
 	} else if (dev->state == STATE_DEV_SETUP) {
 
-		/* IN DATA+STATUS caller makes len <= wLength */
+		len = min_t(size_t, len, dev->setup_wLength);
 		if (dev->setup_in) {
 			retval = setup_req (dev->gadget->ep0, dev->req, len);
 			if (retval == 0) {
@@ -1456,8 +1459,11 @@ delegate:
 							w_length);
 				if (value < 0)
 					break;
+
+				spin_unlock (&dev->lock);
 				value = usb_ep_queue (gadget->ep0, dev->req,
-							GFP_ATOMIC);
+							GFP_KERNEL);
+				spin_lock (&dev->lock);
 				if (value < 0) {
 					clean_req (gadget->ep0, dev->req);
 					break;
@@ -1480,11 +1486,14 @@ delegate:
 	if (value >= 0 && dev->state != STATE_DEV_SETUP) {
 		req->length = value;
 		req->zero = value < w_length;
-		value = usb_ep_queue (gadget->ep0, req, GFP_ATOMIC);
+
+		spin_unlock (&dev->lock);
+		value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL);
 		if (value < 0) {
 			DBG (dev, "ep_queue --> %d\n", value);
 			req->status = 0;
 		}
+		return value;
 	}
 
 	/* device stalls when value < 0 */
@@ -1667,9 +1676,10 @@ static void
 gadgetfs_suspend (struct usb_gadget *gadget)
 {
 	struct dev_data		*dev = get_gadget_data (gadget);
+	unsigned long		flags;
 
 	INFO (dev, "suspended from state %d\n", dev->state);
-	spin_lock (&dev->lock);
+	spin_lock_irqsave(&dev->lock, flags);
 	switch (dev->state) {
 	case STATE_DEV_SETUP:		// VERY odd... host died??
 	case STATE_DEV_CONNECTED:
@@ -1680,7 +1690,7 @@ gadgetfs_suspend (struct usb_gadget *gadget)
 	default:
 		break;
 	}
-	spin_unlock (&dev->lock);
+	spin_unlock_irqrestore(&dev->lock, flags);
 }
 
 static struct usb_gadget_driver gadgetfs_driver = {
@@ -1746,10 +1756,12 @@ static struct usb_gadget_driver probe_driver = {
  * such as configuration notifications.
  */
 
-static int is_valid_config (struct usb_config_descriptor *config)
+static int is_valid_config(struct usb_config_descriptor *config,
+		unsigned int total)
 {
 	return config->bDescriptorType == USB_DT_CONFIG
 		&& config->bLength == USB_DT_CONFIG_SIZE
+		&& total >= USB_DT_CONFIG_SIZE
 		&& config->bConfigurationValue != 0
 		&& (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0
 		&& (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0;
@@ -1774,7 +1786,8 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 	}
 	spin_unlock_irq(&dev->lock);
 
-	if (len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4))
+	if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) ||
+	    (len > PAGE_SIZE * 4))
 		return -EINVAL;
 
 	/* we might need to change message format someday */
@@ -1798,7 +1811,8 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 	/* full or low speed config */
 	dev->config = (void *) kbuf;
 	total = le16_to_cpu(dev->config->wTotalLength);
-	if (!is_valid_config (dev->config) || total >= length)
+	if (!is_valid_config(dev->config, total) ||
+			total > length - USB_DT_DEVICE_SIZE)
 		goto fail;
 	kbuf += total;
 	length -= total;
@@ -1807,10 +1821,13 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 	if (kbuf [1] == USB_DT_CONFIG) {
 		dev->hs_config = (void *) kbuf;
 		total = le16_to_cpu(dev->hs_config->wTotalLength);
-		if (!is_valid_config (dev->hs_config) || total >= length)
+		if (!is_valid_config(dev->hs_config, total) ||
+				total > length - USB_DT_DEVICE_SIZE)
 			goto fail;
 		kbuf += total;
 		length -= total;
+	} else {
+		dev->hs_config = NULL;
 	}
 
 	/* could support multiple configs, using another encoding! */
diff --git a/drivers/usb/gadget/legacy/mass_storage.c b/drivers/usb/gadget/legacy/mass_storage.c
index bda3c519110f..99aa22c81770 100644
--- a/drivers/usb/gadget/legacy/mass_storage.c
+++ b/drivers/usb/gadget/legacy/mass_storage.c
@@ -132,10 +132,6 @@ static int msg_do_config(struct usb_configuration *c)
 	if (IS_ERR(f_msg))
 		return PTR_ERR(f_msg);
 
-	ret = fsg_common_run_thread(opts->common);
-	if (ret)
-		goto put_func;
-
 	ret = usb_add_function(c, f_msg);
 	if (ret)
 		goto put_func;
diff --git a/drivers/usb/gadget/legacy/multi.c b/drivers/usb/gadget/legacy/multi.c
index 4fe794ddcd49..09c7c28f32f7 100644
--- a/drivers/usb/gadget/legacy/multi.c
+++ b/drivers/usb/gadget/legacy/multi.c
@@ -137,7 +137,6 @@ static struct usb_function *f_msg_rndis;
 
 static int rndis_do_config(struct usb_configuration *c)
 {
-	struct fsg_opts *fsg_opts;
 	int ret;
 
 	if (gadget_is_otg(c->cdev->gadget)) {
@@ -169,11 +168,6 @@ static int rndis_do_config(struct usb_configuration *c)
 		goto err_fsg;
 	}
 
-	fsg_opts = fsg_opts_from_func_inst(fi_msg);
-	ret = fsg_common_run_thread(fsg_opts->common);
-	if (ret)
-		goto err_run;
-
 	ret = usb_add_function(c, f_msg_rndis);
 	if (ret)
 		goto err_run;
@@ -225,7 +219,6 @@ static struct usb_function *f_msg_multi;
 
 static int cdc_do_config(struct usb_configuration *c)
 {
-	struct fsg_opts *fsg_opts;
 	int ret;
 
 	if (gadget_is_otg(c->cdev->gadget)) {
@@ -258,11 +251,6 @@ static int cdc_do_config(struct usb_configuration *c)
 		goto err_fsg;
 	}
 
-	fsg_opts = fsg_opts_from_func_inst(fi_msg);
-	ret = fsg_common_run_thread(fsg_opts->common);
-	if (ret)
-		goto err_run;
-
 	ret = usb_add_function(c, f_msg_multi);
 	if (ret)
 		goto err_run;
diff --git a/drivers/usb/gadget/legacy/nokia.c b/drivers/usb/gadget/legacy/nokia.c
index 8b3f6fb1825d..05d3f79e768d 100644
--- a/drivers/usb/gadget/legacy/nokia.c
+++ b/drivers/usb/gadget/legacy/nokia.c
@@ -152,7 +152,6 @@ static int nokia_bind_config(struct usb_configuration *c)
 	struct usb_function *f_ecm;
 	struct usb_function *f_obex2 = NULL;
 	struct usb_function *f_msg;
-	struct fsg_opts *fsg_opts;
 	int status = 0;
 	int obex1_stat = -1;
 	int obex2_stat = -1;
@@ -222,12 +221,6 @@ static int nokia_bind_config(struct usb_configuration *c)
 		goto err_ecm;
 	}
 
-	fsg_opts = fsg_opts_from_func_inst(fi_msg);
-
-	status = fsg_common_run_thread(fsg_opts->common);
-	if (status)
-		goto err_msg;
-
 	status = usb_add_function(c, f_msg);
 	if (status)
 		goto err_msg;
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index dde44450dfa9..64f404a1a072 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -330,7 +330,7 @@ static void nuke(struct dummy *dum, struct dummy_ep *ep)
 /* caller must hold lock */
 static void stop_activity(struct dummy *dum)
 {
-	struct dummy_ep	*ep;
+	int i;
 
 	/* prevent any more requests */
 	dum->address = 0;
@@ -338,8 +338,8 @@ static void stop_activity(struct dummy *dum)
 	/* The timer is left running so that outstanding URBs can fail */
 
 	/* nuke any pending requests first, so driver i/o is quiesced */
-	list_for_each_entry(ep, &dum->gadget.ep_list, ep.ep_list)
-		nuke(dum, ep);
+	for (i = 0; i < DUMMY_ENDPOINTS; ++i)
+		nuke(dum, &dum->ep[i]);
 
 	/* driver now does any non-usb quiescing necessary */
 }
@@ -442,23 +442,16 @@ static void set_link_state(struct dummy_hcd *dum_hcd)
 		/* Report reset and disconnect events to the driver */
 		if (dum->driver && (disconnect || reset)) {
 			stop_activity(dum);
-			spin_unlock(&dum->lock);
 			if (reset)
 				usb_gadget_udc_reset(&dum->gadget, dum->driver);
 			else
 				dum->driver->disconnect(&dum->gadget);
-			spin_lock(&dum->lock);
 		}
 	} else if (dum_hcd->active != dum_hcd->old_active) {
-		if (dum_hcd->old_active && dum->driver->suspend) {
-			spin_unlock(&dum->lock);
+		if (dum_hcd->old_active && dum->driver->suspend)
 			dum->driver->suspend(&dum->gadget);
-			spin_lock(&dum->lock);
-		} else if (!dum_hcd->old_active &&  dum->driver->resume) {
-			spin_unlock(&dum->lock);
+		else if (!dum_hcd->old_active &&  dum->driver->resume)
 			dum->driver->resume(&dum->gadget);
-			spin_lock(&dum->lock);
-		}
 	}
 
 	dum_hcd->old_status = dum_hcd->port_status;
@@ -985,7 +978,9 @@ 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;
 
+	spin_lock_irq(&dum->lock);
 	dum->driver = NULL;
+	spin_unlock_irq(&dum->lock);
 
 	return 0;
 }
@@ -1033,6 +1028,8 @@ static int dummy_udc_probe(struct platform_device *pdev)
 	int		rc;
 
 	dum = *((void **)dev_get_platdata(&pdev->dev));
+	/* Clear usb_gadget region for new registration to udc-core */
+	memzero_explicit(&dum->gadget, sizeof(struct usb_gadget));
 	dum->gadget.name = gadget_name;
 	dum->gadget.ops = &dummy_ops;
 	dum->gadget.max_speed = USB_SPEED_SUPER;
@@ -2009,7 +2006,7 @@ ss_hub_descriptor(struct usb_hub_descriptor *desc)
 			HUB_CHAR_COMMON_OCPM);
 	desc->bNbrPorts = 1;
 	desc->u.ss.bHubHdrDecLat = 0x04; /* Worst case: 0.4 micro sec*/
-	desc->u.ss.DeviceRemovable = 0xffff;
+	desc->u.ss.DeviceRemovable = 0;
 }
 
 static inline void hub_descriptor(struct usb_hub_descriptor *desc)
@@ -2021,8 +2018,8 @@ static inline void hub_descriptor(struct usb_hub_descriptor *desc)
 			HUB_CHAR_INDV_PORT_LPSM |
 			HUB_CHAR_COMMON_OCPM);
 	desc->bNbrPorts = 1;
-	desc->u.hs.DeviceRemovable[0] = 0xff;
-	desc->u.hs.DeviceRemovable[1] = 0xff;
+	desc->u.hs.DeviceRemovable[0] = 0;
+	desc->u.hs.DeviceRemovable[1] = 0xff;	/* PortPwrCtrlMask */
 }
 
 static int dummy_hub_control(
diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c
index 5fb6f8b4f0b4..b38a33584d4a 100644
--- a/drivers/usb/gadget/udc/fsl_qe_udc.c
+++ b/drivers/usb/gadget/udc/fsl_qe_udc.c
@@ -1878,11 +1878,8 @@ static int qe_get_frame(struct usb_gadget *gadget)
 
 	tmp = in_be16(&udc->usb_param->frame_n);
 	if (tmp & 0x8000)
-		tmp = tmp & 0x07ff;
-	else
-		tmp = -EINVAL;
-
-	return (int)tmp;
+		return tmp & 0x07ff;
+	return -EINVAL;
 }
 
 static int fsl_qe_start(struct usb_gadget *gadget,
@@ -2053,7 +2050,7 @@ static void setup_received_handle(struct qe_udc *udc,
 			struct qe_ep *ep;
 
 			if (wValue != 0 || wLength != 0
-				|| pipe > USB_MAX_ENDPOINTS)
+				|| pipe >= USB_MAX_ENDPOINTS)
 				break;
 			ep = &udc->eps[pipe];
 
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index aab5221d6c2e..aac0ce8aeb0b 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1249,6 +1249,12 @@ static const struct usb_gadget_ops fsl_gadget_ops = {
 	.udc_stop = fsl_udc_stop,
 };
 
+/*
+ * Empty complete function used by this driver to fill in the req->complete
+ * field when creating a request since the complete field is mandatory.
+ */
+static void fsl_noop_complete(struct usb_ep *ep, struct usb_request *req) { }
+
 /* Set protocol stall on ep0, protocol stall will automatically be cleared
    on new transaction */
 static void ep0stall(struct fsl_udc *udc)
@@ -1283,7 +1289,7 @@ static int ep0_prime_status(struct fsl_udc *udc, int direction)
 	req->req.length = 0;
 	req->req.status = -EINPROGRESS;
 	req->req.actual = 0;
-	req->req.complete = NULL;
+	req->req.complete = fsl_noop_complete;
 	req->dtd_count = 0;
 
 	ret = usb_gadget_map_request(&ep->udc->gadget, &req->req, ep_is_in(ep));
@@ -1366,7 +1372,7 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value,
 	req->req.length = 2;
 	req->req.status = -EINPROGRESS;
 	req->req.actual = 0;
-	req->req.complete = NULL;
+	req->req.complete = fsl_noop_complete;
 	req->dtd_count = 0;
 
 	ret = usb_gadget_map_request(&ep->udc->gadget, &req->req, ep_is_in(ep));
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 6706aef907f4..a47de8c31ce9 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -2425,11 +2425,8 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver)
 		nuke(&dev->ep[i]);
 
 	/* report disconnect; the driver is already quiesced */
-	if (driver) {
-		spin_unlock(&dev->lock);
+	if (driver)
 		driver->disconnect(&dev->gadget);
-		spin_lock(&dev->lock);
-	}
 
 	usb_reinit(dev);
 }
@@ -3275,8 +3272,6 @@ next_endpoints:
 		BIT(PCI_RETRY_ABORT_INTERRUPT))
 
 static void handle_stat1_irqs(struct net2280 *dev, u32 stat)
-__releases(dev->lock)
-__acquires(dev->lock)
 {
 	struct net2280_ep	*ep;
 	u32			tmp, num, mask, scratch;
@@ -3317,14 +3312,12 @@ __acquires(dev->lock)
 			if (disconnect || reset) {
 				stop_activity(dev, dev->driver);
 				ep0_start(dev);
-				spin_unlock(&dev->lock);
 				if (reset)
 					usb_gadget_udc_reset
 						(&dev->gadget, dev->driver);
 				else
 					(dev->driver->disconnect)
 						(&dev->gadget);
-				spin_lock(&dev->lock);
 				return;
 			}
 		}
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index f660afba715d..89f7cd66f5e6 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -71,7 +71,7 @@ int usb_gadget_map_request(struct usb_gadget *gadget,
 		mapped = dma_map_sg(dev, req->sg, req->num_sgs,
 				is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		if (mapped == 0) {
-			dev_err(&gadget->dev, "failed to map SGs\n");
+			dev_err(dev, "failed to map SGs\n");
 			return -EFAULT;
 		}
 
diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c
index df538fd10aa4..46f5354c534d 100644
--- a/drivers/usb/host/ehci-exynos.c
+++ b/drivers/usb/host/ehci-exynos.c
@@ -77,10 +77,12 @@ static int exynos_ehci_get_phy(struct device *dev,
 		if (IS_ERR(phy)) {
 			ret = PTR_ERR(phy);
 			if (ret == -EPROBE_DEFER) {
+				of_node_put(child);
 				return ret;
 			} else if (ret != -ENOSYS && ret != -ENODEV) {
 				dev_err(dev,
 					"Error retrieving usb2 phy: %d\n", ret);
+				of_node_put(child);
 				return ret;
 			}
 		}
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 48c92bf78bd0..f7661d9750fd 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -332,11 +332,11 @@ static void ehci_turn_off_all_ports(struct ehci_hcd *ehci)
 	int	port = HCS_N_PORTS(ehci->hcs_params);
 
 	while (port--) {
-		ehci_writel(ehci, PORT_RWC_BITS,
-				&ehci->regs->port_status[port]);
 		spin_unlock_irq(&ehci->lock);
 		ehci_port_power(ehci, port, false);
 		spin_lock_irq(&ehci->lock);
+		ehci_writel(ehci, PORT_RWC_BITS,
+				&ehci->regs->port_status[port]);
 	}
 }
 
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index 4031b372008e..c1c1024a054c 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -89,7 +89,7 @@ static int tegra_reset_usb_controller(struct platform_device *pdev)
 	if (!usb1_reset_attempted) {
 		struct reset_control *usb1_reset;
 
-		usb1_reset = of_reset_control_get(phy_np, "usb");
+		usb1_reset = of_reset_control_get(phy_np, "utmi-pads");
 		if (IS_ERR(usb1_reset)) {
 			dev_warn(&pdev->dev,
 				 "can't get utmi-pads reset from the PHY\n");
diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c
index 2cd105be7319..6865b919403f 100644
--- a/drivers/usb/host/ohci-exynos.c
+++ b/drivers/usb/host/ohci-exynos.c
@@ -66,10 +66,12 @@ static int exynos_ohci_get_phy(struct device *dev,
 		if (IS_ERR(phy)) {
 			ret = PTR_ERR(phy);
 			if (ret == -EPROBE_DEFER) {
+				of_node_put(child);
 				return ret;
 			} else if (ret != -ENOSYS && ret != -ENODEV) {
 				dev_err(dev,
 					"Error retrieving usb2 phy: %d\n", ret);
+				of_node_put(child);
 				return ret;
 			}
 		}
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 760cb57e954e..9d1192aea9d0 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -72,7 +72,7 @@
 static const char	hcd_name [] = "ohci_hcd";
 
 #define	STATECHANGE_DELAY	msecs_to_jiffies(300)
-#define	IO_WATCHDOG_DELAY	msecs_to_jiffies(250)
+#define	IO_WATCHDOG_DELAY	msecs_to_jiffies(275)
 
 #include "ohci.h"
 #include "pci-quirks.h"
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index d029bbe9eb36..641fed609911 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -183,7 +183,6 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
 {
 	int	branch;
 
-	ed->state = ED_OPER;
 	ed->ed_prev = NULL;
 	ed->ed_next = NULL;
 	ed->hwNextED = 0;
@@ -259,6 +258,8 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed)
 	/* the HC may not see the schedule updates yet, but if it does
 	 * then they'll be properly ordered.
 	 */
+
+	ed->state = ED_OPER;
 	return 0;
 }
 
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index f9400564cb72..1fc6f478a02c 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -89,6 +89,7 @@ enum amd_chipset_gen {
 	AMD_CHIPSET_HUDSON2,
 	AMD_CHIPSET_BOLTON,
 	AMD_CHIPSET_YANGTZE,
+	AMD_CHIPSET_TAISHAN,
 	AMD_CHIPSET_UNKNOWN,
 };
 
@@ -136,20 +137,26 @@ static int amd_chipset_sb_type_init(struct amd_chipset_info *pinfo)
 		pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
 				PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL);
 
-		if (!pinfo->smbus_dev) {
-			pinfo->sb_type.gen = NOT_AMD_CHIPSET;
-			return 0;
+		if (pinfo->smbus_dev) {
+			rev = pinfo->smbus_dev->revision;
+			if (rev >= 0x11 && rev <= 0x14)
+				pinfo->sb_type.gen = AMD_CHIPSET_HUDSON2;
+			else if (rev >= 0x15 && rev <= 0x18)
+				pinfo->sb_type.gen = AMD_CHIPSET_BOLTON;
+			else if (rev >= 0x39 && rev <= 0x3a)
+				pinfo->sb_type.gen = AMD_CHIPSET_YANGTZE;
+		} else {
+			pinfo->smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
+							  0x145c, NULL);
+			if (pinfo->smbus_dev) {
+				rev = pinfo->smbus_dev->revision;
+				pinfo->sb_type.gen = AMD_CHIPSET_TAISHAN;
+			} else {
+				pinfo->sb_type.gen = NOT_AMD_CHIPSET;
+				return 0;
+			}
 		}
-
-		rev = pinfo->smbus_dev->revision;
-		if (rev >= 0x11 && rev <= 0x14)
-			pinfo->sb_type.gen = AMD_CHIPSET_HUDSON2;
-		else if (rev >= 0x15 && rev <= 0x18)
-			pinfo->sb_type.gen = AMD_CHIPSET_BOLTON;
-		else if (rev >= 0x39 && rev <= 0x3a)
-			pinfo->sb_type.gen = AMD_CHIPSET_YANGTZE;
 	}
-
 	pinfo->sb_type.rev = rev;
 	return 1;
 }
@@ -251,11 +258,12 @@ int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev)
 {
 	/* Make sure amd chipset type has already been initialized */
 	usb_amd_find_chipset_info();
-	if (amd_chipset.sb_type.gen != AMD_CHIPSET_YANGTZE)
-		return 0;
-
-	dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n");
-	return 1;
+	if (amd_chipset.sb_type.gen == AMD_CHIPSET_YANGTZE ||
+	    amd_chipset.sb_type.gen == AMD_CHIPSET_TAISHAN) {
+		dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n");
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_hcd_amd_remote_wakeup_quirk);
 
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 4cbd0633c5c2..a11c2c8bda53 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -1269,7 +1269,7 @@ static void set_td_timer(struct r8a66597 *r8a66597, struct r8a66597_td *td)
 			time = 30;
 			break;
 		default:
-			time = 300;
+			time = 50;
 			break;
 		}
 
@@ -1785,6 +1785,7 @@ static void r8a66597_td_timer(unsigned long _r8a66597)
 		pipe = td->pipe;
 		pipe_stop(r8a66597, pipe);
 
+		/* Select a different address or endpoint */
 		new_td = td;
 		do {
 			list_move_tail(&new_td->queue,
@@ -1794,7 +1795,8 @@ static void r8a66597_td_timer(unsigned long _r8a66597)
 				new_td = td;
 				break;
 			}
-		} while (td != new_td && td->address == new_td->address);
+		} while (td != new_td && td->address == new_td->address &&
+			td->pipe->info.epnum == new_td->pipe->info.epnum);
 
 		start_transfer(r8a66597, new_td);
 
diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c
index 940304c33224..02260cfdedb1 100644
--- a/drivers/usb/host/uhci-pci.c
+++ b/drivers/usb/host/uhci-pci.c
@@ -129,6 +129,10 @@ static int uhci_pci_init(struct usb_hcd *hcd)
 	if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_HP)
 		uhci->wait_for_hp = 1;
 
+	/* Intel controllers use non-PME wakeup signalling */
+	if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_INTEL)
+		device_set_run_wake(uhci_dev(uhci), 1);
+
 	/* Set up pointers to PCI-specific functions */
 	uhci->reset_hc = uhci_pci_reset_hc;
 	uhci->check_and_reset_hc = uhci_pci_check_and_reset_hc;
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index 74c42f722678..3425154baf8b 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -111,7 +111,7 @@ static void xhci_print_cap_regs(struct xhci_hcd *xhci)
 	xhci_dbg(xhci, "RTSOFF 0x%x:\n", temp & RTSOFF_MASK);
 
 	/* xhci 1.1 controllers have the HCCPARAMS2 register */
-	if (hci_version > 100) {
+	if (hci_version > 0x100) {
 		temp = readl(&xhci->cap_regs->hcc_params2);
 		xhci_dbg(xhci, "HCC PARAMS2 0x%x:\n", (unsigned int) temp);
 		xhci_dbg(xhci, "  HC %s Force save context capability",
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index f980c239eded..a8a2d5005e6e 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -377,6 +377,9 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend)
 
 	ret = 0;
 	virt_dev = xhci->devs[slot_id];
+	if (!virt_dev)
+		return -ENODEV;
+
 	cmd = xhci_alloc_command(xhci, false, true, GFP_NOIO);
 	if (!cmd) {
 		xhci_dbg(xhci, "Couldn't allocate command structure.\n");
@@ -765,6 +768,9 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 			clear_bit(wIndex, &bus_state->resuming_ports);
 
 			set_bit(wIndex, &bus_state->rexit_ports);
+
+			xhci_test_and_clear_bit(xhci, port_array, wIndex,
+						PORT_PLC);
 			xhci_set_link_state(xhci, port_array, wIndex,
 					XDEV_U0);
 
@@ -1154,7 +1160,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				xhci_set_link_state(xhci, port_array, wIndex,
 							XDEV_RESUME);
 				spin_unlock_irqrestore(&xhci->lock, flags);
-				msleep(20);
+				msleep(USB_RESUME_TIMEOUT);
 				spin_lock_irqsave(&xhci->lock, flags);
 				xhci_set_link_state(xhci, port_array, wIndex,
 							XDEV_U0);
@@ -1343,6 +1349,35 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 	return 0;
 }
 
+/*
+ * Workaround for missing Cold Attach Status (CAS) if device re-plugged in S3.
+ * warm reset a USB3 device stuck in polling or compliance mode after resume.
+ * See Intel 100/c230 series PCH specification update Doc #332692-006 Errata #8
+ */
+static bool xhci_port_missing_cas_quirk(int port_index,
+					     __le32 __iomem **port_array)
+{
+	u32 portsc;
+
+	portsc = readl(port_array[port_index]);
+
+	/* if any of these are set we are not stuck */
+	if (portsc & (PORT_CONNECT | PORT_CAS))
+		return false;
+
+	if (((portsc & PORT_PLS_MASK) != XDEV_POLLING) &&
+	    ((portsc & PORT_PLS_MASK) != XDEV_COMP_MODE))
+		return false;
+
+	/* clear wakeup/change bits, and do a warm port reset */
+	portsc &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
+	portsc |= PORT_WR;
+	writel(portsc, port_array[port_index]);
+	/* flush write */
+	readl(port_array[port_index]);
+	return true;
+}
+
 int xhci_bus_resume(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -1380,6 +1415,14 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 		u32 temp;
 
 		temp = readl(port_array[port_index]);
+
+		/* warm reset CAS limited ports stuck in polling/compliance */
+		if ((xhci->quirks & XHCI_MISSING_CAS) &&
+		    (hcd->speed >= HCD_USB3) &&
+		    xhci_port_missing_cas_quirk(port_index, port_array)) {
+			xhci_dbg(xhci, "reset stuck port %d\n", port_index);
+			continue;
+		}
 		if (DEV_SUPERSPEED_ANY(temp))
 			temp &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
 		else
@@ -1398,7 +1441,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 
 	if (need_usb2_u3_exit) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		msleep(20);
+		msleep(USB_RESUME_TIMEOUT);
 		spin_lock_irqsave(&xhci->lock, flags);
 	}
 
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index c48cbe731356..cf6bbaff42d0 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -964,6 +964,40 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
 	xhci->devs[slot_id] = NULL;
 }
 
+/*
+ * Free a virt_device structure.
+ * If the virt_device added a tt_info (a hub) and has children pointing to
+ * that tt_info, then free the child first. Recursive.
+ * We can't rely on udev at this point to find child-parent relationships.
+ */
+void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_id)
+{
+	struct xhci_virt_device *vdev;
+	struct list_head *tt_list_head;
+	struct xhci_tt_bw_info *tt_info, *next;
+	int i;
+
+	vdev = xhci->devs[slot_id];
+	if (!vdev)
+		return;
+
+	tt_list_head = &(xhci->rh_bw[vdev->real_port - 1].tts);
+	list_for_each_entry_safe(tt_info, next, tt_list_head, tt_list) {
+		/* is this a hub device that added a tt_info to the tts list */
+		if (tt_info->slot_id == slot_id) {
+			/* are any devices using this tt_info? */
+			for (i = 1; i < HCS_MAX_SLOTS(xhci->hcs_params1); i++) {
+				vdev = xhci->devs[i];
+				if (vdev && (vdev->tt_info == tt_info))
+					xhci_free_virt_devices_depth_first(
+						xhci, i);
+			}
+		}
+	}
+	/* we are now at a leaf device */
+	xhci_free_virt_device(xhci, slot_id);
+}
+
 int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
 		struct usb_device *udev, gfp_t flags)
 {
@@ -1072,7 +1106,7 @@ static u32 xhci_find_real_port_number(struct xhci_hcd *xhci,
 	struct usb_device *top_dev;
 	struct usb_hcd *hcd;
 
-	if (udev->speed == USB_SPEED_SUPER)
+	if (udev->speed >= USB_SPEED_SUPER)
 		hcd = xhci->shared_hcd;
 	else
 		hcd = xhci->main_hcd;
@@ -1107,6 +1141,7 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	/* 3) Only the control endpoint is valid - one endpoint context */
 	slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | udev->route);
 	switch (udev->speed) {
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
 		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_SS);
 		max_packets = MAX_PACKET(512);
@@ -1294,6 +1329,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev,
 		}
 		/* Fall through - SS and HS isoc/int have same decoding */
 
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
 		if (usb_endpoint_xfer_int(&ep->desc) ||
 		    usb_endpoint_xfer_isoc(&ep->desc)) {
@@ -1334,7 +1370,7 @@ static unsigned int xhci_get_endpoint_interval(struct usb_device *udev,
 static u32 xhci_get_endpoint_mult(struct usb_device *udev,
 		struct usb_host_endpoint *ep)
 {
-	if (udev->speed != USB_SPEED_SUPER ||
+	if (udev->speed < USB_SPEED_SUPER ||
 			!usb_endpoint_xfer_isoc(&ep->desc))
 		return 0;
 	return ep->ss_ep_comp.bmAttributes;
@@ -1384,7 +1420,7 @@ static u32 xhci_get_max_esit_payload(struct usb_device *udev,
 			usb_endpoint_xfer_bulk(&ep->desc))
 		return 0;
 
-	if (udev->speed == USB_SPEED_SUPER)
+	if (udev->speed >= USB_SPEED_SUPER)
 		return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval);
 
 	max_packet = GET_MAX_PACKET(usb_endpoint_maxp(&ep->desc));
@@ -1455,6 +1491,7 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	max_packet = GET_MAX_PACKET(usb_endpoint_maxp(&ep->desc));
 	max_burst = 0;
 	switch (udev->speed) {
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
 		/* dig out max burst from ep companion desc */
 		max_burst = ep->ss_ep_comp.bMaxBurst;
@@ -1672,7 +1709,7 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags)
 	xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma);
 	for (i = 0; i < num_sp; i++) {
 		dma_addr_t dma;
-		void *buf = dma_alloc_coherent(dev, xhci->page_size, &dma,
+		void *buf = dma_zalloc_coherent(dev, xhci->page_size, &dma,
 				flags);
 		if (!buf)
 			goto fail_sp5;
@@ -1792,7 +1829,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	int size;
 	int i, j, num_ports;
 
-	del_timer_sync(&xhci->cmd_timer);
+	cancel_delayed_work_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
@@ -1825,8 +1862,8 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 		}
 	}
 
-	for (i = 1; i < MAX_HC_SLOTS; ++i)
-		xhci_free_virt_device(xhci, i);
+	for (i = HCS_MAX_SLOTS(xhci->hcs_params1); i > 0; i--)
+		xhci_free_virt_devices_depth_first(xhci, i);
 
 	dma_pool_destroy(xhci->segment_pool);
 	xhci->segment_pool = NULL;
@@ -1875,6 +1912,12 @@ no_bw:
 	kfree(xhci->rh_bw);
 	kfree(xhci->ext_caps);
 
+	xhci->usb2_ports = NULL;
+	xhci->usb3_ports = NULL;
+	xhci->port_array = NULL;
+	xhci->rh_bw = NULL;
+	xhci->ext_caps = NULL;
+
 	xhci->page_size = 0;
 	xhci->page_shift = 0;
 	xhci->bus_state[0].bus_suspended = 0;
@@ -2352,9 +2395,9 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
+	/* init command timeout work */
+	INIT_DELAYED_WORK(&xhci->cmd_timer, xhci_handle_command_timeout);
+	init_completion(&xhci->cmd_ring_stop_completion);
 
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
@@ -2393,7 +2436,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * "physically contiguous and 64-byte (cache line) aligned".
 	 */
 	xhci->dcbaa = dma_alloc_coherent(dev, sizeof(*xhci->dcbaa), &dma,
-			GFP_KERNEL);
+			flags);
 	if (!xhci->dcbaa)
 		goto fail;
 	memset(xhci->dcbaa, 0, sizeof *(xhci->dcbaa));
@@ -2450,7 +2493,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 		(xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) |
 		xhci->cmd_ring->cycle_state;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
-			"// Setting command ring address to 0x%x", val);
+			"// Setting command ring address to 0x%016llx", val_64);
 	xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
 	xhci_dbg_cmd_ptrs(xhci);
 
@@ -2489,7 +2532,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	xhci->erst.entries = dma_alloc_coherent(dev,
 			sizeof(struct xhci_erst_entry) * ERST_NUM_SEGS, &dma,
-			GFP_KERNEL);
+			flags);
 	if (!xhci->erst.entries)
 		goto fail;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c2d65206ec6c..e8f990642281 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,7 @@
 /* Device for a quirk */
 #define PCI_VENDOR_ID_FRESCO_LOGIC	0x1b73
 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK	0x1000
+#define PCI_DEVICE_ID_FRESCO_LOGIC_FL1009	0x1009
 #define PCI_DEVICE_ID_FRESCO_LOGIC_FL1400	0x1400
 
 #define PCI_VENDOR_ID_ETRON		0x1b6f
@@ -44,10 +45,14 @@
 
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI	0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
+#define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
 #define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI		0x22b5
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI		0xa12f
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI	0x9d2f
 #define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI		0x0aa8
+#define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI		0x1aa8
+#define PCI_DEVICE_ID_INTEL_APL_XHCI			0x5aa8
+#define PCI_DEVICE_ID_INTEL_DNV_XHCI			0x19d0
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -114,6 +119,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
 
+	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
@@ -148,7 +157,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI) {
+		(pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI)) {
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 		xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
 	}
@@ -156,9 +166,18 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		(pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
-		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI)) {
+		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+	    (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI))
+		xhci->quirks |= XHCI_MISSING_CAS;
+
 	if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
 			pdev->device == PCI_DEVICE_ID_EJ168) {
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
@@ -179,6 +198,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 			pdev->device == 0x1042)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
+			pdev->device == 0x1142)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
@@ -299,15 +321,17 @@ static void xhci_pci_remove(struct pci_dev *dev)
 	struct xhci_hcd *xhci;
 
 	xhci = hcd_to_xhci(pci_get_drvdata(dev));
+	xhci->xhc_state |= XHCI_STATE_REMOVING;
 	if (xhci->shared_hcd) {
 		usb_remove_hcd(xhci->shared_hcd);
 		usb_put_hcd(xhci->shared_hcd);
 	}
-	usb_hcd_pci_remove(dev);
 
 	/* Workaround for spurious wakeups at shutdown with HSW */
 	if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
 		pci_set_power_state(dev, PCI_D3hot);
+
+	usb_hcd_pci_remove(dev);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 05647e6753cd..062cf8a84a59 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -92,7 +92,7 @@ static int xhci_plat_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
-		return -ENODEV;
+		return irq;
 
 	/* Try to set 64-bit DMA first */
 	if (WARN_ON(!pdev->dev.dma_mask))
@@ -132,6 +132,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 		ret = clk_prepare_enable(clk);
 		if (ret)
 			goto put_hcd;
+	} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto put_hcd;
 	}
 
 	if (of_device_is_compatible(pdev->dev.of_node,
@@ -159,9 +162,6 @@ static int xhci_plat_probe(struct platform_device *pdev)
 			(pdata && pdata->usb3_lpm_capable))
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 
-	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
-		xhci->shared_hcd->can_do_streams = 1;
-
 	hcd->usb_phy = devm_usb_get_phy_by_phandle(&pdev->dev, "usb-phy", 0);
 	if (IS_ERR(hcd->usb_phy)) {
 		ret = PTR_ERR(hcd->usb_phy);
@@ -178,6 +178,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_usb_phy;
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto dealloc_usb2_hcd;
@@ -210,6 +213,8 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 	struct clk *clk = xhci->clk;
 
+	xhci->xhc_state |= XHCI_STATE_REMOVING;
+
 	usb_remove_hcd(xhci->shared_hcd);
 	usb_phy_shutdown(hcd->usb_phy);
 
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index db0f0831b94f..ece0787d62bf 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -280,15 +280,76 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci)
 	readl(&xhci->dba->doorbell[0]);
 }
 
-static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
+static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
+{
+	return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
+}
+
+static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
+{
+	return list_first_entry_or_null(&xhci->cmd_list, struct xhci_command,
+					cmd_list);
+}
+
+/*
+ * Turn all commands on command ring with status set to "aborted" to no-op trbs.
+ * If there are other commands waiting then restart the ring and kick the timer.
+ * This must be called with command ring stopped and xhci->lock held.
+ */
+static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
+					 struct xhci_command *cur_cmd)
+{
+	struct xhci_command *i_cmd;
+	u32 cycle_state;
+
+	/* Turn all aborted commands in list to no-ops, then restart */
+	list_for_each_entry(i_cmd, &xhci->cmd_list, cmd_list) {
+
+		if (i_cmd->status != COMP_CMD_ABORT)
+			continue;
+
+		i_cmd->status = COMP_CMD_STOP;
+
+		xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
+			 i_cmd->command_trb);
+		/* get cycle state from the original cmd trb */
+		cycle_state = le32_to_cpu(
+			i_cmd->command_trb->generic.field[3]) &	TRB_CYCLE;
+		/* modify the command trb to no-op command */
+		i_cmd->command_trb->generic.field[0] = 0;
+		i_cmd->command_trb->generic.field[1] = 0;
+		i_cmd->command_trb->generic.field[2] = 0;
+		i_cmd->command_trb->generic.field[3] = cpu_to_le32(
+			TRB_TYPE(TRB_CMD_NOOP) | cycle_state);
+
+		/*
+		 * caller waiting for completion is called when command
+		 *  completion event is received for these no-op commands
+		 */
+	}
+
+	xhci->cmd_ring_state = CMD_RING_STATE_RUNNING;
+
+	/* ring command ring doorbell to restart the command ring */
+	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
+	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
+		xhci->current_cmd = cur_cmd;
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_ring_cmd_db(xhci);
+	}
+}
+
+/* Must be called with xhci->lock held, releases and aquires lock back */
+static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 {
 	u64 temp_64;
 	int ret;
 
 	xhci_dbg(xhci, "Abort command ring\n");
 
+	reinit_completion(&xhci->cmd_ring_stop_completion);
+
 	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
-	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
 	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
 			&xhci->op_regs->cmd_ring);
 
@@ -308,15 +369,30 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 		udelay(1000);
 		ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 				     CMD_RING_RUNNING, 0, 3 * 1000 * 1000);
-		if (ret == 0)
-			return 0;
-
-		xhci_err(xhci, "Stopped the command ring failed, "
-				"maybe the host is dead\n");
-		xhci->xhc_state |= XHCI_STATE_DYING;
-		xhci_quiesce(xhci);
-		xhci_halt(xhci);
-		return -ESHUTDOWN;
+		if (ret < 0) {
+			xhci_err(xhci, "Stopped the command ring failed, "
+				 "maybe the host is dead\n");
+			xhci->xhc_state |= XHCI_STATE_DYING;
+			xhci_quiesce(xhci);
+			xhci_halt(xhci);
+			return -ESHUTDOWN;
+		}
+	}
+	/*
+	 * Writing the CMD_RING_ABORT bit should cause a cmd completion event,
+	 * however on some host hw the CMD_RING_RUNNING bit is correctly cleared
+	 * but the completion event in never sent. Wait 2 secs (arbitrary
+	 * number) to handle those cases after negation of CMD_RING_RUNNING.
+	 */
+	spin_unlock_irqrestore(&xhci->lock, flags);
+	ret = wait_for_completion_timeout(&xhci->cmd_ring_stop_completion,
+					  msecs_to_jiffies(2000));
+	spin_lock_irqsave(&xhci->lock, flags);
+	if (!ret) {
+		xhci_dbg(xhci, "No stop event for abort, ring start fail?\n");
+		xhci_cleanup_command_queue(xhci);
+	} else {
+		xhci_handle_stopped_cmd_ring(xhci, xhci_next_queued_cmd(xhci));
 	}
 
 	return 0;
@@ -780,13 +856,16 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
 			(ep->ep_state & EP_GETTING_NO_STREAMS)) {
 		int stream_id;
 
-		for (stream_id = 0; stream_id < ep->stream_info->num_streams;
+		for (stream_id = 1; stream_id < ep->stream_info->num_streams;
 				stream_id++) {
+			ring = ep->stream_info->stream_rings[stream_id];
+			if (!ring)
+				continue;
+
 			xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 					"Killing URBs for slot ID %u, ep index %u, stream %u",
-					slot_id, ep_index, stream_id + 1);
-			xhci_kill_ring_urbs(xhci,
-					ep->stream_info->stream_rings[stream_id]);
+					slot_id, ep_index, stream_id);
+			xhci_kill_ring_urbs(xhci, ring);
 		}
 	} else {
 		ring = ep->ring;
@@ -837,13 +916,6 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	spin_lock_irqsave(&xhci->lock, flags);
 
 	ep->stop_cmds_pending--;
-	if (xhci->xhc_state & XHCI_STATE_DYING) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-				"Stop EP timer ran, but another timer marked "
-				"xHCI as DYING, exiting.");
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		return;
-	}
 	if (!(ep->stop_cmds_pending == 0 && (ep->ep_state & EP_HALT_PENDING))) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 				"Stop EP timer ran, but no command pending, "
@@ -890,7 +962,7 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Calling usb_hc_died()");
-	usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
+	usb_hc_died(xhci_to_hcd(xhci));
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"xHCI host controller is dead.");
 }
@@ -1195,93 +1267,62 @@ void xhci_cleanup_command_queue(struct xhci_hcd *xhci)
 		xhci_complete_del_and_free_cmd(cur_cmd, COMP_CMD_ABORT);
 }
 
-/*
- * Turn all commands on command ring with status set to "aborted" to no-op trbs.
- * If there are other commands waiting then restart the ring and kick the timer.
- * This must be called with command ring stopped and xhci->lock held.
- */
-static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
-					 struct xhci_command *cur_cmd)
-{
-	struct xhci_command *i_cmd, *tmp_cmd;
-	u32 cycle_state;
-
-	/* Turn all aborted commands in list to no-ops, then restart */
-	list_for_each_entry_safe(i_cmd, tmp_cmd, &xhci->cmd_list,
-				 cmd_list) {
-
-		if (i_cmd->status != COMP_CMD_ABORT)
-			continue;
-
-		i_cmd->status = COMP_CMD_STOP;
-
-		xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
-			 i_cmd->command_trb);
-		/* get cycle state from the original cmd trb */
-		cycle_state = le32_to_cpu(
-			i_cmd->command_trb->generic.field[3]) &	TRB_CYCLE;
-		/* modify the command trb to no-op command */
-		i_cmd->command_trb->generic.field[0] = 0;
-		i_cmd->command_trb->generic.field[1] = 0;
-		i_cmd->command_trb->generic.field[2] = 0;
-		i_cmd->command_trb->generic.field[3] = cpu_to_le32(
-			TRB_TYPE(TRB_CMD_NOOP) | cycle_state);
-
-		/*
-		 * caller waiting for completion is called when command
-		 *  completion event is received for these no-op commands
-		 */
-	}
-
-	xhci->cmd_ring_state = CMD_RING_STATE_RUNNING;
-
-	/* ring command ring doorbell to restart the command ring */
-	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
-	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
-		xhci->current_cmd = cur_cmd;
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
-		xhci_ring_cmd_db(xhci);
-	}
-	return;
-}
-
-
-void xhci_handle_command_timeout(unsigned long data)
+void xhci_handle_command_timeout(struct work_struct *work)
 {
 	struct xhci_hcd *xhci;
 	int ret;
 	unsigned long flags;
 	u64 hw_ring_state;
-	struct xhci_command *cur_cmd = NULL;
-	xhci = (struct xhci_hcd *) data;
 
-	/* mark this command to be cancelled */
+	xhci = container_of(to_delayed_work(work), struct xhci_hcd, cmd_timer);
+
 	spin_lock_irqsave(&xhci->lock, flags);
-	if (xhci->current_cmd) {
-		cur_cmd = xhci->current_cmd;
-		cur_cmd->status = COMP_CMD_ABORT;
-	}
 
+	/*
+	 * If timeout work is pending, or current_cmd is NULL, it means we
+	 * raced with command completion. Command is handled so just return.
+	 */
+	if (!xhci->current_cmd || delayed_work_pending(&xhci->cmd_timer)) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		return;
+	}
+	/* mark this command to be cancelled */
+	xhci->current_cmd->status = COMP_CMD_ABORT;
 
 	/* Make sure command ring is running before aborting it */
 	hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
 	if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
 	    (hw_ring_state & CMD_RING_RUNNING))  {
-
-		spin_unlock_irqrestore(&xhci->lock, flags);
+		/* Prevent new doorbell, and start command abort */
+		xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
 		xhci_dbg(xhci, "Command timeout\n");
-		ret = xhci_abort_cmd_ring(xhci);
+		ret = xhci_abort_cmd_ring(xhci, flags);
 		if (unlikely(ret == -ESHUTDOWN)) {
 			xhci_err(xhci, "Abort command ring failed\n");
 			xhci_cleanup_command_queue(xhci);
+			spin_unlock_irqrestore(&xhci->lock, flags);
 			usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
 			xhci_dbg(xhci, "xHCI host controller is dead.\n");
+
+			return;
 		}
-		return;
+
+		goto time_out_completed;
+	}
+
+	/* host removed. Bail out */
+	if (xhci->xhc_state & XHCI_STATE_REMOVING) {
+		xhci_dbg(xhci, "host removed, ring start fail?\n");
+		xhci_cleanup_command_queue(xhci);
+
+		goto time_out_completed;
 	}
+
 	/* command timeout on stopped ring, ring can't be aborted */
 	xhci_dbg(xhci, "Command timeout on stopped ring\n");
 	xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
+
+time_out_completed:
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return;
 }
@@ -1314,13 +1355,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 
 	cmd = list_entry(xhci->cmd_list.next, struct xhci_command, cmd_list);
 
-	if (cmd->command_trb != xhci->cmd_ring->dequeue) {
-		xhci_err(xhci,
-			 "Command completion event does not match command\n");
-		return;
-	}
-
-	del_timer(&xhci->cmd_timer);
+	cancel_delayed_work(&xhci->cmd_timer);
 
 	trace_xhci_cmd_completion(cmd_trb, (struct xhci_generic_trb *) event);
 
@@ -1328,9 +1363,16 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 
 	/* If CMD ring stopped we own the trbs between enqueue and dequeue */
 	if (cmd_comp_code == COMP_CMD_STOP) {
-		xhci_handle_stopped_cmd_ring(xhci, cmd);
+		complete_all(&xhci->cmd_ring_stop_completion);
 		return;
 	}
+
+	if (cmd->command_trb != xhci->cmd_ring->dequeue) {
+		xhci_err(xhci,
+			 "Command completion event does not match command\n");
+		return;
+	}
+
 	/*
 	 * Host aborted the command ring, check if the current command was
 	 * supposed to be aborted, otherwise continue normally.
@@ -1339,8 +1381,11 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	 */
 	if (cmd_comp_code == COMP_CMD_ABORT) {
 		xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
-		if (cmd->status == COMP_CMD_ABORT)
+		if (cmd->status == COMP_CMD_ABORT) {
+			if (xhci->current_cmd == cmd)
+				xhci->current_cmd = NULL;
 			goto event_handled;
+		}
 	}
 
 	cmd_type = TRB_FIELD_TO_TYPE(le32_to_cpu(cmd_trb->generic.field[3]));
@@ -1401,7 +1446,9 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	if (cmd->cmd_list.next != &xhci->cmd_list) {
 		xhci->current_cmd = list_entry(cmd->cmd_list.next,
 					       struct xhci_command, cmd_list);
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+	} else if (xhci->current_cmd == cmd) {
+		xhci->current_cmd = NULL;
 	}
 
 event_handled:
@@ -2727,7 +2774,8 @@ hw_died:
 		writel(irq_pending, &xhci->ir_set->irq_pending);
 	}
 
-	if (xhci->xhc_state & XHCI_STATE_DYING) {
+	if (xhci->xhc_state & XHCI_STATE_DYING ||
+	    xhci->xhc_state & XHCI_STATE_HALTED) {
 		xhci_dbg(xhci, "xHCI dying, ignoring interrupt. "
 				"Shouldn't IRQs be disabled?\n");
 		/* Clear the event handler busy flag (RW1C);
@@ -3557,7 +3605,7 @@ static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci,
 {
 	unsigned int max_burst;
 
-	if (xhci->hci_version < 0x100 || udev->speed != USB_SPEED_SUPER)
+	if (xhci->hci_version < 0x100 || udev->speed < USB_SPEED_SUPER)
 		return 0;
 
 	max_burst = urb->ep->ss_ep_comp.bMaxBurst;
@@ -3583,6 +3631,7 @@ static unsigned int xhci_get_last_burst_packet_count(struct xhci_hcd *xhci,
 		return 0;
 
 	switch (udev->speed) {
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_SUPER:
 		/* bMaxBurst is zero based: 0 means 1 packet per burst */
 		max_burst = urb->ep->ss_ep_comp.bMaxBurst;
@@ -4008,7 +4057,8 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 	int reserved_trbs = xhci->cmd_ring_reserved_trbs;
 	int ret;
 
-	if (xhci->xhc_state) {
+	if ((xhci->xhc_state & XHCI_STATE_DYING) ||
+		(xhci->xhc_state & XHCI_STATE_HALTED)) {
 		xhci_dbg(xhci, "xHCI dying or halted, can't queue_command\n");
 		return -ESHUTDOWN;
 	}
@@ -4031,9 +4081,9 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 
 	/* if there are no other commands queued we start the timeout timer */
 	if (xhci->cmd_list.next == &cmd->cmd_list &&
-	    !timer_pending(&xhci->cmd_timer)) {
+	    !delayed_work_pending(&xhci->cmd_timer)) {
 		xhci->current_cmd = cmd;
-		mod_timer(&xhci->cmd_timer, jiffies + XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
 	}
 
 	queue_trb(xhci, xhci->cmd_ring, false, field1, field2, field3,
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 776d59c32bc5..f2e9f59c90d6 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci)
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
 	if (!ret)
-		xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING);
+		/* clear state flags. Including dying, halted or removing */
+		xhci->xhc_state = 0;
 
 	return ret;
 }
@@ -679,20 +680,23 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (xhci->xhc_state & XHCI_STATE_HALTED)
-		return;
-
 	mutex_lock(&xhci->mutex);
-	spin_lock_irq(&xhci->lock);
-	xhci->xhc_state |= XHCI_STATE_HALTED;
-	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
 
-	/* Make sure the xHC is halted for a USB3 roothub
-	 * (xhci_stop() could be called as part of failed init).
-	 */
-	xhci_halt(xhci);
-	xhci_reset(xhci);
-	spin_unlock_irq(&xhci->lock);
+	if (!(xhci->xhc_state & XHCI_STATE_HALTED)) {
+		spin_lock_irq(&xhci->lock);
+
+		xhci->xhc_state |= XHCI_STATE_HALTED;
+		xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+		xhci_halt(xhci);
+		xhci_reset(xhci);
+
+		spin_unlock_irq(&xhci->lock);
+	}
+
+	if (!usb_hcd_is_primary_hcd(hcd)) {
+		mutex_unlock(&xhci->mutex);
+		return;
+	}
 
 	xhci_cleanup_msix(xhci);
 
@@ -1103,8 +1107,8 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 		/* 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);
+			usb_hcd_resume_root_hub(hcd);
 		}
 	}
 
@@ -1119,10 +1123,10 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
 	/* Re-enable port polling. */
 	xhci_dbg(xhci, "%s: starting port polling.\n", __func__);
-	set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
-	usb_hcd_poll_rh_status(hcd);
 	set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags);
 	usb_hcd_poll_rh_status(xhci->shared_hcd);
+	set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
+	usb_hcd_poll_rh_status(hcd);
 
 	return retval;
 }
@@ -1565,19 +1569,6 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
 		xhci_urb_free_priv(urb_priv);
 		return ret;
 	}
-	if ((xhci->xhc_state & XHCI_STATE_DYING) ||
-			(xhci->xhc_state & XHCI_STATE_HALTED)) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-				"Ep 0x%x: URB %p to be canceled on "
-				"non-responsive xHCI host.",
-				urb->ep->desc.bEndpointAddress, urb);
-		/* Let the stop endpoint command watchdog timer (which set this
-		 * state) finish cleaning up the endpoint TD lists.  We must
-		 * have caught it in the middle of dropping a lock and giving
-		 * back an URB.
-		 */
-		goto done;
-	}
 
 	ep_index = xhci_get_endpoint_index(&urb->ep->desc);
 	ep = &xhci->devs[urb->dev->slot_id]->eps[ep_index];
@@ -2069,6 +2060,7 @@ static unsigned int xhci_get_block_size(struct usb_device *udev)
 	case USB_SPEED_HIGH:
 		return HS_BLOCK;
 	case USB_SPEED_SUPER:
+	case USB_SPEED_SUPER_PLUS:
 		return SS_BLOCK;
 	case USB_SPEED_UNKNOWN:
 	case USB_SPEED_WIRELESS:
@@ -2194,7 +2186,7 @@ static int xhci_check_bw_table(struct xhci_hcd *xhci,
 	unsigned int packets_remaining = 0;
 	unsigned int i;
 
-	if (virt_dev->udev->speed == USB_SPEED_SUPER)
+	if (virt_dev->udev->speed >= USB_SPEED_SUPER)
 		return xhci_check_ss_bw(xhci, virt_dev);
 
 	if (virt_dev->udev->speed == USB_SPEED_HIGH) {
@@ -2395,7 +2387,7 @@ void xhci_drop_ep_from_interval_table(struct xhci_hcd *xhci,
 	if (xhci_is_async_ep(ep_bw->type))
 		return;
 
-	if (udev->speed == USB_SPEED_SUPER) {
+	if (udev->speed >= USB_SPEED_SUPER) {
 		if (xhci_is_sync_in_ep(ep_bw->type))
 			xhci->devs[udev->slot_id]->bw_table->ss_bw_in -=
 				xhci_get_ss_bw_consumed(ep_bw);
@@ -2433,6 +2425,7 @@ void xhci_drop_ep_from_interval_table(struct xhci_hcd *xhci,
 		interval_bw->overhead[HS_OVERHEAD_TYPE] -= 1;
 		break;
 	case USB_SPEED_SUPER:
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_UNKNOWN:
 	case USB_SPEED_WIRELESS:
 		/* Should never happen because only LS/FS/HS endpoints will get
@@ -2492,6 +2485,7 @@ static void xhci_add_ep_to_interval_table(struct xhci_hcd *xhci,
 		interval_bw->overhead[HS_OVERHEAD_TYPE] += 1;
 		break;
 	case USB_SPEED_SUPER:
+	case USB_SPEED_SUPER_PLUS:
 	case USB_SPEED_UNKNOWN:
 	case USB_SPEED_WIRELESS:
 		/* Should never happen because only LS/FS/HS endpoints will get
@@ -2753,7 +2747,8 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 	if (ret <= 0)
 		return ret;
 	xhci = hcd_to_xhci(hcd);
-	if (xhci->xhc_state & XHCI_STATE_DYING)
+	if ((xhci->xhc_state & XHCI_STATE_DYING) ||
+		(xhci->xhc_state & XHCI_STATE_REMOVING))
 		return -ENODEV;
 
 	xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
@@ -3800,8 +3795,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 	mutex_lock(&xhci->mutex);
 
-	if (xhci->xhc_state)	/* dying or halted */
+	if (xhci->xhc_state) {	/* dying, removing or halted */
+		ret = -ESHUTDOWN;
 		goto out;
+	}
 
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 0b9451250e33..fc2ee6c272c4 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -312,6 +312,8 @@ struct xhci_op_regs {
 #define XDEV_U2		(0x2 << 5)
 #define XDEV_U3		(0x3 << 5)
 #define XDEV_INACTIVE	(0x6 << 5)
+#define XDEV_POLLING	(0x7 << 5)
+#define XDEV_COMP_MODE  (0xa << 5)
 #define XDEV_RESUME	(0xf << 5)
 /* true: port has power (see HCC_PPC) */
 #define PORT_POWER	(1 << 9)
@@ -1550,7 +1552,8 @@ struct xhci_hcd {
 #define CMD_RING_STATE_STOPPED         (1 << 2)
 	struct list_head        cmd_list;
 	unsigned int		cmd_ring_reserved_trbs;
-	struct timer_list	cmd_timer;
+	struct delayed_work	cmd_timer;
+	struct completion	cmd_ring_stop_completion;
 	struct xhci_command	*current_cmd;
 	struct xhci_ring	*event_ring;
 	struct xhci_erst	erst;
@@ -1596,6 +1599,7 @@ struct xhci_hcd {
  */
 #define XHCI_STATE_DYING	(1 << 0)
 #define XHCI_STATE_HALTED	(1 << 1)
+#define XHCI_STATE_REMOVING	(1 << 2)
 	/* Statistics */
 	int			error_bitmask;
 	unsigned int		quirks;
@@ -1630,6 +1634,7 @@ struct xhci_hcd {
 /* For controllers with a broken beyond repair streams implementation */
 #define XHCI_BROKEN_STREAMS	(1 << 19)
 #define XHCI_PME_STUCK_QUIRK	(1 << 20)
+#define XHCI_MISSING_CAS	(1 << 24)
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
@@ -1911,7 +1916,7 @@ void xhci_queue_config_ep_quirk(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
 		struct xhci_dequeue_state *deq_state);
 void xhci_stop_endpoint_command_watchdog(unsigned long arg);
-void xhci_handle_command_timeout(unsigned long data);
+void xhci_handle_command_timeout(struct work_struct *work);
 
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index 4e38683c653c..6d4e75785710 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -346,6 +346,9 @@ static int idmouse_probe(struct usb_interface *interface,
 	if (iface_desc->desc.bInterfaceClass != 0x0A)
 		return -ENODEV;
 
+	if (iface_desc->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	/* allocate memory for our device state and initialize it */
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (dev == NULL)
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index c6bfd13f6c92..5e43fd881a9c 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -557,7 +557,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 			info.revision = le16_to_cpu(dev->udev->descriptor.bcdDevice);
 
 			/* 0==UNKNOWN, 1==LOW(usb1.1) ,2=FULL(usb1.1), 3=HIGH(usb2.0) */
-			info.speed = le16_to_cpu(dev->udev->speed);
+			info.speed = dev->udev->speed;
 			info.if_num = dev->interface->cur_altsetting->desc.bInterfaceNumber;
 			info.report_size = dev->report_size;
 
@@ -797,6 +797,21 @@ static int iowarrior_probe(struct usb_interface *interface,
 			/* this one will match for the IOWarrior56 only */
 			dev->int_out_endpoint = endpoint;
 	}
+
+	if (!dev->int_in_endpoint) {
+		dev_err(&interface->dev, "no interrupt-in endpoint found\n");
+		retval = -ENODEV;
+		goto error;
+	}
+
+	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+		if (!dev->int_out_endpoint) {
+			dev_err(&interface->dev, "no interrupt-out endpoint found\n");
+			retval = -ENODEV;
+			goto error;
+		}
+	}
+
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 7771be3ac178..0ec9ee573ffa 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -317,9 +317,16 @@ static int tower_open (struct inode *inode, struct file *file)
 	int subminor;
 	int retval = 0;
 	struct usb_interface *interface;
-	struct tower_reset_reply reset_reply;
+	struct tower_reset_reply *reset_reply;
 	int result;
 
+	reset_reply = kmalloc(sizeof(*reset_reply), GFP_KERNEL);
+
+	if (!reset_reply) {
+		retval = -ENOMEM;
+		goto exit;
+	}
+
 	nonseekable_open(inode, file);
 	subminor = iminor(inode);
 
@@ -364,8 +371,8 @@ static int tower_open (struct inode *inode, struct file *file)
 				  USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE,
 				  0,
 				  0,
-				  &reset_reply,
-				  sizeof(reset_reply),
+				  reset_reply,
+				  sizeof(*reset_reply),
 				  1000);
 	if (result < 0) {
 		dev_err(&dev->udev->dev,
@@ -406,6 +413,7 @@ unlock_exit:
 	mutex_unlock(&dev->lock);
 
 exit:
+	kfree(reset_reply);
 	return retval;
 }
 
@@ -808,7 +816,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 	struct lego_usb_tower *dev = NULL;
 	struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor* endpoint;
-	struct tower_get_version_reply get_version_reply;
+	struct tower_get_version_reply *get_version_reply = NULL;
 	int i;
 	int retval = -ENOMEM;
 	int result;
@@ -898,23 +906,12 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 	dev->interrupt_in_interval = interrupt_in_interval ? interrupt_in_interval : dev->interrupt_in_endpoint->bInterval;
 	dev->interrupt_out_interval = interrupt_out_interval ? interrupt_out_interval : dev->interrupt_out_endpoint->bInterval;
 
-	/* we can register the device now, as it is ready */
-	usb_set_intfdata (interface, dev);
-
-	retval = usb_register_dev (interface, &tower_class);
+	get_version_reply = kmalloc(sizeof(*get_version_reply), GFP_KERNEL);
 
-	if (retval) {
-		/* something prevented us from registering this driver */
-		dev_err(idev, "Not able to get a minor for this device.\n");
-		usb_set_intfdata (interface, NULL);
+	if (!get_version_reply) {
+		retval = -ENOMEM;
 		goto error;
 	}
-	dev->minor = interface->minor;
-
-	/* let the user know what node this device is now attached to */
-	dev_info(&interface->dev, "LEGO USB Tower #%d now attached to major "
-		 "%d minor %d\n", (dev->minor - LEGO_USB_TOWER_MINOR_BASE),
-		 USB_MAJOR, dev->minor);
 
 	/* get the firmware version and log it */
 	result = usb_control_msg (udev,
@@ -923,24 +920,44 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 				  USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE,
 				  0,
 				  0,
-				  &get_version_reply,
-				  sizeof(get_version_reply),
+				  get_version_reply,
+				  sizeof(*get_version_reply),
 				  1000);
 	if (result < 0) {
 		dev_err(idev, "LEGO USB Tower get version control request failed\n");
 		retval = result;
 		goto error;
 	}
-	dev_info(&interface->dev, "LEGO USB Tower firmware version is %d.%d "
-		 "build %d\n", get_version_reply.major,
-		 get_version_reply.minor,
-		 le16_to_cpu(get_version_reply.build_no));
+	dev_info(&interface->dev,
+		 "LEGO USB Tower firmware version is %d.%d build %d\n",
+		 get_version_reply->major,
+		 get_version_reply->minor,
+		 le16_to_cpu(get_version_reply->build_no));
 
+	/* we can register the device now, as it is ready */
+	usb_set_intfdata (interface, dev);
+
+	retval = usb_register_dev (interface, &tower_class);
+
+	if (retval) {
+		/* something prevented us from registering this driver */
+		dev_err(idev, "Not able to get a minor for this device.\n");
+		usb_set_intfdata (interface, NULL);
+		goto error;
+	}
+	dev->minor = interface->minor;
+
+	/* let the user know what node this device is now attached to */
+	dev_info(&interface->dev, "LEGO USB Tower #%d now attached to major "
+		 "%d minor %d\n", (dev->minor - LEGO_USB_TOWER_MINOR_BASE),
+		 USB_MAJOR, dev->minor);
 
 exit:
+	kfree(get_version_reply);
 	return retval;
 
 error:
+	kfree(get_version_reply);
 	tower_delete(dev);
 	return retval;
 }
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index 86b4e4b2ab9a..383fa007348f 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -370,6 +370,10 @@ static int lvs_rh_probe(struct usb_interface *intf,
 
 	hdev = interface_to_usbdev(intf);
 	desc = intf->cur_altsetting;
+
+	if (desc->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	endpoint = &desc->endpoint[0].desc;
 
 	/* valid only for SS root hub */
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 637f3f7cfce8..2e947dc94e32 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -135,6 +135,7 @@ get_endpoints(struct usbtest_dev *dev, struct usb_interface *intf)
 			case USB_ENDPOINT_XFER_INT:
 				if (dev->info->intr)
 					goto try_intr;
+				continue;
 			case USB_ENDPOINT_XFER_ISOC:
 				if (dev->info->iso)
 					goto try_iso;
@@ -505,6 +506,7 @@ static struct scatterlist *
 alloc_sglist(int nents, int max, int vary, struct usbtest_dev *dev, int pipe)
 {
 	struct scatterlist	*sg;
+	unsigned int		n_size = 0;
 	unsigned		i;
 	unsigned		size = max;
 	unsigned		maxpacket =
@@ -537,7 +539,8 @@ alloc_sglist(int nents, int max, int vary, struct usbtest_dev *dev, int pipe)
 			break;
 		case 1:
 			for (j = 0; j < size; j++)
-				*buf++ = (u8) ((j % maxpacket) % 63);
+				*buf++ = (u8) (((j + n_size) % maxpacket) % 63);
+			n_size += size;
 			break;
 		}
 
@@ -556,7 +559,6 @@ static void sg_timeout(unsigned long _req)
 {
 	struct usb_sg_request	*req = (struct usb_sg_request *) _req;
 
-	req->status = -ETIMEDOUT;
 	usb_sg_cancel(req);
 }
 
@@ -587,8 +589,10 @@ static int perform_sglist(
 		mod_timer(&sg_timer, jiffies +
 				msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
 		usb_sg_wait(req);
-		del_timer_sync(&sg_timer);
-		retval = req->status;
+		if (!del_timer_sync(&sg_timer))
+			retval = -ETIMEDOUT;
+		else
+			retval = req->status;
 
 		/* FIXME check resulting data pattern */
 
diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index bbd029c9c725..442b6631162e 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -711,6 +711,11 @@ static int uss720_probe(struct usb_interface *intf,
 
 	interface = intf->cur_altsetting;
 
+	if (interface->desc.bNumEndpoints < 3) {
+		usb_put_dev(usbdev);
+		return -ENODEV;
+	}
+
 	/*
 	 * Allocate parport interface 
 	 */
diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c
index 310238c6b5cd..896798071817 100644
--- a/drivers/usb/musb/blackfin.c
+++ b/drivers/usb/musb/blackfin.c
@@ -469,6 +469,7 @@ static const struct musb_platform_ops bfin_ops = {
 	.init		= bfin_musb_init,
 	.exit		= bfin_musb_exit,
 
+	.fifo_offset	= bfin_fifo_offset,
 	.readb		= bfin_readb,
 	.writeb		= bfin_writeb,
 	.readw		= bfin_readw,
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index b03d3b867fca..9a9c82a4d35d 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -458,15 +458,11 @@ static int da8xx_musb_exit(struct musb *musb)
 }
 
 static const struct musb_platform_ops da8xx_ops = {
-	.quirks		= MUSB_DMA_CPPI | MUSB_INDEXED_EP,
+	.quirks		= MUSB_INDEXED_EP,
 	.init		= da8xx_musb_init,
 	.exit		= da8xx_musb_exit,
 
 	.fifo_mode	= 2,
-#ifdef CONFIG_USB_TI_CPPI_DMA
-	.dma_init	= cppi_dma_controller_create,
-	.dma_exit	= cppi_dma_controller_destroy,
-#endif
 	.enable		= da8xx_musb_enable,
 	.disable	= da8xx_musb_disable,
 
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index ee9ff7028b92..00eed5d66fda 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2401,7 +2401,8 @@ static void musb_restore_context(struct musb *musb)
 	musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe);
 	musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe);
 	musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe);
-	musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
+	if (musb->context.devctl & MUSB_DEVCTL_SESSION)
+		musb_writeb(musb_base, MUSB_DEVCTL, musb->context.devctl);
 
 	for (i = 0; i < musb->config->num_eps; ++i) {
 		struct musb_hw_ep	*hw_ep;
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index 2337d7a7d62d..90de7900e4b8 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -214,6 +214,7 @@ struct musb_platform_ops {
 				dma_addr_t *dma_addr, u32 *len);
 	void	(*pre_root_reset_end)(struct musb *musb);
 	void	(*post_root_reset_end)(struct musb *musb);
+	void	(*clear_ep_rxintr)(struct musb *musb, int epnum);
 };
 
 /*
@@ -612,4 +613,10 @@ static inline void musb_platform_post_root_reset_end(struct musb *musb)
 		musb->ops->post_root_reset_end(musb);
 }
 
+static inline void musb_platform_clear_ep_rxintr(struct musb *musb, int epnum)
+{
+	if (musb->ops->clear_ep_rxintr)
+		musb->ops->clear_ep_rxintr(musb, epnum);
+}
+
 #endif	/* __MUSB_CORE_H__ */
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index e499b862a946..88f26ac2a185 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -250,8 +250,27 @@ static void cppi41_dma_callback(void *private_data)
 			transferred < cppi41_channel->packet_sz)
 		cppi41_channel->prog_len = 0;
 
-	if (cppi41_channel->is_tx)
-		empty = musb_is_tx_fifo_empty(hw_ep);
+	if (cppi41_channel->is_tx) {
+		u8 type;
+
+		if (is_host_active(musb))
+			type = hw_ep->out_qh->type;
+		else
+			type = hw_ep->ep_in.type;
+
+		if (type == USB_ENDPOINT_XFER_ISOC)
+			/*
+			 * Don't use the early-TX-interrupt workaround below
+			 * for Isoch transfter. Since Isoch are periodic
+			 * transfer, by the time the next transfer is
+			 * scheduled, the current one should be done already.
+			 *
+			 * This avoids audio playback underrun issue.
+			 */
+			empty = true;
+		else
+			empty = musb_is_tx_fifo_empty(hw_ep);
+	}
 
 	if (!cppi41_channel->is_tx || empty) {
 		cppi41_trans_done(cppi41_channel);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index eeb7d9ecf7df..5a021b26d7d2 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -301,6 +301,17 @@ static void otg_timer(unsigned long _musb)
 	spin_unlock_irqrestore(&musb->lock, flags);
 }
 
+void dsps_musb_clear_ep_rxintr(struct musb *musb, int epnum)
+{
+	u32 epintr;
+	struct dsps_glue *glue = dev_get_drvdata(musb->controller->parent);
+	const struct dsps_musb_wrapper *wrp = glue->wrp;
+
+	/* musb->lock might already been held */
+	epintr = (1 << epnum) << wrp->rxep_shift;
+	musb_writel(musb->ctrl_base, wrp->epintr_status, epintr);
+}
+
 static irqreturn_t dsps_interrupt(int irq, void *hci)
 {
 	struct musb  *musb = hci;
@@ -647,6 +658,7 @@ static struct musb_platform_ops dsps_ops = {
 	.try_idle	= dsps_musb_try_idle,
 	.set_mode	= dsps_musb_set_mode,
 	.recover	= dsps_musb_recover,
+	.clear_ep_rxintr = dsps_musb_clear_ep_rxintr,
 };
 
 static u64 musb_dmamask = DMA_BIT_MASK(32);
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 795a45b1b25b..0d843e0f8055 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -138,6 +138,7 @@ static void musb_h_tx_flush_fifo(struct musb_hw_ep *ep)
 				"Could not flush host TX%d fifo: csr: %04x\n",
 				ep->epnum, csr))
 			return;
+		mdelay(1);
 	}
 }
 
@@ -594,14 +595,13 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, u8 epnum)
 		musb_writew(ep->regs, MUSB_TXCSR, 0);
 
 	/* scrub all previous state, clearing toggle */
-	} else {
-		csr = musb_readw(ep->regs, MUSB_RXCSR);
-		if (csr & MUSB_RXCSR_RXPKTRDY)
-			WARNING("rx%d, packet/%d ready?\n", ep->epnum,
-				musb_readw(ep->regs, MUSB_RXCOUNT));
-
-		musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 	}
+	csr = musb_readw(ep->regs, MUSB_RXCSR);
+	if (csr & MUSB_RXCSR_RXPKTRDY)
+		WARNING("rx%d, packet/%d ready?\n", ep->epnum,
+			musb_readw(ep->regs, MUSB_RXCOUNT));
+
+	musb_h_flush_rxfifo(ep, MUSB_RXCSR_CLRDATATOG);
 
 	/* target addr and (for multipoint) hub addr/port */
 	if (musb->is_multipoint) {
@@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
 		csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE);
 		csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */
 	}
-	channel->desired_mode = mode;
+	channel->desired_mode = *mode;
 	musb_writew(epio, MUSB_TXCSR, csr);
 
 	return 0;
@@ -995,9 +995,15 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
 	if (is_in) {
 		dma = is_dma_capable() ? ep->rx_channel : NULL;
 
-		/* clear nak timeout bit */
+		/*
+		 * Need to stop the transaction by clearing REQPKT first
+		 * then the NAK Timeout bit ref MUSBMHDRC USB 2.0 HIGH-SPEED
+		 * DUAL-ROLE CONTROLLER Programmer's Guide, section 9.2.2
+		 */
 		rx_csr = musb_readw(epio, MUSB_RXCSR);
 		rx_csr |= MUSB_RXCSR_H_WZC_BITS;
+		rx_csr &= ~MUSB_RXCSR_H_REQPKT;
+		musb_writew(epio, MUSB_RXCSR, rx_csr);
 		rx_csr &= ~MUSB_RXCSR_DATAERROR;
 		musb_writew(epio, MUSB_RXCSR, rx_csr);
 
@@ -1551,7 +1557,7 @@ static int musb_rx_dma_iso_cppi41(struct dma_controller *dma,
 				  struct urb *urb,
 				  size_t len)
 {
-	struct dma_channel *channel = hw_ep->tx_channel;
+	struct dma_channel *channel = hw_ep->rx_channel;
 	void __iomem *epio = hw_ep->regs;
 	dma_addr_t *buf;
 	u32 length, res;
@@ -2003,10 +2009,8 @@ void musb_host_rx(struct musb *musb, u8 epnum)
 				qh->offset,
 				urb->transfer_buffer_length);
 
-			done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh,
-							      urb, xfer_len,
-							      iso_err);
-			if (done)
+			if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb,
+							   xfer_len, iso_err))
 				goto finish;
 			else
 				dev_err(musb->controller, "error: rx_dma failed\n");
@@ -2387,12 +2391,11 @@ static int musb_cleanup_urb(struct urb *urb, struct musb_qh *qh)
 	int			is_in = usb_pipein(urb->pipe);
 	int			status = 0;
 	u16			csr;
+	struct dma_channel	*dma = NULL;
 
 	musb_ep_select(regs, hw_end);
 
 	if (is_dma_capable()) {
-		struct dma_channel	*dma;
-
 		dma = is_in ? ep->rx_channel : ep->tx_channel;
 		if (dma) {
 			status = ep->musb->dma_controller->channel_abort(dma);
@@ -2409,10 +2412,9 @@ static int musb_cleanup_urb(struct urb *urb, struct musb_qh *qh)
 		/* giveback saves bulk toggle */
 		csr = musb_h_flush_rxfifo(ep, 0);
 
-		/* REVISIT we still get an irq; should likely clear the
-		 * endpoint's irq status here to avoid bogus irqs.
-		 * clearing that status is platform-specific...
-		 */
+		/* clear the endpoint's irq status here to avoid bogus irqs */
+		if (is_dma_capable() && dma)
+			musb_platform_clear_ep_rxintr(musb, ep->epnum);
 	} else if (ep->epnum) {
 		musb_h_tx_flush_fifo(ep);
 		csr = musb_readw(epio, MUSB_TXCSR);
diff --git a/drivers/usb/musb/musbhsdma.h b/drivers/usb/musb/musbhsdma.h
index f7b13fd25257..a3dcbd55e436 100644
--- a/drivers/usb/musb/musbhsdma.h
+++ b/drivers/usb/musb/musbhsdma.h
@@ -157,5 +157,5 @@ struct musb_dma_controller {
 	void __iomem			*base;
 	u8				channel_count;
 	u8				used_channels;
-	u8				irq;
+	int				irq;
 };
diff --git a/drivers/usb/musb/tusb6010_omap.c b/drivers/usb/musb/tusb6010_omap.c
index 4c82077da475..6020024cb87c 100644
--- a/drivers/usb/musb/tusb6010_omap.c
+++ b/drivers/usb/musb/tusb6010_omap.c
@@ -220,6 +220,7 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz,
 	u32				dma_remaining;
 	int				src_burst, dst_burst;
 	u16				csr;
+	u32				psize;
 	int				ch;
 	s8				dmareq;
 	s8				sync_dev;
@@ -391,15 +392,19 @@ static int tusb_omap_dma_program(struct dma_channel *channel, u16 packet_sz,
 
 	if (chdat->tx) {
 		/* Send transfer_packet_sz packets at a time */
-		musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET,
-			chdat->transfer_packet_sz);
+		psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET);
+		psize &= ~0x7ff;
+		psize |= chdat->transfer_packet_sz;
+		musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize);
 
 		musb_writel(ep_conf, TUSB_EP_TX_OFFSET,
 			TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len));
 	} else {
 		/* Receive transfer_packet_sz packets at a time */
-		musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET,
-			chdat->transfer_packet_sz << 16);
+		psize = musb_readl(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET);
+		psize &= ~(0x7ff << 16);
+		psize |= (chdat->transfer_packet_sz << 16);
+		musb_writel(ep_conf, TUSB_EP_MAX_PACKET_SIZE_OFFSET, psize);
 
 		musb_writel(ep_conf, TUSB_EP_RX_OFFSET,
 			TUSB_EP_CONFIG_XFR_SIZE(chdat->transfer_len));
diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c
index 7b3035ff9434..1b4d742a2397 100644
--- a/drivers/usb/phy/phy-am335x-control.c
+++ b/drivers/usb/phy/phy-am335x-control.c
@@ -126,10 +126,12 @@ struct phy_control *am335x_get_phy_control(struct device *dev)
 		return NULL;
 
 	dev = bus_find_device(&platform_bus_type, NULL, node, match);
+	of_node_put(node);
 	if (!dev)
 		return NULL;
 
 	ctrl_usb = dev_get_drvdata(dev);
+	put_device(dev);
 	if (!ctrl_usb)
 		return NULL;
 	return &ctrl_usb->phy_ctrl;
diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index d82fa36c3465..005da0866836 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -733,8 +733,10 @@ static int usbhsc_resume(struct device *dev)
 	struct usbhs_priv *priv = dev_get_drvdata(dev);
 	struct platform_device *pdev = usbhs_priv_to_pdev(priv);
 
-	if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL))
+	if (!usbhsc_flags_has(priv, USBHSF_RUNTIME_PWCTRL)) {
 		usbhsc_power_ctrl(priv, 1);
+		usbhs_mod_autonomy_mode(priv);
+	}
 
 	usbhs_platform_call(priv, phy_reset, pdev);
 
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index c0f5c652d272..36e5b5c530bd 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -190,7 +190,8 @@ static int usbhsf_pkt_handler(struct usbhs_pipe *pipe, int type)
 		goto __usbhs_pkt_handler_end;
 	}
 
-	ret = func(pkt, &is_done);
+	if (likely(func))
+		ret = func(pkt, &is_done);
 
 	if (is_done)
 		__usbhsf_pkt_del(pkt);
@@ -807,20 +808,27 @@ static void xfer_work(struct work_struct *work)
 {
 	struct usbhs_pkt *pkt = container_of(work, struct usbhs_pkt, work);
 	struct usbhs_pipe *pipe = pkt->pipe;
-	struct usbhs_fifo *fifo = usbhs_pipe_to_fifo(pipe);
+	struct usbhs_fifo *fifo;
 	struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
 	struct dma_async_tx_descriptor *desc;
-	struct dma_chan *chan = usbhsf_dma_chan_get(fifo, pkt);
+	struct dma_chan *chan;
 	struct device *dev = usbhs_priv_to_dev(priv);
 	enum dma_transfer_direction dir;
+	unsigned long flags;
 
+	usbhs_lock(priv, flags);
+	fifo = usbhs_pipe_to_fifo(pipe);
+	if (!fifo)
+		goto xfer_work_end;
+
+	chan = usbhsf_dma_chan_get(fifo, pkt);
 	dir = usbhs_pipe_is_dir_in(pipe) ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV;
 
 	desc = dmaengine_prep_slave_single(chan, pkt->dma + pkt->actual,
 					pkt->trans, dir,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
-		return;
+		goto xfer_work_end;
 
 	desc->callback		= usbhsf_dma_complete;
 	desc->callback_param	= pipe;
@@ -828,7 +836,7 @@ static void xfer_work(struct work_struct *work)
 	pkt->cookie = dmaengine_submit(desc);
 	if (pkt->cookie < 0) {
 		dev_err(dev, "Failed to submit dma descriptor\n");
-		return;
+		goto xfer_work_end;
 	}
 
 	dev_dbg(dev, "  %s %d (%d/ %d)\n",
@@ -839,6 +847,9 @@ static void xfer_work(struct work_struct *work)
 	usbhs_pipe_set_trans_count_if_bulk(pipe, pkt->trans);
 	dma_async_issue_pending(chan);
 	usbhs_pipe_enable(pipe);
+
+xfer_work_end:
+	usbhs_unlock(priv, flags);
 }
 
 /*
@@ -858,7 +869,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done)
 
 	/* use PIO if packet is less than pio_dma_border or pipe is DCP */
 	if ((len < usbhs_get_dparam(priv, pio_dma_border)) ||
-	    usbhs_pipe_is_dcp(pipe))
+	    usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC))
 		goto usbhsf_pio_prepare_push;
 
 	/* check data length if this driver don't use USB-DMAC */
@@ -889,6 +900,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done)
 
 	pkt->trans = len;
 
+	usbhsf_tx_irq_ctrl(pipe, 0);
 	INIT_WORK(&pkt->work, xfer_work);
 	schedule_work(&pkt->work);
 
@@ -962,7 +974,7 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt,
 
 	/* use PIO if packet is less than pio_dma_border or pipe is DCP */
 	if ((pkt->length < usbhs_get_dparam(priv, pio_dma_border)) ||
-	    usbhs_pipe_is_dcp(pipe))
+	    usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC))
 		goto usbhsf_pio_prepare_pop;
 
 	fifo = usbhsf_get_dma_fifo(priv, pkt);
diff --git a/drivers/usb/renesas_usbhs/mod.c b/drivers/usb/renesas_usbhs/mod.c
index d4be5d594896..28965ef4f824 100644
--- a/drivers/usb/renesas_usbhs/mod.c
+++ b/drivers/usb/renesas_usbhs/mod.c
@@ -282,9 +282,16 @@ static irqreturn_t usbhs_interrupt(int irq, void *data)
 	if (usbhs_mod_is_host(priv))
 		usbhs_write(priv, INTSTS1, ~irq_state.intsts1 & INTSTS1_MAGIC);
 
-	usbhs_write(priv, BRDYSTS, ~irq_state.brdysts);
+	/*
+	 * The driver should not clear the xxxSTS after the line of
+	 * "call irq callback functions" because each "if" statement is
+	 * possible to call the callback function for avoiding any side effects.
+	 */
+	if (irq_state.intsts0 & BRDY)
+		usbhs_write(priv, BRDYSTS, ~irq_state.brdysts);
 	usbhs_write(priv, NRDYSTS, ~irq_state.nrdysts);
-	usbhs_write(priv, BEMPSTS, ~irq_state.bempsts);
+	if (irq_state.intsts0 & BEMP)
+		usbhs_write(priv, BEMPSTS, ~irq_state.bempsts);
 
 	/*
 	 * call irq callback functions
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 8f7a78e70975..8647d2c2a8c4 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -37,6 +37,7 @@ struct usbhsg_gpriv;
 struct usbhsg_uep {
 	struct usb_ep		 ep;
 	struct usbhs_pipe	*pipe;
+	spinlock_t		lock;	/* protect the pipe */
 
 	char ep_name[EP_NAME_SIZE];
 
@@ -158,10 +159,14 @@ static void usbhsg_queue_done(struct usbhs_priv *priv, struct usbhs_pkt *pkt)
 	struct usbhs_pipe *pipe = pkt->pipe;
 	struct usbhsg_uep *uep = usbhsg_pipe_to_uep(pipe);
 	struct usbhsg_request *ureq = usbhsg_pkt_to_ureq(pkt);
+	unsigned long flags;
 
 	ureq->req.actual = pkt->actual;
 
-	usbhsg_queue_pop(uep, ureq, 0);
+	usbhs_lock(priv, flags);
+	if (uep)
+		__usbhsg_queue_pop(uep, ureq, 0);
+	usbhs_unlock(priv, flags);
 }
 
 static void usbhsg_queue_push(struct usbhsg_uep *uep,
@@ -582,6 +587,9 @@ static int usbhsg_ep_enable(struct usb_ep *ep,
 	struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
 	struct usbhs_pipe *pipe;
 	int ret = -EIO;
+	unsigned long flags;
+
+	usbhs_lock(priv, flags);
 
 	/*
 	 * if it already have pipe,
@@ -590,7 +598,8 @@ static int usbhsg_ep_enable(struct usb_ep *ep,
 	if (uep->pipe) {
 		usbhs_pipe_clear(uep->pipe);
 		usbhs_pipe_sequence_data0(uep->pipe);
-		return 0;
+		ret = 0;
+		goto usbhsg_ep_enable_end;
 	}
 
 	pipe = usbhs_pipe_malloc(priv,
@@ -610,24 +619,36 @@ static int usbhsg_ep_enable(struct usb_ep *ep,
 		 * use dmaengine if possible.
 		 * It will use pio handler if impossible.
 		 */
-		if (usb_endpoint_dir_in(desc))
+		if (usb_endpoint_dir_in(desc)) {
 			pipe->handler = &usbhs_fifo_dma_push_handler;
-		else
+		} else {
 			pipe->handler = &usbhs_fifo_dma_pop_handler;
+			usbhs_xxxsts_clear(priv, BRDYSTS,
+					   usbhs_pipe_number(pipe));
+		}
 
 		ret = 0;
 	}
 
+usbhsg_ep_enable_end:
+	usbhs_unlock(priv, flags);
+
 	return ret;
 }
 
 static int usbhsg_ep_disable(struct usb_ep *ep)
 {
 	struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep);
-	struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep);
+	struct usbhs_pipe *pipe;
+	unsigned long flags;
+	int ret = 0;
 
-	if (!pipe)
-		return -EINVAL;
+	spin_lock_irqsave(&uep->lock, flags);
+	pipe = usbhsg_uep_to_pipe(uep);
+	if (!pipe) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	usbhsg_pipe_disable(uep);
 	usbhs_pipe_free(pipe);
@@ -635,6 +656,9 @@ static int usbhsg_ep_disable(struct usb_ep *ep)
 	uep->pipe->mod_private	= NULL;
 	uep->pipe		= NULL;
 
+out:
+	spin_unlock_irqrestore(&uep->lock, flags);
+
 	return 0;
 }
 
@@ -684,8 +708,11 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 {
 	struct usbhsg_uep *uep = usbhsg_ep_to_uep(ep);
 	struct usbhsg_request *ureq = usbhsg_req_to_ureq(req);
-	struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep);
+	struct usbhs_pipe *pipe;
+	unsigned long flags;
 
+	spin_lock_irqsave(&uep->lock, flags);
+	pipe = usbhsg_uep_to_pipe(uep);
 	if (pipe)
 		usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq));
 
@@ -694,6 +721,7 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 	 * even if the pipe is NULL.
 	 */
 	usbhsg_queue_pop(uep, ureq, -ECONNRESET);
+	spin_unlock_irqrestore(&uep->lock, flags);
 
 	return 0;
 }
@@ -840,10 +868,10 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
 	struct usbhs_mod *mod = usbhs_mod_get_current(priv);
-	struct usbhsg_uep *dcp = usbhsg_gpriv_to_dcp(gpriv);
+	struct usbhsg_uep *uep;
 	struct device *dev = usbhs_priv_to_dev(priv);
 	unsigned long flags;
-	int ret = 0;
+	int ret = 0, i;
 
 	/********************  spin lock ********************/
 	usbhs_lock(priv, flags);
@@ -875,7 +903,9 @@ static int usbhsg_try_stop(struct usbhs_priv *priv, u32 status)
 	usbhs_sys_set_test_mode(priv, 0);
 	usbhs_sys_function_ctrl(priv, 0);
 
-	usbhsg_ep_disable(&dcp->ep);
+	/* disable all eps */
+	usbhsg_for_each_uep_with_dcp(uep, gpriv, i)
+		usbhsg_ep_disable(&uep->ep);
 
 	dev_dbg(dev, "stop gadget\n");
 
@@ -1058,10 +1088,11 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 		ret = -ENOMEM;
 		goto usbhs_mod_gadget_probe_err_gpriv;
 	}
+	spin_lock_init(&uep->lock);
 
 	gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED);
 	dev_info(dev, "%stransceiver found\n",
-		 gpriv->transceiver ? "" : "no ");
+		 !IS_ERR(gpriv->transceiver) ? "" : "no ");
 
 	/*
 	 * CAUTION
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 1532cde8a437..754fc3e41005 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -99,10 +99,17 @@ static int ark3116_read_reg(struct usb_serial *serial,
 				 usb_rcvctrlpipe(serial->dev, 0),
 				 0xfe, 0xc0, 0, reg,
 				 buf, 1, ARK_TIMEOUT);
-	if (result < 0)
+	if (result < 1) {
+		dev_err(&serial->interface->dev,
+				"failed to read register %u: %d\n",
+				reg, result);
+		if (result >= 0)
+			result = -EIO;
+
 		return result;
-	else
-		return buf[0];
+	}
+
+	return buf[0];
 }
 
 static inline int calc_divisor(int bps)
@@ -366,23 +373,29 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 		dev_dbg(&port->dev,
 			"%s - usb_serial_generic_open failed: %d\n",
 			__func__, result);
-		goto err_out;
+		goto err_free;
 	}
 
 	/* remove any data still left: also clears error state */
 	ark3116_read_reg(serial, UART_RX, buf);
 
 	/* read modem status */
-	priv->msr = ark3116_read_reg(serial, UART_MSR, buf);
+	result = ark3116_read_reg(serial, UART_MSR, buf);
+	if (result < 0)
+		goto err_close;
+	priv->msr = *buf;
+
 	/* read line status */
-	priv->lsr = ark3116_read_reg(serial, UART_LSR, buf);
+	result = ark3116_read_reg(serial, UART_LSR, buf);
+	if (result < 0)
+		goto err_close;
+	priv->lsr = *buf;
 
 	result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
 	if (result) {
 		dev_err(&port->dev, "submit irq_in urb failed %d\n",
 			result);
-		ark3116_close(port);
-		goto err_out;
+		goto err_close;
 	}
 
 	/* activate interrupts */
@@ -395,8 +408,15 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 	if (tty)
 		ark3116_set_termios(tty, port, NULL);
 
-err_out:
 	kfree(buf);
+
+	return 0;
+
+err_close:
+	usb_serial_generic_close(port);
+err_free:
+	kfree(buf);
+
 	return result;
 }
 
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index c73808f095bb..71133d96f97d 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -99,6 +99,8 @@ static int ch341_control_out(struct usb_device *dev, u8 request,
 	r = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), request,
 			    USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 			    value, index, NULL, 0, DEFAULT_TIMEOUT);
+	if (r < 0)
+		dev_err(&dev->dev, "failed to send control message: %d\n", r);
 
 	return r;
 }
@@ -116,7 +118,20 @@ static int ch341_control_in(struct usb_device *dev,
 	r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
 			    USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
 			    value, index, buf, bufsize, DEFAULT_TIMEOUT);
-	return r;
+	if (r < bufsize) {
+		if (r >= 0) {
+			dev_err(&dev->dev,
+				"short control message received (%d < %u)\n",
+				r, bufsize);
+			r = -EIO;
+		}
+
+		dev_err(&dev->dev, "failed to receive control message: %d\n",
+			r);
+		return r;
+	}
+
+	return 0;
 }
 
 static int ch341_set_baudrate(struct usb_device *dev,
@@ -158,9 +173,9 @@ static int ch341_set_handshake(struct usb_device *dev, u8 control)
 
 static int ch341_get_status(struct usb_device *dev, struct ch341_private *priv)
 {
+	const unsigned int size = 2;
 	char *buffer;
 	int r;
-	const unsigned size = 8;
 	unsigned long flags;
 
 	buffer = kmalloc(size, GFP_KERNEL);
@@ -171,14 +186,9 @@ static int ch341_get_status(struct usb_device *dev, struct ch341_private *priv)
 	if (r < 0)
 		goto out;
 
-	/* setup the private status if available */
-	if (r == 2) {
-		r = 0;
-		spin_lock_irqsave(&priv->lock, flags);
-		priv->line_status = (~(*buffer)) & CH341_BITS_MODEM_STAT;
-		spin_unlock_irqrestore(&priv->lock, flags);
-	} else
-		r = -EPROTO;
+	spin_lock_irqsave(&priv->lock, flags);
+	priv->line_status = (~(*buffer)) & CH341_BITS_MODEM_STAT;
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 out:	kfree(buffer);
 	return r;
@@ -188,9 +198,9 @@ out:	kfree(buffer);
 
 static int ch341_configure(struct usb_device *dev, struct ch341_private *priv)
 {
+	const unsigned int size = 2;
 	char *buffer;
 	int r;
-	const unsigned size = 8;
 
 	buffer = kmalloc(size, GFP_KERNEL);
 	if (!buffer)
@@ -253,7 +263,6 @@ static int ch341_port_probe(struct usb_serial_port *port)
 
 	spin_lock_init(&priv->lock);
 	priv->baud_rate = DEFAULT_BAUD_RATE;
-	priv->line_control = CH341_BIT_RTS | CH341_BIT_DTR;
 
 	r = ch341_configure(port->serial->dev, priv);
 	if (r < 0)
@@ -315,7 +324,7 @@ static int ch341_open(struct tty_struct *tty, struct usb_serial_port *port)
 
 	r = ch341_configure(serial->dev, priv);
 	if (r)
-		goto out;
+		return r;
 
 	if (tty)
 		ch341_set_termios(tty, port, NULL);
@@ -325,12 +334,19 @@ static int ch341_open(struct tty_struct *tty, struct usb_serial_port *port)
 	if (r) {
 		dev_err(&port->dev, "%s - failed to submit interrupt urb: %d\n",
 			__func__, r);
-		goto out;
+		return r;
 	}
 
 	r = usb_serial_generic_open(tty, port);
+	if (r)
+		goto err_kill_interrupt_urb;
 
-out:	return r;
+	return 0;
+
+err_kill_interrupt_urb:
+	usb_kill_urb(port->interrupt_in_urb);
+
+	return r;
 }
 
 /* Old_termios contains the original termios settings and
@@ -345,26 +361,25 @@ static void ch341_set_termios(struct tty_struct *tty,
 
 	baud_rate = tty_get_baud_rate(tty);
 
-	priv->baud_rate = baud_rate;
-
 	if (baud_rate) {
-		spin_lock_irqsave(&priv->lock, flags);
-		priv->line_control |= (CH341_BIT_DTR | CH341_BIT_RTS);
-		spin_unlock_irqrestore(&priv->lock, flags);
+		priv->baud_rate = baud_rate;
 		ch341_set_baudrate(port->serial->dev, priv);
-	} else {
-		spin_lock_irqsave(&priv->lock, flags);
-		priv->line_control &= ~(CH341_BIT_DTR | CH341_BIT_RTS);
-		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
-	ch341_set_handshake(port->serial->dev, priv->line_control);
-
 	/* Unimplemented:
 	 * (cflag & CSIZE) : data bits [5, 8]
 	 * (cflag & PARENB) : parity {NONE, EVEN, ODD}
 	 * (cflag & CSTOPB) : stop bits [1, 2]
 	 */
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (C_BAUD(tty) == B0)
+		priv->line_control &= ~(CH341_BIT_DTR | CH341_BIT_RTS);
+	else if (old_termios && (old_termios->c_cflag & CBAUD) == B0)
+		priv->line_control |= (CH341_BIT_DTR | CH341_BIT_RTS);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	ch341_set_handshake(port->serial->dev, priv->line_control);
 }
 
 static void ch341_break_ctl(struct tty_struct *tty, int break_state)
@@ -539,14 +554,23 @@ static int ch341_tiocmget(struct tty_struct *tty)
 
 static int ch341_reset_resume(struct usb_serial *serial)
 {
-	struct ch341_private *priv;
-
-	priv = usb_get_serial_port_data(serial->port[0]);
+	struct usb_serial_port *port = serial->port[0];
+	struct ch341_private *priv = usb_get_serial_port_data(port);
+	int ret;
 
 	/* reconfigure ch341 serial port after bus-reset */
 	ch341_configure(serial->dev, priv);
 
-	return 0;
+	if (test_bit(ASYNCB_INITIALIZED, &port->port.flags)) {
+		ret = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
+		if (ret) {
+			dev_err(&port->dev, "failed to submit interrupt urb: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	return usb_serial_generic_resume(serial);
 }
 
 static struct usb_serial_driver ch341_device = {
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 7a76fe4c2f9e..41a6513646de 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -108,6 +108,7 @@ static const struct usb_device_id id_table[] = {
 	{ 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, 0x82F4) }, /* Starizona MicroTouch */
 	{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
 	{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
 	{ USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */
@@ -116,7 +117,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */
 	{ USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */
 	{ USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */
+	{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
 	{ USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */
+	{ USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */
 	{ USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */
 	{ USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
@@ -127,9 +130,12 @@ static const struct usb_device_id id_table[] = {
 	{ 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, 0x8962) }, /* Brim Brothers charging dock */
 	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
 	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
 	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
+	{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
+	{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
@@ -140,6 +146,8 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */
 	{ USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */
 	{ USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */
+	{ USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */
+	{ USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */
 	{ USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */
 	{ USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */
 	{ USB_DEVICE(0x166A, 0x0201) }, /* Clipsal 5500PACA C-Bus Pascal Automation Controller */
@@ -164,6 +172,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */
 	{ USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
 	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
+	{ USB_DEVICE(0x1901, 0x0194) },	/* GE Healthcare Remote Alarm Box */
+	{ USB_DEVICE(0x1901, 0x0195) },	/* GE B850/B650/B450 CP2104 DP UART interface */
+	{ USB_DEVICE(0x1901, 0x0196) },	/* GE B850 CP2105 DP UART interface */
 	{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
 	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
@@ -779,7 +790,7 @@ static void cp210x_set_termios(struct tty_struct *tty,
 		} else {
 			modem_ctl[0] &= ~0x7B;
 			modem_ctl[0] |= 0x01;
-			modem_ctl[1] |= 0x40;
+			modem_ctl[1] = 0x40;
 			dev_dbg(dev, "%s - flow control = NONE\n", __func__);
 		}
 
@@ -839,7 +850,9 @@ static int cp210x_tiocmget(struct tty_struct *tty)
 	unsigned int control;
 	int result;
 
-	cp210x_get_config(port, CP210X_GET_MDMSTS, &control, 1);
+	result = cp210x_get_config(port, CP210X_GET_MDMSTS, &control, 1);
+	if (result)
+		return result;
 
 	result = ((control & CONTROL_DTR) ? TIOCM_DTR : 0)
 		|((control & CONTROL_RTS) ? TIOCM_RTS : 0)
diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c
index 2916dea3ede8..8948f375e75d 100644
--- a/drivers/usb/serial/cyberjack.c
+++ b/drivers/usb/serial/cyberjack.c
@@ -50,6 +50,7 @@
 #define CYBERJACK_PRODUCT_ID	0x0100
 
 /* Function prototypes */
+static int cyberjack_attach(struct usb_serial *serial);
 static int cyberjack_port_probe(struct usb_serial_port *port);
 static int cyberjack_port_remove(struct usb_serial_port *port);
 static int  cyberjack_open(struct tty_struct *tty,
@@ -77,6 +78,7 @@ static struct usb_serial_driver cyberjack_device = {
 	.description =		"Reiner SCT Cyberjack USB card reader",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		cyberjack_attach,
 	.port_probe =		cyberjack_port_probe,
 	.port_remove =		cyberjack_port_remove,
 	.open =			cyberjack_open,
@@ -100,6 +102,14 @@ struct cyberjack_private {
 	short		wrsent;		/* Data already sent */
 };
 
+static int cyberjack_attach(struct usb_serial *serial)
+{
+	if (serial->num_bulk_out < serial->num_ports)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int cyberjack_port_probe(struct usb_serial_port *port)
 {
 	struct cyberjack_private *priv;
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index 01bf53392819..244acb1299a9 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -447,6 +447,11 @@ static int cypress_generic_port_probe(struct usb_serial_port *port)
 	struct usb_serial *serial = port->serial;
 	struct cypress_private *priv;
 
+	if (!port->interrupt_out_urb || !port->interrupt_in_urb) {
+		dev_err(&port->dev, "required endpoint is missing\n");
+		return -ENODEV;
+	}
+
 	priv = kzalloc(sizeof(struct cypress_private), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -606,12 +611,6 @@ static int cypress_open(struct tty_struct *tty, struct usb_serial_port *port)
 		cypress_set_termios(tty, port, &priv->tmp_termios);
 
 	/* setup the port and start reading from the device */
-	if (!port->interrupt_in_urb) {
-		dev_err(&port->dev, "%s - interrupt_in_urb is empty!\n",
-			__func__);
-		return -1;
-	}
-
 	usb_fill_int_urb(port->interrupt_in_urb, serial->dev,
 		usb_rcvintpipe(serial->dev, port->interrupt_in_endpointAddress),
 		port->interrupt_in_urb->transfer_buffer,
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 12b0e67473ba..be93b9ff2d98 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -1251,8 +1251,27 @@ static int digi_port_init(struct usb_serial_port *port, unsigned port_num)
 
 static int digi_startup(struct usb_serial *serial)
 {
+	struct device *dev = &serial->interface->dev;
 	struct digi_serial *serial_priv;
 	int ret;
+	int i;
+
+	/* check whether the device has the expected number of endpoints */
+	if (serial->num_port_pointers < serial->type->num_ports + 1) {
+		dev_err(dev, "OOB endpoints missing\n");
+		return -ENODEV;
+	}
+
+	for (i = 0; i < serial->type->num_ports + 1 ; i++) {
+		if (!serial->port[i]->read_urb) {
+			dev_err(dev, "bulk-in endpoint missing\n");
+			return -ENODEV;
+		}
+		if (!serial->port[i]->write_urb) {
+			dev_err(dev, "bulk-out endpoint missing\n");
+			return -ENODEV;
+		}
+	}
 
 	serial_priv = kzalloc(sizeof(*serial_priv), GFP_KERNEL);
 	if (!serial_priv)
@@ -1380,25 +1399,30 @@ static int digi_read_inb_callback(struct urb *urb)
 {
 	struct usb_serial_port *port = urb->context;
 	struct digi_port *priv = usb_get_serial_port_data(port);
-	int opcode = ((unsigned char *)urb->transfer_buffer)[0];
-	int len = ((unsigned char *)urb->transfer_buffer)[1];
-	int port_status = ((unsigned char *)urb->transfer_buffer)[2];
-	unsigned char *data = ((unsigned char *)urb->transfer_buffer) + 3;
+	unsigned char *buf = urb->transfer_buffer;
+	int opcode;
+	int len;
+	int port_status;
+	unsigned char *data;
 	int flag, throttled;
-	int status = urb->status;
-
-	/* do not process callbacks on closed ports */
-	/* but do continue the read chain */
-	if (urb->status == -ENOENT)
-		return 0;
 
 	/* short/multiple packet check */
+	if (urb->actual_length < 2) {
+		dev_warn(&port->dev, "short packet received\n");
+		return -1;
+	}
+
+	opcode = buf[0];
+	len = buf[1];
+
 	if (urb->actual_length != len + 2) {
-		dev_err(&port->dev, "%s: INCOMPLETE OR MULTIPLE PACKET, "
-			"status=%d, port=%d, opcode=%d, len=%d, "
-			"actual_length=%d, status=%d\n", __func__, status,
-			priv->dp_port_num, opcode, len, urb->actual_length,
-			port_status);
+		dev_err(&port->dev, "malformed packet received: port=%d, opcode=%d, len=%d, actual_length=%u\n",
+			priv->dp_port_num, opcode, len, urb->actual_length);
+		return -1;
+	}
+
+	if (opcode == DIGI_CMD_RECEIVE_DATA && len < 1) {
+		dev_err(&port->dev, "malformed data packet received\n");
 		return -1;
 	}
 
@@ -1412,6 +1436,9 @@ static int digi_read_inb_callback(struct urb *urb)
 
 	/* receive data */
 	if (opcode == DIGI_CMD_RECEIVE_DATA) {
+		port_status = buf[2];
+		data = &buf[3];
+
 		/* get flag from port_status */
 		flag = 0;
 
@@ -1464,16 +1491,20 @@ static int digi_read_oob_callback(struct urb *urb)
 	struct usb_serial *serial = port->serial;
 	struct tty_struct *tty;
 	struct digi_port *priv = usb_get_serial_port_data(port);
+	unsigned char *buf = urb->transfer_buffer;
 	int opcode, line, status, val;
 	int i;
 	unsigned int rts;
 
+	if (urb->actual_length < 4)
+		return -1;
+
 	/* handle each oob command */
-	for (i = 0; i < urb->actual_length - 3;) {
-		opcode = ((unsigned char *)urb->transfer_buffer)[i++];
-		line = ((unsigned char *)urb->transfer_buffer)[i++];
-		status = ((unsigned char *)urb->transfer_buffer)[i++];
-		val = ((unsigned char *)urb->transfer_buffer)[i++];
+	for (i = 0; i < urb->actual_length - 3; i += 4) {
+		opcode = buf[i];
+		line = buf[i + 1];
+		status = buf[i + 2];
+		val = buf[i + 3];
 
 		dev_dbg(&port->dev, "digi_read_oob_callback: opcode=%d, line=%d, status=%d, val=%d\n",
 			opcode, line, status, val);
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 8c660ae401d8..e0385d6c0abb 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -648,6 +648,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_TFD128_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_FM3RX_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_WS777_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_PALMSENS_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_IVIUM_XSTAT_PID) },
 	{ USB_DEVICE(FTDI_VID, LINX_SDMUSBQSS_PID) },
 	{ USB_DEVICE(FTDI_VID, LINX_MASTERDEVEL2_PID) },
 	{ USB_DEVICE(FTDI_VID, LINX_FUTURE_0_PID) },
@@ -807,10 +809,10 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
 	{ USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
-	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
-		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
-	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
-		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(OLIMEX_VID, OLIMEX_ARM_USB_TINY_H_PID, 1) },
 	{ USB_DEVICE(FIC_VID, FIC_NEO1973_DEBUG_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_OOCDLINK_PID),
@@ -871,6 +873,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(MICROCHIP_VID, MICROCHIP_USB_BOARD_PID,
 					USB_CLASS_VENDOR_SPEC,
 					USB_SUBCLASS_VENDOR_SPEC, 0x00) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ACTEL_VID, MICROSEMI_ARROW_SF2PLUS_BOARD_PID, 2) },
 	{ USB_DEVICE(JETI_VID, JETI_SPC1201_PID) },
 	{ USB_DEVICE(MARVELL_VID, MARVELL_SHEEVAPLUG_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
@@ -984,7 +987,8 @@ static const struct usb_device_id id_table_combined[] = {
 	/* ekey Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
 	/* Infineon Devices */
-	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC1798_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC2X7_PID, 1) },
 	/* GE Healthcare devices */
 	{ USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) },
 	/* Active Research (Actisense) devices */
@@ -1004,6 +1008,13 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) },
+	/* ICP DAS I-756xU devices */
+	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) },
+	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) },
+	{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) },
+	{ USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) },
+	{ USB_DEVICE(TI_VID, TI_CC3200_LAUNCHPAD_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ }					/* Terminating entry */
 };
 
@@ -1429,10 +1440,13 @@ static int read_latency_timer(struct usb_serial_port *port)
 			     FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE,
 			     0, priv->interface,
 			     buf, 1, WDR_TIMEOUT);
-	if (rv < 0)
+	if (rv < 1) {
 		dev_err(&port->dev, "Unable to read latency timer: %i\n", rv);
-	else
+		if (rv >= 0)
+			rv = -EIO;
+	} else {
 		priv->latency = buf[0];
+	}
 
 	kfree(buf);
 
@@ -1494,9 +1508,9 @@ static int set_serial_info(struct tty_struct *tty,
 					(new_serial.flags & ASYNC_FLAGS));
 	priv->custom_divisor = new_serial.custom_divisor;
 
+check_and_exit:
 	write_latency_timer(port);
 
-check_and_exit:
 	if ((old_priv.flags & ASYNC_SPD_MASK) !=
 	     (priv->flags & ASYNC_SPD_MASK)) {
 		if ((priv->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI)
@@ -1797,8 +1811,6 @@ static int ftdi_sio_port_probe(struct usb_serial_port *port)
 
 	mutex_init(&priv->cfg_lock);
 
-	priv->flags = ASYNC_LOW_LATENCY;
-
 	if (quirk && quirk->port_probe)
 		quirk->port_probe(priv);
 
@@ -2062,6 +2074,20 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 		priv->prev_status = status;
 	}
 
+	/* save if the transmitter is empty or not */
+	if (packet[1] & FTDI_RS_TEMT)
+		priv->transmit_empty = 1;
+	else
+		priv->transmit_empty = 0;
+
+	len -= 2;
+	if (!len)
+		return 0;	/* status only */
+
+	/*
+	 * Break and error status must only be processed for packets with
+	 * data payload to avoid over-reporting.
+	 */
 	flag = TTY_NORMAL;
 	if (packet[1] & FTDI_RS_ERR_MASK) {
 		/* Break takes precedence over parity, which takes precedence
@@ -2084,15 +2110,6 @@ static int ftdi_process_packet(struct usb_serial_port *port,
 		}
 	}
 
-	/* save if the transmitter is empty or not */
-	if (packet[1] & FTDI_RS_TEMT)
-		priv->transmit_empty = 1;
-	else
-		priv->transmit_empty = 0;
-
-	len -= 2;
-	if (!len)
-		return 0;	/* status only */
 	port->icount.rx += len;
 	ch = packet + 2;
 
@@ -2423,8 +2440,12 @@ static int ftdi_get_modem_status(struct usb_serial_port *port,
 			FTDI_SIO_GET_MODEM_STATUS_REQUEST_TYPE,
 			0, priv->interface,
 			buf, len, WDR_TIMEOUT);
-	if (ret < 0) {
+
+	/* NOTE: We allow short responses and handle that below. */
+	if (ret < 1) {
 		dev_err(&port->dev, "failed to get modem status: %d\n", ret);
+		if (ret >= 0)
+			ret = -EIO;
 		ret = usb_translate_errors(ret);
 		goto out;
 	}
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index a84df2513994..4fcf1cecb6d7 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -406,6 +406,12 @@
 #define FTDI_4N_GALAXY_DE_3_PID	0xF3C2
 
 /*
+ * Ivium Technologies product IDs
+ */
+#define FTDI_PALMSENS_PID	0xf440
+#define FTDI_IVIUM_XSTAT_PID	0xf441
+
+/*
  * Linx Technologies product ids
  */
 #define LINX_SDMUSBQSS_PID	0xF448	/* Linx SDM-USB-QS-S */
@@ -590,6 +596,12 @@
 #define STK541_PID		0x2109 /* Zigbee Controller */
 
 /*
+ * Texas Instruments
+ */
+#define TI_VID			0x0451
+#define TI_CC3200_LAUNCHPAD_PID	0xC32A /* SimpleLink Wi-Fi CC3200 LaunchPad */
+
+/*
  * Blackfin gnICE JTAG
  * http://docs.blackfin.uclinux.org/doku.php?id=hw:jtag:gnice
  */
@@ -620,8 +632,9 @@
 /*
  * Infineon Technologies
  */
-#define INFINEON_VID		0x058b
-#define INFINEON_TRIBOARD_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_VID		        0x058b
+#define INFINEON_TRIBOARD_TC1798_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_TRIBOARD_TC2X7_PID	0x0043 /* DAS JTAG TriBoard TC2X7 V1.0 */
 
 /*
  * Acton Research Corp.
@@ -673,6 +686,12 @@
 #define INTREPID_NEOVI_PID	0x0701
 
 /*
+ * WICED USB UART
+ */
+#define WICED_VID		0x0A5C
+#define WICED_USB20706V2_PID	0x6422
+
+/*
  * Definitions for ID TECH (www.idt-net.com) devices
  */
 #define IDTECH_VID		0x0ACD	/* ID TECH Vendor ID */
@@ -854,9 +873,17 @@
 #define	FIC_VID			0x1457
 #define	FIC_NEO1973_DEBUG_PID	0x5118
 
+/*
+ * Actel / Microsemi
+ */
+#define ACTEL_VID				0x1514
+#define MICROSEMI_ARROW_SF2PLUS_BOARD_PID	0x2008
+
 /* Olimex */
 #define OLIMEX_VID			0x15BA
 #define OLIMEX_ARM_USB_OCD_PID		0x0003
+#define OLIMEX_ARM_USB_TINY_PID	0x0004
+#define OLIMEX_ARM_USB_TINY_H_PID	0x002a
 #define OLIMEX_ARM_USB_OCD_H_PID	0x002b
 
 /*
@@ -872,6 +899,14 @@
 #define NOVITUS_BONO_E_PID		0x6010
 
 /*
+ * ICPDAS I-756*U devices
+ */
+#define ICPDAS_VID			0x1b5c
+#define ICPDAS_I7560U_PID		0x0103
+#define ICPDAS_I7561U_PID		0x0104
+#define ICPDAS_I7563U_PID		0x0105
+
+/*
  * RT Systems programming cables for various ham radios
  */
 #define RTSYSTEMS_VID		0x2100	/* Vendor ID */
diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c
index db591d19d416..37d0e8cc7af6 100644
--- a/drivers/usb/serial/garmin_gps.c
+++ b/drivers/usb/serial/garmin_gps.c
@@ -1044,6 +1044,7 @@ static int garmin_write_bulk(struct usb_serial_port *port,
 		   "%s - usb_submit_urb(write bulk) failed with status = %d\n",
 				__func__, status);
 		count = status;
+		kfree(buffer);
 	}
 
 	/* we are done with this urb, so let the host driver
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index c0866971db2b..749e1b674145 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -492,20 +492,24 @@ static int get_epic_descriptor(struct edgeport_serial *ep)
 	int result;
 	struct usb_serial *serial = ep->serial;
 	struct edgeport_product_info *product_info = &ep->product_info;
-	struct edge_compatibility_descriptor *epic = &ep->epic_descriptor;
+	struct edge_compatibility_descriptor *epic;
 	struct edge_compatibility_bits *bits;
 	struct device *dev = &serial->dev->dev;
 
 	ep->is_epic = 0;
+
+	epic = kmalloc(sizeof(*epic), GFP_KERNEL);
+	if (!epic)
+		return -ENOMEM;
+
 	result = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
 				 USB_REQUEST_ION_GET_EPIC_DESC,
 				 0xC0, 0x00, 0x00,
-				 &ep->epic_descriptor,
-				 sizeof(struct edge_compatibility_descriptor),
+				 epic, sizeof(*epic),
 				 300);
-
-	if (result > 0) {
+	if (result == sizeof(*epic)) {
 		ep->is_epic = 1;
+		memcpy(&ep->epic_descriptor, epic, sizeof(*epic));
 		memset(product_info, 0, sizeof(struct edgeport_product_info));
 
 		product_info->NumPorts = epic->NumPorts;
@@ -534,8 +538,16 @@ static int get_epic_descriptor(struct edgeport_serial *ep)
 		dev_dbg(dev, "  IOSPWriteLCR     : %s\n", bits->IOSPWriteLCR	? "TRUE": "FALSE");
 		dev_dbg(dev, "  IOSPSetBaudRate  : %s\n", bits->IOSPSetBaudRate	? "TRUE": "FALSE");
 		dev_dbg(dev, "  TrueEdgeport     : %s\n", bits->TrueEdgeport	? "TRUE": "FALSE");
+
+		result = 0;
+	} else if (result >= 0) {
+		dev_warn(&serial->interface->dev, "short epic descriptor received: %d\n",
+			 result);
+		result = -EIO;
 	}
 
+	kfree(epic);
+
 	return result;
 }
 
@@ -2097,8 +2109,7 @@ static int rom_write(struct usb_serial *serial, __u16 extAddr, __u16 addr,
  * rom_read
  *	reads a number of bytes from the Edgeport device starting at the given
  *	address.
- *	If successful returns the number of bytes read, otherwise it returns
- *	a negative error number of the problem.
+ *	Returns zero on success or a negative error number.
  ****************************************************************************/
 static int rom_read(struct usb_serial *serial, __u16 extAddr,
 					__u16 addr, __u16 length, __u8 *data)
@@ -2123,12 +2134,17 @@ static int rom_read(struct usb_serial *serial, __u16 extAddr,
 					USB_REQUEST_ION_READ_ROM,
 					0xC0, addr, extAddr, transfer_buffer,
 					current_length, 300);
-		if (result < 0)
+		if (result < current_length) {
+			if (result >= 0)
+				result = -EIO;
 			break;
+		}
 		memcpy(data, transfer_buffer, current_length);
 		length -= current_length;
 		addr += current_length;
 		data += current_length;
+
+		result = 0;
 	}
 
 	kfree(transfer_buffer);
@@ -2585,9 +2601,10 @@ static void get_manufacturing_desc(struct edgeport_serial *edge_serial)
 				EDGE_MANUF_DESC_LEN,
 				(__u8 *)(&edge_serial->manuf_descriptor));
 
-	if (response < 1)
-		dev_err(dev, "error in getting manufacturer descriptor\n");
-	else {
+	if (response < 0) {
+		dev_err(dev, "error in getting manufacturer descriptor: %d\n",
+				response);
+	} else {
 		char string[30];
 		dev_dbg(dev, "**Manufacturer Descriptor\n");
 		dev_dbg(dev, "  RomSize:        %dK\n",
@@ -2644,9 +2661,10 @@ static void get_boot_desc(struct edgeport_serial *edge_serial)
 				EDGE_BOOT_DESC_LEN,
 				(__u8 *)(&edge_serial->boot_descriptor));
 
-	if (response < 1)
-		dev_err(dev, "error in getting boot descriptor\n");
-	else {
+	if (response < 0) {
+		dev_err(dev, "error in getting boot descriptor: %d\n",
+				response);
+	} else {
 		dev_dbg(dev, "**Boot Descriptor:\n");
 		dev_dbg(dev, "  BootCodeLength: %d\n",
 			le16_to_cpu(edge_serial->boot_descriptor.BootCodeLength));
@@ -2761,6 +2779,11 @@ static int edge_startup(struct usb_serial *serial)
 					EDGE_COMPATIBILITY_MASK1,
 					EDGE_COMPATIBILITY_MASK2 };
 
+	if (serial->num_bulk_in < 1 || serial->num_interrupt_in < 1) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
 	dev = serial->dev;
 
 	/* create our private serial structure */
@@ -2784,7 +2807,7 @@ static int edge_startup(struct usb_serial *serial)
 	dev_info(&serial->dev->dev, "%s detected\n", edge_serial->name);
 
 	/* Read the epic descriptor */
-	if (get_epic_descriptor(edge_serial) <= 0) {
+	if (get_epic_descriptor(edge_serial) < 0) {
 		/* memcpy descriptor to Supports structures */
 		memcpy(&edge_serial->epic_descriptor.Supports, descriptor,
 		       sizeof(struct edge_compatibility_bits));
@@ -2856,14 +2879,16 @@ static int edge_startup(struct usb_serial *serial)
 				/* not set up yet, so do it now */
 				edge_serial->interrupt_read_urb =
 						usb_alloc_urb(0, GFP_KERNEL);
-				if (!edge_serial->interrupt_read_urb)
-					return -ENOMEM;
+				if (!edge_serial->interrupt_read_urb) {
+					response = -ENOMEM;
+					break;
+				}
 
 				edge_serial->interrupt_in_buffer =
 					kmalloc(buffer_size, GFP_KERNEL);
 				if (!edge_serial->interrupt_in_buffer) {
-					usb_free_urb(edge_serial->interrupt_read_urb);
-					return -ENOMEM;
+					response = -ENOMEM;
+					break;
 				}
 				edge_serial->interrupt_in_endpoint =
 						endpoint->bEndpointAddress;
@@ -2891,14 +2916,16 @@ static int edge_startup(struct usb_serial *serial)
 				/* not set up yet, so do it now */
 				edge_serial->read_urb =
 						usb_alloc_urb(0, GFP_KERNEL);
-				if (!edge_serial->read_urb)
-					return -ENOMEM;
+				if (!edge_serial->read_urb) {
+					response = -ENOMEM;
+					break;
+				}
 
 				edge_serial->bulk_in_buffer =
 					kmalloc(buffer_size, GFP_KERNEL);
 				if (!edge_serial->bulk_in_buffer) {
-					usb_free_urb(edge_serial->read_urb);
-					return -ENOMEM;
+					response = -ENOMEM;
+					break;
 				}
 				edge_serial->bulk_in_endpoint =
 						endpoint->bEndpointAddress;
@@ -2924,9 +2951,22 @@ static int edge_startup(struct usb_serial *serial)
 			}
 		}
 
-		if (!interrupt_in_found || !bulk_in_found || !bulk_out_found) {
-			dev_err(ddev, "Error - the proper endpoints were not found!\n");
-			return -ENODEV;
+		if (response || !interrupt_in_found || !bulk_in_found ||
+							!bulk_out_found) {
+			if (!response) {
+				dev_err(ddev, "expected endpoints not found\n");
+				response = -ENODEV;
+			}
+
+			usb_free_urb(edge_serial->interrupt_read_urb);
+			kfree(edge_serial->interrupt_in_buffer);
+
+			usb_free_urb(edge_serial->read_urb);
+			kfree(edge_serial->bulk_in_buffer);
+
+			kfree(edge_serial);
+
+			return response;
 		}
 
 		/* start interrupt read for this edgeport this interrupt will
@@ -2949,16 +2989,9 @@ static void edge_disconnect(struct usb_serial *serial)
 {
 	struct edgeport_serial *edge_serial = usb_get_serial_data(serial);
 
-	/* stop reads and writes on all ports */
-	/* free up our endpoint stuff */
 	if (edge_serial->is_epic) {
 		usb_kill_urb(edge_serial->interrupt_read_urb);
-		usb_free_urb(edge_serial->interrupt_read_urb);
-		kfree(edge_serial->interrupt_in_buffer);
-
 		usb_kill_urb(edge_serial->read_urb);
-		usb_free_urb(edge_serial->read_urb);
-		kfree(edge_serial->bulk_in_buffer);
 	}
 }
 
@@ -2971,6 +3004,16 @@ static void edge_release(struct usb_serial *serial)
 {
 	struct edgeport_serial *edge_serial = usb_get_serial_data(serial);
 
+	if (edge_serial->is_epic) {
+		usb_kill_urb(edge_serial->interrupt_read_urb);
+		usb_free_urb(edge_serial->interrupt_read_urb);
+		kfree(edge_serial->interrupt_in_buffer);
+
+		usb_kill_urb(edge_serial->read_urb);
+		usb_free_urb(edge_serial->read_urb);
+		kfree(edge_serial->bulk_in_buffer);
+	}
+
 	kfree(edge_serial);
 }
 
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index fce82fd79f77..e98532feb0cc 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -1499,8 +1499,7 @@ static int do_boot_mode(struct edgeport_serial *serial,
 
 		dev_dbg(dev, "%s - Download successful -- Device rebooting...\n", __func__);
 
-		/* return an error on purpose */
-		return -ENODEV;
+		return 1;
 	}
 
 stayinbootmode:
@@ -1508,7 +1507,7 @@ stayinbootmode:
 	dev_dbg(dev, "%s - STAYING IN BOOT MODE\n", __func__);
 	serial->product_info.TiMode = TI_MODE_BOOT;
 
-	return 0;
+	return 1;
 }
 
 static int ti_do_config(struct edgeport_port *port, int feature, int on)
@@ -1675,6 +1674,12 @@ static void edge_interrupt_callback(struct urb *urb)
 	function    = TIUMP_GET_FUNC_FROM_CODE(data[0]);
 	dev_dbg(dev, "%s - port_number %d, function %d, info 0x%x\n", __func__,
 		port_number, function, data[1]);
+
+	if (port_number >= edge_serial->serial->num_ports) {
+		dev_err(dev, "bad port number %d\n", port_number);
+		goto exit;
+	}
+
 	port = edge_serial->serial->port[port_number];
 	edge_port = usb_get_serial_port_data(port);
 	if (!edge_port) {
@@ -1756,7 +1761,7 @@ static void edge_bulk_in_callback(struct urb *urb)
 
 	port_number = edge_port->port->port_number;
 
-	if (edge_port->lsr_event) {
+	if (urb->actual_length > 0 && edge_port->lsr_event) {
 		edge_port->lsr_event = 0;
 		dev_dbg(dev, "%s ===== Port %u LSR Status = %02x, Data = %02x ======\n",
 			__func__, port_number, edge_port->lsr_mask, *data);
@@ -2344,8 +2349,11 @@ static void change_port_settings(struct tty_struct *tty,
 	if (!baud) {
 		/* pick a default, any default... */
 		baud = 9600;
-	} else
+	} else {
+		/* Avoid a zero divisor. */
+		baud = min(baud, 461550);
 		tty_encode_baud_rate(tty, baud, baud);
+	}
 
 	edge_port->baud_rate = baud;
 	config->wBaudRate = (__u16)((461550L + baud/2) / baud);
@@ -2549,6 +2557,13 @@ static int edge_startup(struct usb_serial *serial)
 	int status;
 	u16 product_id;
 
+	/* Make sure we have the required endpoints when in download mode. */
+	if (serial->interface->cur_altsetting->desc.bNumEndpoints > 1) {
+		if (serial->num_bulk_in < serial->num_ports ||
+				serial->num_bulk_out < serial->num_ports)
+			return -ENODEV;
+	}
+
 	/* create our private serial structure */
 	edge_serial = kzalloc(sizeof(struct edgeport_serial), GFP_KERNEL);
 	if (!edge_serial)
@@ -2556,14 +2571,18 @@ static int edge_startup(struct usb_serial *serial)
 
 	mutex_init(&edge_serial->es_lock);
 	edge_serial->serial = serial;
+	INIT_DELAYED_WORK(&edge_serial->heartbeat_work, edge_heartbeat_work);
 	usb_set_serial_data(serial, edge_serial);
 
 	status = download_fw(edge_serial);
-	if (status) {
+	if (status < 0) {
 		kfree(edge_serial);
 		return status;
 	}
 
+	if (status > 0)
+		return 1;	/* bind but do not register any ports */
+
 	product_id = le16_to_cpu(
 			edge_serial->serial->dev->descriptor.idProduct);
 
@@ -2575,7 +2594,6 @@ static int edge_startup(struct usb_serial *serial)
 		}
 	}
 
-	INIT_DELAYED_WORK(&edge_serial->heartbeat_work, edge_heartbeat_work);
 	edge_heartbeat_schedule(edge_serial);
 
 	return 0;
@@ -2583,6 +2601,9 @@ static int edge_startup(struct usb_serial *serial)
 
 static void edge_disconnect(struct usb_serial *serial)
 {
+	struct edgeport_serial *edge_serial = usb_get_serial_data(serial);
+
+	cancel_delayed_work_sync(&edge_serial->heartbeat_work);
 }
 
 static void edge_release(struct usb_serial *serial)
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 5ad4a0fb4b26..7ed7d33d6c10 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -68,6 +68,16 @@ struct iuu_private {
 	u32 clk;
 };
 
+static int iuu_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports || serial->num_bulk_out < num_ports)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int iuu_port_probe(struct usb_serial_port *port)
 {
 	struct iuu_private *priv;
@@ -1196,6 +1206,7 @@ static struct usb_serial_driver iuu_device = {
 	.tiocmset = iuu_tiocmset,
 	.set_termios = iuu_set_termios,
 	.init_termios = iuu_init_termios,
+	.attach = iuu_attach,
 	.port_probe = iuu_port_probe,
 	.port_remove = iuu_port_remove,
 };
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index e07b15ed5814..7faa901ee47f 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -2376,6 +2376,10 @@ static void keyspan_release(struct usb_serial *serial)
 
 	s_priv = usb_get_serial_data(serial);
 
+	/* Make sure to unlink the URBs submitted in attach. */
+	usb_kill_urb(s_priv->instat_urb);
+	usb_kill_urb(s_priv->indat_urb);
+
 	usb_free_urb(s_priv->instat_urb);
 	usb_free_urb(s_priv->indat_urb);
 	usb_free_urb(s_priv->glocont_urb);
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 4f7e072e4e00..6b0942428917 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -139,6 +139,7 @@ static void keyspan_pda_rx_interrupt(struct urb *urb)
 {
 	struct usb_serial_port *port = urb->context;
 	unsigned char *data = urb->transfer_buffer;
+	unsigned int len = urb->actual_length;
 	int retval;
 	int status = urb->status;
 	struct keyspan_pda_private *priv;
@@ -159,18 +160,26 @@ static void keyspan_pda_rx_interrupt(struct urb *urb)
 		goto exit;
 	}
 
+	if (len < 1) {
+		dev_warn(&port->dev, "short message received\n");
+		goto exit;
+	}
+
 	/* see if the message is data or a status interrupt */
 	switch (data[0]) {
 	case 0:
 		 /* rest of message is rx data */
-		if (urb->actual_length) {
-			tty_insert_flip_string(&port->port, data + 1,
-						urb->actual_length - 1);
-			tty_flip_buffer_push(&port->port);
-		}
+		if (len < 2)
+			break;
+		tty_insert_flip_string(&port->port, data + 1, len - 1);
+		tty_flip_buffer_push(&port->port);
 		break;
 	case 1:
 		/* status interrupt */
+		if (len < 3) {
+			dev_warn(&port->dev, "short interrupt message received\n");
+			break;
+		}
 		dev_dbg(&port->dev, "rx int, d1=%d, d2=%d\n", data[1], data[2]);
 		switch (data[1]) {
 		case 1: /* modemline change */
@@ -699,6 +708,19 @@ MODULE_FIRMWARE("keyspan_pda/keyspan_pda.fw");
 MODULE_FIRMWARE("keyspan_pda/xircom_pgs.fw");
 #endif
 
+static int keyspan_pda_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int keyspan_pda_port_probe(struct usb_serial_port *port)
 {
 
@@ -776,6 +798,7 @@ static struct usb_serial_driver keyspan_pda_device = {
 	.break_ctl =		keyspan_pda_break_ctl,
 	.tiocmget =		keyspan_pda_tiocmget,
 	.tiocmset =		keyspan_pda_tiocmset,
+	.attach =		keyspan_pda_attach,
 	.port_probe =		keyspan_pda_port_probe,
 	.port_remove =		keyspan_pda_port_remove,
 };
diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c
index e020ad28a00c..83c823d32ff9 100644
--- a/drivers/usb/serial/kl5kusb105.c
+++ b/drivers/usb/serial/kl5kusb105.c
@@ -192,10 +192,11 @@ static int klsi_105_get_line_state(struct usb_serial_port *port,
 			     status_buf, KLSI_STATUSBUF_LEN,
 			     10000
 			     );
-	if (rc < 0)
-		dev_err(&port->dev, "Reading line status failed (error = %d)\n",
-			rc);
-	else {
+	if (rc != KLSI_STATUSBUF_LEN) {
+		dev_err(&port->dev, "reading line status failed: %d\n", rc);
+		if (rc >= 0)
+			rc = -EIO;
+	} else {
 		status = get_unaligned_le16(status_buf);
 
 		dev_info(&port->serial->dev->dev, "read status %x %x\n",
@@ -296,7 +297,7 @@ static int  klsi_105_open(struct tty_struct *tty, struct usb_serial_port *port)
 	rc = usb_serial_generic_open(tty, port);
 	if (rc) {
 		retval = rc;
-		goto exit;
+		goto err_free_cfg;
 	}
 
 	rc = usb_control_msg(port->serial->dev,
@@ -311,21 +312,38 @@ static int  klsi_105_open(struct tty_struct *tty, struct usb_serial_port *port)
 	if (rc < 0) {
 		dev_err(&port->dev, "Enabling read failed (error = %d)\n", rc);
 		retval = rc;
+		goto err_generic_close;
 	} else
 		dev_dbg(&port->dev, "%s - enabled reading\n", __func__);
 
 	rc = klsi_105_get_line_state(port, &line_state);
-	if (rc >= 0) {
-		spin_lock_irqsave(&priv->lock, flags);
-		priv->line_state = line_state;
-		spin_unlock_irqrestore(&priv->lock, flags);
-		dev_dbg(&port->dev, "%s - read line state 0x%lx\n", __func__, line_state);
-		retval = 0;
-	} else
+	if (rc < 0) {
 		retval = rc;
+		goto err_disable_read;
+	}
+
+	spin_lock_irqsave(&priv->lock, flags);
+	priv->line_state = line_state;
+	spin_unlock_irqrestore(&priv->lock, flags);
+	dev_dbg(&port->dev, "%s - read line state 0x%lx\n", __func__,
+			line_state);
+
+	return 0;
 
-exit:
+err_disable_read:
+	usb_control_msg(port->serial->dev,
+			     usb_sndctrlpipe(port->serial->dev, 0),
+			     KL5KUSB105A_SIO_CONFIGURE,
+			     USB_TYPE_VENDOR | USB_DIR_OUT,
+			     KL5KUSB105A_SIO_CONFIGURE_READ_OFF,
+			     0, /* index */
+			     NULL, 0,
+			     KLSI_TIMEOUT);
+err_generic_close:
+	usb_serial_generic_close(port);
+err_free_cfg:
 	kfree(cfg);
+
 	return retval;
 }
 
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index 2363654cafc9..813035f51fe7 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -51,6 +51,7 @@
 
 
 /* Function prototypes */
+static int kobil_attach(struct usb_serial *serial);
 static int kobil_port_probe(struct usb_serial_port *probe);
 static int kobil_port_remove(struct usb_serial_port *probe);
 static int  kobil_open(struct tty_struct *tty, struct usb_serial_port *port);
@@ -86,6 +87,7 @@ static struct usb_serial_driver kobil_device = {
 	.description =		"KOBIL USB smart card terminal",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		kobil_attach,
 	.port_probe =		kobil_port_probe,
 	.port_remove =		kobil_port_remove,
 	.ioctl =		kobil_ioctl,
@@ -113,6 +115,16 @@ struct kobil_private {
 };
 
 
+static int kobil_attach(struct usb_serial *serial)
+{
+	if (serial->num_interrupt_out < serial->num_ports) {
+		dev_err(&serial->interface->dev, "missing interrupt-out endpoint\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int kobil_port_probe(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c
index fd707d6a10e2..a6c07c6be25f 100644
--- a/drivers/usb/serial/mct_u232.c
+++ b/drivers/usb/serial/mct_u232.c
@@ -189,7 +189,7 @@ static int mct_u232_set_baud_rate(struct tty_struct *tty,
 		return -ENOMEM;
 
 	divisor = mct_u232_calculate_baud_rate(serial, value, &speed);
-	put_unaligned_le32(cpu_to_le32(divisor), buf);
+	put_unaligned_le32(divisor, buf);
 	rc = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
 				MCT_U232_SET_BAUD_RATE_REQUEST,
 				MCT_U232_SET_REQUEST_TYPE,
@@ -322,8 +322,12 @@ static int mct_u232_get_modem_stat(struct usb_serial_port *port,
 			MCT_U232_GET_REQUEST_TYPE,
 			0, 0, buf, MCT_U232_GET_MODEM_STAT_SIZE,
 			WDR_TIMEOUT);
-	if (rc < 0) {
+	if (rc < MCT_U232_GET_MODEM_STAT_SIZE) {
 		dev_err(&port->dev, "Get MODEM STATus failed (error = %d)\n", rc);
+
+		if (rc >= 0)
+			rc = -EIO;
+
 		*msr = 0;
 	} else {
 		*msr = buf[0];
@@ -376,14 +380,21 @@ static void mct_u232_msr_to_state(struct usb_serial_port *port,
 
 static int mct_u232_port_probe(struct usb_serial_port *port)
 {
+	struct usb_serial *serial = port->serial;
 	struct mct_u232_private *priv;
 
+	/* check first to simplify error handling */
+	if (!serial->port[1] || !serial->port[1]->interrupt_in_urb) {
+		dev_err(&port->dev, "expected endpoint missing\n");
+		return -ENODEV;
+	}
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	/* Use second interrupt-in endpoint for reading. */
-	priv->read_urb = port->serial->port[1]->interrupt_in_urb;
+	priv->read_urb = serial->port[1]->interrupt_in_urb;
 	priv->read_urb->context = port;
 
 	spin_lock_init(&priv->lock);
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 78b4f64c6b00..e56cdb436de3 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -65,8 +65,6 @@ struct moschip_port {
 	struct urb		*write_urb_pool[NUM_URBS];
 };
 
-static struct usb_serial_driver moschip7720_2port_driver;
-
 #define USB_VENDOR_ID_MOSCHIP		0x9710
 #define MOSCHIP_DEVICE_ID_7720		0x7720
 #define MOSCHIP_DEVICE_ID_7715		0x7715
@@ -970,25 +968,6 @@ static void mos7720_bulk_out_data_callback(struct urb *urb)
 		tty_port_tty_wakeup(&mos7720_port->port->port);
 }
 
-/*
- * mos77xx_probe
- *	this function installs the appropriate read interrupt endpoint callback
- *	depending on whether the device is a 7720 or 7715, thus avoiding costly
- *	run-time checks in the high-frequency callback routine itself.
- */
-static int mos77xx_probe(struct usb_serial *serial,
-			 const struct usb_device_id *id)
-{
-	if (id->idProduct == MOSCHIP_DEVICE_ID_7715)
-		moschip7720_2port_driver.read_int_callback =
-			mos7715_interrupt_callback;
-	else
-		moschip7720_2port_driver.read_int_callback =
-			mos7720_interrupt_callback;
-
-	return 0;
-}
-
 static int mos77xx_calc_num_ports(struct usb_serial *serial)
 {
 	u16 product = le16_to_cpu(serial->dev->descriptor.idProduct);
@@ -1252,7 +1231,7 @@ static int mos7720_write(struct tty_struct *tty, struct usb_serial_port *port,
 
 	if (urb->transfer_buffer == NULL) {
 		urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE,
-					       GFP_KERNEL);
+					       GFP_ATOMIC);
 		if (!urb->transfer_buffer)
 			goto exit;
 	}
@@ -1920,6 +1899,11 @@ static int mos7720_startup(struct usb_serial *serial)
 	u16 product;
 	int ret_val;
 
+	if (serial->num_bulk_in < 2 || serial->num_bulk_out < 2) {
+		dev_err(&serial->interface->dev, "missing bulk endpoints\n");
+		return -ENODEV;
+	}
+
 	product = le16_to_cpu(serial->dev->descriptor.idProduct);
 	dev = serial->dev;
 
@@ -1944,19 +1928,18 @@ static int mos7720_startup(struct usb_serial *serial)
 			tmp->interrupt_in_endpointAddress;
 		serial->port[1]->interrupt_in_urb = NULL;
 		serial->port[1]->interrupt_in_buffer = NULL;
+
+		if (serial->port[0]->interrupt_in_urb) {
+			struct urb *urb = serial->port[0]->interrupt_in_urb;
+
+			urb->complete = mos7715_interrupt_callback;
+		}
 	}
 
 	/* setting configuration feature to one */
 	usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
 			(__u8)0x03, 0x00, 0x01, 0x00, NULL, 0x00, 5000);
 
-	/* start the interrupt urb */
-	ret_val = usb_submit_urb(serial->port[0]->interrupt_in_urb, GFP_KERNEL);
-	if (ret_val)
-		dev_err(&dev->dev,
-			"%s - Error %d submitting control urb\n",
-			__func__, ret_val);
-
 #ifdef CONFIG_USB_SERIAL_MOS7715_PARPORT
 	if (product == MOSCHIP_DEVICE_ID_7715) {
 		ret_val = mos7715_parport_init(serial);
@@ -1964,6 +1947,13 @@ static int mos7720_startup(struct usb_serial *serial)
 			return ret_val;
 	}
 #endif
+	/* start the interrupt urb */
+	ret_val = usb_submit_urb(serial->port[0]->interrupt_in_urb, GFP_KERNEL);
+	if (ret_val) {
+		dev_err(&dev->dev, "failed to submit interrupt urb: %d\n",
+			ret_val);
+	}
+
 	/* LSR For Port 1 */
 	read_mos_reg(serial, 0, MOS7720_LSR, &data);
 	dev_dbg(&dev->dev, "LSR:%x\n", data);
@@ -1973,6 +1963,8 @@ static int mos7720_startup(struct usb_serial *serial)
 
 static void mos7720_release(struct usb_serial *serial)
 {
+	usb_kill_urb(serial->port[0]->interrupt_in_urb);
+
 #ifdef CONFIG_USB_SERIAL_MOS7715_PARPORT
 	/* close the parallel port */
 
@@ -2007,6 +1999,7 @@ static void mos7720_release(struct usb_serial *serial)
 				    urblist_entry)
 			usb_unlink_urb(urbtrack->urb);
 		spin_unlock_irqrestore(&mos_parport->listlock, flags);
+		parport_del_port(mos_parport->pp);
 
 		kref_put(&mos_parport->ref_count, destroy_mos_parport);
 	}
@@ -2055,7 +2048,6 @@ static struct usb_serial_driver moschip7720_2port_driver = {
 	.close			= mos7720_close,
 	.throttle		= mos7720_throttle,
 	.unthrottle		= mos7720_unthrottle,
-	.probe			= mos77xx_probe,
 	.attach			= mos7720_startup,
 	.release		= mos7720_release,
 	.port_probe		= mos7720_port_probe,
@@ -2069,7 +2061,7 @@ static struct usb_serial_driver moschip7720_2port_driver = {
 	.chars_in_buffer	= mos7720_chars_in_buffer,
 	.break_ctl		= mos7720_break,
 	.read_bulk_callback	= mos7720_bulk_in_callback,
-	.read_int_callback	= NULL  /* dynamically assigned in probe() */
+	.read_int_callback	= mos7720_interrupt_callback,
 };
 
 static struct usb_serial_driver * const serial_drivers[] = {
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 8ac9b55f05af..d17685cc00c9 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1024,6 +1024,7 @@ static int mos7840_open(struct tty_struct *tty, struct usb_serial_port *port)
 	 * (can't set it up in mos7840_startup as the structures *
 	 * were not set up at that time.)                        */
 	if (port0->open_ports == 1) {
+		/* FIXME: Buffer never NULL, so URB is not submitted. */
 		if (serial->port[0]->interrupt_in_buffer == NULL) {
 			/* set up interrupt urb */
 			usb_fill_int_urb(serial->port[0]->interrupt_in_urb,
@@ -1340,8 +1341,8 @@ static int mos7840_write(struct tty_struct *tty, struct usb_serial_port *port,
 	}
 
 	if (urb->transfer_buffer == NULL) {
-		urb->transfer_buffer =
-		    kmalloc(URB_TRANSFER_BUFFER_SIZE, GFP_KERNEL);
+		urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE,
+					       GFP_ATOMIC);
 		if (!urb->transfer_buffer)
 			goto exit;
 	}
@@ -2116,6 +2117,18 @@ static int mos7840_calc_num_ports(struct usb_serial *serial)
 	return mos7840_num_ports;
 }
 
+static int mos7840_attach(struct usb_serial *serial)
+{
+	if (serial->num_bulk_in < serial->num_ports ||
+			serial->num_bulk_out < serial->num_ports ||
+			serial->num_interrupt_in < 1) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int mos7840_port_probe(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
@@ -2391,6 +2404,7 @@ static struct usb_serial_driver moschip7840_4port_device = {
 	.tiocmset = mos7840_tiocmset,
 	.tiocmiwait = usb_serial_generic_tiocmiwait,
 	.get_icount = usb_serial_generic_get_icount,
+	.attach = mos7840_attach,
 	.port_probe = mos7840_port_probe,
 	.port_remove = mos7840_port_remove,
 	.read_bulk_callback = mos7840_bulk_in_callback,
diff --git a/drivers/usb/serial/mxuport.c b/drivers/usb/serial/mxuport.c
index 31a8b47f1ac6..c6596cbcc4b6 100644
--- a/drivers/usb/serial/mxuport.c
+++ b/drivers/usb/serial/mxuport.c
@@ -1259,6 +1259,15 @@ static int mxuport_attach(struct usb_serial *serial)
 	return 0;
 }
 
+static void mxuport_release(struct usb_serial *serial)
+{
+	struct usb_serial_port *port0 = serial->port[0];
+	struct usb_serial_port *port1 = serial->port[1];
+
+	usb_serial_generic_close(port1);
+	usb_serial_generic_close(port0);
+}
+
 static int mxuport_open(struct tty_struct *tty, struct usb_serial_port *port)
 {
 	struct mxuport_port *mxport = usb_get_serial_port_data(port);
@@ -1361,6 +1370,7 @@ static struct usb_serial_driver mxuport_device = {
 	.probe			= mxuport_probe,
 	.port_probe		= mxuport_port_probe,
 	.attach			= mxuport_attach,
+	.release		= mxuport_release,
 	.calc_num_ports		= mxuport_calc_num_ports,
 	.open			= mxuport_open,
 	.close			= mxuport_close,
diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index f6c6900bccf0..76564b3bebb9 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -38,6 +38,7 @@ static int  omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
 				const unsigned char *buf, int count);
 static int  omninet_write_room(struct tty_struct *tty);
 static void omninet_disconnect(struct usb_serial *serial);
+static int omninet_attach(struct usb_serial *serial);
 static int omninet_port_probe(struct usb_serial_port *port);
 static int omninet_port_remove(struct usb_serial_port *port);
 
@@ -56,6 +57,7 @@ static struct usb_serial_driver zyxel_omninet_device = {
 	.description =		"ZyXEL - omni.net lcd plus usb",
 	.id_table =		id_table,
 	.num_ports =		1,
+	.attach =		omninet_attach,
 	.port_probe =		omninet_port_probe,
 	.port_remove =		omninet_port_remove,
 	.open =			omninet_open,
@@ -104,6 +106,17 @@ struct omninet_data {
 	__u8	od_outseq;	/* Sequence number for bulk_out URBs */
 };
 
+static int omninet_attach(struct usb_serial *serial)
+{
+	/* The second bulk-out endpoint is used for writing. */
+	if (serial->num_bulk_out < 2) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int omninet_port_probe(struct usb_serial_port *port)
 {
 	struct omninet_data *od;
@@ -129,12 +142,6 @@ static int omninet_port_remove(struct usb_serial_port *port)
 
 static int omninet_open(struct tty_struct *tty, struct usb_serial_port *port)
 {
-	struct usb_serial	*serial = port->serial;
-	struct usb_serial_port	*wport;
-
-	wport = serial->port[1];
-	tty_port_tty_set(&wport->port, tty);
-
 	return usb_serial_generic_open(tty, port);
 }
 
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index 4b7bfb394a32..64bf258e7e00 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -142,7 +142,7 @@ static int opticon_open(struct tty_struct *tty, struct usb_serial_port *port)
 	usb_clear_halt(port->serial->dev, port->read_urb->pipe);
 
 	res = usb_serial_generic_open(tty, port);
-	if (!res)
+	if (res)
 		return res;
 
 	/* Request CTS line state, sometimes during opening the current
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 348e19834b83..2a9944326210 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -233,6 +233,14 @@ static void option_instat_callback(struct urb *urb);
 #define BANDRICH_PRODUCT_1012			0x1012
 
 #define QUALCOMM_VENDOR_ID			0x05C6
+/* These Quectel products use Qualcomm's vendor ID */
+#define QUECTEL_PRODUCT_UC20			0x9003
+#define QUECTEL_PRODUCT_UC15			0x9090
+
+#define QUECTEL_VENDOR_ID			0x2c7c
+/* These Quectel products use Quectel's vendor ID */
+#define QUECTEL_PRODUCT_EC21			0x0121
+#define QUECTEL_PRODUCT_EC25			0x0125
 
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
@@ -268,11 +276,21 @@ static void option_instat_callback(struct urb *urb);
 #define TELIT_PRODUCT_CC864_SINGLE		0x1006
 #define TELIT_PRODUCT_DE910_DUAL		0x1010
 #define TELIT_PRODUCT_UE910_V2			0x1012
+#define TELIT_PRODUCT_LE922_USBCFG1		0x1040
+#define TELIT_PRODUCT_LE922_USBCFG2		0x1041
 #define TELIT_PRODUCT_LE922_USBCFG0		0x1042
 #define TELIT_PRODUCT_LE922_USBCFG3		0x1043
 #define TELIT_PRODUCT_LE922_USBCFG5		0x1045
+#define TELIT_PRODUCT_ME910			0x1100
 #define TELIT_PRODUCT_LE920			0x1200
 #define TELIT_PRODUCT_LE910			0x1201
+#define TELIT_PRODUCT_LE910_USBCFG4		0x1206
+#define TELIT_PRODUCT_LE920A4_1207		0x1207
+#define TELIT_PRODUCT_LE920A4_1208		0x1208
+#define TELIT_PRODUCT_LE920A4_1211		0x1211
+#define TELIT_PRODUCT_LE920A4_1212		0x1212
+#define TELIT_PRODUCT_LE920A4_1213		0x1213
+#define TELIT_PRODUCT_LE920A4_1214		0x1214
 
 /* ZTE PRODUCTS */
 #define ZTE_VENDOR_ID				0x19d2
@@ -375,18 +393,22 @@ static void option_instat_callback(struct urb *urb);
 #define HAIER_PRODUCT_CE81B			0x10f8
 #define HAIER_PRODUCT_CE100			0x2009
 
-/* Cinterion (formerly Siemens) products */
-#define SIEMENS_VENDOR_ID				0x0681
-#define CINTERION_VENDOR_ID				0x1e2d
+/* Gemalto's Cinterion products (formerly Siemens) */
+#define SIEMENS_VENDOR_ID			0x0681
+#define CINTERION_VENDOR_ID			0x1e2d
+#define CINTERION_PRODUCT_HC25_MDMNET		0x0040
 #define CINTERION_PRODUCT_HC25_MDM		0x0047
-#define CINTERION_PRODUCT_HC25_MDMNET	0x0040
+#define CINTERION_PRODUCT_HC28_MDMNET		0x004A /* same for HC28J */
 #define CINTERION_PRODUCT_HC28_MDM		0x004C
-#define CINTERION_PRODUCT_HC28_MDMNET	0x004A /* same for HC28J */
 #define CINTERION_PRODUCT_EU3_E			0x0051
 #define CINTERION_PRODUCT_EU3_P			0x0052
 #define CINTERION_PRODUCT_PH8			0x0053
 #define CINTERION_PRODUCT_AHXX			0x0055
 #define CINTERION_PRODUCT_PLXX			0x0060
+#define CINTERION_PRODUCT_PH8_2RMNET		0x0082
+#define CINTERION_PRODUCT_PH8_AUDIO		0x0083
+#define CINTERION_PRODUCT_AHXX_2RMNET		0x0084
+#define CINTERION_PRODUCT_AHXX_AUDIO		0x0085
 
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
@@ -514,6 +536,12 @@ static void option_instat_callback(struct urb *urb);
 #define VIATELECOM_VENDOR_ID			0x15eb
 #define VIATELECOM_PRODUCT_CDS7			0x0001
 
+/* WeTelecom products */
+#define WETELECOM_VENDOR_ID			0x22de
+#define WETELECOM_PRODUCT_WMD200		0x6801
+#define WETELECOM_PRODUCT_6802			0x6802
+#define WETELECOM_PRODUCT_WMD300		0x6803
+
 struct option_blacklist_info {
 	/* bitmask of interface numbers blacklisted for send_setup */
 	const unsigned long sendsetup;
@@ -613,6 +641,11 @@ static const struct option_blacklist_info simcom_sim7100e_blacklist = {
 	.reserved = BIT(5) | BIT(6),
 };
 
+static const struct option_blacklist_info telit_me910_blacklist = {
+	.sendsetup = BIT(0),
+	.reserved = BIT(1) | BIT(3),
+};
+
 static const struct option_blacklist_info telit_le910_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(2),
@@ -623,6 +656,11 @@ static const struct option_blacklist_info telit_le920_blacklist = {
 	.reserved = BIT(1) | BIT(5),
 };
 
+static const struct option_blacklist_info telit_le920a4_blacklist_1 = {
+	.sendsetup = BIT(0),
+	.reserved = BIT(1),
+};
+
 static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = {
 	.sendsetup = BIT(2),
 	.reserved = BIT(0) | BIT(1) | BIT(3),
@@ -633,6 +671,10 @@ static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = {
 	.reserved = BIT(1) | BIT(2) | BIT(3),
 };
 
+static const struct option_blacklist_info cinterion_rmnet2_blacklist = {
+	.reserved = BIT(4) | BIT(5),
+};
+
 static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1133,7 +1175,14 @@ static const struct usb_device_id option_ids[] = {
 	{ 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(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */
+	/* Quectel products using Qualcomm vendor ID */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	/* Quectel products using Quectel vendor ID */
+	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
@@ -1184,14 +1233,32 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1),
+		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG2),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3),
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff),
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
+		.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
 		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
 		.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1207) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1208),
+		.driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1211),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1212),
+		.driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
@@ -1602,7 +1669,79 @@ 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 },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff42, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff43, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff44, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff45, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff46, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff47, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff48, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff49, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4a, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4b, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4c, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4d, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4e, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff50, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff51, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff52, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff53, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff54, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff55, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff56, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff57, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff58, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff59, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5a, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5b, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5c, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5d, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5e, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff60, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff61, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff62, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff63, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff64, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff65, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff66, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff67, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff68, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff69, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6a, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6b, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6c, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6d, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6e, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff70, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff71, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff72, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff73, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff74, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff75, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff76, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff77, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff78, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff79, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7a, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7b, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7c, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7d, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7e, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff80, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff81, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff82, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff83, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff84, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff85, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff86, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff87, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff88, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff89, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8a, 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) },
@@ -1613,6 +1752,61 @@ static const struct usb_device_id option_ids[] = {
 	{ 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, 0xff9f, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa0, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa1, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa2, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa3, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa4, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa5, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa6, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa7, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa8, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa9, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffaa, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffab, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffac, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffae, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffaf, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb0, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb1, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb2, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb3, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb4, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb5, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb6, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb7, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb8, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb9, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffba, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbb, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbc, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbd, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbe, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbf, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc0, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc1, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc2, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc3, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc4, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc5, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc6, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc7, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc8, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc9, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffca, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcb, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcc, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcd, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffce, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcf, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd0, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd1, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd2, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd3, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd4, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd5, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffec, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffee, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xfff6, 0xff, 0xff, 0xff) },
@@ -1683,6 +1877,10 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = (kernel_ulong_t)&four_g_w100_blacklist
 	},
 	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9801, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ 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) },
@@ -1712,7 +1910,13 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
 		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
-	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, 
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8_2RMNET, 0xff),
+		.driver_info = (kernel_ulong_t)&cinterion_rmnet2_blacklist },
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8_AUDIO, 0xff),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_2RMNET, 0xff) },
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) },
+	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) },
@@ -1818,11 +2022,22 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d04, 0xff) },			/* D-Link DWM-158 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7d0e, 0xff) },			/* D-Link DWM-157 C1 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff),			/* D-Link DWM-221 B1 */
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff),			/* D-Link DWM-222 */
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ 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_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },                /* OLICARD300 - MT6225 */
 	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
 	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index a4b88bc038b6..b8bf52bf7a94 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -134,6 +134,7 @@ static int oti6858_chars_in_buffer(struct tty_struct *tty);
 static int oti6858_tiocmget(struct tty_struct *tty);
 static int oti6858_tiocmset(struct tty_struct *tty,
 				unsigned int set, unsigned int clear);
+static int oti6858_attach(struct usb_serial *serial);
 static int oti6858_port_probe(struct usb_serial_port *port);
 static int oti6858_port_remove(struct usb_serial_port *port);
 
@@ -158,6 +159,7 @@ static struct usb_serial_driver oti6858_device = {
 	.write_bulk_callback =	oti6858_write_bulk_callback,
 	.write_room =		oti6858_write_room,
 	.chars_in_buffer =	oti6858_chars_in_buffer,
+	.attach =		oti6858_attach,
 	.port_probe =		oti6858_port_probe,
 	.port_remove =		oti6858_port_remove,
 };
@@ -324,6 +326,20 @@ static void send_data(struct work_struct *work)
 	usb_serial_port_softint(port);
 }
 
+static int oti6858_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int oti6858_port_probe(struct usb_serial_port *port)
 {
 	struct oti6858_private *priv;
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index ae682e4eeaef..a51b28379850 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -49,6 +49,8 @@ static const struct usb_device_id id_table[] = {
 	{ 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) },
+	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_UC485) },
+	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) },
 	{ USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) },
 	{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) },
 	{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID_UCSGT) },
@@ -220,9 +222,17 @@ static int pl2303_probe(struct usb_serial *serial,
 static int pl2303_startup(struct usb_serial *serial)
 {
 	struct pl2303_serial_private *spriv;
+	unsigned char num_ports = serial->num_ports;
 	enum pl2303_type type = TYPE_01;
 	unsigned char *buf;
 
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports ||
+			serial->num_interrupt_in < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
 	spriv = kzalloc(sizeof(*spriv), GFP_KERNEL);
 	if (!spriv)
 		return -ENOMEM;
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index e3b7af8adfb7..3b5a15d1dc0d 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -27,6 +27,8 @@
 #define ATEN_VENDOR_ID		0x0557
 #define ATEN_VENDOR_ID2		0x0547
 #define ATEN_PRODUCT_ID		0x2008
+#define ATEN_PRODUCT_UC485	0x2021
+#define ATEN_PRODUCT_ID2	0x2118
 
 #define IODATA_VENDOR_ID	0x04bb
 #define IODATA_PRODUCT_ID	0x0a03
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 1bc6089b9008..652b4334b26d 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE(0x1410, 0xa021)},	/* Novatel Gobi 3000 Composite */
 	{USB_DEVICE(0x413c, 0x8193)},	/* Dell Gobi 3000 QDL */
 	{USB_DEVICE(0x413c, 0x8194)},	/* Dell Gobi 3000 Composite */
+	{USB_DEVICE(0x413c, 0x81a6)},	/* Dell DW5570 QDL (MC8805) */
 	{USB_DEVICE(0x1199, 0x68a4)},	/* Sierra Wireless QDL */
 	{USB_DEVICE(0x1199, 0x68a5)},	/* Sierra Wireless Modem */
 	{USB_DEVICE(0x1199, 0x68a8)},	/* Sierra Wireless QDL */
@@ -157,10 +158,13 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
+	{DEVICE_SWI(0x1199, 0x9063)},	/* Sierra Wireless EM7305 */
 	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9078)},	/* Sierra Wireless EM74xx */
 	{DEVICE_SWI(0x1199, 0x9079)},	/* Sierra Wireless EM74xx */
+	{DEVICE_SWI(0x1199, 0x907a)},	/* Sierra Wireless EM74xx QDL */
+	{DEVICE_SWI(0x1199, 0x907b)},	/* Sierra Wireless EM74xx */
 	{DEVICE_SWI(0x413c, 0x81a2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a4)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
@@ -168,6 +172,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b1)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index 504f5bff79c0..af0c87276299 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -141,6 +141,7 @@ static void qt2_release(struct usb_serial *serial)
 
 	serial_priv = usb_get_serial_data(serial);
 
+	usb_kill_urb(serial_priv->read_urb);
 	usb_free_urb(serial_priv->read_urb);
 	kfree(serial_priv->read_buffer);
 	kfree(serial_priv);
@@ -187,22 +188,22 @@ static inline int qt2_setdevice(struct usb_device *dev, u8 *data)
 }
 
 
-static inline int qt2_getdevice(struct usb_device *dev, u8 *data)
-{
-	return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
-			       QT_SET_GET_DEVICE, 0xc0, 0, 0,
-			       data, 3, QT2_USB_TIMEOUT);
-}
-
 static inline int qt2_getregister(struct usb_device *dev,
 				  u8 uart,
 				  u8 reg,
 				  u8 *data)
 {
-	return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
-			       QT_SET_GET_REGISTER, 0xc0, reg,
-			       uart, data, sizeof(*data), QT2_USB_TIMEOUT);
+	int ret;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
+			      QT_SET_GET_REGISTER, 0xc0, reg,
+			      uart, data, sizeof(*data), QT2_USB_TIMEOUT);
+	if (ret < sizeof(*data)) {
+		if (ret >= 0)
+			ret = -EIO;
+	}
 
+	return ret;
 }
 
 static inline int qt2_setregister(struct usb_device *dev,
@@ -371,9 +372,11 @@ static int qt2_open(struct tty_struct *tty, struct usb_serial_port *port)
 				 0xc0, 0,
 				 device_port, data, 2, QT2_USB_TIMEOUT);
 
-	if (status < 0) {
+	if (status < 2) {
 		dev_err(&port->dev, "%s - open port failed %i\n", __func__,
 			status);
+		if (status >= 0)
+			status = -EIO;
 		kfree(data);
 		return status;
 	}
@@ -407,16 +410,12 @@ static void qt2_close(struct usb_serial_port *port)
 {
 	struct usb_serial *serial;
 	struct qt2_port_private *port_priv;
-	unsigned long flags;
 	int i;
 
 	serial = port->serial;
 	port_priv = usb_get_serial_port_data(port);
 
-	spin_lock_irqsave(&port_priv->urb_lock, flags);
 	usb_kill_urb(port_priv->write_urb);
-	port_priv->urb_in_use = false;
-	spin_unlock_irqrestore(&port_priv->urb_lock, flags);
 
 	/* flush the port transmit buffer */
 	i = usb_control_msg(serial->dev,
diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c
index b2dff0f14743..236ea43f7815 100644
--- a/drivers/usb/serial/safe_serial.c
+++ b/drivers/usb/serial/safe_serial.c
@@ -205,6 +205,11 @@ static void safe_process_read_urb(struct urb *urb)
 	if (!safe)
 		goto out;
 
+	if (length < 2) {
+		dev_err(&port->dev, "malformed packet\n");
+		return;
+	}
+
 	fcs = fcs_compute10(data, length, CRC10_INITFCS);
 	if (fcs) {
 		dev_err(&port->dev, "%s - bad CRC %x\n", __func__, fcs);
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index ef0dbf0703c5..ddfd787c461c 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -154,6 +154,19 @@ static int spcp8x5_probe(struct usb_serial *serial,
 	return 0;
 }
 
+static int spcp8x5_attach(struct usb_serial *serial)
+{
+	unsigned char num_ports = serial->num_ports;
+
+	if (serial->num_bulk_in < num_ports ||
+			serial->num_bulk_out < num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int spcp8x5_port_probe(struct usb_serial_port *port)
 {
 	const struct usb_device_id *id = usb_get_serial_data(port->serial);
@@ -219,11 +232,17 @@ static int spcp8x5_get_msr(struct usb_serial_port *port, u8 *status)
 	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
 			      GET_UART_STATUS, GET_UART_STATUS_TYPE,
 			      0, GET_UART_STATUS_MSR, buf, 1, 100);
-	if (ret < 0)
+	if (ret < 1) {
 		dev_err(&port->dev, "failed to get modem status: %d\n", ret);
+		if (ret >= 0)
+			ret = -EIO;
+		goto out;
+	}
 
 	dev_dbg(&port->dev, "0xc0:0x22:0:6  %d - 0x02%x\n", ret, *buf);
 	*status = *buf;
+	ret = 0;
+out:
 	kfree(buf);
 
 	return ret;
@@ -477,6 +496,7 @@ static struct usb_serial_driver spcp8x5_device = {
 	.tiocmget		= spcp8x5_tiocmget,
 	.tiocmset		= spcp8x5_tiocmset,
 	.probe			= spcp8x5_probe,
+	.attach			= spcp8x5_attach,
 	.port_probe		= spcp8x5_port_probe,
 	.port_remove		= spcp8x5_port_remove,
 };
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index 70a098de429f..886e1294b120 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -80,9 +80,17 @@ static inline int ssu100_setdevice(struct usb_device *dev, u8 *data)
 
 static inline int ssu100_getdevice(struct usb_device *dev, u8 *data)
 {
-	return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
-			       QT_SET_GET_DEVICE, 0xc0, 0, 0,
-			       data, 3, 300);
+	int ret;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
+			      QT_SET_GET_DEVICE, 0xc0, 0, 0,
+			      data, 3, 300);
+	if (ret < 3) {
+		if (ret >= 0)
+			ret = -EIO;
+	}
+
+	return ret;
 }
 
 static inline int ssu100_getregister(struct usb_device *dev,
@@ -90,10 +98,17 @@ static inline int ssu100_getregister(struct usb_device *dev,
 				     unsigned short reg,
 				     u8 *data)
 {
-	return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
-			       QT_SET_GET_REGISTER, 0xc0, reg,
-			       uart, data, sizeof(*data), 300);
+	int ret;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
+			      QT_SET_GET_REGISTER, 0xc0, reg,
+			      uart, data, sizeof(*data), 300);
+	if (ret < sizeof(*data)) {
+		if (ret >= 0)
+			ret = -EIO;
+	}
 
+	return ret;
 }
 
 
@@ -289,8 +304,10 @@ static int ssu100_open(struct tty_struct *tty, struct usb_serial_port *port)
 				 QT_OPEN_CLOSE_CHANNEL,
 				 QT_TRANSFER_IN, 0x01,
 				 0, data, 2, 300);
-	if (result < 0) {
+	if (result < 2) {
 		dev_dbg(&port->dev, "%s - open failed %i\n", __func__, result);
+		if (result >= 0)
+			result = -EIO;
 		kfree(data);
 		return result;
 	}
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 2694df2f4559..fe7f5ace6064 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -339,6 +339,13 @@ static int ti_startup(struct usb_serial *serial)
 		goto free_tdev;
 	}
 
+	if (serial->num_bulk_in < serial->num_ports ||
+			serial->num_bulk_out < serial->num_ports) {
+		dev_err(&serial->interface->dev, "missing endpoints\n");
+		status = -ENODEV;
+		goto free_tdev;
+	}
+
 	return 0;
 
 free_tdev:
@@ -1345,13 +1352,10 @@ static int ti_command_out_sync(struct ti_device *tdev, __u8 command,
 		(USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT),
 		value, moduleid, data, size, 1000);
 
-	if (status == size)
-		status = 0;
-
-	if (status > 0)
-		status = -ECOMM;
+	if (status < 0)
+		return status;
 
-	return status;
+	return 0;
 }
 
 
@@ -1367,8 +1371,7 @@ static int ti_command_in_sync(struct ti_device *tdev, __u8 command,
 
 	if (status == size)
 		status = 0;
-
-	if (status > 0)
+	else if (status >= 0)
 		status = -ECOMM;
 
 	return status;
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index a204782ae530..e98b6e57b703 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -54,7 +54,8 @@ DEVICE(funsoft, FUNSOFT_IDS);
 /* Infineon Flashloader driver */
 #define FLASHLOADER_IDS()		\
 	{ USB_DEVICE_INTERFACE_CLASS(0x058b, 0x0041, USB_CLASS_CDC_DATA) }, \
-	{ USB_DEVICE(0x8087, 0x0716) }
+	{ USB_DEVICE(0x8087, 0x0716) }, \
+	{ USB_DEVICE(0x8087, 0x0801) }
 DEVICE(flashloader, FLASHLOADER_IDS);
 
 /* Google Serial USB SubClass */
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 46f1f13b41f1..e7e29c797824 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1077,7 +1077,8 @@ static int usb_serial_probe(struct usb_interface *interface,
 
 	serial->disconnected = 0;
 
-	usb_serial_console_init(serial->port[0]->minor);
+	if (num_ports > 0)
+		usb_serial_console_init(serial->port[0]->minor);
 exit:
 	module_put(type->driver.owner);
 	return 0;
@@ -1432,7 +1433,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[]
 
 	rc = usb_register(udriver);
 	if (rc)
-		return rc;
+		goto failed_usb_register;
 
 	for (sd = serial_drivers; *sd; ++sd) {
 		(*sd)->usb_driver = udriver;
@@ -1450,6 +1451,8 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[]
 	while (sd-- > serial_drivers)
 		usb_serial_deregister(*sd);
 	usb_deregister(udriver);
+failed_usb_register:
+	kfree(udriver);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(usb_serial_register_drivers);
diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c
index f3cf4cecd2b7..091e8ec7a6c0 100644
--- a/drivers/usb/storage/ene_ub6250.c
+++ b/drivers/usb/storage/ene_ub6250.c
@@ -446,6 +446,10 @@ struct ms_lib_ctrl {
 #define SD_BLOCK_LEN  9
 
 struct ene_ub6250_info {
+
+	/* I/O bounce buffer */
+	u8		*bbuf;
+
 	/* for 6250 code */
 	struct SD_STATUS	SD_Status;
 	struct MS_STATUS	MS_Status;
@@ -493,8 +497,11 @@ static int ene_load_bincode(struct us_data *us, unsigned char flag);
 
 static void ene_ub6250_info_destructor(void *extra)
 {
+	struct ene_ub6250_info *info = (struct ene_ub6250_info *) extra;
+
 	if (!extra)
 		return;
+	kfree(info->bbuf);
 }
 
 static int ene_send_scsi_cmd(struct us_data *us, u8 fDir, void *buf, int use_sg)
@@ -858,8 +865,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr,
 		u8 PageNum, u32 *PageBuf, struct ms_lib_type_extdat *ExtraDat)
 {
 	struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
+	struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+	u8 *bbuf = info->bbuf;
 	int result;
-	u8 ExtBuf[4];
 	u32 bn = PhyBlockAddr * 0x20 + PageNum;
 
 	/* printk(KERN_INFO "MS --- MS_ReaderReadPage,
@@ -902,7 +910,7 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr,
 	bcb->CDB[2]     = (unsigned char)(PhyBlockAddr>>16);
 	bcb->CDB[6]     = 0x01;
 
-	result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0);
+	result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
 	if (result != USB_STOR_XFER_GOOD)
 		return USB_STOR_TRANSPORT_ERROR;
 
@@ -911,9 +919,9 @@ static int ms_read_readpage(struct us_data *us, u32 PhyBlockAddr,
 	ExtraDat->status0  = 0x10;  /* Not yet,fireware support */
 
 	ExtraDat->status1  = 0x00;  /* Not yet,fireware support */
-	ExtraDat->ovrflg   = ExtBuf[0];
-	ExtraDat->mngflg   = ExtBuf[1];
-	ExtraDat->logadr   = memstick_logaddr(ExtBuf[2], ExtBuf[3]);
+	ExtraDat->ovrflg   = bbuf[0];
+	ExtraDat->mngflg   = bbuf[1];
+	ExtraDat->logadr   = memstick_logaddr(bbuf[2], bbuf[3]);
 
 	return USB_STOR_TRANSPORT_GOOD;
 }
@@ -1339,8 +1347,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock,
 				u8 PageNum, struct ms_lib_type_extdat *ExtraDat)
 {
 	struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
+	struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+	u8 *bbuf = info->bbuf;
 	int result;
-	u8 ExtBuf[4];
 
 	/* printk("MS_LibReadExtra --- PhyBlock = %x, PageNum = %x\n", PhyBlock, PageNum); */
 	memset(bcb, 0, sizeof(struct bulk_cb_wrap));
@@ -1355,7 +1364,7 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock,
 	bcb->CDB[2]     = (unsigned char)(PhyBlock>>16);
 	bcb->CDB[6]     = 0x01;
 
-	result = ene_send_scsi_cmd(us, FDIR_READ, &ExtBuf, 0);
+	result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
 	if (result != USB_STOR_XFER_GOOD)
 		return USB_STOR_TRANSPORT_ERROR;
 
@@ -1363,9 +1372,9 @@ static int ms_lib_read_extra(struct us_data *us, u32 PhyBlock,
 	ExtraDat->intr     = 0x80;  /* Not yet, waiting for fireware support */
 	ExtraDat->status0  = 0x10;  /* Not yet, waiting for fireware support */
 	ExtraDat->status1  = 0x00;  /* Not yet, waiting for fireware support */
-	ExtraDat->ovrflg   = ExtBuf[0];
-	ExtraDat->mngflg   = ExtBuf[1];
-	ExtraDat->logadr   = memstick_logaddr(ExtBuf[2], ExtBuf[3]);
+	ExtraDat->ovrflg   = bbuf[0];
+	ExtraDat->mngflg   = bbuf[1];
+	ExtraDat->logadr   = memstick_logaddr(bbuf[2], bbuf[3]);
 
 	return USB_STOR_TRANSPORT_GOOD;
 }
@@ -1569,9 +1578,9 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st)
 	u16 PhyBlock, newblk, i;
 	u16 LogStart, LogEnde;
 	struct ms_lib_type_extdat extdat;
-	u8 buf[0x200];
 	u32 count = 0, index = 0;
 	struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+	u8 *bbuf = info->bbuf;
 
 	for (PhyBlock = 0; PhyBlock < info->MS_Lib.NumberOfPhyBlock;) {
 		ms_lib_phy_to_log_range(PhyBlock, &LogStart, &LogEnde);
@@ -1585,14 +1594,16 @@ static int ms_lib_scan_logicalblocknumber(struct us_data *us, u16 btBlk1st)
 			}
 
 			if (count == PhyBlock) {
-				ms_lib_read_extrablock(us, PhyBlock, 0, 0x80, &buf);
+				ms_lib_read_extrablock(us, PhyBlock, 0, 0x80,
+						bbuf);
 				count += 0x80;
 			}
 			index = (PhyBlock % 0x80) * 4;
 
-			extdat.ovrflg = buf[index];
-			extdat.mngflg = buf[index+1];
-			extdat.logadr = memstick_logaddr(buf[index+2], buf[index+3]);
+			extdat.ovrflg = bbuf[index];
+			extdat.mngflg = bbuf[index+1];
+			extdat.logadr = memstick_logaddr(bbuf[index+2],
+					bbuf[index+3]);
 
 			if ((extdat.ovrflg & MS_REG_OVR_BKST) != MS_REG_OVR_BKST_OK) {
 				ms_lib_setacquired_errorblock(us, PhyBlock);
@@ -2075,9 +2086,9 @@ static int ene_ms_init(struct us_data *us)
 {
 	struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
 	int result;
-	u8 buf[0x200];
 	u16 MSP_BlockSize, MSP_UserAreaBlocks;
 	struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+	u8 *bbuf = info->bbuf;
 
 	printk(KERN_INFO "transport --- ENE_MSInit\n");
 
@@ -2096,13 +2107,13 @@ static int ene_ms_init(struct us_data *us)
 	bcb->CDB[0]     = 0xF1;
 	bcb->CDB[1]     = 0x01;
 
-	result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0);
+	result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
 	if (result != USB_STOR_XFER_GOOD) {
 		printk(KERN_ERR "Execution MS Init Code Fail !!\n");
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 	/* the same part to test ENE */
-	info->MS_Status = *(struct MS_STATUS *)&buf[0];
+	info->MS_Status = *(struct MS_STATUS *) bbuf;
 
 	if (info->MS_Status.Insert && info->MS_Status.Ready) {
 		printk(KERN_INFO "Insert     = %x\n", info->MS_Status.Insert);
@@ -2111,15 +2122,15 @@ static int ene_ms_init(struct us_data *us)
 		printk(KERN_INFO "IsMSPHG    = %x\n", info->MS_Status.IsMSPHG);
 		printk(KERN_INFO "WtP= %x\n", info->MS_Status.WtP);
 		if (info->MS_Status.IsMSPro) {
-			MSP_BlockSize      = (buf[6] << 8) | buf[7];
-			MSP_UserAreaBlocks = (buf[10] << 8) | buf[11];
+			MSP_BlockSize      = (bbuf[6] << 8) | bbuf[7];
+			MSP_UserAreaBlocks = (bbuf[10] << 8) | bbuf[11];
 			info->MSP_TotalBlock = MSP_BlockSize * MSP_UserAreaBlocks;
 		} else {
 			ms_card_init(us); /* Card is MS (to ms.c)*/
 		}
 		usb_stor_dbg(us, "MS Init Code OK !!\n");
 	} else {
-		usb_stor_dbg(us, "MS Card Not Ready --- %x\n", buf[0]);
+		usb_stor_dbg(us, "MS Card Not Ready --- %x\n", bbuf[0]);
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 
@@ -2129,9 +2140,9 @@ static int ene_ms_init(struct us_data *us)
 static int ene_sd_init(struct us_data *us)
 {
 	int result;
-	u8  buf[0x200];
 	struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap *) us->iobuf;
 	struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra;
+	u8 *bbuf = info->bbuf;
 
 	usb_stor_dbg(us, "transport --- ENE_SDInit\n");
 	/* SD Init Part-1 */
@@ -2165,17 +2176,17 @@ static int ene_sd_init(struct us_data *us)
 	bcb->Flags              = US_BULK_FLAG_IN;
 	bcb->CDB[0]             = 0xF1;
 
-	result = ene_send_scsi_cmd(us, FDIR_READ, &buf, 0);
+	result = ene_send_scsi_cmd(us, FDIR_READ, bbuf, 0);
 	if (result != USB_STOR_XFER_GOOD) {
 		usb_stor_dbg(us, "Execution SD Init Code Fail !!\n");
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 
-	info->SD_Status =  *(struct SD_STATUS *)&buf[0];
+	info->SD_Status =  *(struct SD_STATUS *) bbuf;
 	if (info->SD_Status.Insert && info->SD_Status.Ready) {
 		struct SD_STATUS *s = &info->SD_Status;
 
-		ene_get_card_status(us, (unsigned char *)&buf);
+		ene_get_card_status(us, bbuf);
 		usb_stor_dbg(us, "Insert     = %x\n", s->Insert);
 		usb_stor_dbg(us, "Ready      = %x\n", s->Ready);
 		usb_stor_dbg(us, "IsMMC      = %x\n", s->IsMMC);
@@ -2183,7 +2194,7 @@ static int ene_sd_init(struct us_data *us)
 		usb_stor_dbg(us, "HiSpeed    = %x\n", s->HiSpeed);
 		usb_stor_dbg(us, "WtP        = %x\n", s->WtP);
 	} else {
-		usb_stor_dbg(us, "SD Card Not Ready --- %x\n", buf[0]);
+		usb_stor_dbg(us, "SD Card Not Ready --- %x\n", bbuf[0]);
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 	return USB_STOR_TRANSPORT_GOOD;
@@ -2193,13 +2204,15 @@ static int ene_sd_init(struct us_data *us)
 static int ene_init(struct us_data *us)
 {
 	int result;
-	u8  misc_reg03 = 0;
+	u8  misc_reg03;
 	struct ene_ub6250_info *info = (struct ene_ub6250_info *)(us->extra);
+	u8 *bbuf = info->bbuf;
 
-	result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03);
+	result = ene_get_card_type(us, REG_CARD_STATUS, bbuf);
 	if (result != USB_STOR_XFER_GOOD)
 		return USB_STOR_TRANSPORT_ERROR;
 
+	misc_reg03 = bbuf[0];
 	if (misc_reg03 & 0x01) {
 		if (!info->SD_Status.Ready) {
 			result = ene_sd_init(us);
@@ -2316,8 +2329,9 @@ static int ene_ub6250_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	int result;
-	u8  misc_reg03 = 0;
+	u8  misc_reg03;
 	struct us_data *us;
+	struct ene_ub6250_info *info;
 
 	result = usb_stor_probe1(&us, intf, id,
 		   (id - ene_ub6250_usb_ids) + ene_ub6250_unusual_dev_list,
@@ -2326,11 +2340,16 @@ static int ene_ub6250_probe(struct usb_interface *intf,
 		return result;
 
 	/* FIXME: where should the code alloc extra buf ? */
-	if (!us->extra) {
-		us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL);
-		if (!us->extra)
-			return -ENOMEM;
-		us->extra_destructor = ene_ub6250_info_destructor;
+	us->extra = kzalloc(sizeof(struct ene_ub6250_info), GFP_KERNEL);
+	if (!us->extra)
+		return -ENOMEM;
+	us->extra_destructor = ene_ub6250_info_destructor;
+
+	info = (struct ene_ub6250_info *)(us->extra);
+	info->bbuf = kmalloc(512, GFP_KERNEL);
+	if (!info->bbuf) {
+		kfree(us->extra);
+		return -ENOMEM;
 	}
 
 	us->transport_name = "ene_ub6250";
@@ -2342,12 +2361,13 @@ static int ene_ub6250_probe(struct usb_interface *intf,
 		return result;
 
 	/* probe card type */
-	result = ene_get_card_type(us, REG_CARD_STATUS, &misc_reg03);
+	result = ene_get_card_type(us, REG_CARD_STATUS, info->bbuf);
 	if (result != USB_STOR_XFER_GOOD) {
 		usb_stor_disconnect(intf);
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 
+	misc_reg03 = info->bbuf[0];
 	if (!(misc_reg03 & 0x01)) {
 		pr_info("ums_eneub6250: This driver only supports SD/MS cards. "
 			"It does not support SM cards.\n");
diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c
index 39afd7045c43..7bb5f8da5357 100644
--- a/drivers/usb/storage/isd200.c
+++ b/drivers/usb/storage/isd200.c
@@ -1520,8 +1520,11 @@ static void isd200_ata_command(struct scsi_cmnd *srb, struct us_data *us)
 
 	/* Make sure driver was initialized */
 
-	if (us->extra == NULL)
+	if (us->extra == NULL) {
 		usb_stor_dbg(us, "ERROR Driver not initialized\n");
+		srb->result = DID_ERROR << 16;
+		return;
+	}
 
 	scsi_set_resid(srb, 0);
 	/* scsi_bufflen might change in protocol translation to ata */
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 5e67f63b2e46..02f86dd1a340 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -919,10 +919,15 @@ int usb_stor_CB_transport(struct scsi_cmnd *srb, struct us_data *us)
 
 	/* COMMAND STAGE */
 	/* let's send the command via the control pipe */
+	/*
+	 * Command is sometime (f.e. after scsi_eh_prep_cmnd) on the stack.
+	 * Stack may be vmallocated.  So no DMA for us.  Make a copy.
+	 */
+	memcpy(us->iobuf, srb->cmnd, srb->cmd_len);
 	result = usb_stor_ctrl_transfer(us, us->send_ctrl_pipe,
 				      US_CBI_ADSC, 
 				      USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, 
-				      us->ifnum, srb->cmnd, srb->cmd_len);
+				      us->ifnum, us->iobuf, srb->cmd_len);
 
 	/* check the return code for the command */
 	usb_stor_dbg(us, "Call to usb_stor_ctrl_transfer() returned %d\n",
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 5c66d3f7a6d0..e26e32169a36 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -2,7 +2,7 @@
  * USB Attached SCSI
  * Note that this is not the same as the USB Mass Storage driver
  *
- * Copyright Hans de Goede <hdegoede@redhat.com> for Red Hat, Inc. 2013 - 2014
+ * Copyright Hans de Goede <hdegoede@redhat.com> for Red Hat, Inc. 2013 - 2016
  * Copyright Matthew Wilcox for Intel Corp, 2010
  * Copyright Sarah Sharp for Intel Corp, 2010
  *
@@ -757,6 +757,17 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd)
 	return SUCCESS;
 }
 
+static int uas_target_alloc(struct scsi_target *starget)
+{
+	struct uas_dev_info *devinfo = (struct uas_dev_info *)
+			dev_to_shost(starget->dev.parent)->hostdata;
+
+	if (devinfo->flags & US_FL_NO_REPORT_LUNS)
+		starget->no_report_luns = 1;
+
+	return 0;
+}
+
 static int uas_slave_alloc(struct scsi_device *sdev)
 {
 	struct uas_dev_info *devinfo =
@@ -808,11 +819,12 @@ static struct scsi_host_template uas_host_template = {
 	.module = THIS_MODULE,
 	.name = "uas",
 	.queuecommand = uas_queuecommand,
+	.target_alloc = uas_target_alloc,
 	.slave_alloc = uas_slave_alloc,
 	.slave_configure = uas_slave_configure,
 	.eh_abort_handler = uas_eh_abort_handler,
 	.eh_bus_reset_handler = uas_eh_bus_reset_handler,
-	.can_queue = 65536,	/* Is there a limit on the _host_ ? */
+	.can_queue = MAX_CMNDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,
 	.skip_settle_delay = 1,
@@ -932,6 +944,12 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	if (result)
 		goto set_alt0;
 
+	/*
+	 * 1 tag is reserved for untagged commands +
+	 * 1 tag to avoid off by one errors in some bridge firmwares
+	 */
+	shost->can_queue = devinfo->qdepth - 2;
+
 	usb_set_intfdata(intf, shost);
 	result = scsi_add_host(shost, &intf->dev);
 	if (result)
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 7ffe4209067b..640a2e2ec04d 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2135,6 +2135,13 @@ UNUSUAL_DEV(  0x22b8, 0x3010, 0x0001, 0x0001,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY | US_FL_IGNORE_RESIDUE ),
 
+/* Reported-by George Cherian <george.cherian@cavium.com> */
+UNUSUAL_DEV(0x152d, 0x9561, 0x0000, 0x9999,
+		"JMicron",
+		"JMS56x",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /*
  * Patch by Constantin Baranov <const@tltsu.ru>
  * Report by Andreas Koenecke.
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index ccc113e83d88..a37ed1e59e99 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -64,6 +64,13 @@ UNUSUAL_DEV(0x0bc2, 0x3312, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: David Webb <djw@noc.ac.uk> */
+UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
+		"Seagate",
+		"Expansion Desk",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_LUNS),
+
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x0bc2, 0x3320, 0x0000, 0x9999,
 		"Seagate",
@@ -116,9 +123,9 @@ UNUSUAL_DEV(0x0bc2, 0xab2a, 0x0000, 0x9999,
 /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
 UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
 		"Initio Corporation",
-		"",
+		"INIC-3069",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-		US_FL_NO_ATA_1X),
+		US_FL_NO_ATA_1X | US_FL_IGNORE_RESIDUE),
 
 /* Reported-by: Tom Arild Naess <tanaess@gmail.com> */
 UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999,
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 43576ed31ccd..9de988a0f856 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -482,7 +482,7 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 |
 			US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE |
 			US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES |
-			US_FL_MAX_SECTORS_240);
+			US_FL_MAX_SECTORS_240 | US_FL_NO_REPORT_LUNS);
 
 	p = quirks;
 	while (*p) {
@@ -532,6 +532,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 		case 'i':
 			f |= US_FL_IGNORE_DEVICE;
 			break;
+		case 'j':
+			f |= US_FL_NO_REPORT_LUNS;
+			break;
 		case 'l':
 			f |= US_FL_NOT_LOCKABLE;
 			break;
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 44ab43fc4fcc..af10f7b131a4 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -262,7 +262,11 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
 		kmem_cache_free(stub_priv_cache, priv);
 
 		kfree(urb->transfer_buffer);
+		urb->transfer_buffer = NULL;
+
 		kfree(urb->setup_packet);
+		urb->setup_packet = NULL;
+
 		usb_free_urb(urb);
 	}
 }
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index dbcabc9dbe0d..021003c4de53 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -28,7 +28,11 @@ static void stub_free_priv_and_urb(struct stub_priv *priv)
 	struct urb *urb = priv->urb;
 
 	kfree(urb->setup_packet);
+	urb->setup_packet = NULL;
+
 	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = NULL;
+
 	list_del(&priv->list);
 	kmem_cache_free(stub_priv_cache, priv);
 	usb_free_urb(urb);
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index facaaf003f19..e40da7759a0e 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -741,6 +741,17 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb)
 	if (!(size > 0))
 		return 0;
 
+	if (size > urb->transfer_buffer_length) {
+		/* should not happen, probably malicious packet */
+		if (ud->side == USBIP_STUB) {
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+			return 0;
+		} else {
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+			return -EPIPE;
+		}
+	}
+
 	ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size);
 	if (ret != size) {
 		dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret);
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 7fbe19d5279e..81b2b9f808b5 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -215,14 +215,19 @@ done:
 
 static inline void hub_descriptor(struct usb_hub_descriptor *desc)
 {
+	int width;
+
 	memset(desc, 0, sizeof(*desc));
 	desc->bDescriptorType = USB_DT_HUB;
-	desc->bDescLength = 9;
 	desc->wHubCharacteristics = cpu_to_le16(
 		HUB_CHAR_INDV_PORT_LPSM | HUB_CHAR_COMMON_OCPM);
+
 	desc->bNbrPorts = VHCI_NPORTS;
-	desc->u.hs.DeviceRemovable[0] = 0xff;
-	desc->u.hs.DeviceRemovable[1] = 0xff;
+	BUILD_BUG_ON(VHCI_NPORTS > USB_MAXCHILDREN);
+	width = desc->bNbrPorts / 8 + 1;
+	desc->bDescLength = USB_DT_HUB_NONVAR_SIZE + 2 * width;
+	memset(&desc->u.hs.DeviceRemovable[0], 0, width);
+	memset(&desc->u.hs.DeviceRemovable[width], 0xff, width);
 }
 
 static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
diff --git a/drivers/usb/wusbcore/wa-hc.c b/drivers/usb/wusbcore/wa-hc.c
index 252c7bd9218a..d01496fd27fe 100644
--- a/drivers/usb/wusbcore/wa-hc.c
+++ b/drivers/usb/wusbcore/wa-hc.c
@@ -39,6 +39,9 @@ int wa_create(struct wahc *wa, struct usb_interface *iface,
 	int result;
 	struct device *dev = &iface->dev;
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 3)
+		return -ENODEV;
+
 	result = wa_rpipes_create(wa);
 	if (result < 0)
 		goto error_rpipes_create;
diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c
index 0257f35cfb9d..e75bbe5a10cd 100644
--- a/drivers/uwb/hwa-rc.c
+++ b/drivers/uwb/hwa-rc.c
@@ -825,6 +825,9 @@ static int hwarc_probe(struct usb_interface *iface,
 	struct hwarc *hwarc;
 	struct device *dev = &iface->dev;
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	result = -ENOMEM;
 	uwb_rc = uwb_rc_alloc();
 	if (uwb_rc == NULL) {
diff --git a/drivers/uwb/i1480/dfu/usb.c b/drivers/uwb/i1480/dfu/usb.c
index 2bfc846ac071..a50cf45e530f 100644
--- a/drivers/uwb/i1480/dfu/usb.c
+++ b/drivers/uwb/i1480/dfu/usb.c
@@ -341,6 +341,7 @@ error_submit_ep1:
 static
 int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
 {
+	struct usb_device *udev = interface_to_usbdev(iface);
 	struct i1480_usb *i1480_usb;
 	struct i1480 *i1480;
 	struct device *dev = &iface->dev;
@@ -352,8 +353,8 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
 			iface->cur_altsetting->desc.bInterfaceNumber);
 		goto error;
 	}
-	if (iface->num_altsetting > 1
-	    && interface_to_usbdev(iface)->descriptor.idProduct == 0xbabe) {
+	if (iface->num_altsetting > 1 &&
+			le16_to_cpu(udev->descriptor.idProduct) == 0xbabe) {
 		/* Need altsetting #1 [HW QUIRK] or EP1 won't work */
 		result = usb_set_interface(interface_to_usbdev(iface), 0, 1);
 		if (result < 0)
@@ -362,6 +363,9 @@ int i1480_usb_probe(struct usb_interface *iface, const struct usb_device_id *id)
 				 result);
 	}
 
+	if (iface->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	result = -ENOMEM;
 	i1480_usb = kzalloc(sizeof(*i1480_usb), GFP_KERNEL);
 	if (i1480_usb == NULL) {
diff --git a/drivers/uwb/lc-rc.c b/drivers/uwb/lc-rc.c
index d059ad4d0dbd..97ee1b46db69 100644
--- a/drivers/uwb/lc-rc.c
+++ b/drivers/uwb/lc-rc.c
@@ -56,8 +56,11 @@ static struct uwb_rc *uwb_rc_find_by_index(int index)
 	struct uwb_rc *rc = NULL;
 
 	dev = class_find_device(&uwb_rc_class, NULL, &index, uwb_rc_index_match);
-	if (dev)
+	if (dev) {
 		rc = dev_get_drvdata(dev);
+		put_device(dev);
+	}
+
 	return rc;
 }
 
@@ -467,7 +470,9 @@ struct uwb_rc *__uwb_rc_try_get(struct uwb_rc *target_rc)
 	if (dev) {
 		rc = dev_get_drvdata(dev);
 		__uwb_rc_get(rc);
+		put_device(dev);
 	}
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(__uwb_rc_try_get);
@@ -520,8 +525,11 @@ struct uwb_rc *uwb_rc_get_by_grandpa(const struct device *grandpa_dev)
 
 	dev = class_find_device(&uwb_rc_class, NULL, grandpa_dev,
 				find_rc_grandpa);
-	if (dev)
+	if (dev) {
 		rc = dev_get_drvdata(dev);
+		put_device(dev);
+	}
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(uwb_rc_get_by_grandpa);
@@ -553,8 +561,10 @@ struct uwb_rc *uwb_rc_get_by_dev(const struct uwb_dev_addr *addr)
 	struct uwb_rc *rc = NULL;
 
 	dev = class_find_device(&uwb_rc_class, NULL, addr, find_rc_dev);
-	if (dev)
+	if (dev) {
 		rc = dev_get_drvdata(dev);
+		put_device(dev);
+	}
 
 	return rc;
 }
diff --git a/drivers/uwb/pal.c b/drivers/uwb/pal.c
index c1304b8d4985..678e93741ae1 100644
--- a/drivers/uwb/pal.c
+++ b/drivers/uwb/pal.c
@@ -97,6 +97,8 @@ static bool uwb_rc_class_device_exists(struct uwb_rc *target_rc)
 
 	dev = class_find_device(&uwb_rc_class, NULL, target_rc,	find_rc);
 
+	put_device(dev);
+
 	return (dev != NULL);
 }
 
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 9982cb176ce8..b31b84f56e8f 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -562,8 +562,9 @@ static long vfio_pci_ioctl(void *device_data,
 
 	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
 		struct vfio_irq_set hdr;
+		size_t size;
 		u8 *data = NULL;
-		int ret = 0;
+		int max, ret = 0;
 
 		minsz = offsetofend(struct vfio_irq_set, count);
 
@@ -571,23 +572,31 @@ static long vfio_pci_ioctl(void *device_data,
 			return -EFAULT;
 
 		if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
+		    hdr.count >= (U32_MAX - hdr.start) ||
 		    hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
 				  VFIO_IRQ_SET_ACTION_TYPE_MASK))
 			return -EINVAL;
 
-		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
-			size_t size;
-			int max = vfio_pci_get_irq_count(vdev, hdr.index);
+		max = vfio_pci_get_irq_count(vdev, hdr.index);
+		if (hdr.start >= max || hdr.start + hdr.count > max)
+			return -EINVAL;
 
-			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
-				size = sizeof(uint8_t);
-			else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
-				size = sizeof(int32_t);
-			else
-				return -EINVAL;
+		switch (hdr.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
+		case VFIO_IRQ_SET_DATA_NONE:
+			size = 0;
+			break;
+		case VFIO_IRQ_SET_DATA_BOOL:
+			size = sizeof(uint8_t);
+			break;
+		case VFIO_IRQ_SET_DATA_EVENTFD:
+			size = sizeof(int32_t);
+			break;
+		default:
+			return -EINVAL;
+		}
 
-			if (hdr.argsz - minsz < hdr.count * size ||
-			    hdr.start >= max || hdr.start + hdr.count > max)
+		if (size) {
+			if (hdr.argsz - minsz < hdr.count * size)
 				return -EINVAL;
 
 			data = memdup_user((void __user *)(arg + minsz),
@@ -893,6 +902,10 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 			return ret;
 
 		vdev->barmap[index] = pci_iomap(pdev, index, 0);
+		if (!vdev->barmap[index]) {
+			pci_release_selected_regions(pdev, 1 << index);
+			return -ENOMEM;
+		}
 	}
 
 	vma->vm_private_data = vdev;
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 3b3ba15558b7..5c8f767b6368 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -255,7 +255,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	if (!is_irq_none(vdev))
 		return -EINVAL;
 
-	vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
+	vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
 	if (!vdev->ctx)
 		return -ENOMEM;
 
@@ -563,67 +563,80 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev,
 }
 
 static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
-					   uint32_t flags, void *data)
+					   unsigned int count, uint32_t flags,
+					   void *data)
 {
-	int32_t fd = *(int32_t *)data;
-
-	if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
-		return -EINVAL;
-
 	/* DATA_NONE/DATA_BOOL enables loopback testing */
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		if (*ctx)
-			eventfd_signal(*ctx, 1);
-		return 0;
+		if (*ctx) {
+			if (count) {
+				eventfd_signal(*ctx, 1);
+			} else {
+				eventfd_ctx_put(*ctx);
+				*ctx = NULL;
+			}
+			return 0;
+		}
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
-		uint8_t trigger = *(uint8_t *)data;
+		uint8_t trigger;
+
+		if (!count)
+			return -EINVAL;
+
+		trigger = *(uint8_t *)data;
 		if (trigger && *ctx)
 			eventfd_signal(*ctx, 1);
-		return 0;
-	}
 
-	/* Handle SET_DATA_EVENTFD */
-	if (fd == -1) {
-		if (*ctx)
-			eventfd_ctx_put(*ctx);
-		*ctx = NULL;
 		return 0;
-	} else if (fd >= 0) {
-		struct eventfd_ctx *efdctx;
-		efdctx = eventfd_ctx_fdget(fd);
-		if (IS_ERR(efdctx))
-			return PTR_ERR(efdctx);
-		if (*ctx)
-			eventfd_ctx_put(*ctx);
-		*ctx = efdctx;
+	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		int32_t fd;
+
+		if (!count)
+			return -EINVAL;
+
+		fd = *(int32_t *)data;
+		if (fd == -1) {
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+			*ctx = NULL;
+		} else if (fd >= 0) {
+			struct eventfd_ctx *efdctx;
+
+			efdctx = eventfd_ctx_fdget(fd);
+			if (IS_ERR(efdctx))
+				return PTR_ERR(efdctx);
+
+			if (*ctx)
+				eventfd_ctx_put(*ctx);
+
+			*ctx = efdctx;
+		}
 		return 0;
-	} else
-		return -EINVAL;
+	}
+
+	return -EINVAL;
 }
 
 static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
 				    unsigned index, unsigned start,
 				    unsigned count, uint32_t flags, void *data)
 {
-	if (index != VFIO_PCI_ERR_IRQ_INDEX)
+	if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1)
 		return -EINVAL;
 
-	/*
-	 * We should sanitize start & count, but that wasn't caught
-	 * originally, so this IRQ index must forever ignore them :-(
-	 */
-
-	return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data);
+	return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger,
+					       count, flags, data);
 }
 
 static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
 				    unsigned index, unsigned start,
 				    unsigned count, uint32_t flags, void *data)
 {
-	if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1)
+	if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1)
 		return -EINVAL;
 
-	return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data);
+	return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger,
+					       count, flags, data);
 }
 
 int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 210db24d2204..4d39f7959adf 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -190,7 +190,10 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
 	if (!vdev->has_vga)
 		return -EINVAL;
 
-	switch (pos) {
+	if (pos > 0xbfffful)
+		return -EINVAL;
+
+	switch ((u32)pos) {
 	case 0xa0000 ... 0xbffff:
 		count = min(count, (size_t)(0xc0000 - pos));
 		iomem = ioremap_nocache(0xa0000, 0xbffff - 0xa0000 + 1);
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 6070b793cbcb..1e01e28f40f3 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -296,6 +296,34 @@ static void vfio_group_put(struct vfio_group *group)
 	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
 }
 
+struct vfio_group_put_work {
+	struct work_struct work;
+	struct vfio_group *group;
+};
+
+static void vfio_group_put_bg(struct work_struct *work)
+{
+	struct vfio_group_put_work *do_work;
+
+	do_work = container_of(work, struct vfio_group_put_work, work);
+
+	vfio_group_put(do_work->group);
+	kfree(do_work);
+}
+
+static void vfio_group_schedule_put(struct vfio_group *group)
+{
+	struct vfio_group_put_work *do_work;
+
+	do_work = kmalloc(sizeof(*do_work), GFP_KERNEL);
+	if (WARN_ON(!do_work))
+		return;
+
+	INIT_WORK(&do_work->work, vfio_group_put_bg);
+	do_work->group = group;
+	schedule_work(&do_work->work);
+}
+
 /* Assume group_lock or group reference is held */
 static void vfio_group_get(struct vfio_group *group)
 {
@@ -620,7 +648,14 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 		break;
 	}
 
-	vfio_group_put(group);
+	/*
+	 * If we're the last reference to the group, the group will be
+	 * released, which includes unregistering the iommu group notifier.
+	 * We hold a read-lock on that notifier list, unregistering needs
+	 * a write-lock... deadlock.  Release our reference asynchronously
+	 * to avoid that situation.
+	 */
+	vfio_group_schedule_put(group);
 	return NOTIFY_OK;
 }
 
@@ -1552,6 +1587,15 @@ void vfio_group_put_external_user(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
 
+bool vfio_external_group_match_file(struct vfio_group *test_group,
+				    struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	return (filep->f_op == &vfio_group_fops) && (group == test_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_group_match_file);
+
 int vfio_external_user_iommu_id(struct vfio_group *group)
 {
 	return iommu_group_id(group->iommu_group);
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 0582b72ef377..34e4b3ad8b92 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -511,6 +511,12 @@ static long tce_iommu_build_v2(struct tce_container *container,
 	unsigned long hpa;
 	enum dma_data_direction dirtmp;
 
+	if (!tbl->it_userspace) {
+		ret = tce_iommu_userspace_view_alloc(tbl);
+		if (ret)
+			return ret;
+	}
+
 	for (i = 0; i < pages; ++i) {
 		struct mm_iommu_table_group_mem_t *mem = NULL;
 		unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
@@ -584,15 +590,6 @@ static long tce_iommu_create_table(struct tce_container *container,
 	WARN_ON(!ret && !(*ptbl)->it_ops->free);
 	WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
 
-	if (!ret && container->v2) {
-		ret = tce_iommu_userspace_view_alloc(*ptbl);
-		if (ret)
-			(*ptbl)->it_ops->free(*ptbl);
-	}
-
-	if (ret)
-		decrement_locked_vm(table_size >> PAGE_SHIFT);
-
 	return ret;
 }
 
@@ -1064,10 +1061,7 @@ static int tce_iommu_take_ownership(struct tce_container *container,
 		if (!tbl || !tbl->it_map)
 			continue;
 
-		rc = tce_iommu_userspace_view_alloc(tbl);
-		if (!rc)
-			rc = iommu_take_ownership(tbl);
-
+		rc = iommu_take_ownership(tbl);
 		if (rc) {
 			for (j = 0; j < i; ++j)
 				iommu_release_ownership(
@@ -1169,6 +1163,10 @@ static int tce_iommu_attach_group(void *iommu_data,
 	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
 			iommu_group_id(iommu_group), iommu_group); */
 	table_group = iommu_group_get_iommudata(iommu_group);
+	if (!table_group) {
+		ret = -ENODEV;
+		goto unlock_exit;
+	}
 
 	if (tce_groups_attached(container) && (!table_group->ops ||
 			!table_group->ops->take_ownership ||
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index ecb826eefe02..2fa280671c1e 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -130,57 +130,34 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
 	rb_erase(&old->node, &iommu->dma_list);
 }
 
-struct vwork {
-	struct mm_struct	*mm;
-	long			npage;
-	struct work_struct	work;
-};
-
-/* delayed decrement/increment for locked_vm */
-static void vfio_lock_acct_bg(struct work_struct *work)
+static int vfio_lock_acct(long npage, bool *lock_cap)
 {
-	struct vwork *vwork = container_of(work, struct vwork, work);
-	struct mm_struct *mm;
-
-	mm = vwork->mm;
-	down_write(&mm->mmap_sem);
-	mm->locked_vm += vwork->npage;
-	up_write(&mm->mmap_sem);
-	mmput(mm);
-	kfree(vwork);
-}
+	int ret = 0;
 
-static void vfio_lock_acct(long npage)
-{
-	struct vwork *vwork;
-	struct mm_struct *mm;
+	if (!npage)
+		return 0;
 
-	if (!current->mm || !npage)
-		return; /* process exited or nothing to do */
+	if (!current->mm)
+		return -ESRCH; /* process exited */
 
-	if (down_write_trylock(&current->mm->mmap_sem)) {
-		current->mm->locked_vm += npage;
-		up_write(&current->mm->mmap_sem);
-		return;
-	}
+	down_write(&current->mm->mmap_sem);
+	if (npage > 0) {
+		if (lock_cap ? !*lock_cap : !capable(CAP_IPC_LOCK)) {
+			unsigned long limit;
 
-	/*
-	 * Couldn't get mmap_sem lock, so must setup to update
-	 * mm->locked_vm later. If locked_vm were atomic, we
-	 * wouldn't need this silliness
-	 */
-	vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
-	if (!vwork)
-		return;
-	mm = get_task_mm(current);
-	if (!mm) {
-		kfree(vwork);
-		return;
+			limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+			if (current->mm->locked_vm + npage > limit)
+				ret = -ENOMEM;
+		}
 	}
-	INIT_WORK(&vwork->work, vfio_lock_acct_bg);
-	vwork->mm = mm;
-	vwork->npage = npage;
-	schedule_work(&vwork->work);
+
+	if (!ret)
+		current->mm->locked_vm += npage;
+
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
 }
 
 /*
@@ -262,9 +239,9 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
 static long vfio_pin_pages(unsigned long vaddr, long npage,
 			   int prot, unsigned long *pfn_base)
 {
-	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	unsigned long pfn = 0, limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	bool lock_cap = capable(CAP_IPC_LOCK);
-	long ret, i;
+	long ret, i = 1;
 	bool rsvd;
 
 	if (!current->mm)
@@ -283,16 +260,11 @@ static long vfio_pin_pages(unsigned long vaddr, long npage,
 		return -ENOMEM;
 	}
 
-	if (unlikely(disable_hugepages)) {
-		if (!rsvd)
-			vfio_lock_acct(1);
-		return 1;
-	}
+	if (unlikely(disable_hugepages))
+		goto out;
 
 	/* Lock all the consecutive pages from pfn_base */
-	for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
-		unsigned long pfn = 0;
-
+	for (vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
 		ret = vaddr_get_pfn(vaddr, prot, &pfn);
 		if (ret)
 			break;
@@ -308,12 +280,24 @@ static long vfio_pin_pages(unsigned long vaddr, long npage,
 			put_pfn(pfn, prot);
 			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
 				__func__, limit << PAGE_SHIFT);
-			break;
+			ret = -ENOMEM;
+			goto unpin_out;
 		}
 	}
 
+out:
 	if (!rsvd)
-		vfio_lock_acct(i);
+		ret = vfio_lock_acct(i, &lock_cap);
+
+unpin_out:
+	if (ret) {
+		if (!rsvd) {
+			for (pfn = *pfn_base ; i ; pfn++, i--)
+				put_pfn(pfn, prot);
+		}
+
+		return ret;
+	}
 
 	return i;
 }
@@ -328,7 +312,7 @@ static long vfio_unpin_pages(unsigned long pfn, long npage,
 		unlocked += put_pfn(pfn++, prot);
 
 	if (do_accounting)
-		vfio_lock_acct(-unlocked);
+		vfio_lock_acct(-unlocked, NULL);
 
 	return unlocked;
 }
@@ -390,7 +374,7 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
 		cond_resched();
 	}
 
-	vfio_lock_acct(-unlocked);
+	vfio_lock_acct(-unlocked, NULL);
 }
 
 static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 29cfc57d496e..e4110d6de0b5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -88,7 +88,7 @@ struct vhost_scsi_cmd {
 	struct scatterlist *tvc_prot_sgl;
 	struct page **tvc_upages;
 	/* Pointer to response header iovec */
-	struct iovec *tvc_resp_iov;
+	struct iovec tvc_resp_iov;
 	/* Pointer to vhost_scsi for our device */
 	struct vhost_scsi *tvc_vhost;
 	/* Pointer to vhost_virtqueue for the cmd */
@@ -557,7 +557,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 		memcpy(v_rsp.sense, cmd->tvc_sense_buf,
 		       se_cmd->scsi_sense_length);
 
-		iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov,
+		iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
 			      cmd->tvc_in_iovs, sizeof(v_rsp));
 		ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
 		if (likely(ret == sizeof(v_rsp))) {
@@ -1054,7 +1054,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		}
 		cmd->tvc_vhost = vs;
 		cmd->tvc_vq = vq;
-		cmd->tvc_resp_iov = &vq->iov[out];
+		cmd->tvc_resp_iov = vq->iov[out];
 		cmd->tvc_in_iovs = in;
 
 		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 6e92917ba77a..4e3c78d88832 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -1168,6 +1168,8 @@ static void fbcon_free_font(struct display *p, bool freefont)
 	p->userfont = 0;
 }
 
+static void set_vc_hi_font(struct vc_data *vc, bool set);
+
 static void fbcon_deinit(struct vc_data *vc)
 {
 	struct display *p = &fb_display[vc->vc_num];
@@ -1203,6 +1205,9 @@ finished:
 	if (free_font)
 		vc->vc_font.data = NULL;
 
+	if (vc->vc_hi_font_mask)
+		set_vc_hi_font(vc, false);
+
 	if (!con_is_bound(&fb_con))
 		fbcon_exit();
 
@@ -2439,32 +2444,10 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font)
 	return 0;
 }
 
-static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
-			     const u8 * data, int userfont)
+/* set/clear vc_hi_font_mask and update vc attrs accordingly */
+static void set_vc_hi_font(struct vc_data *vc, bool set)
 {
-	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
-	struct fbcon_ops *ops = info->fbcon_par;
-	struct display *p = &fb_display[vc->vc_num];
-	int resize;
-	int cnt;
-	char *old_data = NULL;
-
-	if (CON_IS_VISIBLE(vc) && softback_lines)
-		fbcon_set_origin(vc);
-
-	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
-	if (p->userfont)
-		old_data = vc->vc_font.data;
-	if (userfont)
-		cnt = FNTCHARCNT(data);
-	else
-		cnt = 256;
-	vc->vc_font.data = (void *)(p->fontdata = data);
-	if ((p->userfont = userfont))
-		REFCOUNT(data)++;
-	vc->vc_font.width = w;
-	vc->vc_font.height = h;
-	if (vc->vc_hi_font_mask && cnt == 256) {
+	if (!set) {
 		vc->vc_hi_font_mask = 0;
 		if (vc->vc_can_do_color) {
 			vc->vc_complement_mask >>= 1;
@@ -2487,7 +2470,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 			    ((c & 0xfe00) >> 1) | (c & 0xff);
 			vc->vc_attr >>= 1;
 		}
-	} else if (!vc->vc_hi_font_mask && cnt == 512) {
+	} else {
 		vc->vc_hi_font_mask = 0x100;
 		if (vc->vc_can_do_color) {
 			vc->vc_complement_mask <<= 1;
@@ -2519,8 +2502,38 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 			} else
 				vc->vc_video_erase_char = c & ~0x100;
 		}
-
 	}
+}
+
+static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
+			     const u8 * data, int userfont)
+{
+	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
+	struct fbcon_ops *ops = info->fbcon_par;
+	struct display *p = &fb_display[vc->vc_num];
+	int resize;
+	int cnt;
+	char *old_data = NULL;
+
+	if (CON_IS_VISIBLE(vc) && softback_lines)
+		fbcon_set_origin(vc);
+
+	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
+	if (p->userfont)
+		old_data = vc->vc_font.data;
+	if (userfont)
+		cnt = FNTCHARCNT(data);
+	else
+		cnt = 256;
+	vc->vc_font.data = (void *)(p->fontdata = data);
+	if ((p->userfont = userfont))
+		REFCOUNT(data)++;
+	vc->vc_font.width = w;
+	vc->vc_font.height = h;
+	if (vc->vc_hi_font_mask && cnt == 256)
+		set_vc_hi_font(vc, false);
+	else if (!vc->vc_hi_font_mask && cnt == 512)
+		set_vc_hi_font(vc, true);
 
 	if (resize) {
 		int cols, rows;
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index e6d16d65e4e6..f07a0974fda2 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -2249,7 +2249,6 @@ config XEN_FBDEV_FRONTEND
 	select FB_SYS_IMAGEBLIT
 	select FB_SYS_FOPS
 	select FB_DEFERRED_IO
-	select INPUT_XEN_KBDDEV_FRONTEND if INPUT_MISC
 	select XEN_XENBUS_FRONTEND
 	default y
 	help
diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c
index 07675d6f323e..d4530b54479c 100644
--- a/drivers/video/fbdev/cobalt_lcdfb.c
+++ b/drivers/video/fbdev/cobalt_lcdfb.c
@@ -350,6 +350,11 @@ static int cobalt_lcdfb_probe(struct platform_device *dev)
 	info->screen_size = resource_size(res);
 	info->screen_base = devm_ioremap(&dev->dev, res->start,
 					 info->screen_size);
+	if (!info->screen_base) {
+		framebuffer_release(info);
+		return -ENOMEM;
+	}
+
 	info->fbops = &cobalt_lcd_fbops;
 	info->fix = cobalt_lcdfb_fix;
 	info->fix.smem_start = res->start;
diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c
index f89245b8ba8e..68a113594808 100644
--- a/drivers/video/fbdev/core/fbcmap.c
+++ b/drivers/video/fbdev/core/fbcmap.c
@@ -163,17 +163,18 @@ void fb_dealloc_cmap(struct fb_cmap *cmap)
 
 int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 
@@ -187,17 +188,18 @@ int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 
 int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 0081725c6b5b..d00510029c93 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -209,8 +209,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 0,
 		.vsync_len      = 0,
-		.sync           = FB_SYNC_CLK_INVERT |
-			FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = FB_SYNC_CLK_INVERT,
 	},
 	/* Sharp LK043T1DG01 */
 	[1] = {
@@ -224,7 +223,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 41,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[2] = {
@@ -239,7 +238,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 10,
 		.hsync_len      = 10,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[3] = {
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 95d293b7445a..dc2fcda54d53 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -52,9 +52,9 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
 		return 1;
 
 	if (regno < 16) {
-		red   >>= 8;
-		green >>= 8;
-		blue  >>= 8;
+		red   >>= 16 - info->var.red.length;
+		green >>= 16 - info->var.green.length;
+		blue  >>= 16 - info->var.blue.length;
 		((u32 *)(info->pseudo_palette))[regno] =
 			(red   << info->var.red.offset)   |
 			(green << info->var.green.offset) |
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index 0567d517eed3..ea2f19f5fbde 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -644,7 +644,6 @@ static void xenfb_backend_changed(struct xenbus_device *dev,
 		break;
 
 	case XenbusStateInitWait:
-InitWait:
 		xenbus_switch_state(dev, XenbusStateConnected);
 		break;
 
@@ -655,7 +654,8 @@ InitWait:
 		 * get Connected twice here.
 		 */
 		if (dev->state != XenbusStateConnected)
-			goto InitWait; /* no InitWait seen yet, fudge it */
+			/* no InitWait seen yet, fudge it */
+			xenbus_switch_state(dev, XenbusStateConnected);
 
 		if (xenbus_scanf(XBT_NIL, info->xbdev->otherend,
 				 "request-update", "%d", &val) < 0)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 7d3e5d0e9aa4..01d15dca940e 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -73,7 +73,7 @@ struct virtio_balloon {
 
 	/* The array of pfns we tell the Host about. */
 	unsigned int num_pfns;
-	u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
+	__virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
 
 	/* Memory statistics */
 	int need_stats_update;
@@ -125,14 +125,16 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
 }
 
-static void set_page_pfns(u32 pfns[], struct page *page)
+static void set_page_pfns(struct virtio_balloon *vb,
+			  __virtio32 pfns[], struct page *page)
 {
 	unsigned int i;
 
 	/* Set balloon pfns pointing at this page.
 	 * Note that the first pfn points at start of the page. */
 	for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
-		pfns[i] = page_to_balloon_pfn(page) + i;
+		pfns[i] = cpu_to_virtio32(vb->vdev,
+					  page_to_balloon_pfn(page) + i);
 }
 
 static void fill_balloon(struct virtio_balloon *vb, size_t num)
@@ -155,7 +157,7 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 			msleep(200);
 			break;
 		}
-		set_page_pfns(vb->pfns + vb->num_pfns, page);
+		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
 		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
 		if (!virtio_has_feature(vb->vdev,
 					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
@@ -171,10 +173,12 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 static void release_pages_balloon(struct virtio_balloon *vb)
 {
 	unsigned int i;
+	struct page *page;
 
 	/* Find pfns pointing at start of each page, get pages and free them. */
 	for (i = 0; i < vb->num_pfns; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
-		struct page *page = balloon_pfn_to_page(vb->pfns[i]);
+		page = balloon_pfn_to_page(virtio32_to_cpu(vb->vdev,
+							   vb->pfns[i]));
 		if (!virtio_has_feature(vb->vdev,
 					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
 			adjust_managed_page_count(page, 1);
@@ -192,12 +196,14 @@ static unsigned leak_balloon(struct virtio_balloon *vb, size_t num)
 	num = min(num, ARRAY_SIZE(vb->pfns));
 
 	mutex_lock(&vb->balloon_lock);
+	/* We can't release more pages than taken */
+	num = min(num, (size_t)vb->num_pages);
 	for (vb->num_pfns = 0; vb->num_pfns < num;
 	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
 		page = balloon_page_dequeue(vb_dev_info);
 		if (!page)
 			break;
-		set_page_pfns(vb->pfns + vb->num_pfns, page);
+		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
 		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
 	}
 
@@ -410,6 +416,8 @@ static int init_vqs(struct virtio_balloon *vb)
 		 * Prime this virtqueue with one buffer so the hypervisor can
 		 * use it to signal us later (it can't be broken yet!).
 		 */
+		update_balloon_stats(vb);
+
 		sg_init_one(&sg, vb->stats, sizeof vb->stats);
 		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
 		    < 0)
@@ -465,13 +473,13 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 	__count_vm_event(BALLOON_MIGRATE);
 	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
-	set_page_pfns(vb->pfns, newpage);
+	set_page_pfns(vb, vb->pfns, newpage);
 	tell_host(vb, vb->inflate_vq);
 
 	/* balloon's page migration 2nd step -- deflate "page" */
 	balloon_page_delete(page);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
-	set_page_pfns(vb->pfns, page);
+	set_page_pfns(vb, vb->pfns, page);
 	tell_host(vb, vb->deflate_vq);
 
 	mutex_unlock(&vb->balloon_lock);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 8e5cf194cc0b..4469202eaa8e 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -17,6 +17,7 @@
  *
  */
 
+#include <linux/delay.h>
 #define VIRTIO_PCI_NO_LEGACY
 #include "virtio_pci_common.h"
 
@@ -271,9 +272,13 @@ static void vp_reset(struct virtio_device *vdev)
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	/* 0 status means a reset. */
 	vp_iowrite8(0, &vp_dev->common->device_status);
-	/* Flush out the status write, and flush in device writes,
-	 * including MSI-X interrupts, if any. */
-	vp_ioread8(&vp_dev->common->device_status);
+	/* After writing 0 to device_status, the driver MUST wait for a read of
+	 * device_status to return 0 before reinitializing the device.
+	 * This will flush out the status write, and flush in device writes,
+	 * including MSI-X interrupts, if any.
+	 */
+	while (vp_ioread8(&vp_dev->common->device_status))
+		msleep(1);
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index ee663c458b20..a01a41a41269 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -202,6 +202,8 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		 * host should service the ring ASAP. */
 		if (out_sgs)
 			vq->notify(&vq->vq);
+		if (indirect)
+			kfree(desc);
 		END_USE(vq);
 		return -ENOSPC;
 	}
@@ -546,7 +548,8 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 
 	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
 		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 
 }
@@ -578,7 +581,8 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 	 * entry. Always do both to keep code simple. */
 	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
 		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
 	END_USE(vq);
@@ -646,10 +650,11 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	 * more to do. */
 	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
-	 * entry. Always do both to keep code simple. */
+	 * entry. Always update the event index to keep code simple. */
 	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
 		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 	/* TODO: tune this threshold */
 	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
@@ -768,7 +773,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
 		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
 	}
 
 	/* Put everything in free lists. */
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index b79a74a98a23..ad94d8a45728 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -467,7 +467,7 @@ static int ca91cx42_slave_get(struct vme_slave_resource *image, int *enabled,
 	vme_bound = ioread32(bridge->base + CA91CX42_VSI_BD[i]);
 	pci_offset = ioread32(bridge->base + CA91CX42_VSI_TO[i]);
 
-	*pci_base = (dma_addr_t)vme_base + pci_offset;
+	*pci_base = (dma_addr_t)*vme_base + pci_offset;
 	*size = (unsigned long long)((vme_bound - *vme_base) + granularity);
 
 	*enabled = 0;
diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index 049a884a756f..59d74d1b47a8 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -153,6 +153,9 @@ struct ds_device
 	 */
 	u16			spu_bit;
 
+	u8			st_buf[ST_SIZE];
+	u8			byte_buf;
+
 	struct w1_bus_master	master;
 };
 
@@ -174,7 +177,6 @@ struct ds_status
 	u8			data_in_buffer_status;
 	u8			reserved1;
 	u8			reserved2;
-
 };
 
 static struct usb_device_id ds_id_table [] = {
@@ -244,28 +246,6 @@ static int ds_send_control(struct ds_device *dev, u16 value, u16 index)
 	return err;
 }
 
-static int ds_recv_status_nodump(struct ds_device *dev, struct ds_status *st,
-				 unsigned char *buf, int size)
-{
-	int count, err;
-
-	memset(st, 0, sizeof(*st));
-
-	count = 0;
-	err = usb_interrupt_msg(dev->udev, usb_rcvintpipe(dev->udev,
-		dev->ep[EP_STATUS]), buf, size, &count, 1000);
-	if (err < 0) {
-		pr_err("Failed to read 1-wire data from 0x%x: err=%d.\n",
-		       dev->ep[EP_STATUS], err);
-		return err;
-	}
-
-	if (count >= sizeof(*st))
-		memcpy(st, buf, sizeof(*st));
-
-	return count;
-}
-
 static inline void ds_print_msg(unsigned char *buf, unsigned char *str, int off)
 {
 	pr_info("%45s: %8x\n", str, buf[off]);
@@ -324,6 +304,35 @@ static void ds_dump_status(struct ds_device *dev, unsigned char *buf, int count)
 	}
 }
 
+static int ds_recv_status(struct ds_device *dev, struct ds_status *st,
+			  bool dump)
+{
+	int count, err;
+
+	if (st)
+		memset(st, 0, sizeof(*st));
+
+	count = 0;
+	err = usb_interrupt_msg(dev->udev,
+				usb_rcvintpipe(dev->udev,
+					       dev->ep[EP_STATUS]),
+				dev->st_buf, sizeof(dev->st_buf),
+				&count, 1000);
+	if (err < 0) {
+		pr_err("Failed to read 1-wire data from 0x%x: err=%d.\n",
+		       dev->ep[EP_STATUS], err);
+		return err;
+	}
+
+	if (dump)
+		ds_dump_status(dev, dev->st_buf, count);
+
+	if (st && count >= sizeof(*st))
+		memcpy(st, dev->st_buf, sizeof(*st));
+
+	return count;
+}
+
 static void ds_reset_device(struct ds_device *dev)
 {
 	ds_send_control_cmd(dev, CTL_RESET_DEVICE, 0);
@@ -344,7 +353,6 @@ static void ds_reset_device(struct ds_device *dev)
 static int ds_recv_data(struct ds_device *dev, unsigned char *buf, int size)
 {
 	int count, err;
-	struct ds_status st;
 
 	/* Careful on size.  If size is less than what is available in
 	 * the input buffer, the device fails the bulk transfer and
@@ -359,14 +367,9 @@ static int ds_recv_data(struct ds_device *dev, unsigned char *buf, int size)
 	err = usb_bulk_msg(dev->udev, usb_rcvbulkpipe(dev->udev, dev->ep[EP_DATA_IN]),
 				buf, size, &count, 1000);
 	if (err < 0) {
-		u8 buf[ST_SIZE];
-		int count;
-
 		pr_info("Clearing ep0x%x.\n", dev->ep[EP_DATA_IN]);
 		usb_clear_halt(dev->udev, usb_rcvbulkpipe(dev->udev, dev->ep[EP_DATA_IN]));
-
-		count = ds_recv_status_nodump(dev, &st, buf, sizeof(buf));
-		ds_dump_status(dev, buf, count);
+		ds_recv_status(dev, NULL, true);
 		return err;
 	}
 
@@ -404,7 +407,6 @@ int ds_stop_pulse(struct ds_device *dev, int limit)
 {
 	struct ds_status st;
 	int count = 0, err = 0;
-	u8 buf[ST_SIZE];
 
 	do {
 		err = ds_send_control(dev, CTL_HALT_EXE_IDLE, 0);
@@ -413,7 +415,7 @@ int ds_stop_pulse(struct ds_device *dev, int limit)
 		err = ds_send_control(dev, CTL_RESUME_EXE, 0);
 		if (err)
 			break;
-		err = ds_recv_status_nodump(dev, &st, buf, sizeof(buf));
+		err = ds_recv_status(dev, &st, false);
 		if (err)
 			break;
 
@@ -456,18 +458,17 @@ int ds_detect(struct ds_device *dev, struct ds_status *st)
 
 static int ds_wait_status(struct ds_device *dev, struct ds_status *st)
 {
-	u8 buf[ST_SIZE];
 	int err, count = 0;
 
 	do {
 		st->status = 0;
-		err = ds_recv_status_nodump(dev, st, buf, sizeof(buf));
+		err = ds_recv_status(dev, st, false);
 #if 0
 		if (err >= 0) {
 			int i;
 			printk("0x%x: count=%d, status: ", dev->ep[EP_STATUS], err);
 			for (i=0; i<err; ++i)
-				printk("%02x ", buf[i]);
+				printk("%02x ", dev->st_buf[i]);
 			printk("\n");
 		}
 #endif
@@ -485,7 +486,7 @@ static int ds_wait_status(struct ds_device *dev, struct ds_status *st)
 	 * can do something with it).
 	 */
 	if (err > 16 || count >= 100 || err < 0)
-		ds_dump_status(dev, buf, err);
+		ds_dump_status(dev, dev->st_buf, err);
 
 	/* Extended data isn't an error.  Well, a short is, but the dump
 	 * would have already told the user that and we can't do anything
@@ -608,7 +609,6 @@ static int ds_write_byte(struct ds_device *dev, u8 byte)
 {
 	int err;
 	struct ds_status st;
-	u8 rbyte;
 
 	err = ds_send_control(dev, COMM_BYTE_IO | COMM_IM | dev->spu_bit, byte);
 	if (err)
@@ -621,11 +621,11 @@ static int ds_write_byte(struct ds_device *dev, u8 byte)
 	if (err)
 		return err;
 
-	err = ds_recv_data(dev, &rbyte, sizeof(rbyte));
+	err = ds_recv_data(dev, &dev->byte_buf, 1);
 	if (err < 0)
 		return err;
 
-	return !(byte == rbyte);
+	return !(byte == dev->byte_buf);
 }
 
 static int ds_read_byte(struct ds_device *dev, u8 *byte)
@@ -712,7 +712,6 @@ static void ds9490r_search(void *data, struct w1_master *master,
 	int err;
 	u16 value, index;
 	struct ds_status st;
-	u8 st_buf[ST_SIZE];
 	int search_limit;
 	int found = 0;
 	int i;
@@ -724,7 +723,12 @@ static void ds9490r_search(void *data, struct w1_master *master,
 	/* FIFO 128 bytes, bulk packet size 64, read a multiple of the
 	 * packet size.
 	 */
-	u64 buf[2*64/8];
+	const size_t bufsize = 2 * 64;
+	u64 *buf;
+
+	buf = kmalloc(bufsize, GFP_KERNEL);
+	if (!buf)
+		return;
 
 	mutex_lock(&master->bus_mutex);
 
@@ -745,10 +749,9 @@ static void ds9490r_search(void *data, struct w1_master *master,
 	do {
 		schedule_timeout(jtime);
 
-		if (ds_recv_status_nodump(dev, &st, st_buf, sizeof(st_buf)) <
-			sizeof(st)) {
+		err = ds_recv_status(dev, &st, false);
+		if (err < 0 || err < sizeof(st))
 			break;
-		}
 
 		if (st.data_in_buffer_status) {
 			/* Bulk in can receive partial ids, but when it does
@@ -758,7 +761,7 @@ static void ds9490r_search(void *data, struct w1_master *master,
 			 * bulk without first checking if status says there
 			 * is data to read.
 			 */
-			err = ds_recv_data(dev, (u8 *)buf, sizeof(buf));
+			err = ds_recv_data(dev, (u8 *)buf, bufsize);
 			if (err < 0)
 				break;
 			for (i = 0; i < err/8; ++i) {
@@ -794,9 +797,14 @@ static void ds9490r_search(void *data, struct w1_master *master,
 	}
 search_out:
 	mutex_unlock(&master->bus_mutex);
+	kfree(buf);
 }
 
 #if 0
+/*
+ * FIXME: if this disabled code is ever used in the future all ds_send_data()
+ * calls must be changed to use a DMAable buffer.
+ */
 static int ds_match_access(struct ds_device *dev, u64 init)
 {
 	int err;
@@ -845,13 +853,12 @@ static int ds_set_path(struct ds_device *dev, u64 init)
 
 static u8 ds9490r_touch_bit(void *data, u8 bit)
 {
-	u8 ret;
 	struct ds_device *dev = data;
 
-	if (ds_touch_bit(dev, bit, &ret))
+	if (ds_touch_bit(dev, bit, &dev->byte_buf))
 		return 0;
 
-	return ret;
+	return dev->byte_buf;
 }
 
 #if 0
@@ -866,13 +873,12 @@ static u8 ds9490r_read_bit(void *data)
 {
 	struct ds_device *dev = data;
 	int err;
-	u8 bit = 0;
 
-	err = ds_touch_bit(dev, 1, &bit);
+	err = ds_touch_bit(dev, 1, &dev->byte_buf);
 	if (err)
 		return 0;
 
-	return bit & 1;
+	return dev->byte_buf & 1;
 }
 #endif
 
@@ -887,32 +893,52 @@ static u8 ds9490r_read_byte(void *data)
 {
 	struct ds_device *dev = data;
 	int err;
-	u8 byte = 0;
 
-	err = ds_read_byte(dev, &byte);
+	err = ds_read_byte(dev, &dev->byte_buf);
 	if (err)
 		return 0;
 
-	return byte;
+	return dev->byte_buf;
 }
 
 static void ds9490r_write_block(void *data, const u8 *buf, int len)
 {
 	struct ds_device *dev = data;
+	u8 *tbuf;
+
+	if (len <= 0)
+		return;
+
+	tbuf = kmalloc(len, GFP_KERNEL);
+	if (!tbuf)
+		return;
 
-	ds_write_block(dev, (u8 *)buf, len);
+	memcpy(tbuf, buf, len);
+	ds_write_block(dev, tbuf, len);
+
+	kfree(tbuf);
 }
 
 static u8 ds9490r_read_block(void *data, u8 *buf, int len)
 {
 	struct ds_device *dev = data;
 	int err;
+	u8 *tbuf;
 
-	err = ds_read_block(dev, buf, len);
-	if (err < 0)
+	if (len <= 0)
+		return 0;
+
+	tbuf = kmalloc(len, GFP_KERNEL);
+	if (!tbuf)
 		return 0;
 
-	return len;
+	err = ds_read_block(dev, tbuf, len);
+	if (err >= 0)
+		memcpy(buf, tbuf, len);
+
+	kfree(tbuf);
+
+	return err >= 0 ? len : 0;
 }
 
 static u8 ds9490r_reset(void *data)
diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c
index 0e2f43bccf1f..0c427d6a12d1 100644
--- a/drivers/w1/masters/omap_hdq.c
+++ b/drivers/w1/masters/omap_hdq.c
@@ -390,8 +390,6 @@ static int hdq_read_byte(struct hdq_data *hdq_data, u8 *val)
 		goto out;
 	}
 
-	hdq_data->hdq_irqstatus = 0;
-
 	if (!(hdq_data->hdq_irqstatus & OMAP_HDQ_INT_STATUS_RXCOMPLETE)) {
 		hdq_reg_merge(hdq_data, OMAP_HDQ_CTRL_STATUS,
 			OMAP_HDQ_CTRL_STATUS_DIR | OMAP_HDQ_CTRL_STATUS_GO,
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index c9a7ff67d395..39886edfa222 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -763,6 +763,7 @@ int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn)
 		dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__,
 			 sl->name);
 		w1_family_put(sl->family);
+		atomic_dec(&sl->master->refcnt);
 		kfree(sl);
 		return err;
 	}
diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c
index e0c98423f2c9..11a72bc2c71b 100644
--- a/drivers/watchdog/bcm_kona_wdt.c
+++ b/drivers/watchdog/bcm_kona_wdt.c
@@ -304,6 +304,8 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev)
 	if (!wdt)
 		return -ENOMEM;
 
+	spin_lock_init(&wdt->lock);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	wdt->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(wdt->base))
@@ -316,7 +318,6 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	spin_lock_init(&wdt->lock);
 	platform_set_drvdata(pdev, wdt);
 	watchdog_set_drvdata(&bcm_kona_wdt_wdd, wdt);
 	bcm_kona_wdt_wdd.parent = &pdev->dev;
diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c
index 1a11aedc4fe8..9eb5b314ba06 100644
--- a/drivers/watchdog/pcwd_usb.c
+++ b/drivers/watchdog/pcwd_usb.c
@@ -630,6 +630,9 @@ static int usb_pcwd_probe(struct usb_interface *interface,
 		return -ENODEV;
 	}
 
+	if (iface_desc->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	/* check out the endpoint: it has to be Interrupt & IN */
 	endpoint = &iface_desc->endpoint[0].desc;
 
diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c
index 71e78ef4b736..3a75f3b53452 100644
--- a/drivers/watchdog/rc32434_wdt.c
+++ b/drivers/watchdog/rc32434_wdt.c
@@ -237,7 +237,7 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		/* Fall through */
 	case WDIOC_GETTIMEOUT:
-		return copy_to_user(argp, &timeout, sizeof(int));
+		return copy_to_user(argp, &timeout, sizeof(int)) ? -EFAULT : 0;
 	default:
 		return -ENOTTY;
 	}
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 12eab503efd1..cfab1d24e4bc 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -247,6 +247,19 @@ static enum bp_state update_schedule(enum bp_state state)
 }
 
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static void release_memory_resource(struct resource *resource)
+{
+	if (!resource)
+		return;
+
+	/*
+	 * No need to reset region to identity mapped since we now
+	 * know that no I/O can be in this region
+	 */
+	release_resource(resource);
+	kfree(resource);
+}
+
 static struct resource *additional_memory_resource(phys_addr_t size)
 {
 	struct resource *res;
@@ -268,20 +281,21 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 		return NULL;
 	}
 
-	return res;
-}
-
-static void release_memory_resource(struct resource *resource)
-{
-	if (!resource)
-		return;
+#ifdef CONFIG_SPARSEMEM
+	{
+		unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT);
+		unsigned long pfn = res->start >> PAGE_SHIFT;
+
+		if (pfn > limit) {
+			pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n",
+			       pfn, limit);
+			release_memory_resource(res);
+			return NULL;
+		}
+	}
+#endif
 
-	/*
-	 * No need to reset region to identity mapped since we now
-	 * know that no I/O can be in this region
-	 */
-	release_resource(resource);
-	kfree(resource);
+	return res;
 }
 
 static enum bp_state reserve_additional_memory(void)
diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
index 4da69dbf7dca..1bdd02a6d6ac 100644
--- a/drivers/xen/biomerge.c
+++ b/drivers/xen/biomerge.c
@@ -10,8 +10,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 	unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page));
 	unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page));
 
-	return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&
-		((bfn1 == bfn2) || ((bfn1+1) == bfn2));
+	return bfn1 + PFN_DOWN(vec1->bv_offset + vec1->bv_len) == bfn2;
 #else
 	/*
 	 * XXX: Add support for merging bio_vec when using different page
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 524c22146429..83ec7b89d308 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -484,9 +484,20 @@ static void eoi_pirq(struct irq_data *data)
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
-	irq_move_irq(data);
+	if (!VALID_EVTCHN(evtchn))
+		return;
 
-	if (VALID_EVTCHN(evtchn))
+	if (unlikely(irqd_is_setaffinity_pending(data)) &&
+	    likely(!irqd_irq_disabled(data))) {
+		int masked = test_and_set_mask(evtchn);
+
+		clear_evtchn(evtchn);
+
+		irq_move_masked_irq(data);
+
+		if (!masked)
+			unmask_evtchn(evtchn);
+	} else
 		clear_evtchn(evtchn);
 
 	if (pirq_needs_eoi(data->irq)) {
@@ -1357,9 +1368,20 @@ static void ack_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);
 
-	irq_move_irq(data);
+	if (!VALID_EVTCHN(evtchn))
+		return;
 
-	if (VALID_EVTCHN(evtchn))
+	if (unlikely(irqd_is_setaffinity_pending(data)) &&
+	    likely(!irqd_irq_disabled(data))) {
+		int masked = test_and_set_mask(evtchn);
+
+		clear_evtchn(evtchn);
+
+		irq_move_masked_irq(data);
+
+		if (!masked)
+			unmask_evtchn(evtchn);
+	} else
 		clear_evtchn(evtchn);
 }
 
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 38272ad24551..f4edd6df3df2 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -316,7 +316,6 @@ static int evtchn_resize_ring(struct per_user_data *u)
 {
 	unsigned int new_size;
 	evtchn_port_t *new_ring, *old_ring;
-	unsigned int p, c;
 
 	/*
 	 * Ensure the ring is large enough to capture all possible
@@ -346,20 +345,17 @@ static int evtchn_resize_ring(struct per_user_data *u)
 	/*
 	 * Copy the old ring contents to the new ring.
 	 *
-	 * If the ring contents crosses the end of the current ring,
-	 * it needs to be copied in two chunks.
+	 * To take care of wrapping, a full ring, and the new index
+	 * pointing into the second half, simply copy the old contents
+	 * twice.
 	 *
 	 * +---------+    +------------------+
-	 * |34567  12| -> |       1234567    |
-	 * +-----p-c-+    +------------------+
+	 * |34567  12| -> |34567  1234567  12|
+	 * +-----p-c-+    +-------c------p---+
 	 */
-	p = evtchn_ring_offset(u, u->ring_prod);
-	c = evtchn_ring_offset(u, u->ring_cons);
-	if (p < c) {
-		memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring));
-		memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring));
-	} else
-		memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring));
+	memcpy(new_ring, old_ring, u->ring_size * sizeof(*u->ring));
+	memcpy(new_ring + u->ring_size, old_ring,
+	       u->ring_size * sizeof(*u->ring));
 
 	u->ring = new_ring;
 	u->ring_size = new_size;
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 1be5dd048622..308600adf6e0 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -804,7 +804,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
 	vma->vm_ops = &gntdev_vmops;
 
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP;
 
 	if (use_ptemod)
 		vma->vm_flags |= VM_DONTCOPY;
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index df2e6f783318..527de56f832f 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -335,8 +335,8 @@ static int mmap_batch_fn(void *data, int nr, void *state)
 				st->global_error = 1;
 		}
 	}
-	st->va += PAGE_SIZE * nr;
-	st->index += nr;
+	st->va += XEN_PAGE_SIZE * nr;
+	st->index += nr / XEN_PFN_PER_PAGE;
 
 	return 0;
 }
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 7399782c0998..8a58bbc14de2 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -409,9 +409,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
+	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
 					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
-	dev_addr = xen_phys_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
@@ -567,13 +567,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
+			dev_addr = xen_phys_to_bus(map);
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
 						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
 						attrs);
-			sg->dma_address = xen_phys_to_bus(map);
+			sg->dma_address = dev_addr;
 		} else {
 			/* we are not interested in the dma_addr returned by
 			 * xen_dma_map_page, only in the potential cache flushes executed
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 70fa438000af..2e319d0c395d 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -27,10 +27,10 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/syscore_ops.h>
 #include <linux/acpi.h>
 #include <acpi/processor.h>
 #include <xen/xen.h>
-#include <xen/xen-ops.h>
 #include <xen/interface/platform.h>
 #include <asm/xen/hypercall.h>
 
@@ -423,36 +423,7 @@ upload:
 
 	return 0;
 }
-static int __init check_prereq(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!xen_initial_domain())
-		return -ENODEV;
-
-	if (!acpi_gbl_FADT.smi_command)
-		return -ENODEV;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		if (!cpu_has(c, X86_FEATURE_EST))
-			return -ENODEV;
 
-		return 0;
-	}
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
-		 * as we get compile warnings for the static functions.
-		 */
-#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
-#define USE_HW_PSTATE                   0x00000080
-		u32 eax, ebx, ecx, edx;
-		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
-		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
-}
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
@@ -495,24 +466,42 @@ static int xen_upload_processor_pm_data(void)
 	return rc;
 }
 
-static int xen_acpi_processor_resume(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void xen_acpi_processor_resume_worker(struct work_struct *dummy)
 {
+	int rc;
+
 	bitmap_zero(acpi_ids_done, nr_acpi_bits);
-	return xen_upload_processor_pm_data();
+
+	rc = xen_upload_processor_pm_data();
+	if (rc != 0)
+		pr_info("ACPI data upload failed, error = %d\n", rc);
+}
+
+static void xen_acpi_processor_resume(void)
+{
+	static DECLARE_WORK(wq, xen_acpi_processor_resume_worker);
+
+	/*
+	 * xen_upload_processor_pm_data() calls non-atomic code.
+	 * However, the context for xen_acpi_processor_resume is syscore
+	 * with only the boot CPU online and in an atomic context.
+	 *
+	 * So defer the upload for some point safer.
+	 */
+	schedule_work(&wq);
 }
 
-struct notifier_block xen_acpi_processor_resume_nb = {
-	.notifier_call = xen_acpi_processor_resume,
+static struct syscore_ops xap_syscore_ops = {
+	.resume	= xen_acpi_processor_resume,
 };
 
 static int __init xen_acpi_processor_init(void)
 {
 	unsigned int i;
-	int rc = check_prereq();
+	int rc;
 
-	if (rc)
-		return rc;
+	if (!xen_initial_domain())
+		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
 	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
@@ -556,7 +545,7 @@ static int __init xen_acpi_processor_init(void)
 	if (rc)
 		goto err_unregister;
 
-	xen_resume_notifier_register(&xen_acpi_processor_resume_nb);
+	register_syscore_ops(&xap_syscore_ops);
 
 	return 0;
 err_unregister:
@@ -573,7 +562,7 @@ static void __exit xen_acpi_processor_exit(void)
 {
 	int i;
 
-	xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb);
+	unregister_syscore_ops(&xap_syscore_ops);
 	kfree(acpi_ids_done);
 	kfree(acpi_id_present);
 	kfree(acpi_id_cst_present);
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 9c234209d8b5..47a4177b16d2 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size,
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			err = conf_space_read(dev, cfg_entry, field_start,
 					      &tmp_val);
 			if (err)
@@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		field_start = OFFSET(cfg_entry);
 		field_end = OFFSET(cfg_entry) + field->size;
 
-		if ((req_start >= field_start && req_start < field_end)
-		    || (req_end > field_start && req_end <= field_end)) {
+		 if (req_end > field_start && field_end > req_start) {
 			tmp_val = 0;
 
 			err = xen_pcibk_config_read(dev, field_start,
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 9433e46518c8..0e0eb10f82a0 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type,
 			rc = -ENOMEM;
 			goto out;
 		}
+	} else if (msg_type == XS_TRANSACTION_END) {
+		list_for_each_entry(trans, &u->transactions, list)
+			if (trans->handle.id == u->u.msg.tx_id)
+				break;
+		if (&trans->list == &u->transactions)
+			return -ESRCH;
 	}
 
 	reply = xenbus_dev_request_and_reply(&u->u.msg);
 	if (IS_ERR(reply)) {
-		kfree(trans);
+		if (msg_type == XS_TRANSACTION_START)
+			kfree(trans);
 		rc = PTR_ERR(reply);
 		goto out;
 	}
@@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type,
 			list_add(&trans->list, &u->transactions);
 		}
 	} else if (u->u.msg.type == XS_TRANSACTION_END) {
-		list_for_each_entry(trans, &u->transactions, list)
-			if (trans->handle.id == u->u.msg.tx_id)
-				break;
-		BUG_ON(&trans->list == &u->transactions);
 		list_del(&trans->list);
-
 		kfree(trans);
 	}
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index ba804f3d8278..ce65591b4168 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -250,9 +250,6 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 
 	mutex_unlock(&xs_state.request_mutex);
 
-	if (IS_ERR(ret))
-		return ret;
-
 	if ((msg->type == XS_TRANSACTION_END) ||
 	    ((req_msg.type == XS_TRANSACTION_START) &&
 	     (msg->type == XS_ERROR)))
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index a7e28890f5ef..c30c6ceac2c4 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -282,32 +282,28 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
 	switch (handler->flags) {
 	case ACL_TYPE_ACCESS:
 		if (acl) {
-			umode_t mode = inode->i_mode;
-			retval = posix_acl_equiv_mode(acl, &mode);
-			if (retval < 0)
+			struct iattr iattr;
+			struct posix_acl *old_acl = acl;
+
+			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
+			if (retval)
 				goto err_out;
-			else {
-				struct iattr iattr;
-				if (retval == 0) {
-					/*
-					 * ACL can be represented
-					 * by the mode bits. So don't
-					 * update ACL.
-					 */
-					acl = NULL;
-					value = NULL;
-					size = 0;
-				}
-				/* Updte the mode bits */
-				iattr.ia_mode = ((mode & S_IALLUGO) |
-						 (inode->i_mode & ~S_IALLUGO));
-				iattr.ia_valid = ATTR_MODE;
-				/* FIXME should we update ctime ?
-				 * What is the following setxattr update the
-				 * mode ?
+			if (!acl) {
+				/*
+				 * ACL can be represented
+				 * by the mode bits. So don't
+				 * update ACL.
 				 */
-				v9fs_vfs_setattr_dotl(dentry, &iattr);
+				posix_acl_release(old_acl);
+				value = NULL;
+				size = 0;
 			}
+			iattr.ia_valid = ATTR_MODE;
+			/* FIXME should we update ctime ?
+			 * What is the following setxattr update the
+			 * mode ?
+			 */
+			v9fs_vfs_setattr_dotl(dentry, &iattr);
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 7bf835f85bc8..12ceaf52dae6 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 					v9fs_proto_dotu(v9ses));
 	fid = file->private_data;
 	if (!fid) {
-		fid = v9fs_fid_clone(file->f_path.dentry);
+		fid = v9fs_fid_clone(file_dentry(file));
 		if (IS_ERR(fid))
 			return PTR_ERR(fid);
 
@@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 		 * because we want write after unlink usecase
 		 * to work.
 		 */
-		fid = v9fs_writeback_fid(file->f_path.dentry);
+		fid = v9fs_writeback_fid(file_dentry(file));
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			mutex_unlock(&v9inode->v_mutex);
@@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
 		 * because we want write after unlink usecase
 		 * to work.
 		 */
-		fid = v9fs_writeback_fid(filp->f_path.dentry);
+		fid = v9fs_writeback_fid(file_dentry(filp));
 		if (IS_ERR(fid)) {
 			retval = PTR_ERR(fid);
 			mutex_unlock(&v9inode->v_mutex);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 5b50c4ca43a7..f90c535703ce 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -528,7 +528,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	char			*prefix = NULL;
 
 	new_opts = kstrdup(data, GFP_KERNEL);
-	if (!new_opts)
+	if (data && !new_opts)
 		return -ENOMEM;
 
 	pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
@@ -546,7 +546,8 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	flush_delayed_work(&sbi->sb_work);
-	replace_mount_options(sb, new_opts);
+	if (new_opts)
+		replace_mount_options(sb, new_opts);
 
 	sbi->s_flags = mount_flags;
 	sbi->s_mode  = mode;
diff --git a/fs/aio.c b/fs/aio.c
index 155f84253f33..fe4f49212b99 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -239,7 +239,12 @@ static struct dentry *aio_mount(struct file_system_type *fs_type,
 	static const struct dentry_operations ops = {
 		.d_dname	= simple_dname,
 	};
-	return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+					   AIO_RING_MAGIC);
+
+	if (!IS_ERR(root))
+		root->d_sb->s_iflags |= SB_I_NOEXEC;
+	return root;
 }
 
 /* aio_setup
diff --git a/fs/attr.c b/fs/attr.c
index 6530ced19697..d62f674a605f 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -202,6 +202,21 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
 			return -EPERM;
 	}
 
+	/*
+	 * If utimes(2) and friends are called with times == NULL (or both
+	 * times are UTIME_NOW), then we need to check for write permission
+	 */
+	if (ia_valid & ATTR_TOUCH) {
+		if (IS_IMMUTABLE(inode))
+			return -EPERM;
+
+		if (!inode_owner_or_capable(inode)) {
+			error = inode_permission(inode, MAY_WRITE);
+			if (error)
+				return error;
+		}
+	}
+
 	if ((ia_valid & ATTR_MODE)) {
 		umode_t amode = attr->ia_mode;
 		/* Flag setting protected by i_mutex */
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c37149b929be..502d3892d8a4 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -79,9 +79,13 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
-#define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
+#define AUTOFS_INF_WANT_EXPIRE	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
-					* not permitted
+					* not permitted.  If it progresses to
+					* actual expiry attempt, the flag is
+					* not cleared when EXPIRING is set -
+					* in that case it gets cleared only
+					* when it comes to clearing EXPIRING.
 					*/
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..257425511d10 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -331,7 +331,7 @@ static int autofs_dev_ioctl_fail(struct file *fp,
 	int status;
 
 	token = (autofs_wqt_t) param->fail.token;
-	status = param->fail.status ? param->fail.status : -ENOENT;
+	status = param->fail.status < 0 ? param->fail.status : -ENOENT;
 	return autofs4_wait_release(sbi, token, status);
 }
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1cebc3c52fa5..7a5a598a2d94 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -315,19 +315,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	if (ino->flags & AUTOFS_INF_PENDING)
 		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
 		spin_lock(&sbi->fs_lock);
 		if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 			ino->flags |= AUTOFS_INF_EXPIRING;
-			smp_mb();
-			ino->flags &= ~AUTOFS_INF_NO_RCU;
 			init_completion(&ino->expire_complete);
 			spin_unlock(&sbi->fs_lock);
 			return root;
 		}
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 	}
 out:
 	spin_unlock(&sbi->fs_lock);
@@ -417,6 +415,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 	return NULL;
 }
+
 /*
  * Find an eligible tree to time-out
  * A tree is eligible if :-
@@ -432,6 +431,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
 	struct dentry *expired;
+	struct dentry *found;
 	struct autofs_info *ino;
 
 	if (!root)
@@ -442,48 +442,54 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
 	dentry = NULL;
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
+		int flags = how;
+
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		if (ino->flags & AUTOFS_INF_NO_RCU)
-			expired = NULL;
-		else
-			expired = should_expire(dentry, mnt, timeout, how);
-		if (!expired) {
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
 			spin_unlock(&sbi->fs_lock);
 			continue;
 		}
+		spin_unlock(&sbi->fs_lock);
+
+		expired = should_expire(dentry, mnt, timeout, flags);
+		if (!expired)
+			continue;
+
+		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(expired);
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
-		spin_lock(&sbi->fs_lock);
-		if (should_expire(expired, mnt, timeout, how)) {
-			if (expired != dentry)
-				dput(dentry);
-			goto found;
-		}
 
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		/* Make sure a reference is not taken on found if
+		 * things have changed.
+		 */
+		flags &= ~AUTOFS_EXP_LEAVES;
+		found = should_expire(expired, mnt, timeout, how);
+		if (!found || found != expired)
+			/* Something has changed, continue */
+			goto next;
+
 		if (expired != dentry)
-			dput(expired);
+			dput(dentry);
+
+		spin_lock(&sbi->fs_lock);
+		goto found;
+next:
+		spin_lock(&sbi->fs_lock);
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
+		if (expired != dentry)
+			dput(expired);
 	}
 	return NULL;
 
 found:
 	DPRINTK("returning %p %pd", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
-	smp_mb();
-	ino->flags &= ~AUTOFS_INF_NO_RCU;
 	init_completion(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
-	spin_lock(&sbi->lookup_lock);
-	spin_lock(&expired->d_parent->d_lock);
-	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&expired->d_parent->d_subdirs, &expired->d_child);
-	spin_unlock(&expired->d_lock);
-	spin_unlock(&expired->d_parent->d_lock);
-	spin_unlock(&sbi->lookup_lock);
 	return expired;
 }
 
@@ -492,15 +498,27 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
+	int state;
 
 	/* Block on any pending expire */
-	if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+	if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
 		return 0;
 	if (rcu_walk)
 		return -ECHILD;
 
+retry:
 	spin_lock(&sbi->fs_lock);
-	if (ino->flags & AUTOFS_INF_EXPIRING) {
+	state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+	if (state == AUTOFS_INF_WANT_EXPIRE) {
+		spin_unlock(&sbi->fs_lock);
+		/*
+		 * Possibly being selected for expire, wait until
+		 * it's selected or not.
+		 */
+		schedule_timeout_uninterruptible(HZ/10);
+		goto retry;
+	}
+	if (state & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
 		DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
@@ -551,7 +569,7 @@ int autofs4_expire_run(struct super_block *sb,
 	ino = autofs4_dentry_ino(dentry);
 	/* avoid rapid-fire expire attempts if expiry fails */
 	ino->last_used = now;
-	ino->flags &= ~AUTOFS_INF_EXPIRING;
+	ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -579,7 +597,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		spin_lock(&sbi->fs_lock);
 		/* avoid rapid-fire expire attempts if expiry fails */
 		ino->last_used = now;
-		ino->flags &= ~AUTOFS_INF_EXPIRING;
+		ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		dput(dentry);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c6d7d3dbd52a..7a54c6a867c8 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -455,7 +455,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * a mount-trap.
 		 */
 		struct inode *inode;
-		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
 			return 0;
 		if (d_mountpoint(dentry))
 			return 0;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3a93755e880f..f44e93d2650d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -905,17 +905,60 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
 
 		vaddr = elf_ppnt->p_vaddr;
+		/*
+		 * If we are loading ET_EXEC or we have already performed
+		 * the ET_DYN load_addr calculations, proceed normally.
+		 */
 		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
 			elf_flags |= MAP_FIXED;
 		} else if (loc->elf_ex.e_type == ET_DYN) {
-			/* Try and get dynamic programs out of the way of the
-			 * default mmap base, as well as whatever program they
-			 * might try to exec.  This is because the brk will
-			 * follow the loader, and is not movable.  */
-			load_bias = ELF_ET_DYN_BASE - vaddr;
-			if (current->flags & PF_RANDOMIZE)
-				load_bias += arch_mmap_rnd();
-			load_bias = ELF_PAGESTART(load_bias);
+			/*
+			 * This logic is run once for the first LOAD Program
+			 * Header for ET_DYN binaries to calculate the
+			 * randomization (load_bias) for all the LOAD
+			 * Program Headers, and to calculate the entire
+			 * size of the ELF mapping (total_size). (Note that
+			 * load_addr_set is set to true later once the
+			 * initial mapping is performed.)
+			 *
+			 * There are effectively two types of ET_DYN
+			 * binaries: programs (i.e. PIE: ET_DYN with INTERP)
+			 * and loaders (ET_DYN without INTERP, since they
+			 * _are_ the ELF interpreter). The loaders must
+			 * be loaded away from programs since the program
+			 * may otherwise collide with the loader (especially
+			 * for ET_EXEC which does not have a randomized
+			 * position). For example to handle invocations of
+			 * "./ld.so someprog" to test out a new version of
+			 * the loader, the subsequent program that the
+			 * loader loads must avoid the loader itself, so
+			 * they cannot share the same load range. Sufficient
+			 * room for the brk must be allocated with the
+			 * loader as well, since brk must be available with
+			 * the loader.
+			 *
+			 * Therefore, programs are loaded offset from
+			 * ELF_ET_DYN_BASE and loaders are loaded into the
+			 * independently randomized mmap region (0 load_bias
+			 * without MAP_FIXED).
+			 */
+			if (elf_interpreter) {
+				load_bias = ELF_ET_DYN_BASE;
+				if (current->flags & PF_RANDOMIZE)
+					load_bias += arch_mmap_rnd();
+				elf_flags |= MAP_FIXED;
+			} else
+				load_bias = 0;
+
+			/*
+			 * Since load_bias is used for all subsequent loading
+			 * calculations, we must lower it by the first vaddr
+			 * so that the remaining calculations based on the
+			 * ELF vaddrs will be correctly offset. The result
+			 * is then page aligned.
+			 */
+			load_bias = ELF_PAGESTART(load_bias - vaddr);
+
 			total_size = total_mapping_size(elf_phdata,
 							loc->elf_ex.e_phnum);
 			if (!total_size) {
@@ -2295,6 +2338,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 		}
 	}
+	dump_truncate(cprm);
 
 	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 44d4a1e9244e..26bbaaefdff4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -88,12 +88,11 @@ void invalidate_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
-		return;
-
-	invalidate_bh_lrus();
-	lru_add_drain_all();	/* make sure all lru add caches are flushed */
-	invalidate_mapping_pages(mapping, 0, -1);
+	if (mapping->nrpages) {
+		invalidate_bh_lrus();
+		lru_add_drain_all();	/* make sure all lru add caches are flushed */
+		invalidate_mapping_pages(mapping, 0, -1);
+	}
 	/* 99% of the time, we don't need to flush the cleancache on the bdev.
 	 * But, for the strange corners, lets be cautious
 	 */
@@ -759,7 +758,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 		return true;	 /* already a holder */
 	else if (bdev->bd_holder != NULL)
 		return false; 	 /* held by someone else */
-	else if (bdev->bd_contains == bdev)
+	else if (whole == bdev)
 		return true;  	 /* is a whole device which isn't held */
 
 	else if (whole->bd_holder == bd_may_claim)
@@ -1098,7 +1097,6 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	bdev = bdget_disk(disk, 0);
 	if (!bdev)
 		return ret;
@@ -1806,6 +1804,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 	spin_lock(&blockdev_superblock->s_inode_list_lock);
 	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
 		struct address_space *mapping = inode->i_mapping;
+		struct block_device *bdev;
 
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
@@ -1826,8 +1825,12 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 		 */
 		iput(old_inode);
 		old_inode = inode;
+		bdev = I_BDEV(inode);
 
-		func(I_BDEV(inode), arg);
+		mutex_lock(&bdev->bd_mutex);
+		if (bdev->bd_openers)
+			func(bdev, arg);
+		mutex_unlock(&bdev->bd_mutex);
 
 		spin_lock(&blockdev_superblock->s_inode_list_lock);
 	}
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9a0124a95851..fb3e64d37cb4 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			ret = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (ret < 0)
+			ret = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (ret)
 				return ret;
-			if (ret == 0)
-				acl = NULL;
 		}
 		ret = 0;
 		break;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 9aba42b78253..a09264d8b853 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -70,6 +70,20 @@ void btrfs_##name(struct work_struct *arg)				\
 	normal_work_helper(work);					\
 }
 
+bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq)
+{
+	/*
+	 * We could compare wq->normal->pending with num_online_cpus()
+	 * to support "thresh == NO_THRESHOLD" case, but it requires
+	 * moving up atomic_inc/dec in thresh_queue/exec_hook. Let's
+	 * postpone it until someone needs the support of that case.
+	 */
+	if (wq->normal->thresh == NO_THRESHOLD)
+		return false;
+
+	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
+}
+
 BTRFS_WORK_HELPER(worker_helper);
 BTRFS_WORK_HELPER(delalloc_helper);
 BTRFS_WORK_HELPER(flush_delalloc_helper);
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index ad4d0647d1a6..8e1d6576d764 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -80,4 +80,5 @@ void btrfs_queue_work(struct btrfs_workqueue *wq,
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
 void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
+bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq);
 #endif
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42d7d6c..bae05c5c75ba 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -694,7 +694,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			ret = btrfs_map_bio(root, READ, comp_bio,
 					    mirror_num, 0);
 			if (ret) {
-				bio->bi_error = ret;
+				comp_bio->bi_error = ret;
 				bio_endio(comp_bio);
 			}
 
@@ -723,7 +723,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
 	if (ret) {
-		bio->bi_error = ret;
+		comp_bio->bi_error = ret;
 		bio_endio(comp_bio);
 	}
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5b8e235c4b6d..0f2b7c622ce3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1551,6 +1551,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		trans->dirty = true;
 		*cow_ret = buf;
 		return 0;
 	}
@@ -2773,8 +2774,10 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				trans->dirty = true;
 				goto cow_done;
+			}
 
 			/*
 			 * must have write locks on this node and the
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 385b449fd7ed..e847573c6db0 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1770,6 +1770,7 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
 	struct btrfs_work qgroup_rescan_work;
+	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
 
 	/* filesystem state */
 	unsigned long fs_state;
@@ -3069,6 +3070,8 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
 	cpu->target = le64_to_cpu(disk->target);
 	cpu->flags = le64_to_cpu(disk->flags);
 	cpu->limit = le64_to_cpu(disk->limit);
+	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
+	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
 }
 
 static inline void
@@ -3087,6 +3090,8 @@ btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
 	disk->target = cpu_to_le64(cpu->target);
 	disk->flags = cpu_to_le64(cpu->flags);
 	disk->limit = cpu_to_le64(cpu->limit);
+	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
+	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
 }
 
 /* struct btrfs_super_block */
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 02b934d0ee65..09fa5af9782e 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1375,7 +1375,8 @@ release_path:
 	total_done++;
 
 	btrfs_release_prepared_delayed_node(delayed_node);
-	if (async_work->nr == 0 || total_done < async_work->nr)
+	if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) ||
+	    total_done < async_work->nr)
 		goto again;
 
 free_path:
@@ -1391,7 +1392,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 {
 	struct btrfs_async_delayed_work *async_work;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND ||
+	    btrfs_workqueue_normal_congested(fs_info->delayed_workers))
 		return 0;
 
 	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 41fb43183406..85b207d19aa5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2276,6 +2276,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
 	fs_info->qgroup_ulist = NULL;
+	fs_info->qgroup_rescan_running = false;
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 
@@ -3811,7 +3812,7 @@ void close_ctree(struct btrfs_root *root)
 	smp_mb();
 
 	/* wait for the qgroup rescan worker to stop */
-	btrfs_qgroup_wait_for_completion(fs_info);
+	btrfs_qgroup_wait_for_completion(fs_info, false);
 
 	/* wait for the uuid_scan task to finish */
 	down(&fs_info->uuid_tree_rescan_sem);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2368cac1115a..c36a03fa7678 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2520,11 +2520,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		if (ref && ref->seq &&
 		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
-			btrfs_delayed_ref_unlock(locked_ref);
 			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
 			delayed_refs->num_heads_ready++;
 			spin_unlock(&delayed_refs->lock);
+			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 			cond_resched();
 			count++;
@@ -2570,7 +2570,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 					 */
 					if (must_insert_reserved)
 						locked_ref->must_insert_reserved = 1;
+					spin_lock(&delayed_refs->lock);
 					locked_ref->processing = 0;
+					delayed_refs->num_heads_ready++;
+					spin_unlock(&delayed_refs->lock);
 					btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
 					btrfs_delayed_ref_unlock(locked_ref);
 					return ret;
@@ -3851,6 +3854,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
@@ -7856,7 +7860,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
-	trans->blocks_used++;
+	trans->dirty = true;
 	/* this returns a buffer locked for blocking */
 	return buf;
 }
@@ -8486,14 +8490,13 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	ret = btrfs_lookup_extent_info(trans, root, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
 				       &wc->flags[level - 1]);
-	if (ret < 0) {
-		btrfs_tree_unlock(next);
-		return ret;
-	}
+	if (ret < 0)
+		goto out_unlock;
 
 	if (unlikely(wc->refs[level - 1] == 0)) {
 		btrfs_err(root->fs_info, "Missing references.");
-		BUG();
+		ret = -EIO;
+		goto out_unlock;
 	}
 	*lookup_info = 0;
 
@@ -8545,7 +8548,12 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	}
 
 	level--;
-	BUG_ON(level != btrfs_header_level(next));
+	ASSERT(level == btrfs_header_level(next));
+	if (level != btrfs_header_level(next)) {
+		btrfs_err(root->fs_info, "mismatched level");
+		ret = -EIO;
+		goto out_unlock;
+	}
 	path->nodes[level] = next;
 	path->slots[level] = 0;
 	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
@@ -8560,8 +8568,15 @@ skip:
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
 			parent = path->nodes[level]->start;
 		} else {
-			BUG_ON(root->root_key.objectid !=
+			ASSERT(root->root_key.objectid ==
 			       btrfs_header_owner(path->nodes[level]));
+			if (root->root_key.objectid !=
+			    btrfs_header_owner(path->nodes[level])) {
+				btrfs_err(root->fs_info,
+						"mismatched block owner");
+				ret = -EIO;
+				goto out_unlock;
+			}
 			parent = 0;
 		}
 
@@ -8578,12 +8593,18 @@ skip:
 		}
 		ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
 				root->root_key.objectid, level - 1, 0);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			goto out_unlock;
 	}
+
+	*lookup_info = 1;
+	ret = 1;
+
+out_unlock:
 	btrfs_tree_unlock(next);
 	free_extent_buffer(next);
-	*lookup_info = 1;
-	return 1;
+
+	return ret;
 }
 
 /*
@@ -9686,6 +9707,11 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	struct extent_buffer *leaf;
 	int need_clear = 0;
 	u64 cache_gen;
+	u64 feature;
+	int mixed;
+
+	feature = btrfs_super_incompat_flags(info->super_copy);
+	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);
 
 	root = info->extent_root;
 	key.objectid = 0;
@@ -9739,6 +9765,15 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 				   btrfs_item_ptr_offset(leaf, path->slots[0]),
 				   sizeof(cache->item));
 		cache->flags = btrfs_block_group_flags(&cache->item);
+		if (!mixed &&
+		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
+			btrfs_err(info,
+"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
+				  cache->key.objectid);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		key.objectid = found_key.objectid + found_key.offset;
 		btrfs_release_path(path);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9abe18763a7f..e767f347f2b1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2786,12 +2786,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
 		btrfs_bio->csum = NULL;
 		btrfs_bio->csum_allocated = NULL;
 		btrfs_bio->end_io = NULL;
-
-#ifdef CONFIG_BLK_CGROUP
-		/* FIXME, put this into bio_clone_bioset */
-		if (bio->bi_css)
-			bio_associate_blkcg(new, bio->bi_css);
-#endif
 	}
 	return new;
 }
@@ -5300,11 +5294,20 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			lock_page(page);
 		}
 		locked_pages++;
+	}
+	/*
+	 * We need to firstly lock all pages to make sure that
+	 * the uptodate bit of our pages won't be affected by
+	 * clear_extent_buffer_uptodate().
+	 */
+	for (i = start_i; i < num_pages; i++) {
+		page = eb->pages[i];
 		if (!PageUptodate(page)) {
 			num_reads++;
 			all_uptodate = 0;
 		}
 	}
+
 	if (all_uptodate) {
 		if (start_i == 0)
 			set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0f09526aa7d9..d4a6eef31854 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1526,27 +1526,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
 
-		if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					     BTRFS_INODE_PREALLOC)) {
-			ret = check_can_nocow(inode, pos, &write_bytes);
-			if (ret < 0)
-				break;
-			if (ret > 0) {
-				/*
-				 * For nodata cow case, no need to reserve
-				 * data space.
-				 */
-				only_release_metadata = true;
-				/*
-				 * our prealloc extent may be smaller than
-				 * write_bytes, so scale down.
-				 */
-				num_pages = DIV_ROUND_UP(write_bytes + offset,
-							 PAGE_CACHE_SIZE);
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-				goto reserve_metadata;
-			}
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			/*
+			 * For nodata cow case, no need to reserve
+			 * data space.
+			 */
+			only_release_metadata = true;
+			/*
+			 * our prealloc extent may be smaller than
+			 * write_bytes, so scale down.
+			 */
+			num_pages = DIV_ROUND_UP(write_bytes + offset,
+						 PAGE_CACHE_SIZE);
+			reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+			goto reserve_metadata;
 		}
+
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
 		if (ret < 0)
 			break;
@@ -1885,7 +1882,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
  */
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct dentry *dentry = file->f_path.dentry;
+	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
@@ -2774,7 +2771,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret)
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, 1 << inode->i_blkbits,
+					range->len, i_blocksize(inode),
 					offset + len, &alloc_hint);
 		list_del(&range->list);
 		kfree(range);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4bc9dbf29a73..bebd6517355d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4397,8 +4397,19 @@ search_again:
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
@@ -7318,8 +7329,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_CACHE_SHIFT;
 
@@ -7510,11 +7521,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode,
 	 * within our reservation, otherwise we need to adjust our inode
 	 * counter appropriately.
 	 */
-	if (dio_data->outstanding_extents) {
+	if (dio_data->outstanding_extents >= num_extents) {
 		dio_data->outstanding_extents -= num_extents;
 	} else {
+		/*
+		 * If dio write length has been split due to no large enough
+		 * contiguous space, we need to compensate our inode counter
+		 * appropriately.
+		 */
+		u64 num_needed = num_extents - dio_data->outstanding_extents;
+
 		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->outstanding_extents += num_extents;
+		BTRFS_I(inode)->outstanding_extents += num_needed;
 		spin_unlock(&BTRFS_I(inode)->lock);
 	}
 }
@@ -8691,9 +8709,14 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	 *    So even we call qgroup_free_data(), it won't decrease reserved
 	 *    space.
 	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here.
+	 *    This means the reserved space should be freed here. However,
+	 *    if a truncate invalidates the page (by clearing PageDirty)
+	 *    and the page is accounted for while allocating extent
+	 *    in btrfs_check_data_free_space() we let delayed_ref to
+	 *    free the entire extent.
 	 */
-	btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE);
+	if (PageDirty(page))
+		btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f07d01bc4875..317b99acdf4b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1619,6 +1619,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 	int namelen;
 	int ret = 0;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	ret = mnt_want_write_file(file);
 	if (ret)
 		goto out;
@@ -1648,7 +1651,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 
 		src_inode = file_inode(src.file);
 		if (src_inode->i_sb != file_inode(file)->i_sb) {
-			btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+			btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
 				   "Snapshot src from another FS");
 			ret = -EXDEV;
 		} else if (!inode_owner_or_capable(src_inode)) {
@@ -1676,6 +1679,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 	struct btrfs_ioctl_vol_args *vol_args;
 	int ret;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -1699,6 +1705,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	bool readonly = false;
 	struct btrfs_qgroup_inherit *inherit = NULL;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -2345,6 +2354,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	int ret;
 	int err = 0;
 
+	if (!S_ISDIR(dir->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -3813,6 +3825,11 @@ process_slot:
 		}
 		btrfs_release_path(path);
 		key.offset = next_key_min_offset;
+
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
 	}
 	ret = 0;
 
@@ -5121,7 +5138,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	return btrfs_qgroup_wait_for_completion(root->fs_info);
+	return btrfs_qgroup_wait_for_completion(root->fs_info, true);
 }
 
 static long _btrfs_ioctl_set_received_subvol(struct file *file,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5279fdae7142..88d9b66e2207 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 		goto out;
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
-	btrfs_qgroup_wait_for_completion(fs_info);
+	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
 	fs_info->quota_root = NULL;
@@ -2349,6 +2349,9 @@ out:
 	}
 
 done:
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = false;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
 	complete_all(&fs_info->qgroup_rescan_completion);
 }
 
@@ -2390,6 +2393,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		sizeof(fs_info->qgroup_rescan_progress));
 	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
 	init_completion(&fs_info->qgroup_rescan_completion);
+	fs_info->qgroup_rescan_running = true;
 
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -2467,20 +2471,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+				     bool interruptible)
 {
 	int running;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	spin_lock(&fs_info->qgroup_lock);
-	running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	running = fs_info->qgroup_rescan_running;
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	if (running)
+	if (!running)
+		return 0;
+
+	if (interruptible)
 		ret = wait_for_completion_interruptible(
 					&fs_info->qgroup_rescan_completion);
+	else
+		wait_for_completion(&fs_info->qgroup_rescan_completion);
 
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index ecb2c143ef75..3d73e4c9c7df 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+				     bool interruptible);
 int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index b4ca5454ef1a..8ca9aa92972d 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -921,9 +921,16 @@ again:
 			path2->slots[level]--;
 
 		eb = path2->nodes[level];
-		WARN_ON(btrfs_node_blockptr(eb, path2->slots[level]) !=
-			cur->bytenr);
-
+		if (btrfs_node_blockptr(eb, path2->slots[level]) !=
+		    cur->bytenr) {
+			btrfs_err(root->fs_info,
+	"couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)",
+				  cur->bytenr, level - 1, root->objectid,
+				  node_key->objectid, node_key->type,
+				  node_key->offset);
+			err = -ENOENT;
+			goto out;
+		}
 		lower = cur;
 		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
@@ -2343,6 +2350,10 @@ void free_reloc_roots(struct list_head *list)
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
+		free_extent_buffer(reloc_root->node);
+		free_extent_buffer(reloc_root->commit_root);
+		reloc_root->node = NULL;
+		reloc_root->commit_root = NULL;
 		__del_reloc_root(reloc_root);
 	}
 }
@@ -2676,11 +2687,15 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
 		if (!upper->eb) {
 			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
-			if (ret < 0) {
-				err = ret;
+			if (ret) {
+				if (ret < 0)
+					err = ret;
+				else
+					err = -ENOENT;
+
+				btrfs_release_path(path);
 				break;
 			}
-			BUG_ON(ret > 0);
 
 			if (!upper->eb) {
 				upper->eb = path->nodes[upper->level];
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index fe609b81dd1b..3bd2233737ac 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -239,7 +239,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 	trans->aborted = errno;
 	/* Nothing used. The other threads that have joined this
 	 * transaction may be able to continue. */
-	if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+	if (!trans->dirty && list_empty(&trans->new_bgs)) {
 		const char *errstr;
 
 		errstr = btrfs_decode_error(errno);
@@ -1727,6 +1727,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 		}
 
+		btrfs_qgroup_rescan_resume(fs_info);
+
 		if (!fs_info->uuid_root) {
 			btrfs_info(fs_info, "creating UUID tree");
 			ret = btrfs_create_uuid_tree(fs_info);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 64c8221b6165..1e872923ec2c 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -110,7 +110,6 @@ struct btrfs_trans_handle {
 	u64 chunk_bytes_reserved;
 	unsigned long use_count;
 	unsigned long blocks_reserved;
-	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
@@ -121,6 +120,7 @@ struct btrfs_trans_handle {
 	bool can_flush_pending_bgs;
 	bool reloc_reserved;
 	bool sync;
+	bool dirty;
 	unsigned int type;
 	/*
 	 * this root is only needed to validate that the root passed to
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 323e12cc9d2f..ee7832e2d39d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1923,12 +1923,11 @@ static noinline int find_dir_range(struct btrfs_root *root,
 next:
 	/* check the next slot in the tree to see if it is a valid item */
 	nritems = btrfs_header_nritems(path->nodes[0]);
+	path->slots[0]++;
 	if (path->slots[0] >= nritems) {
 		ret = btrfs_next_leaf(root, path);
 		if (ret)
 			goto out;
-	} else {
-		path->slots[0]++;
 	}
 
 	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
@@ -2696,14 +2695,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
 					     int index, int error)
 {
 	struct btrfs_log_ctx *ctx;
+	struct btrfs_log_ctx *safe;
 
-	if (!error) {
-		INIT_LIST_HEAD(&root->log_ctxs[index]);
-		return;
-	}
-
-	list_for_each_entry(ctx, &root->log_ctxs[index], list)
+	list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) {
+		list_del_init(&ctx->list);
 		ctx->log_ret = error;
+	}
 
 	INIT_LIST_HEAD(&root->log_ctxs[index]);
 }
@@ -2850,6 +2847,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
 		blk_finish_plug(&plug);
+		list_del_init(&root_log_ctx.list);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
@@ -2943,13 +2941,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	mutex_unlock(&root->log_mutex);
 
 out_wake_log_root:
-	/*
-	 * We needn't get log_mutex here because we are sure all
-	 * the other tasks are blocked.
-	 */
+	mutex_lock(&log_root_tree->log_mutex);
 	btrfs_remove_all_log_ctxs(log_root_tree, index2, ret);
 
-	mutex_lock(&log_root_tree->log_mutex);
 	log_root_tree->log_transid_committed++;
 	atomic_set(&log_root_tree->log_commit[index2], 0);
 	mutex_unlock(&log_root_tree->log_mutex);
@@ -2960,10 +2954,8 @@ out_wake_log_root:
 	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
 		wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
-	/* See above. */
-	btrfs_remove_all_log_ctxs(root, index1, ret);
-
 	mutex_lock(&root->log_mutex);
+	btrfs_remove_all_log_ctxs(root, index1, ret);
 	root->log_transid_committed++;
 	atomic_set(&root->log_commit[index1], 0);
 	mutex_unlock(&root->log_mutex);
@@ -4406,6 +4398,127 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * When we are logging a new inode X, check if it doesn't have a reference that
+ * matches the reference from some other inode Y created in a past transaction
+ * and that was renamed in the current transaction. If we don't do this, then at
+ * log replay time we can lose inode Y (and all its files if it's a directory):
+ *
+ * mkdir /mnt/x
+ * echo "hello world" > /mnt/x/foobar
+ * sync
+ * mv /mnt/x /mnt/y
+ * mkdir /mnt/x                 # or touch /mnt/x
+ * xfs_io -c fsync /mnt/x
+ * <power fail>
+ * mount fs, trigger log replay
+ *
+ * After the log replay procedure, we would lose the first directory and all its
+ * files (file foobar).
+ * For the case where inode Y is not a directory we simply end up losing it:
+ *
+ * echo "123" > /mnt/foo
+ * sync
+ * mv /mnt/foo /mnt/bar
+ * echo "abc" > /mnt/foo
+ * xfs_io -c fsync /mnt/foo
+ * <power fail>
+ *
+ * We also need this for cases where a snapshot entry is replaced by some other
+ * entry (file or directory) otherwise we end up with an unreplayable log due to
+ * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as
+ * if it were a regular entry:
+ *
+ * mkdir /mnt/x
+ * btrfs subvolume snapshot /mnt /mnt/x/snap
+ * btrfs subvolume delete /mnt/x/snap
+ * rmdir /mnt/x
+ * mkdir /mnt/x
+ * fsync /mnt/x or fsync some new file inside it
+ * <power fail>
+ *
+ * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in
+ * the same transaction.
+ */
+static int btrfs_check_ref_name_override(struct extent_buffer *eb,
+					 const int slot,
+					 const struct btrfs_key *key,
+					 struct inode *inode)
+{
+	int ret;
+	struct btrfs_path *search_path;
+	char *name = NULL;
+	u32 name_len = 0;
+	u32 item_size = btrfs_item_size_nr(eb, slot);
+	u32 cur_offset = 0;
+	unsigned long ptr = btrfs_item_ptr_offset(eb, slot);
+
+	search_path = btrfs_alloc_path();
+	if (!search_path)
+		return -ENOMEM;
+	search_path->search_commit_root = 1;
+	search_path->skip_locking = 1;
+
+	while (cur_offset < item_size) {
+		u64 parent;
+		u32 this_name_len;
+		u32 this_len;
+		unsigned long name_ptr;
+		struct btrfs_dir_item *di;
+
+		if (key->type == BTRFS_INODE_REF_KEY) {
+			struct btrfs_inode_ref *iref;
+
+			iref = (struct btrfs_inode_ref *)(ptr + cur_offset);
+			parent = key->offset;
+			this_name_len = btrfs_inode_ref_name_len(eb, iref);
+			name_ptr = (unsigned long)(iref + 1);
+			this_len = sizeof(*iref) + this_name_len;
+		} else {
+			struct btrfs_inode_extref *extref;
+
+			extref = (struct btrfs_inode_extref *)(ptr +
+							       cur_offset);
+			parent = btrfs_inode_extref_parent(eb, extref);
+			this_name_len = btrfs_inode_extref_name_len(eb, extref);
+			name_ptr = (unsigned long)&extref->name;
+			this_len = sizeof(*extref) + this_name_len;
+		}
+
+		if (this_name_len > name_len) {
+			char *new_name;
+
+			new_name = krealloc(name, this_name_len, GFP_NOFS);
+			if (!new_name) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			name_len = this_name_len;
+			name = new_name;
+		}
+
+		read_extent_buffer(eb, name, name_ptr, this_name_len);
+		di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root,
+					   search_path, parent,
+					   name, this_name_len, 0);
+		if (di && !IS_ERR(di)) {
+			ret = 1;
+			goto out;
+		} else if (IS_ERR(di)) {
+			ret = PTR_ERR(di);
+			goto out;
+		}
+		btrfs_release_path(search_path);
+
+		cur_offset += this_len;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(search_path);
+	kfree(name);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4578,6 +4691,22 @@ again:
 		if (min_key.type == BTRFS_INODE_ITEM_KEY)
 			need_log_inode_item = false;
 
+		if ((min_key.type == BTRFS_INODE_REF_KEY ||
+		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
+		    BTRFS_I(inode)->generation == trans->transid) {
+			ret = btrfs_check_ref_name_override(path->nodes[0],
+							    path->slots[0],
+							    &min_key, inode);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			} else if (ret > 0) {
+				err = 1;
+				btrfs_set_log_full_commit(root->fs_info, trans);
+				goto out_unlock;
+			}
+		}
+
 		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
 		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
 			if (ins_nr == 0)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9c62a6f9757a..600c67ef8a03 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	},
 };
 
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
 	[BTRFS_RAID_RAID1]  = BTRFS_BLOCK_GROUP_RAID1,
 	[BTRFS_RAID_DUP]    = BTRFS_BLOCK_GROUP_DUP,
diff --git a/fs/buffer.c b/fs/buffer.c
index 4f4cd959da7c..6f7d519a093b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2298,7 +2298,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned int blocksize = i_blocksize(inode);
 	struct page *page;
 	void *fsdata;
 	pgoff_t index, curidx;
@@ -2378,8 +2378,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 			get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
-	unsigned zerofrom;
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int zerofrom;
 	int err;
 
 	err = cont_expand_zero(file, mapping, pos, bytes);
@@ -2741,7 +2741,7 @@ int nobh_truncate_page(struct address_space *mapping,
 	struct buffer_head map_bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2819,7 +2819,7 @@ int block_truncate_page(struct address_space *mapping,
 	struct buffer_head *bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2931,7 +2931,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 	struct inode *inode = mapping->host;
 	tmp.b_state = 0;
 	tmp.b_blocknr = 0;
-	tmp.b_size = 1 << inode->i_blkbits;
+	tmp.b_size = i_blocksize(inode);
 	get_block(inode, block, &tmp, 0);
 	return tmp.b_blocknr;
 }
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 8f84646f10e9..bdb9c94335f1 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -94,11 +94,9 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			ret = posix_acl_equiv_mode(acl, &new_mode);
-			if (ret < 0)
+			ret = posix_acl_update_mode(inode, &new_mode, &acl);
+			if (ret)
 				goto out;
-			if (ret == 0)
-				acl = NULL;
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
@@ -130,7 +128,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	if (new_mode != old_mode) {
 		newattrs.ia_mode = new_mode;
 		newattrs.ia_valid = ATTR_MODE;
-		ret = ceph_setattr(dentry, &newattrs);
+		ret = __ceph_setattr(dentry, &newattrs);
 		if (ret)
 			goto out_dput;
 	}
@@ -140,7 +138,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		if (new_mode != old_mode) {
 			newattrs.ia_mode = old_mode;
 			newattrs.ia_valid = ATTR_MODE;
-			ceph_setattr(dentry, &newattrs);
+			__ceph_setattr(dentry, &newattrs);
 		}
 		goto out_dput;
 	}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b7d218a168fb..22bae2b434e2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -189,7 +189,7 @@ static int ceph_releasepage(struct page *page, gfp_t g)
 /*
  * read a single page, without unlocking it.
  */
-static int readpage_nounlock(struct file *filp, struct page *page)
+static int ceph_do_readpage(struct file *filp, struct page *page)
 {
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -219,7 +219,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 
 	err = ceph_readpage_from_fscache(inode, page);
 	if (err == 0)
-		goto out;
+		return -EINPROGRESS;
 
 	dout("readpage inode %p file %p page %p index %lu\n",
 	     inode, filp, page, page->index);
@@ -249,8 +249,11 @@ out:
 
 static int ceph_readpage(struct file *filp, struct page *page)
 {
-	int r = readpage_nounlock(filp, page);
-	unlock_page(page);
+	int r = ceph_do_readpage(filp, page);
+	if (r != -EINPROGRESS)
+		unlock_page(page);
+	else
+		r = 0;
 	return r;
 }
 
@@ -697,7 +700,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
-	unsigned wsize = 1 << inode->i_blkbits;
+	unsigned int wsize = i_blocksize(inode);
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
 	loff_t snap_size, i_size;
@@ -1094,7 +1097,7 @@ retry_locked:
 			goto retry_locked;
 		r = writepage_nounlock(page, NULL);
 		if (r < 0)
-			goto fail_nosnap;
+			goto fail_unlock;
 		goto retry_locked;
 	}
 
@@ -1122,11 +1125,14 @@ retry_locked:
 	}
 
 	/* we need to read it. */
-	r = readpage_nounlock(file, page);
-	if (r < 0)
-		goto fail_nosnap;
+	r = ceph_do_readpage(file, page);
+	if (r < 0) {
+		if (r == -EINPROGRESS)
+			return -EAGAIN;
+		goto fail_unlock;
+	}
 	goto retry_locked;
-fail_nosnap:
+fail_unlock:
 	unlock_page(page);
 	return r;
 }
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index a4766ded1ba7..ff1cfd7b1083 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -224,13 +224,7 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
 	fscache_relinquish_cookie(cookie, 0);
 }
 
-static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
-{
-	if (!error)
-		SetPageUptodate(page);
-}
-
-static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
 {
 	if (!error)
 		SetPageUptodate(page);
@@ -259,7 +253,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_page(ci->fscache, page,
-					 ceph_vfs_readpage_complete, NULL,
+					 ceph_readpage_from_fscache_complete, NULL,
 					 GFP_KERNEL);
 
 	switch (ret) {
@@ -288,7 +282,7 @@ int ceph_readpages_from_fscache(struct inode *inode,
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
-					  ceph_vfs_readpage_complete_unlock,
+					  ceph_readpage_from_fscache_complete,
 					  NULL, mapping_gfp_mask(mapping));
 
 	switch (ret) {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 9314b4ea2375..be7d187d53fd 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -247,6 +247,11 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		if (ret < 0)
 			err = ret;
 		dput(last);
+		/* last_name no longer match cache index */
+		if (fi->readdir_cache_idx >= 0) {
+			fi->readdir_cache_idx = -1;
+			fi->dir_release_count = 0;
+		}
 	}
 	return err;
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3c68e6aee2f0..c8222bfe1e56 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -929,7 +929,8 @@ again:
 		statret = __ceph_do_getattr(inode, page,
 					    CEPH_STAT_CAP_INLINE_DATA, !!page);
 		if (statret < 0) {
-			 __free_page(page);
+			if (page)
+				__free_page(page);
 			if (statret == -ENODATA) {
 				BUG_ON(retry_op != READ_INLINE);
 				goto again;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 498dcfa2dcdb..9f0d99094cc1 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1358,15 +1358,20 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
 
 	if (!ctl->page || pgoff != page_index(ctl->page)) {
 		ceph_readdir_cache_release(ctl);
-		ctl->page  = grab_cache_page(&dir->i_data, pgoff);
+		if (idx == 0)
+			ctl->page = grab_cache_page(&dir->i_data, pgoff);
+		else
+			ctl->page = find_lock_page(&dir->i_data, pgoff);
 		if (!ctl->page) {
 			ctl->index = -1;
-			return -ENOMEM;
+			return idx == 0 ? -ENOMEM : 0;
 		}
 		/* reading/filling the cache are serialized by
 		 * i_mutex, no need to use page lock */
 		unlock_page(ctl->page);
 		ctl->dentries = kmap(ctl->page);
+		if (idx == 0)
+			memset(ctl->dentries, 0, PAGE_CACHE_SIZE);
 	}
 
 	if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
@@ -1768,7 +1773,7 @@ static const struct inode_operations ceph_symlink_iops = {
 /*
  * setattr
  */
-int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+int __ceph_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1970,11 +1975,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-	if (ia_valid & ATTR_MODE) {
-		err = posix_acl_chmod(inode, attr->ia_mode);
-		if (err)
-			goto out_put;
-	}
 
 	if (mask) {
 		req->r_inode = inode;
@@ -1988,13 +1988,23 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	     ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
-	if (mask & CEPH_SETATTR_SIZE)
-		__ceph_do_pending_vmtruncate(inode);
 	ceph_free_cap_flush(prealloc_cf);
+
+	if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+		__ceph_do_pending_vmtruncate(inode);
+
 	return err;
-out_put:
-	ceph_mdsc_put_request(req);
-	ceph_free_cap_flush(prealloc_cf);
+}
+
+int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	int err;
+
+	err = __ceph_setattr(dentry, attr);
+
+	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+		err = posix_acl_chmod(d_inode(dentry), attr->ia_mode);
+
 	return err;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index e7b130a637f9..f54f77037d22 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -274,12 +274,13 @@ static int parse_reply_info_extra(void **p, void *end,
 				  struct ceph_mds_reply_info_parsed *info,
 				  u64 features)
 {
-	if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+	u32 op = le32_to_cpu(info->head->op);
+
+	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_READDIR ||
-		 info->head->op == CEPH_MDS_OP_LSSNAP)
+	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
 		return parse_reply_info_dir(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_CREATE)
+	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features);
 	else
 		return -EIO;
@@ -643,6 +644,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 {
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
 
+	/* Never leave an unregistered request on an unsafe list! */
+	list_del_init(&req->r_unsafe_item);
+
 	if (req->r_tid == mdsc->oldest_tid) {
 		struct rb_node *p = rb_next(&req->r_node);
 		mdsc->oldest_tid = 0;
@@ -1050,7 +1054,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
 	while (!list_empty(&session->s_unsafe)) {
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
-		list_del_init(&req->r_unsafe_item);
 		pr_warn_ratelimited(" dropping unsafe request %llu\n",
 				    req->r_tid);
 		__unregister_request(mdsc, req);
@@ -2476,7 +2479,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			 * useful we could do with a revised return value.
 			 */
 			dout("got safe reply %llu, mds%d\n", tid, mds);
-			list_del_init(&req->r_unsafe_item);
 
 			/* last unsafe request during umount? */
 			if (mdsc->stopping && !__get_oldest_req(mdsc))
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 75b7d125ce66..8c8cb8fe3d32 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -788,6 +788,7 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
 	return __ceph_do_getattr(inode, NULL, mask, force);
 }
 extern int ceph_permission(struct inode *inode, int mask);
+extern int __ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
 			struct kstat *stat);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 819163d8313b..b24275ef97f7 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -369,6 +369,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 
 	if (update_xattr) {
 		int err = 0;
+
 		if (xattr && (flags & XATTR_CREATE))
 			err = -EEXIST;
 		else if (!xattr && (flags & XATTR_REPLACE))
@@ -376,12 +377,14 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		if (err) {
 			kfree(name);
 			kfree(val);
+			kfree(*newxattr);
 			return err;
 		}
 		if (update_xattr < 0) {
 			if (xattr)
 				__remove_xattr(ci, xattr);
 			kfree(name);
+			kfree(*newxattr);
 			return 0;
 		}
 	}
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 50b268483302..0a3544fb50f9 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -152,6 +152,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	list_for_each(tmp1, &cifs_tcp_ses_list) {
 		server = list_entry(tmp1, struct TCP_Server_Info,
 				    tcp_ses_list);
+		seq_printf(m, "\nNumber of credits: %d", server->credits);
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
@@ -255,7 +256,6 @@ static const struct file_operations cifs_debug_data_proc_fops = {
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
 	bool bv;
 	int rc;
 	struct list_head *tmp1, *tmp2, *tmp3;
@@ -263,11 +263,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	rc = get_user(c, buffer);
-	if (rc)
-		return rc;
-
-	if (strtobool(&c, &bv) == 0) {
+	rc = kstrtobool_from_user(buffer, count, &bv);
+	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
@@ -290,6 +287,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 			}
 		}
 		spin_unlock(&cifs_tcp_ses_lock);
+	} else {
+		return rc;
 	}
 
 	return count;
@@ -433,17 +432,17 @@ static int cifsFYI_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
+	char c[2] = { '\0' };
 	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = get_user(c[0], buffer);
 	if (rc)
 		return rc;
-	if (strtobool(&c, &bv) == 0)
+	if (strtobool(c, &bv) == 0)
 		cifsFYI = bv;
-	else if ((c > '1') && (c <= '9'))
-		cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */
+	else if ((c[0] > '1') && (c[0] <= '9'))
+		cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
 
 	return count;
 }
@@ -471,20 +470,12 @@ static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_linux_ext_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &linuxExtEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	linuxExtEnabled = bv;
-
 	return count;
 }
 
@@ -511,20 +502,12 @@ static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file)
 static ssize_t cifs_lookup_cache_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &lookupCacheEnabled);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	lookupCacheEnabled = bv;
-
 	return count;
 }
 
@@ -551,20 +534,12 @@ static int traceSMB_proc_open(struct inode *inode, struct file *file)
 static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
-	char c;
-	bool bv;
 	int rc;
 
-	rc = get_user(c, buffer);
+	rc = kstrtobool_from_user(buffer, count, &traceSMB);
 	if (rc)
 		return rc;
 
-	rc = strtobool(&c, &bv);
-	if (rc)
-		return rc;
-
-	traceSMB = bv;
-
 	return count;
 }
 
@@ -622,7 +597,6 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	int rc;
 	unsigned int flags;
 	char flags_string[12];
-	char c;
 	bool bv;
 
 	if ((count < 1) || (count > 11))
@@ -635,11 +609,10 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 
 	if (count < 3) {
 		/* single char or single char followed by null */
-		c = flags_string[0];
-		if (strtobool(&c, &bv) == 0) {
+		if (strtobool(flags_string, &bv) == 0) {
 			global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF;
 			return count;
-		} else if (!isdigit(c)) {
+		} else if (!isdigit(flags_string[0])) {
 			cifs_dbg(VFS, "Invalid SecurityFlags: %s\n",
 					flags_string);
 			return -EINVAL;
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index 66cf0f9fff89..c611ca2339d7 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -25,7 +25,7 @@
 void cifs_dump_mem(char *label, void *data, int length);
 void cifs_dump_detail(void *);
 void cifs_dump_mids(struct TCP_Server_Info *);
-extern int traceSMB;		/* flag which enables the function below */
+extern bool traceSMB;		/* flag which enables the function below */
 void dump_smb(void *, int);
 #define CIFS_INFO	0x01
 #define CIFS_RC		0x02
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 3182273a3407..1418daa03d95 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -46,6 +46,9 @@
 #define CIFS_MOUNT_CIFS_BACKUPUID 0x200000 /* backup intent bit for a user */
 #define CIFS_MOUNT_CIFS_BACKUPGID 0x400000 /* backup intent bit for a group */
 #define CIFS_MOUNT_MAP_SFM_CHR	0x800000 /* SFM/MAC mapping for illegal chars */
+#define CIFS_MOUNT_USE_PREFIX_PATH 0x1000000 /* make subpath with unaccessible
+					      * root mountable
+					      */
 
 struct cifs_sb_info {
 	struct rb_root tlink_tree;
@@ -67,5 +70,6 @@ struct cifs_sb_info {
 	struct backing_dev_info bdi;
 	struct delayed_work prune_tlinks;
 	struct rcu_head rcu;
+	char *prepath;
 };
 #endif				/* _CIFS_FS_SB_H */
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 5a53ac6b1e02..a0b3e7d1be48 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -83,6 +83,9 @@ convert_sfm_char(const __u16 src_char, char *target)
 	case SFM_COLON:
 		*target = ':';
 		break;
+	case SFM_DOUBLEQUOTE:
+		*target = '"';
+		break;
 	case SFM_ASTERISK:
 		*target = '*';
 		break;
@@ -101,6 +104,12 @@ convert_sfm_char(const __u16 src_char, char *target)
 	case SFM_SLASH:
 		*target = '\\';
 		break;
+	case SFM_SPACE:
+		*target = ' ';
+		break;
+	case SFM_PERIOD:
+		*target = '.';
+		break;
 	default:
 		return false;
 	}
@@ -404,7 +413,7 @@ static __le16 convert_to_sfu_char(char src_char)
 	return dest_char;
 }
 
-static __le16 convert_to_sfm_char(char src_char)
+static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
 {
 	__le16 dest_char;
 
@@ -412,6 +421,9 @@ static __le16 convert_to_sfm_char(char src_char)
 	case ':':
 		dest_char = cpu_to_le16(SFM_COLON);
 		break;
+	case '"':
+		dest_char = cpu_to_le16(SFM_DOUBLEQUOTE);
+		break;
 	case '*':
 		dest_char = cpu_to_le16(SFM_ASTERISK);
 		break;
@@ -427,6 +439,18 @@ static __le16 convert_to_sfm_char(char src_char)
 	case '|':
 		dest_char = cpu_to_le16(SFM_PIPE);
 		break;
+	case '.':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_PERIOD);
+		else
+			dest_char = 0;
+		break;
+	case ' ':
+		if (end_of_string)
+			dest_char = cpu_to_le16(SFM_SPACE);
+		else
+			dest_char = 0;
+		break;
 	default:
 		dest_char = 0;
 	}
@@ -469,9 +493,16 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		/* see if we must remap this char */
 		if (map_chars == SFU_MAP_UNI_RSVD)
 			dst_char = convert_to_sfu_char(src_char);
-		else if (map_chars == SFM_MAP_UNI_RSVD)
-			dst_char = convert_to_sfm_char(src_char);
-		else
+		else if (map_chars == SFM_MAP_UNI_RSVD) {
+			bool end_of_string;
+
+			if (i == srclen - 1)
+				end_of_string = true;
+			else
+				end_of_string = false;
+
+			dst_char = convert_to_sfm_char(src_char, end_of_string);
+		} else
 			dst_char = 0;
 		/*
 		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index bdc52cb9a676..07ade707fa60 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -57,6 +57,7 @@
  * not conflict (although almost does) with the mapping above.
  */
 
+#define SFM_DOUBLEQUOTE ((__u16) 0xF020)
 #define SFM_ASTERISK    ((__u16) 0xF021)
 #define SFM_QUESTION    ((__u16) 0xF025)
 #define SFM_COLON       ((__u16) 0xF022)
@@ -64,6 +65,8 @@
 #define SFM_LESSTHAN    ((__u16) 0xF023)
 #define SFM_PIPE        ((__u16) 0xF027)
 #define SFM_SLASH       ((__u16) 0xF026)
+#define SFM_SPACE	((__u16) 0xF028)
+#define SFM_PERIOD	((__u16) 0xF029)
 
 /*
  * Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index e682b36a210f..4acbc390a7d6 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -731,24 +731,26 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	memcpy(ses->auth_key.response + baselen, tiblob, tilen);
 
+	mutex_lock(&ses->server->srv_mutex);
+
 	rc = crypto_hmacmd5_alloc(ses->server);
 	if (rc) {
 		cifs_dbg(VFS, "could not crypto alloc hmacmd5 rc %d\n", rc);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	/* calculate ntlmv2_hash */
 	rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp);
 	if (rc) {
 		cifs_dbg(VFS, "could not get v2 hash rc %d\n", rc);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	/* calculate first part of the client response (CR1) */
 	rc = CalcNTLMv2_response(ses, ntlmv2_hash);
 	if (rc) {
 		cifs_dbg(VFS, "Could not calculate CR1 rc: %d\n", rc);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	/* now calculate the session key for NTLMv2 */
@@ -757,13 +759,13 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set NTLMV2 Hash as a key\n",
 			 __func__);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	rc = crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash,
@@ -771,7 +773,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 		CIFS_HMAC_MD5_HASH_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
-		goto setup_ntlmv2_rsp_ret;
+		goto unlock;
 	}
 
 	rc = crypto_shash_final(&ses->server->secmech.sdeschmacmd5->shash,
@@ -779,6 +781,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	if (rc)
 		cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__);
 
+unlock:
+	mutex_unlock(&ses->server->srv_mutex);
 setup_ntlmv2_rsp_ret:
 	kfree(tiblob);
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index cbc0f4bca0c0..4f4fc9ff3636 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -54,10 +54,10 @@
 #endif
 
 int cifsFYI = 0;
-int traceSMB = 0;
+bool traceSMB;
 bool enable_oplocks = true;
-unsigned int linuxExtEnabled = 1;
-unsigned int lookupCacheEnabled = 1;
+bool linuxExtEnabled = true;
+bool lookupCacheEnabled = true;
 unsigned int global_secflags = CIFSSEC_DEF;
 /* unsigned int ntlmv2_support = 0; */
 unsigned int sign_CIFS_PDUs = 1;
@@ -268,7 +268,7 @@ cifs_alloc_inode(struct super_block *sb)
 	cifs_inode->createtime = 0;
 	cifs_inode->epoch = 0;
 #ifdef CONFIG_CIFS_SMB2
-	get_random_bytes(cifs_inode->lease_key, SMB2_LEASE_KEY_SIZE);
+	generate_random_uuid(cifs_inode->lease_key);
 #endif
 	/*
 	 * Can not set i_flags here - they get immediately overwritten to zero
@@ -686,6 +686,14 @@ cifs_do_mount(struct file_system_type *fs_type,
 		goto out_cifs_sb;
 	}
 
+	if (volume_info->prepath) {
+		cifs_sb->prepath = kstrdup(volume_info->prepath, GFP_KERNEL);
+		if (cifs_sb->prepath == NULL) {
+			root = ERR_PTR(-ENOMEM);
+			goto out_cifs_sb;
+		}
+	}
+
 	cifs_setup_cifs_sb(volume_info, cifs_sb);
 
 	rc = cifs_mount(cifs_sb, volume_info);
@@ -724,7 +732,11 @@ cifs_do_mount(struct file_system_type *fs_type,
 		sb->s_flags |= MS_ACTIVE;
 	}
 
-	root = cifs_get_root(volume_info, sb);
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+		root = dget(sb->s_root);
+	else
+		root = cifs_get_root(volume_info, sb);
+
 	if (IS_ERR(root))
 		goto out_super;
 
@@ -1198,7 +1210,6 @@ init_cifs(void)
 	GlobalTotalActiveXid = 0;
 	GlobalMaxActiveXid = 0;
 	spin_lock_init(&cifs_tcp_ses_lock);
-	spin_lock_init(&cifs_file_list_lock);
 	spin_lock_init(&GlobalMid_Lock);
 
 	if (cifs_max_pending < 2) {
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 2b510c537a0d..e2f6a79e9b01 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -227,6 +227,7 @@ struct smb_version_operations {
 	/* verify the message */
 	int (*check_message)(char *, unsigned int);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+	int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *,
 					struct cifsInodeInfo *, bool);
 	/* process transaction2 response */
@@ -627,6 +628,8 @@ struct TCP_Server_Info {
 #ifdef CONFIG_CIFS_SMB2
 	unsigned int	max_read;
 	unsigned int	max_write;
+	struct delayed_work reconnect; /* reconnect workqueue job */
+	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 #endif /* CONFIG_CIFS_SMB2 */
 };
 
@@ -826,7 +829,9 @@ cap_unix(struct cifs_ses *ses)
 struct cifs_tcon {
 	struct list_head tcon_list;
 	int tc_count;
+	struct list_head rlist; /* reconnect list */
 	struct list_head openFileList;
+	spinlock_t open_file_lock; /* protects list above */
 	struct cifs_ses *ses;	/* pointer to session associated with */
 	char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */
 	char *nativeFileSystem;
@@ -883,7 +888,7 @@ struct cifs_tcon {
 #endif /* CONFIG_CIFS_STATS2 */
 	__u64    bytes_read;
 	__u64    bytes_written;
-	spinlock_t stat_lock;
+	spinlock_t stat_lock;  /* protects the two fields above */
 #endif /* CONFIG_CIFS_STATS */
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
@@ -902,7 +907,6 @@ struct cifs_tcon {
 	bool use_persistent:1; /* use persistent instead of durable handles */
 #ifdef CONFIG_CIFS_SMB2
 	bool print:1;		/* set if connection to printer share */
-	bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
 	__le32 capabilities;
 	__u32 share_flags;
 	__u32 maximal_access;
@@ -1034,8 +1038,10 @@ struct cifs_fid_locks {
 };
 
 struct cifsFileInfo {
+	/* following two lists are protected by tcon->open_file_lock */
 	struct list_head tlist;	/* pointer to next fid owned by tcon */
 	struct list_head flist;	/* next fid (file instance) for this inode */
+	/* lock list below protected by cifsi->lock_sem */
 	struct cifs_fid_locks *llist;	/* brlocks held by this fid */
 	kuid_t uid;		/* allows finding which FileInfo structure */
 	__u32 pid;		/* process id who opened file */
@@ -1043,11 +1049,12 @@ struct cifsFileInfo {
 	/* BB add lock scope info here if needed */ ;
 	/* lock scope id (0 if none) */
 	struct dentry *dentry;
-	unsigned int f_flags;
 	struct tcon_link *tlink;
+	unsigned int f_flags;
 	bool invalidHandle:1;	/* file closed via session abend */
 	bool oplock_break_cancelled:1;
-	int count;		/* refcount protected by cifs_file_list_lock */
+	int count;
+	spinlock_t file_info_lock; /* protects four flag/count fields above */
 	struct mutex fh_mutex; /* prevents reopen race after dead ses*/
 	struct cifs_search_info srch_inf;
 	struct work_struct oplock_break; /* work for oplock breaks */
@@ -1114,7 +1121,7 @@ struct cifs_writedata {
 
 /*
  * Take a reference on the file private data. Must be called with
- * cifs_file_list_lock held.
+ * cfile->file_info_lock held.
  */
 static inline void
 cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file)
@@ -1283,12 +1290,19 @@ struct mid_q_entry {
 	void *callback_data;	  /* general purpose pointer for callback */
 	void *resp_buf;		/* pointer to received SMB header */
 	int mid_state;	/* wish this were enum but can not pass to wait_event */
+	unsigned int mid_flags;
 	__le16 command;		/* smb command code */
 	bool large_buf:1;	/* if valid response, is pointer to large buf */
 	bool multiRsp:1;	/* multiple trans2 responses for one request  */
 	bool multiEnd:1;	/* both received */
 };
 
+struct close_cancelled_open {
+	struct cifs_fid         fid;
+	struct cifs_tcon        *tcon;
+	struct work_struct      work;
+};
+
 /*	Make code in transport.c a little cleaner by moving
 	update of optional stats into function below */
 #ifdef CONFIG_CIFS_STATS2
@@ -1420,6 +1434,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   MID_RESPONSE_MALFORMED 0x10
 #define   MID_SHUTDOWN		 0x20
 
+/* Flags */
+#define   MID_WAIT_CANCELLED	 1 /* Cancelled while waiting for response */
+
 /* Types of response buffer returned from SendReceive2 */
 #define   CIFS_NO_BUFFER        0    /* Response buffer not returned */
 #define   CIFS_SMALL_BUFFER     1
@@ -1508,8 +1525,10 @@ require use of the stronger protocol */
  *  GlobalMid_Lock protects:
  *	list operations on pending_mid_q and oplockQ
  *      updates to XID counters, multiplex id  and SMB sequence numbers
- *  cifs_file_list_lock protects:
- *	list operations on tcp and SMB session lists and tCon lists
+ *  tcp_ses_lock protects:
+ *	list operations on tcp and SMB session lists
+ *  tcon->open_file_lock protects the list of open files hanging off the tcon
+ *  cfile->file_info_lock protects counters and fields in cifs file struct
  *  f_owner.lock protects certain per file struct operations
  *  mapping->page_lock protects certain per page operations
  *
@@ -1541,18 +1560,12 @@ GLOBAL_EXTERN struct list_head		cifs_tcp_ses_list;
  * tcp session, and the list of tcon's per smb session. It also protects
  * the reference counters for the server, smb session, and tcon. Finally,
  * changes to the tcon->tidStatus should be done while holding this lock.
+ * generally the locks should be taken in order tcp_ses_lock before
+ * tcon->open_file_lock and that before file->file_info_lock since the
+ * structure order is cifs_socket-->cifs_ses-->cifs_tcon-->cifs_file
  */
 GLOBAL_EXTERN spinlock_t		cifs_tcp_ses_lock;
 
-/*
- * This lock protects the cifs_file->llist and cifs_file->flist
- * list operations, and updates to some flags (cifs_file->invalidHandle)
- * It will be moved to either use the tcon->stat_lock or equivalent later.
- * If cifs_tcp_ses_lock and the lock below are both needed to be held, then
- * the cifs_tcp_ses_lock must be grabbed first and released last.
- */
-GLOBAL_EXTERN spinlock_t	cifs_file_list_lock;
-
 #ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
 /* Outstanding dir notify requests */
 GLOBAL_EXTERN struct list_head GlobalDnotifyReqList;
@@ -1588,11 +1601,11 @@ GLOBAL_EXTERN atomic_t midCount;
 
 /* Misc globals */
 GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN unsigned int lookupCacheEnabled;
+GLOBAL_EXTERN bool lookupCacheEnabled;
 GLOBAL_EXTERN unsigned int global_secflags;	/* if on, session setup sent
 				with more secure ntlmssp2 challenge/resp */
 GLOBAL_EXTERN unsigned int sign_CIFS_PDUs;  /* enable smb packet signing */
-GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
 GLOBAL_EXTERN unsigned int CIFSMaxBufSize;  /* max size not including hdr */
 GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c63fd1dde25b..54590fd33df1 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -205,6 +205,9 @@ extern void cifs_add_pending_open_locked(struct cifs_fid *fid,
 					 struct tcon_link *tlink,
 					 struct cifs_pending_open *open);
 extern void cifs_del_pending_open(struct cifs_pending_open *open);
+extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
+				 int from_reconnect);
+extern void cifs_put_tcon(struct cifs_tcon *tcon);
 
 #if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL)
 extern void cifs_dfs_release_automount_timer(void);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 76fcb50295a3..b60150e5b5ce 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -98,13 +98,13 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
 	struct list_head *tmp1;
 
 	/* list all files open on tree connection and mark them invalid */
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
 	list_for_each_safe(tmp, tmp1, &tcon->openFileList) {
 		open_file = list_entry(tmp, struct cifsFileInfo, tlist);
 		open_file->invalidHandle = true;
 		open_file->oplock_break_cancelled = true;
 	}
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tcon->open_file_lock);
 	/*
 	 * BB Add call to invalidate_inodes(sb) for all superblocks mounted
 	 * to this tcon.
@@ -717,6 +717,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
+	if (server->capabilities & CAP_UNICODE)
+		smb->hdr.Flags2 |= SMBFLG2_UNICODE;
+
 	/* set up echo request */
 	smb->hdr.Tid = 0xffff;
 	smb->hdr.WordCount = 1;
@@ -1424,6 +1427,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	length = discard_remaining_data(server);
 	dequeue_mid(mid, rdata->result);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
@@ -1538,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return cifs_readv_discard(server, mid);
 
 	dequeue_mid(mid, false);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 3c194ff0d2f0..53a827c6d8b1 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -52,6 +52,9 @@
 #include "nterr.h"
 #include "rfc1002pdu.h"
 #include "fscache.h"
+#ifdef CONFIG_CIFS_SMB2
+#include "smb2proto.h"
+#endif
 
 #define CIFS_PORT 445
 #define RFC1001_PORT 139
@@ -409,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		}
 	} while (server->tcpStatus == CifsNeedReconnect);
 
+	if (server->tcpStatus == CifsNeedNegotiate)
+		mod_delayed_work(cifsiod_wq, &server->echo, 0);
+
 	return rc;
 }
 
@@ -418,16 +424,27 @@ cifs_echo_request(struct work_struct *work)
 	int rc;
 	struct TCP_Server_Info *server = container_of(work,
 					struct TCP_Server_Info, echo.work);
+	unsigned long echo_interval;
+
+	/*
+	 * If we need to renegotiate, set echo interval to zero to
+	 * immediately call echo service where we can renegotiate.
+	 */
+	if (server->tcpStatus == CifsNeedNegotiate)
+		echo_interval = 0;
+	else
+		echo_interval = SMB_ECHO_INTERVAL;
 
 	/*
-	 * We cannot send an echo if it is disabled or until the
-	 * NEGOTIATE_PROTOCOL request is done, which is indicated by
-	 * server->ops->need_neg() == true. Also, no need to ping if
-	 * we got a response recently.
+	 * We cannot send an echo if it is disabled.
+	 * Also, no need to ping if we got a response recently.
 	 */
-	if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+	if (server->tcpStatus == CifsNeedReconnect ||
+	    server->tcpStatus == CifsExiting ||
+	    server->tcpStatus == CifsNew ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
-	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+	    time_before(jiffies, server->lstrp + echo_interval - HZ))
 		goto requeue_echo;
 
 	rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS;
@@ -919,10 +936,19 @@ cifs_demultiplex_thread(void *p)
 
 		server->lstrp = jiffies;
 		if (mid_entry != NULL) {
+			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+					server->ops->handle_cancelled_mid)
+				server->ops->handle_cancelled_mid(
+							mid_entry->resp_buf,
+							server);
+
 			if (!mid_entry->multiRsp || mid_entry->multiEnd)
 				mid_entry->callback(mid_entry);
-		} else if (!server->ops->is_oplock_break ||
-			   !server->ops->is_oplock_break(buf, server)) {
+		} else if (server->ops->is_oplock_break &&
+			   server->ops->is_oplock_break(buf, server)) {
+			cifs_dbg(FYI, "Received oplock break\n");
+		} else {
 			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
 				 atomic_read(&midCount));
 			cifs_dump_mem("Received Data is: ", buf,
@@ -2111,8 +2137,8 @@ cifs_find_tcp_session(struct smb_vol *vol)
 	return NULL;
 }
 
-static void
-cifs_put_tcp_session(struct TCP_Server_Info *server)
+void
+cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 {
 	struct task_struct *task;
 
@@ -2129,6 +2155,19 @@ cifs_put_tcp_session(struct TCP_Server_Info *server)
 
 	cancel_delayed_work_sync(&server->echo);
 
+#ifdef CONFIG_CIFS_SMB2
+	if (from_reconnect)
+		/*
+		 * Avoid deadlock here: reconnect work calls
+		 * cifs_put_tcp_session() at its end. Need to be sure
+		 * that reconnect work does nothing with server pointer after
+		 * that step.
+		 */
+		cancel_delayed_work(&server->reconnect);
+	else
+		cancel_delayed_work_sync(&server->reconnect);
+#endif
+
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
@@ -2193,12 +2232,16 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
 	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
+#ifdef CONFIG_CIFS_SMB2
+	INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
+	mutex_init(&tcp_ses->reconnect_mutex);
+#endif
 	memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr,
 	       sizeof(tcp_ses->srcaddr));
 	memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
 		sizeof(tcp_ses->dstaddr));
 #ifdef CONFIG_CIFS_SMB2
-	get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE);
+	generate_random_uuid(tcp_ses->client_guid);
 #endif
 	/*
 	 * at this point we are the only ones with the pointer
@@ -2345,7 +2388,7 @@ cifs_put_smb_ses(struct cifs_ses *ses)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	sesInfoFree(ses);
-	cifs_put_tcp_session(server);
+	cifs_put_tcp_session(server, 0);
 }
 
 #ifdef CONFIG_KEYS
@@ -2519,7 +2562,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		mutex_unlock(&ses->session_mutex);
 
 		/* existing SMB ses has a server reference already */
-		cifs_put_tcp_session(server);
+		cifs_put_tcp_session(server, 0);
 		free_xid(xid);
 		return ses;
 	}
@@ -2609,7 +2652,7 @@ cifs_find_tcon(struct cifs_ses *ses, const char *unc)
 	return NULL;
 }
 
-static void
+void
 cifs_put_tcon(struct cifs_tcon *tcon)
 {
 	unsigned int xid;
@@ -3515,6 +3558,44 @@ cifs_get_volume_info(char *mount_data, const char *devname)
 	return volume_info;
 }
 
+static int
+cifs_are_all_path_components_accessible(struct TCP_Server_Info *server,
+					unsigned int xid,
+					struct cifs_tcon *tcon,
+					struct cifs_sb_info *cifs_sb,
+					char *full_path)
+{
+	int rc;
+	char *s;
+	char sep, tmp;
+
+	sep = CIFS_DIR_SEP(cifs_sb);
+	s = full_path;
+
+	rc = server->ops->is_path_accessible(xid, tcon, cifs_sb, "");
+	while (rc == 0) {
+		/* skip separators */
+		while (*s == sep)
+			s++;
+		if (!*s)
+			break;
+		/* next separator */
+		while (*s && *s != sep)
+			s++;
+
+		/*
+		 * temporarily null-terminate the path at the end of
+		 * the current component
+		 */
+		tmp = *s;
+		*s = 0;
+		rc = server->ops->is_path_accessible(xid, tcon, cifs_sb,
+						     full_path);
+		*s = tmp;
+	}
+	return rc;
+}
+
 int
 cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 {
@@ -3652,6 +3733,18 @@ remote_path_check:
 			kfree(full_path);
 			goto mount_fail_check;
 		}
+
+		if (rc != -EREMOTE) {
+			rc = cifs_are_all_path_components_accessible(server,
+							     xid, tcon, cifs_sb,
+							     full_path);
+			if (rc != 0) {
+				cifs_dbg(VFS, "cannot query dirs between root and final path, "
+					 "enabling CIFS_MOUNT_USE_PREFIX_PATH\n");
+				cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+				rc = 0;
+			}
+		}
 		kfree(full_path);
 	}
 
@@ -3715,7 +3808,7 @@ mount_fail_check:
 		else if (ses)
 			cifs_put_smb_ses(ses);
 		else
-			cifs_put_tcp_session(server);
+			cifs_put_tcp_session(server, 0);
 		bdi_destroy(&cifs_sb->bdi);
 	}
 
@@ -3921,6 +4014,7 @@ cifs_umount(struct cifs_sb_info *cifs_sb)
 
 	bdi_destroy(&cifs_sb->bdi);
 	kfree(cifs_sb->mountdata);
+	kfree(cifs_sb->prepath);
 	call_rcu(&cifs_sb->rcu, delayed_free);
 }
 
@@ -4025,7 +4119,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	ses = cifs_get_smb_ses(master_tcon->ses->server, vol_info);
 	if (IS_ERR(ses)) {
 		tcon = (struct cifs_tcon *)ses;
-		cifs_put_tcp_session(master_tcon->ses->server);
+		cifs_put_tcp_session(master_tcon->ses->server, 0);
 		goto out;
 	}
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index c3eb998a99bd..297e05c9e2b0 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -84,6 +84,7 @@ build_path_from_dentry(struct dentry *direntry)
 	struct dentry *temp;
 	int namelen;
 	int dfsplen;
+	int pplen = 0;
 	char *full_path;
 	char dirsep;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
@@ -95,8 +96,12 @@ build_path_from_dentry(struct dentry *direntry)
 		dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
 	else
 		dfsplen = 0;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+		pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0;
+
 cifs_bp_rename_retry:
-	namelen = dfsplen;
+	namelen = dfsplen + pplen;
 	seq = read_seqbegin(&rename_lock);
 	rcu_read_lock();
 	for (temp = direntry; !IS_ROOT(temp);) {
@@ -137,7 +142,7 @@ cifs_bp_rename_retry:
 		}
 	}
 	rcu_read_unlock();
-	if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) {
+	if (namelen != dfsplen + pplen || read_seqretry(&rename_lock, seq)) {
 		cifs_dbg(FYI, "did not end path lookup where expected. namelen=%ddfsplen=%d\n",
 			 namelen, dfsplen);
 		/* presumably this is only possible if racing with a rename
@@ -153,6 +158,17 @@ cifs_bp_rename_retry:
 	   those safely to '/' if any are found in the middle of the prepath */
 	/* BB test paths to Windows with '/' in the midst of prepath */
 
+	if (pplen) {
+		int i;
+
+		cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath);
+		memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1);
+		full_path[dfsplen] = '\\';
+		for (i = 0; i < pplen-1; i++)
+			if (full_path[dfsplen+1+i] == '/')
+				full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb);
+	}
+
 	if (dfsplen) {
 		strncpy(full_path, tcon->treeName, dfsplen);
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
@@ -167,15 +183,20 @@ cifs_bp_rename_retry:
 }
 
 /*
+ * Don't allow path components longer than the server max.
  * Don't allow the separator character in a path component.
  * The VFS will not allow "/", but "\" is allowed by posix.
  */
 static int
-check_name(struct dentry *direntry)
+check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
 	int i;
 
+	if (unlikely(direntry->d_name.len >
+		     le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
+		return -ENAMETOOLONG;
+
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
 		for (i = 0; i < direntry->d_name.len; i++) {
 			if (direntry->d_name.name[i] == '\\') {
@@ -229,6 +250,13 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 				goto cifs_create_get_file_info;
 			}
 
+			if (S_ISDIR(newinode->i_mode)) {
+				CIFSSMBClose(xid, tcon, fid->netfid);
+				iput(newinode);
+				rc = -EISDIR;
+				goto out;
+			}
+
 			if (!S_ISREG(newinode->i_mode)) {
 				/*
 				 * The server may allow us to open things like
@@ -399,10 +427,14 @@ cifs_create_set_dentry:
 	if (rc != 0) {
 		cifs_dbg(FYI, "Create worked, get_inode_info failed rc = %d\n",
 			 rc);
-		if (server->ops->close)
-			server->ops->close(xid, tcon, fid);
-		goto out;
+		goto out_err;
 	}
+
+	if (S_ISDIR(newinode->i_mode)) {
+		rc = -EISDIR;
+		goto out_err;
+	}
+
 	d_drop(direntry);
 	d_add(direntry, newinode);
 
@@ -410,6 +442,13 @@ out:
 	kfree(buf);
 	kfree(full_path);
 	return rc;
+
+out_err:
+	if (server->ops->close)
+		server->ops->close(xid, tcon, fid);
+	if (newinode)
+		iput(newinode);
+	goto out;
 }
 
 int
@@ -455,10 +494,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		return finish_no_open(file, res);
 	}
 
-	rc = check_name(direntry);
-	if (rc)
-		return rc;
-
 	xid = get_xid();
 
 	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
@@ -471,6 +506,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	}
 
 	tcon = tlink_tcon(tlink);
+
+	rc = check_name(direntry, tcon);
+	if (rc)
+		goto out_free_xid;
+
 	server = tcon->ses->server;
 
 	if (server->ops->new_lease_key)
@@ -731,7 +771,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	}
 	pTcon = tlink_tcon(tlink);
 
-	rc = check_name(direntry);
+	rc = check_name(direntry, pTcon);
 	if (rc)
 		goto lookup_out;
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0068e82217c3..a0c0a49b6620 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -305,6 +305,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	cfile->tlink = cifs_get_tlink(tlink);
 	INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
 	mutex_init(&cfile->fh_mutex);
+	spin_lock_init(&cfile->file_info_lock);
 
 	cifs_sb_active(inode->i_sb);
 
@@ -317,7 +318,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 		oplock = 0;
 	}
 
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
 	if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock)
 		oplock = fid->pending_open->oplock;
 	list_del(&fid->pending_open->olist);
@@ -326,12 +327,13 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	server->ops->set_fid(cfile, fid, oplock);
 
 	list_add(&cfile->tlist, &tcon->openFileList);
+
 	/* if readable file instance put first in list*/
 	if (file->f_mode & FMODE_READ)
 		list_add(&cfile->flist, &cinode->openFileList);
 	else
 		list_add_tail(&cfile->flist, &cinode->openFileList);
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tcon->open_file_lock);
 
 	if (fid->purge_cache)
 		cifs_zap_mapping(inode);
@@ -343,16 +345,16 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 struct cifsFileInfo *
 cifsFileInfo_get(struct cifsFileInfo *cifs_file)
 {
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&cifs_file->file_info_lock);
 	cifsFileInfo_get_locked(cifs_file);
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&cifs_file->file_info_lock);
 	return cifs_file;
 }
 
 /*
  * Release a reference on the file private data. This may involve closing
  * the filehandle out on the server. Must be called without holding
- * cifs_file_list_lock.
+ * tcon->open_file_lock and cifs_file->file_info_lock.
  */
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 {
@@ -367,11 +369,15 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	struct cifs_pending_open open;
 	bool oplock_break_cancelled;
 
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
+
+	spin_lock(&cifs_file->file_info_lock);
 	if (--cifs_file->count > 0) {
-		spin_unlock(&cifs_file_list_lock);
+		spin_unlock(&cifs_file->file_info_lock);
+		spin_unlock(&tcon->open_file_lock);
 		return;
 	}
+	spin_unlock(&cifs_file->file_info_lock);
 
 	if (server->ops->get_lease_key)
 		server->ops->get_lease_key(inode, &fid);
@@ -395,7 +401,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 			set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
 		cifs_set_oplock_level(cifsi, 0);
 	}
-	spin_unlock(&cifs_file_list_lock);
+
+	spin_unlock(&tcon->open_file_lock);
 
 	oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
 
@@ -772,10 +779,10 @@ int cifs_closedir(struct inode *inode, struct file *file)
 	server = tcon->ses->server;
 
 	cifs_dbg(FYI, "Freeing private data in close dir\n");
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&cfile->file_info_lock);
 	if (server->ops->dir_needs_close(cfile)) {
 		cfile->invalidHandle = true;
-		spin_unlock(&cifs_file_list_lock);
+		spin_unlock(&cfile->file_info_lock);
 		if (server->ops->close_dir)
 			rc = server->ops->close_dir(xid, tcon, &cfile->fid);
 		else
@@ -784,7 +791,7 @@ int cifs_closedir(struct inode *inode, struct file *file)
 		/* not much we can do if it fails anyway, ignore rc */
 		rc = 0;
 	} else
-		spin_unlock(&cifs_file_list_lock);
+		spin_unlock(&cfile->file_info_lock);
 
 	buf = cfile->srch_inf.ntwrk_buf_start;
 	if (buf) {
@@ -1720,12 +1727,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 {
 	struct cifsFileInfo *open_file = NULL;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
 	/* we could simply get the first_list_entry since write-only entries
 	   are always at the end of the list but since the first entry might
 	   have a close pending, we go through the whole list */
@@ -1736,8 +1744,8 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 			if (!open_file->invalidHandle) {
 				/* found a good file */
 				/* lock it so it will not be closed on us */
-				cifsFileInfo_get_locked(open_file);
-				spin_unlock(&cifs_file_list_lock);
+				cifsFileInfo_get(open_file);
+				spin_unlock(&tcon->open_file_lock);
 				return open_file;
 			} /* else might as well continue, and look for
 			     another, or simply have the caller reopen it
@@ -1745,7 +1753,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 		} else /* write only file */
 			break; /* write only files are last so must be done */
 	}
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tcon->open_file_lock);
 	return NULL;
 }
 
@@ -1754,6 +1762,7 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 {
 	struct cifsFileInfo *open_file, *inv_file = NULL;
 	struct cifs_sb_info *cifs_sb;
+	struct cifs_tcon *tcon;
 	bool any_available = false;
 	int rc;
 	unsigned int refind = 0;
@@ -1769,15 +1778,16 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 	}
 
 	cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+	tcon = cifs_sb_master_tcon(cifs_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
 refind_writable:
 	if (refind > MAX_REOPEN_ATT) {
-		spin_unlock(&cifs_file_list_lock);
+		spin_unlock(&tcon->open_file_lock);
 		return NULL;
 	}
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
@@ -1788,8 +1798,8 @@ refind_writable:
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
-				cifsFileInfo_get_locked(open_file);
-				spin_unlock(&cifs_file_list_lock);
+				cifsFileInfo_get(open_file);
+				spin_unlock(&tcon->open_file_lock);
 				return open_file;
 			} else {
 				if (!inv_file)
@@ -1805,24 +1815,24 @@ refind_writable:
 
 	if (inv_file) {
 		any_available = false;
-		cifsFileInfo_get_locked(inv_file);
+		cifsFileInfo_get(inv_file);
 	}
 
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tcon->open_file_lock);
 
 	if (inv_file) {
 		rc = cifs_reopen_file(inv_file, false);
 		if (!rc)
 			return inv_file;
 		else {
-			spin_lock(&cifs_file_list_lock);
+			spin_lock(&tcon->open_file_lock);
 			list_move_tail(&inv_file->flist,
 					&cifs_inode->openFileList);
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&tcon->open_file_lock);
 			cifsFileInfo_put(inv_file);
-			spin_lock(&cifs_file_list_lock);
 			++refind;
 			inv_file = NULL;
+			spin_lock(&tcon->open_file_lock);
 			goto refind_writable;
 		}
 	}
@@ -2535,7 +2545,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->credits = credits;
 
 		if (!wdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(wdata->cfile, false))
+		    !(rc = cifs_reopen_file(wdata->cfile, false)))
 			rc = server->ops->async_writev(wdata,
 					cifs_uncached_writedata_release);
 		if (rc) {
@@ -2948,7 +2958,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->credits = credits;
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 error:
 		if (rc) {
@@ -3534,7 +3544,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		}
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
@@ -3632,15 +3642,17 @@ static int cifs_readpage(struct file *file, struct page *page)
 static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
 {
 	struct cifsFileInfo *open_file;
+	struct cifs_tcon *tcon =
+		cifs_sb_master_tcon(CIFS_SB(cifs_inode->vfs_inode.i_sb));
 
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tcon->open_file_lock);
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&tcon->open_file_lock);
 			return 1;
 		}
 	}
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tcon->open_file_lock);
 	return 0;
 }
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a329f5ba35aa..9cdeb0293267 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -982,10 +982,26 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	struct inode *inode = NULL;
 	long rc;
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	char *path = NULL;
+	int len;
+
+	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	    && cifs_sb->prepath) {
+		len = strlen(cifs_sb->prepath);
+		path = kzalloc(len + 2 /* leading sep + null */, GFP_KERNEL);
+		if (path == NULL)
+			return ERR_PTR(-ENOMEM);
+		path[0] = '/';
+		memcpy(path+1, cifs_sb->prepath, len);
+	} else {
+		path = kstrdup("", GFP_KERNEL);
+		if (path == NULL)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	xid = get_xid();
 	if (tcon->unix_ext) {
-		rc = cifs_get_inode_info_unix(&inode, "", sb, xid);
+		rc = cifs_get_inode_info_unix(&inode, path, sb, xid);
 		/* some servers mistakenly claim POSIX support */
 		if (rc != -EOPNOTSUPP)
 			goto iget_no_retry;
@@ -993,7 +1009,8 @@ struct inode *cifs_root_iget(struct super_block *sb)
 		tcon->unix_ext = false;
 	}
 
-	rc = cifs_get_inode_info(&inode, "", NULL, sb, xid, NULL);
+	convert_delimiter(path, CIFS_DIR_SEP(cifs_sb));
+	rc = cifs_get_inode_info(&inode, path, NULL, sb, xid, NULL);
 
 iget_no_retry:
 	if (!inode) {
@@ -1022,6 +1039,7 @@ iget_no_retry:
 	}
 
 out:
+	kfree(path);
 	/* can not call macro free_xid here since in a void func
 	 * TODO: This is no longer true
 	 */
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 35cf990f87d3..a8f5b31636dc 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -272,6 +272,8 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				rc = -EOPNOTSUPP;
 			break;
 		case CIFS_IOC_GET_MNT_INFO:
+			if (pSMBFile == NULL)
+				break;
 			tcon = tlink_tcon(pSMBFile->tlink);
 			rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg);
 			break;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 8442b8b8e0be..2396ab099849 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -120,6 +120,7 @@ tconInfoAlloc(void)
 		++ret_buf->tc_count;
 		INIT_LIST_HEAD(&ret_buf->openFileList);
 		INIT_LIST_HEAD(&ret_buf->tcon_list);
+		spin_lock_init(&ret_buf->open_file_lock);
 #ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
 #endif
@@ -465,7 +466,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 				continue;
 
 			cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
-			spin_lock(&cifs_file_list_lock);
+			spin_lock(&tcon->open_file_lock);
 			list_for_each(tmp2, &tcon->openFileList) {
 				netfile = list_entry(tmp2, struct cifsFileInfo,
 						     tlist);
@@ -495,11 +496,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 					   &netfile->oplock_break);
 				netfile->oplock_break_cancelled = false;
 
-				spin_unlock(&cifs_file_list_lock);
+				spin_unlock(&tcon->open_file_lock);
 				spin_unlock(&cifs_tcp_ses_lock);
 				return true;
 			}
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&tcon->open_file_lock);
 			spin_unlock(&cifs_tcp_ses_lock);
 			cifs_dbg(FYI, "No matching file for oplock break\n");
 			return true;
@@ -613,9 +614,9 @@ backup_cred(struct cifs_sb_info *cifs_sb)
 void
 cifs_del_pending_open(struct cifs_pending_open *open)
 {
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tlink_tcon(open->tlink)->open_file_lock);
 	list_del(&open->olist);
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
 }
 
 void
@@ -635,7 +636,7 @@ void
 cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink,
 		      struct cifs_pending_open *open)
 {
-	spin_lock(&cifs_file_list_lock);
+	spin_lock(&tlink_tcon(tlink)->open_file_lock);
 	cifs_add_pending_open_locked(fid, tlink, open);
-	spin_unlock(&cifs_file_list_lock);
+	spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
 }
diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 848249fa120f..3079b38f0afb 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -133,6 +133,6 @@ typedef struct _AUTHENTICATE_MESSAGE {
 
 int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
 void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
-int build_ntlmssp_auth_blob(unsigned char *pbuffer, u16 *buflen,
+int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
 			struct cifs_ses *ses,
 			const struct nls_table *nls_cp);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b30a4a6d98a0..97d1a15873c5 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -282,6 +282,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file)
 			rc = -ENOMEM;
 			goto error_exit;
 		}
+		spin_lock_init(&cifsFile->file_info_lock);
 		file->private_data = cifsFile;
 		cifsFile->tlink = cifs_get_tlink(tlink);
 		tcon = tlink_tcon(tlink);
@@ -594,14 +595,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 	     is_dir_changed(file)) || (index_to_find < first_entry_in_buffer)) {
 		/* close and restart search */
 		cifs_dbg(FYI, "search backing up - close and restart search\n");
-		spin_lock(&cifs_file_list_lock);
+		spin_lock(&cfile->file_info_lock);
 		if (server->ops->dir_needs_close(cfile)) {
 			cfile->invalidHandle = true;
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&cfile->file_info_lock);
 			if (server->ops->close_dir)
 				server->ops->close_dir(xid, tcon, &cfile->fid);
 		} else
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&cfile->file_info_lock);
 		if (cfile->srch_inf.ntwrk_buf_start) {
 			cifs_dbg(FYI, "freeing SMB ff cache buf on search rewind\n");
 			if (cfile->srch_inf.smallBuf)
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 59727e32ed0f..e88ffe1da045 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -364,19 +364,43 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	sec_blob->DomainName.MaximumLength = 0;
 }
 
-/* We do not malloc the blob, it is passed in pbuffer, because its
-   maximum possible size is fixed and small, making this approach cleaner.
-   This function returns the length of the data in the blob */
-int build_ntlmssp_auth_blob(unsigned char *pbuffer,
+static int size_of_ntlmssp_blob(struct cifs_ses *ses)
+{
+	int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
+		- CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+	if (ses->domainName)
+		sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+	else
+		sz += 2;
+
+	if (ses->user_name)
+		sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+	else
+		sz += 2;
+
+	return sz;
+}
+
+int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 					u16 *buflen,
 				   struct cifs_ses *ses,
 				   const struct nls_table *nls_cp)
 {
 	int rc;
-	AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer;
+	AUTHENTICATE_MESSAGE *sec_blob;
 	__u32 flags;
 	unsigned char *tmp;
 
+	rc = setup_ntlmv2_rsp(ses, nls_cp);
+	if (rc) {
+		cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
+		*buflen = 0;
+		goto setup_ntlmv2_ret;
+	}
+	*pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+	sec_blob = (AUTHENTICATE_MESSAGE *)*pbuffer;
+
 	memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
 	sec_blob->MessageType = NtLmAuthenticate;
 
@@ -391,7 +415,7 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 	}
 
-	tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
+	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
 	sec_blob->LmChallengeResponse.BufferOffset =
@@ -399,23 +423,27 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 	sec_blob->LmChallengeResponse.Length = 0;
 	sec_blob->LmChallengeResponse.MaximumLength = 0;
 
-	sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer);
-	rc = setup_ntlmv2_rsp(ses, nls_cp);
-	if (rc) {
-		cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc);
-		goto setup_ntlmv2_ret;
+	sec_blob->NtChallengeResponse.BufferOffset =
+				cpu_to_le32(tmp - *pbuffer);
+	if (ses->user_name != NULL) {
+		memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+				ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+		tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
+
+		sec_blob->NtChallengeResponse.Length =
+				cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+		sec_blob->NtChallengeResponse.MaximumLength =
+				cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+	} else {
+		/*
+		 * don't send an NT Response for anonymous access
+		 */
+		sec_blob->NtChallengeResponse.Length = 0;
+		sec_blob->NtChallengeResponse.MaximumLength = 0;
 	}
-	memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
-			ses->auth_key.len - CIFS_SESS_KEY_SIZE);
-	tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
-
-	sec_blob->NtChallengeResponse.Length =
-			cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
-	sec_blob->NtChallengeResponse.MaximumLength =
-			cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
 
 	if (ses->domainName == NULL) {
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = 0;
 		sec_blob->DomainName.MaximumLength = 0;
 		tmp += 2;
@@ -424,14 +452,14 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
 				      CIFS_MAX_USERNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->DomainName.Length = cpu_to_le16(len);
 		sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
 	if (ses->user_name == NULL) {
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = 0;
 		sec_blob->UserName.MaximumLength = 0;
 		tmp += 2;
@@ -440,13 +468,13 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
 				      CIFS_MAX_USERNAME_LEN, nls_cp);
 		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->UserName.Length = cpu_to_le16(len);
 		sec_blob->UserName.MaximumLength = cpu_to_le16(len);
 		tmp += len;
 	}
 
-	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - pbuffer);
+	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 	sec_blob->WorkstationName.Length = 0;
 	sec_blob->WorkstationName.MaximumLength = 0;
 	tmp += 2;
@@ -455,19 +483,19 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer,
 		(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
 			&& !calc_seckey(ses)) {
 		memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
 		sec_blob->SessionKey.MaximumLength =
 				cpu_to_le16(CIFS_CPHTXT_SIZE);
 		tmp += CIFS_CPHTXT_SIZE;
 	} else {
-		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
+		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = 0;
 		sec_blob->SessionKey.MaximumLength = 0;
 	}
 
+	*buflen = tmp - *pbuffer;
 setup_ntlmv2_ret:
-	*buflen = tmp - pbuffer;
 	return rc;
 }
 
@@ -670,20 +698,24 @@ sess_auth_lanman(struct sess_data *sess_data)
 
 	pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE;
 
-	/* no capabilities flags in old lanman negotiation */
-	pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
-
-	/* Calculate hash with password and copy into bcc_ptr.
-	 * Encryption Key (stored as in cryptkey) gets used if the
-	 * security mode bit in Negottiate Protocol response states
-	 * to use challenge/response method (i.e. Password bit is 1).
-	 */
-	rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
-			      ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
-			      true : false, lnm_session_key);
-
-	memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
-	bcc_ptr += CIFS_AUTH_RESP_SIZE;
+	if (ses->user_name != NULL) {
+		/* no capabilities flags in old lanman negotiation */
+		pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+
+		/* Calculate hash with password and copy into bcc_ptr.
+		 * Encryption Key (stored as in cryptkey) gets used if the
+		 * security mode bit in Negottiate Protocol response states
+		 * to use challenge/response method (i.e. Password bit is 1).
+		 */
+		rc = calc_lanman_hash(ses->password, ses->server->cryptkey,
+				      ses->server->sec_mode & SECMODE_PW_ENCRYPT ?
+				      true : false, lnm_session_key);
+
+		memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
+		bcc_ptr += CIFS_AUTH_RESP_SIZE;
+	} else {
+		pSMB->old_req.PasswordLength = 0;
+	}
 
 	/*
 	 * can not sign if LANMAN negotiated so no need
@@ -769,27 +801,32 @@ sess_auth_ntlm(struct sess_data *sess_data)
 	capabilities = cifs_ssetup_hdr(ses, pSMB);
 
 	pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities);
-	pSMB->req_no_secext.CaseInsensitivePasswordLength =
-			cpu_to_le16(CIFS_AUTH_RESP_SIZE);
-	pSMB->req_no_secext.CaseSensitivePasswordLength =
-			cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+	if (ses->user_name != NULL) {
+		pSMB->req_no_secext.CaseInsensitivePasswordLength =
+				cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+		pSMB->req_no_secext.CaseSensitivePasswordLength =
+				cpu_to_le16(CIFS_AUTH_RESP_SIZE);
+
+		/* calculate ntlm response and session key */
+		rc = setup_ntlm_response(ses, sess_data->nls_cp);
+		if (rc) {
+			cifs_dbg(VFS, "Error %d during NTLM authentication\n",
+					 rc);
+			goto out;
+		}
 
-	/* calculate ntlm response and session key */
-	rc = setup_ntlm_response(ses, sess_data->nls_cp);
-	if (rc) {
-		cifs_dbg(VFS, "Error %d during NTLM authentication\n",
-				 rc);
-		goto out;
+		/* copy ntlm response */
+		memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+				CIFS_AUTH_RESP_SIZE);
+		bcc_ptr += CIFS_AUTH_RESP_SIZE;
+		memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+				CIFS_AUTH_RESP_SIZE);
+		bcc_ptr += CIFS_AUTH_RESP_SIZE;
+	} else {
+		pSMB->req_no_secext.CaseInsensitivePasswordLength = 0;
+		pSMB->req_no_secext.CaseSensitivePasswordLength = 0;
 	}
 
-	/* copy ntlm response */
-	memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
-			CIFS_AUTH_RESP_SIZE);
-	bcc_ptr += CIFS_AUTH_RESP_SIZE;
-	memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
-			CIFS_AUTH_RESP_SIZE);
-	bcc_ptr += CIFS_AUTH_RESP_SIZE;
-
 	if (ses->capabilities & CAP_UNICODE) {
 		/* unicode strings must be word aligned */
 		if (sess_data->iov[0].iov_len % 2) {
@@ -878,22 +915,26 @@ sess_auth_ntlmv2(struct sess_data *sess_data)
 	/* LM2 password would be here if we supported it */
 	pSMB->req_no_secext.CaseInsensitivePasswordLength = 0;
 
-	/* calculate nlmv2 response and session key */
-	rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp);
-	if (rc) {
-		cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc);
-		goto out;
-	}
+	if (ses->user_name != NULL) {
+		/* calculate nlmv2 response and session key */
+		rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp);
+		if (rc) {
+			cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc);
+			goto out;
+		}
 
-	memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
-			ses->auth_key.len - CIFS_SESS_KEY_SIZE);
-	bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
+		memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE,
+				ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+		bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE;
 
-	/* set case sensitive password length after tilen may get
-	 * assigned, tilen is 0 otherwise.
-	 */
-	pSMB->req_no_secext.CaseSensitivePasswordLength =
-		cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+		/* set case sensitive password length after tilen may get
+		 * assigned, tilen is 0 otherwise.
+		 */
+		pSMB->req_no_secext.CaseSensitivePasswordLength =
+			cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE);
+	} else {
+		pSMB->req_no_secext.CaseSensitivePasswordLength = 0;
+	}
 
 	if (ses->capabilities & CAP_UNICODE) {
 		if (sess_data->iov[0].iov_len % 2) {
@@ -1245,7 +1286,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 	__u16 bytes_remaining;
 	char *bcc_ptr;
-	char *ntlmsspblob = NULL;
+	unsigned char *ntlmsspblob = NULL;
 	u16 blob_len;
 
 	cifs_dbg(FYI, "rawntlmssp session setup authenticate phase\n");
@@ -1258,19 +1299,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data)
 	/* Build security blob before we assemble the request */
 	pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
 	smb_buf = (struct smb_hdr *)pSMB;
-	/*
-	 * 5 is an empirical value, large enough to hold
-	 * authenticate message plus max 10 of av paris,
-	 * domain, user, workstation names, flags, etc.
-	 */
-	ntlmsspblob = kzalloc(5*sizeof(struct _AUTHENTICATE_MESSAGE),
-				GFP_KERNEL);
-	if (!ntlmsspblob) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	rc = build_ntlmssp_auth_blob(ntlmsspblob,
+	rc = build_ntlmssp_auth_blob(&ntlmsspblob,
 					&blob_len, ses, sess_data->nls_cp);
 	if (rc)
 		goto out_free_ntlmsspblob;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index fc537c29044e..efd72e1fae74 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 		     struct cifs_fid *fid, __u16 search_flags,
 		     struct cifs_search_info *srch_inf)
 {
-	return CIFSFindFirst(xid, tcon, path, cifs_sb,
-			     &fid->netfid, search_flags, srch_inf, true);
+	int rc;
+
+	rc = CIFSFindFirst(xid, tcon, path, cifs_sb,
+			   &fid->netfid, search_flags, srch_inf, true);
+	if (rc)
+		cifs_dbg(FYI, "find first failed=%d\n", rc);
+	return rc;
 }
 
 static int
@@ -1015,6 +1020,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
 }
 
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+	if (server->tcpStatus == CifsGood)
+		return true;
+
+	return false;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1049,6 +1063,7 @@ struct smb_version_operations smb1_operations = {
 	.get_dfs_refer = CIFSGetDFSRefer,
 	.qfs_tcon = cifs_qfs_tcon,
 	.is_path_accessible = cifs_is_path_accessible,
+	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index f9e766f464be..b2aff0c6f22c 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -260,7 +260,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 	 * and check it for zero before using.
 	 */
 	max_buf = tlink_tcon(cfile->tlink)->ses->server->maxBuf;
-	if (!max_buf) {
+	if (max_buf < sizeof(struct smb2_lock_element)) {
 		free_xid(xid);
 		return -EINVAL;
 	}
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index bc0bb9c34f72..238759c146ba 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -44,6 +44,7 @@
 #define SMB2_OP_DELETE 7
 #define SMB2_OP_HARDLINK 8
 #define SMB2_OP_SET_EOF 9
+#define SMB2_OP_RMDIR 10
 
 /* Used when constructing chained read requests. */
 #define CHAINED_REQUEST 1
@@ -60,4 +61,14 @@
 /* Maximum buffer size value we can send with 1 credit */
 #define SMB2_MAX_BUFFER_SIZE 65536
 
+/*
+ * Maximum number of credits to keep available.
+ * This value is chosen somewhat arbitrarily. The Windows client
+ * defaults to 128 credits, the Windows server allows clients up to
+ * 512 credits, and the NetApp server does not limit clients at all.
+ * Choose a high enough value such that the client shouldn't limit
+ * performance.
+ */
+#define SMB2_MAX_CREDITS_AVAILABLE 32000
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 899bbc86f73e..1238cd3552f9 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -80,6 +80,10 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		 * SMB2_open() call.
 		 */
 		break;
+	case SMB2_OP_RMDIR:
+		tmprc = SMB2_rmdir(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid);
+		break;
 	case SMB2_OP_RENAME:
 		tmprc = SMB2_rename(xid, tcon, fid.persistent_fid,
 				    fid.volatile_fid, (__le16 *)data);
@@ -191,8 +195,8 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	   struct cifs_sb_info *cifs_sb)
 {
 	return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN,
-				  CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE,
-				  NULL, SMB2_OP_DELETE);
+				  CREATE_NOT_FILE,
+				  NULL, SMB2_OP_RMDIR);
 }
 
 int
@@ -262,9 +266,15 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	struct tcon_link *tlink;
 	int rc;
 
+	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
+	    (buf->LastWriteTime == 0) && (buf->ChangeTime) &&
+	    (buf->Attributes == 0))
+		return 0; /* would be a no op, no sense sending this */
+
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
+
 	rc = smb2_open_op_close(xid, tlink_tcon(tlink), cifs_sb, full_path,
 				FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, buf,
 				SMB2_OP_SET_INFO);
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 1c5907019045..76ccf20fbfb7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -525,19 +525,19 @@ smb2_is_valid_lease_break(char *buffer)
 		list_for_each(tmp1, &server->smb_ses_list) {
 			ses = list_entry(tmp1, struct cifs_ses, smb_ses_list);
 
-			spin_lock(&cifs_file_list_lock);
 			list_for_each(tmp2, &ses->tcon_list) {
 				tcon = list_entry(tmp2, struct cifs_tcon,
 						  tcon_list);
+				spin_lock(&tcon->open_file_lock);
 				cifs_stats_inc(
 				    &tcon->stats.cifs_stats.num_oplock_brks);
 				if (smb2_tcon_has_lease(tcon, rsp, lw)) {
-					spin_unlock(&cifs_file_list_lock);
+					spin_unlock(&tcon->open_file_lock);
 					spin_unlock(&cifs_tcp_ses_lock);
 					return true;
 				}
+				spin_unlock(&tcon->open_file_lock);
 			}
-			spin_unlock(&cifs_file_list_lock);
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
@@ -579,7 +579,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 			tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
 
 			cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
-			spin_lock(&cifs_file_list_lock);
+			spin_lock(&tcon->open_file_lock);
 			list_for_each(tmp2, &tcon->openFileList) {
 				cfile = list_entry(tmp2, struct cifsFileInfo,
 						     tlist);
@@ -591,7 +591,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 
 				cifs_dbg(FYI, "file id match, oplock break\n");
 				cinode = CIFS_I(d_inode(cfile->dentry));
-
+				spin_lock(&cfile->file_info_lock);
 				if (!CIFS_CACHE_WRITE(cinode) &&
 				    rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE)
 					cfile->oplock_break_cancelled = true;
@@ -613,14 +613,14 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 					clear_bit(
 					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 					   &cinode->flags);
-
+				spin_unlock(&cfile->file_info_lock);
 				queue_work(cifsiod_wq, &cfile->oplock_break);
 
-				spin_unlock(&cifs_file_list_lock);
+				spin_unlock(&tcon->open_file_lock);
 				spin_unlock(&cifs_tcp_ses_lock);
 				return true;
 			}
-			spin_unlock(&cifs_file_list_lock);
+			spin_unlock(&tcon->open_file_lock);
 			spin_unlock(&cifs_tcp_ses_lock);
 			cifs_dbg(FYI, "No matching file for oplock break\n");
 			return true;
@@ -630,3 +630,47 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
 	return false;
 }
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+	struct close_cancelled_open *cancelled = container_of(work,
+					struct close_cancelled_open, work);
+
+	cifs_dbg(VFS, "Close unmatched open\n");
+
+	SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+		   cancelled->fid.volatile_fid);
+	cifs_put_tcon(cancelled->tcon);
+	kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+	struct smb2_hdr *hdr = (struct smb2_hdr *)buffer;
+	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+	struct cifs_tcon *tcon;
+	struct close_cancelled_open *cancelled;
+
+	if (hdr->Command != SMB2_CREATE || hdr->Status != STATUS_SUCCESS)
+		return 0;
+
+	cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+	if (!cancelled)
+		return -ENOMEM;
+
+	tcon = smb2_find_smb_tcon(server, hdr->SessionId, hdr->TreeId);
+	if (!tcon) {
+		kfree(cancelled);
+		return -ENOENT;
+	}
+
+	cancelled->fid.persistent_fid = rsp->PersistentFileId;
+	cancelled->fid.volatile_fid = rsp->VolatileFileId;
+	cancelled->tcon = tcon;
+	INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+	queue_work(cifsiod_wq, &cancelled->work);
+
+	return 0;
+}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 53ccdde6ff18..1d125d3d0d89 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -282,7 +282,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 		cifs_dbg(FYI, "Link Speed %lld\n",
 			le64_to_cpu(out_buf->LinkSpeed));
 	}
-
+	kfree(out_buf);
 	return rc;
 }
 #endif /* STATS2 */
@@ -536,6 +536,7 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
 	server->ops->set_oplock_level(cinode, oplock, fid->epoch,
 				      &fid->purge_cache);
 	cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
+	memcpy(cfile->fid.create_guid, fid->create_guid, 16);
 }
 
 static void
@@ -694,6 +695,7 @@ smb2_clone_range(const unsigned int xid,
 
 cchunk_out:
 	kfree(pcchunk);
+	kfree(retbuf);
 	return rc;
 }
 
@@ -818,7 +820,6 @@ smb2_duplicate_extents(const unsigned int xid,
 {
 	int rc;
 	unsigned int ret_data_len;
-	char *retbuf = NULL;
 	struct duplicate_extents_to_file dup_ext_buf;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
 
@@ -844,7 +845,7 @@ smb2_duplicate_extents(const unsigned int xid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
 			true /* is_fsctl */, (char *)&dup_ext_buf,
 			sizeof(struct duplicate_extents_to_file),
-			(char **)&retbuf,
+			NULL,
 			&ret_data_len);
 
 	if (ret_data_len > 0)
@@ -867,7 +868,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifsFileInfo *cfile)
 {
 	struct fsctl_set_integrity_information_req integr_info;
-	char *retbuf = NULL;
 	unsigned int ret_data_len;
 
 	integr_info.ChecksumAlgorithm = cpu_to_le16(CHECKSUM_TYPE_UNCHANGED);
@@ -879,7 +879,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 			FSCTL_SET_INTEGRITY_INFORMATION,
 			true /* is_fsctl */, (char *)&integr_info,
 			sizeof(struct fsctl_set_integrity_information_req),
-			(char **)&retbuf,
+			NULL,
 			&ret_data_len);
 
 }
@@ -909,7 +909,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
 	kfree(utf16_path);
 	if (rc) {
-		cifs_dbg(VFS, "open dir failed\n");
+		cifs_dbg(FYI, "open dir failed rc=%d\n", rc);
 		return rc;
 	}
 
@@ -919,7 +919,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_query_directory(xid, tcon, fid->persistent_fid,
 				  fid->volatile_fid, 0, srch_inf);
 	if (rc) {
-		cifs_dbg(VFS, "query directory failed\n");
+		cifs_dbg(FYI, "query directory failed rc=%d\n", rc);
 		SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
 	}
 	return rc;
@@ -1036,9 +1036,12 @@ smb2_set_lease_key(struct inode *inode, struct cifs_fid *fid)
 static void
 smb2_new_lease_key(struct cifs_fid *fid)
 {
-	get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE);
+	generate_random_uuid(fid->lease_key);
 }
 
+#define SMB2_SYMLINK_STRUCT_SIZE \
+	(sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp))
+
 static int
 smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 		   const char *full_path, char **target_path,
@@ -1051,7 +1054,10 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_fid fid;
 	struct smb2_err_rsp *err_buf = NULL;
 	struct smb2_symlink_err_rsp *symlink;
-	unsigned int sub_len, sub_offset;
+	unsigned int sub_len;
+	unsigned int sub_offset;
+	unsigned int print_len;
+	unsigned int print_offset;
 
 	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
 
@@ -1072,11 +1078,33 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 		kfree(utf16_path);
 		return -ENOENT;
 	}
+
+	if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) ||
+	    get_rfc1002_length(err_buf) + 4 < SMB2_SYMLINK_STRUCT_SIZE) {
+		kfree(utf16_path);
+		return -ENOENT;
+	}
+
 	/* open must fail on symlink - reset rc */
 	rc = 0;
 	symlink = (struct smb2_symlink_err_rsp *)err_buf->ErrorData;
 	sub_len = le16_to_cpu(symlink->SubstituteNameLength);
 	sub_offset = le16_to_cpu(symlink->SubstituteNameOffset);
+	print_len = le16_to_cpu(symlink->PrintNameLength);
+	print_offset = le16_to_cpu(symlink->PrintNameOffset);
+
+	if (get_rfc1002_length(err_buf) + 4 <
+			SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) {
+		kfree(utf16_path);
+		return -ENOENT;
+	}
+
+	if (get_rfc1002_length(err_buf) + 4 <
+			SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) {
+		kfree(utf16_path);
+		return -ENOENT;
+	}
+
 	*target_path = cifs_strndup_from_utf16(
 				(char *)symlink->PathBuffer + sub_offset,
 				sub_len, true, cifs_sb->local_nls);
@@ -1483,6 +1511,7 @@ struct smb_version_operations smb20_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1561,6 +1590,7 @@ struct smb_version_operations smb21_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1642,6 +1672,7 @@ struct smb_version_operations smb30_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1729,6 +1760,7 @@ struct smb_version_operations smb311_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 373b5cd1c913..6c484ddf26a9 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -103,7 +103,21 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	hdr->ProtocolId[3] = 'B';
 	hdr->StructureSize = cpu_to_le16(64);
 	hdr->Command = smb2_cmd;
-	hdr->CreditRequest = cpu_to_le16(2); /* BB make this dynamic */
+	if (tcon && tcon->ses && tcon->ses->server) {
+		struct TCP_Server_Info *server = tcon->ses->server;
+
+		spin_lock(&server->req_lock);
+		/* Request up to 2 credits but don't go over the limit. */
+		if (server->credits >= SMB2_MAX_CREDITS_AVAILABLE)
+			hdr->CreditRequest = cpu_to_le16(0);
+		else
+			hdr->CreditRequest = cpu_to_le16(
+				min_t(int, SMB2_MAX_CREDITS_AVAILABLE -
+						server->credits, 2));
+		spin_unlock(&server->req_lock);
+	} else {
+		hdr->CreditRequest = cpu_to_le16(2);
+	}
 	hdr->ProcessId = cpu_to_le32((__u16)current->tgid);
 
 	if (!tcon)
@@ -264,7 +278,7 @@ out:
 	case SMB2_CHANGE_NOTIFY:
 	case SMB2_QUERY_INFO:
 	case SMB2_SET_INFO:
-		return -EAGAIN;
+		rc = -EAGAIN;
 	}
 	unload_nls(nls_codepage);
 	return rc;
@@ -550,8 +564,12 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	}
 
 	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
-		cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
-		return -EIO;
+		cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
+			 rsplen);
+
+		/* relax check since Mac returns max bufsize allowed on ioctl */
+		if (rsplen > CIFSMaxBufSize)
+			return -EIO;
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
@@ -591,8 +609,9 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	u16 blob_length = 0;
 	struct key *spnego_key = NULL;
 	char *security_blob = NULL;
-	char *ntlmssp_blob = NULL;
+	unsigned char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
+	u64 previous_session = ses->Suid;
 
 	cifs_dbg(FYI, "Session Setup\n");
 
@@ -630,6 +649,10 @@ ssetup_ntlmssp_authenticate:
 		return rc;
 
 	req->hdr.SessionId = 0; /* First session, not a reauthenticate */
+
+	/* if reconnect, we need to send previous sess id, otherwise it is 0 */
+	req->PreviousSessionId = previous_session;
+
 	req->Flags = 0; /* MBZ */
 	/* to enable echos and oplocks */
 	req->hdr.CreditRequest = cpu_to_le16(3);
@@ -716,13 +739,7 @@ ssetup_ntlmssp_authenticate:
 		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
-		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
-				       GFP_KERNEL);
-		if (ntlmssp_blob == NULL) {
-			rc = -ENOMEM;
-			goto ssetup_exit;
-		}
-		rc = build_ntlmssp_auth_blob(ntlmssp_blob, &blob_length, ses,
+		rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
 					     nls_cp);
 		if (rc) {
 			cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
@@ -919,9 +936,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	else
 		return -EIO;
 
-	if (tcon && tcon->bad_network_name)
-		return -ENOENT;
-
 	if ((tcon && tcon->seal) &&
 	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
 		cifs_dbg(VFS, "encryption requested but no server support");
@@ -939,6 +953,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return -EINVAL;
 	}
 
+	/* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+	if (tcon)
+		tcon->tid = 0;
+
 	rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
 	if (rc) {
 		kfree(unc_path);
@@ -1019,8 +1037,6 @@ tcon_exit:
 tcon_error_exit:
 	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		if (tcon)
-			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -1173,7 +1189,7 @@ create_durable_v2_buf(struct cifs_fid *pfid)
 
 	buf->dcontext.Timeout = 0; /* Should this be configurable by workload */
 	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
-	get_random_bytes(buf->dcontext.CreateGuid, 16);
+	generate_random_uuid(buf->dcontext.CreateGuid);
 	memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
 
 	/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
@@ -1506,8 +1522,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	 * than one credit. Windows typically sets this smaller, but for some
 	 * ioctls it may be useful to allow server to send more. No point
 	 * limiting what the server can send as long as fits in one credit
+	 * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
+	 * (by default, note that it can be overridden to make max larger)
+	 * in responses (except for read responses which can be bigger.
+	 * We may want to bump this limit up
 	 */
-	req->MaxOutputResponse = cpu_to_le32(0xFF00); /* < 64K uses 1 credit */
+	req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
 
 	if (is_fsctl)
 		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
@@ -1809,6 +1829,54 @@ smb2_echo_callback(struct mid_q_entry *mid)
 	add_credits(server, credits_received, CIFS_ECHO_OP);
 }
 
+void smb2_reconnect_server(struct work_struct *work)
+{
+	struct TCP_Server_Info *server = container_of(work,
+					struct TCP_Server_Info, reconnect.work);
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon, *tcon2;
+	struct list_head tmp_list;
+	int tcon_exist = false;
+
+	/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
+	mutex_lock(&server->reconnect_mutex);
+
+	INIT_LIST_HEAD(&tmp_list);
+	cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+		list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+			if (tcon->need_reconnect) {
+				tcon->tc_count++;
+				list_add_tail(&tcon->rlist, &tmp_list);
+				tcon_exist = true;
+			}
+		}
+	}
+	/*
+	 * Get the reference to server struct to be sure that the last call of
+	 * cifs_put_tcon() in the loop below won't release the server pointer.
+	 */
+	if (tcon_exist)
+		server->srv_count++;
+
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
+		smb2_reconnect(SMB2_ECHO, tcon);
+		list_del_init(&tcon->rlist);
+		cifs_put_tcon(tcon);
+	}
+
+	cifs_dbg(FYI, "Reconnecting tcons finished\n");
+	mutex_unlock(&server->reconnect_mutex);
+
+	/* now we can safely release srv struct */
+	if (tcon_exist)
+		cifs_put_tcp_session(server, 1);
+}
+
 int
 SMB2_echo(struct TCP_Server_Info *server)
 {
@@ -1820,6 +1888,12 @@ SMB2_echo(struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "In echo request\n");
 
+	if (server->tcpStatus == CifsNeedNegotiate) {
+		/* No need to send echo on newly established connections */
+		queue_delayed_work(cifsiod_wq, &server->reconnect, 0);
+		return rc;
+	}
+
 	rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
 	if (rc)
 		return rc;
@@ -2038,6 +2112,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 	if (rdata->credits) {
 		buf->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
 						SMB2_MAX_BUFFER_SIZE));
+		buf->CreditRequest = buf->CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += rdata->credits -
 						le16_to_cpu(buf->CreditCharge);
@@ -2224,6 +2299,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	if (wdata->credits) {
 		req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
 						    SMB2_MAX_BUFFER_SIZE));
+		req->hdr.CreditRequest = req->hdr.CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += wdata->credits -
 					le16_to_cpu(req->hdr.CreditCharge);
@@ -2577,6 +2653,22 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 int
+SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
+		  u64 persistent_fid, u64 volatile_fid)
+{
+	__u8 delete_pending = 1;
+	void *data;
+	unsigned int size;
+
+	data = &delete_pending;
+	size = 1; /* sizeof __u8 */
+
+	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
+			current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data,
+			&size);
+}
+
+int
 SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
 		  u64 persistent_fid, u64 volatile_fid, __le16 *target_file)
 {
@@ -2676,8 +2768,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
 	kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
 			  le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
 	kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits);
-	kst->f_bfree  = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits);
-	kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
+	kst->f_bfree  = kst->f_bavail =
+			le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
 	return;
 }
 
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 4af52780ec35..aacb15bd56fe 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -82,8 +82,8 @@
 
 #define NUMBER_OF_SMB2_COMMANDS	0x0013
 
-/* BB FIXME - analyze following length BB */
-#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
+/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
+#define MAX_SMB2_HDR_SIZE 0x00b0
 
 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 
@@ -276,7 +276,7 @@ struct smb2_sess_setup_req {
 	__le32 Channel;
 	__le16 SecurityBufferOffset;
 	__le16 SecurityBufferLength;
-	__le64 PreviousSessionId;
+	__u64 PreviousSessionId;
 	__u8   Buffer[1];	/* variable length GSS security buffer */
 } __packed;
 
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 79dc650c18b2..adc5234486c3 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -47,6 +47,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses,
 			      struct smb_rqst *rqst);
 extern struct mid_q_entry *smb2_setup_async_request(
 			struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+					   __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+						__u64 ses_id, __u32  tid);
 extern int smb2_calc_signature(struct smb_rqst *rqst,
 				struct TCP_Server_Info *server);
 extern int smb3_calc_signature(struct smb_rqst *rqst,
@@ -95,6 +99,7 @@ extern int smb2_open_file(const unsigned int xid,
 extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
+extern void smb2_reconnect_server(struct work_struct *work);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
@@ -140,6 +145,8 @@ extern int SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon,
 		       u64 persistent_fid, u64 volatile_fid,
 		       __le16 *target_file);
+extern int SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
+		      u64 persistent_fid, u64 volatile_fid);
 extern int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
 			     u64 persistent_fid, u64 volatile_fid,
 			     __le16 *target_file);
@@ -154,6 +161,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 			     const u64 persistent_fid, const u64 volatile_fid,
 			     const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+					struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index d4c5b6f109a7..69e3b322bbfe 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -115,22 +115,68 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
 }
 
 static struct cifs_ses *
-smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
 {
 	struct cifs_ses *ses;
 
-	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
-		if (ses->Suid != smb2hdr->SessionId)
+		if (ses->Suid != ses_id)
 			continue;
-		spin_unlock(&cifs_tcp_ses_lock);
 		return ses;
 	}
+
+	return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+	struct cifs_ses *ses;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32  tid)
+{
+	struct cifs_tcon *tcon;
+
+	list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+		if (tcon->tid != tid)
+			continue;
+		++tcon->tc_count;
+		return tcon;
+	}
+
 	return NULL;
 }
 
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid)
+{
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
+	if (!ses) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return NULL;
+	}
+	tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return tcon;
+}
 
 int
 smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
@@ -143,7 +189,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, smb2_pdu->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
@@ -314,7 +360,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, smb2_pdu->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 87abe8ed074c..54af10204e83 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -786,9 +786,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
+		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
 		send_cancel(ses->server, buf, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+			midQ->mid_flags |= MID_WAIT_CANCELLED;
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
 			cifs_small_buf_release(buf);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index ec5c8325b503..0525ebc3aea2 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -83,14 +83,13 @@ static int create_link(struct config_item *parent_item,
 	ret = -ENOMEM;
 	sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
 	if (sl) {
-		sl->sl_target = config_item_get(item);
 		spin_lock(&configfs_dirent_lock);
 		if (target_sd->s_type & CONFIGFS_USET_DROPPING) {
 			spin_unlock(&configfs_dirent_lock);
-			config_item_put(item);
 			kfree(sl);
 			return -ENOENT;
 		}
+		sl->sl_target = config_item_get(item);
 		list_add(&sl->sl_list, &target_sd->s_links);
 		spin_unlock(&configfs_dirent_lock);
 		ret = configfs_create_link(sl, parent_item->ci_dentry,
diff --git a/fs/coredump.c b/fs/coredump.c
index 1777331eee76..a8852293038a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1,6 +1,7 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/freezer.h>
 #include <linux/mm.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
@@ -32,6 +33,9 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/path.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -396,7 +400,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 	if (core_waiters > 0) {
 		struct core_thread *ptr;
 
+		freezer_do_not_count();
 		wait_for_completion(&core_state->startup);
+		freezer_count();
 		/*
 		 * Wait for all the threads to become inactive, so that
 		 * all the thread context (extended register state, like
@@ -627,6 +633,8 @@ void do_coredump(const siginfo_t *siginfo)
 		}
 	} else {
 		struct inode *inode;
+		int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
+				 O_LARGEFILE | O_EXCL;
 
 		if (cprm.limit < binfmt->min_coredump)
 			goto fail_unlock;
@@ -665,10 +673,27 @@ void do_coredump(const siginfo_t *siginfo)
 		 * what matters is that at least one of the two processes
 		 * writes its coredump successfully, not which one.
 		 */
-		cprm.file = filp_open(cn.corename,
-				 O_CREAT | 2 | O_NOFOLLOW |
-				 O_LARGEFILE | O_EXCL,
-				 0600);
+		if (need_suid_safe) {
+			/*
+			 * Using user namespaces, normal user tasks can change
+			 * their current->fs->root to point to arbitrary
+			 * directories. Since the intention of the "only dump
+			 * with a fully qualified path" rule is to control where
+			 * coredumps may be placed using root privileges,
+			 * current->fs->root must not be used. Instead, use the
+			 * root directory of init_task.
+			 */
+			struct path root;
+
+			task_lock(&init_task);
+			get_fs_root(init_task.fs, &root);
+			task_unlock(&init_task);
+			cprm.file = file_open_root(root.dentry, root.mnt,
+				cn.corename, open_flags, 0600);
+			path_put(&root);
+		} else {
+			cprm.file = filp_open(cn.corename, open_flags, 0600);
+		}
 		if (IS_ERR(cprm.file))
 			goto fail_unlock;
 
@@ -785,3 +810,21 @@ int dump_align(struct coredump_params *cprm, int align)
 	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+	struct file *file = cprm->file;
+	loff_t offset;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		offset = file->f_op->llseek(file, 0, SEEK_CUR);
+		if (i_size_read(file->f_mapping->host) < offset)
+			do_truncate(file->f_path.dentry, offset, 0, file);
+	}
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/fs/dcache.c b/fs/dcache.c
index 877bcbbd03ff..3ed642e0a0c2 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,6 +269,33 @@ static inline int dname_external(const struct dentry *dentry)
 	return dentry->d_name.name != dentry->d_iname;
 }
 
+void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	if (unlikely(dname_external(dentry))) {
+		struct external_name *p = external_name(dentry);
+		atomic_inc(&p->u.count);
+		spin_unlock(&dentry->d_lock);
+		name->name = p->name;
+	} else {
+		memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
+		spin_unlock(&dentry->d_lock);
+		name->name = name->inline_name;
+	}
+}
+EXPORT_SYMBOL(take_dentry_name_snapshot);
+
+void release_dentry_name_snapshot(struct name_snapshot *name)
+{
+	if (unlikely(name->name != name->inline_name)) {
+		struct external_name *p;
+		p = container_of(name->name, struct external_name, name[0]);
+		if (unlikely(atomic_dec_and_test(&p->u.count)))
+			kfree_rcu(p, u.head);
+	}
+}
+EXPORT_SYMBOL(release_dentry_name_snapshot);
+
 static inline void __d_set_inode_and_type(struct dentry *dentry,
 					  struct inode *inode,
 					  unsigned type_flags)
@@ -578,7 +605,6 @@ static struct dentry *dentry_kill(struct dentry *dentry)
 
 failed:
 	spin_unlock(&dentry->d_lock);
-	cpu_relax();
 	return dentry; /* try again with same dentry */
 }
 
@@ -752,6 +778,8 @@ void dput(struct dentry *dentry)
 		return;
 
 repeat:
+	might_sleep();
+
 	rcu_read_lock();
 	if (likely(fast_dput(dentry))) {
 		rcu_read_unlock();
@@ -783,8 +811,10 @@ repeat:
 
 kill_it:
 	dentry = dentry_kill(dentry);
-	if (dentry)
+	if (dentry) {
+		cond_resched();
 		goto repeat;
+	}
 }
 EXPORT_SYMBOL(dput);
 
@@ -1125,11 +1155,12 @@ void shrink_dcache_sb(struct super_block *sb)
 		LIST_HEAD(dispose);
 
 		freed = list_lru_walk(&sb->s_dentry_lru,
-			dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+			dentry_lru_isolate_shrink, &dispose, 1024);
 
 		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
-	} while (freed > 0);
+		cond_resched();
+	} while (list_lru_count(&sb->s_dentry_lru) > 0);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -1319,8 +1350,11 @@ int d_set_mounted(struct dentry *dentry)
 	}
 	spin_lock(&dentry->d_lock);
 	if (!d_unlinked(dentry)) {
-		dentry->d_flags |= DCACHE_MOUNTED;
-		ret = 0;
+		ret = -EBUSY;
+		if (!d_mountpoint(dentry)) {
+			dentry->d_flags |= DCACHE_MOUNTED;
+			ret = 0;
+		}
 	}
  	spin_unlock(&dentry->d_lock);
 out:
@@ -1618,7 +1652,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	struct dentry *dentry = __d_alloc(parent->d_sb, name);
 	if (!dentry)
 		return NULL;
-
+	dentry->d_flags |= DCACHE_RCUACCESS;
 	spin_lock(&parent->d_lock);
 	/*
 	 * don't need child lock because it is not subject
@@ -1666,7 +1700,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_WEAK_REVALIDATE	|
 				DCACHE_OP_DELETE	|
-				DCACHE_OP_SELECT_INODE));
+				DCACHE_OP_SELECT_INODE	|
+				DCACHE_OP_REAL));
 	dentry->d_op = op;
 	if (!op)
 		return;
@@ -1684,6 +1719,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 		dentry->d_flags |= DCACHE_OP_PRUNE;
 	if (op->d_select_inode)
 		dentry->d_flags |= DCACHE_OP_SELECT_INODE;
+	if (op->d_real)
+		dentry->d_flags |= DCACHE_OP_REAL;
 
 }
 EXPORT_SYMBOL(d_set_d_op);
@@ -2410,7 +2447,6 @@ static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b)
 {
 	BUG_ON(!d_unhashed(entry));
 	hlist_bl_lock(b);
-	entry->d_flags |= DCACHE_RCUACCESS;
 	hlist_bl_add_head_rcu(&entry->d_hash, b);
 	hlist_bl_unlock(b);
 }
@@ -2629,6 +2665,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
 		/* splicing a tree */
+		dentry->d_flags |= DCACHE_RCUACCESS;
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
 		list_del_init(&target->d_child);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index b7fcc0de0b2f..e49ba072bd64 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -457,7 +457,7 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
 	dentry->d_fsdata = (void *)f;
@@ -669,7 +669,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 {
 	int error;
 	struct dentry *dentry = NULL, *trap;
-	const char *old_name;
+	struct name_snapshot old_name;
 
 	trap = lock_rename(new_dir, old_dir);
 	/* Source or destination directories don't exist? */
@@ -684,19 +684,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 	if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
 		goto exit;
 
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+	take_dentry_name_snapshot(&old_name, old_dentry);
 
 	error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
 		dentry);
 	if (error) {
-		fsnotify_oldname_free(old_name);
+		release_dentry_name_snapshot(&old_name);
 		goto exit;
 	}
 	d_move(old_dentry, dentry);
-	fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name,
+	fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name,
 		d_is_dir(old_dentry),
 		NULL, old_dentry);
-	fsnotify_oldname_free(old_name);
+	release_dentry_name_snapshot(&old_name);
 	unlock_rename(new_dir, old_dir);
 	dput(dentry);
 	return old_dentry;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 706de324f2a6..c82edb049117 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -128,6 +128,7 @@ static const match_table_t tokens = {
 struct pts_fs_info {
 	struct ida allocated_ptys;
 	struct pts_mount_opts mount_opts;
+	struct super_block *sb;
 	struct dentry *ptmx_dentry;
 };
 
@@ -358,7 +359,7 @@ static const struct super_operations devpts_sops = {
 	.show_options	= devpts_show_options,
 };
 
-static void *new_pts_fs_info(void)
+static void *new_pts_fs_info(struct super_block *sb)
 {
 	struct pts_fs_info *fsi;
 
@@ -369,6 +370,7 @@ static void *new_pts_fs_info(void)
 	ida_init(&fsi->allocated_ptys);
 	fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE;
 	fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+	fsi->sb = sb;
 
 	return fsi;
 }
@@ -384,7 +386,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
 	s->s_op = &devpts_sops;
 	s->s_time_gran = 1;
 
-	s->s_fs_info = new_pts_fs_info();
+	s->s_fs_info = new_pts_fs_info(s);
 	if (!s->s_fs_info)
 		goto fail;
 
@@ -524,17 +526,14 @@ static struct file_system_type devpts_fs_type = {
  * to the System V naming convention
  */
 
-int devpts_new_index(struct inode *ptmx_inode)
+int devpts_new_index(struct pts_fs_info *fsi)
 {
-	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-	struct pts_fs_info *fsi;
 	int index;
 	int ida_ret;
 
-	if (!sb)
+	if (!fsi)
 		return -ENODEV;
 
-	fsi = DEVPTS_SB(sb);
 retry:
 	if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
 		return -ENOMEM;
@@ -564,11 +563,8 @@ retry:
 	return index;
 }
 
-void devpts_kill_index(struct inode *ptmx_inode, int idx)
+void devpts_kill_index(struct pts_fs_info *fsi, int idx)
 {
-	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-	struct pts_fs_info *fsi = DEVPTS_SB(sb);
-
 	mutex_lock(&allocated_ptys_lock);
 	ida_remove(&fsi->allocated_ptys, idx);
 	pty_count--;
@@ -578,21 +574,25 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 /*
  * pty code needs to hold extra references in case of last /dev/tty close
  */
-
-void devpts_add_ref(struct inode *ptmx_inode)
+struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
 {
-	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+	struct super_block *sb;
+	struct pts_fs_info *fsi;
+
+	sb = pts_sb_from_inode(ptmx_inode);
+	if (!sb)
+		return NULL;
+	fsi = DEVPTS_SB(sb);
+	if (!fsi)
+		return NULL;
 
 	atomic_inc(&sb->s_active);
-	ihold(ptmx_inode);
+	return fsi;
 }
 
-void devpts_del_ref(struct inode *ptmx_inode)
+void devpts_put_ref(struct pts_fs_info *fsi)
 {
-	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-
-	iput(ptmx_inode);
-	deactivate_super(sb);
+	deactivate_super(fsi->sb);
 }
 
 /**
@@ -604,22 +604,21 @@ void devpts_del_ref(struct inode *ptmx_inode)
  *
  * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill.
  */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index,
 		void *priv)
 {
 	struct dentry *dentry;
-	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+	struct super_block *sb;
 	struct inode *inode;
 	struct dentry *root;
-	struct pts_fs_info *fsi;
 	struct pts_mount_opts *opts;
 	char s[12];
 
-	if (!sb)
+	if (!fsi)
 		return ERR_PTR(-ENODEV);
 
+	sb = fsi->sb;
 	root = sb->s_root;
-	fsi = DEVPTS_SB(sb);
 	opts = &fsi->mount_opts;
 
 	inode = new_inode(sb);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 01171d8a6ee9..c772fdf36cd9 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -575,7 +575,7 @@ static int dio_set_defer_completion(struct dio *dio)
 /*
  * Call into the fs to map some more disk blocks.  We record the current number
  * of available blocks at sdio->blocks_available.  These are in units of the
- * fs blocksize, (1 << inode->i_blkbits).
+ * fs blocksize, i_blocksize(inode).
  *
  * The fs is allowed to map lots of blocks at once.  If it wants to do that,
  * it uses the passed inode-relative block number as the file offset, as usual.
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 3a37bd3f9637..9d7a4a714907 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1607,16 +1607,12 @@ void dlm_lowcomms_stop(void)
 	mutex_lock(&connections_lock);
 	dlm_allow_conn = 0;
 	foreach_conn(stop_conn);
+	clean_writequeues();
+	foreach_conn(free_conn);
 	mutex_unlock(&connections_lock);
 
 	work_stop();
 
-	mutex_lock(&connections_lock);
-	clean_writequeues();
-
-	foreach_conn(free_conn);
-
-	mutex_unlock(&connections_lock);
 	kmem_cache_destroy(con_cache);
 }
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 173b3873a4f4..e40c440a4555 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -355,6 +355,10 @@ static int dlm_device_register(struct dlm_ls *ls, char *name)
 	error = misc_register(&ls->ls_device);
 	if (error) {
 		kfree(ls->ls_device.name);
+		/* this has to be set to NULL
+		 * to avoid a double-free in dlm_device_deregister
+		 */
+		ls->ls_device.name = NULL;
 	}
 fail:
 	return error;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index feef8a9c4de7..27794b137b24 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
 		.sb = inode->i_sb,
 	};
 	lower_file = ecryptfs_file_to_lower(file);
-	lower_file->f_pos = ctx->pos;
 	rc = iterate_dir(lower_file, &buf.ctx);
 	ctx->pos = buf.ctx.pos;
 	if (rc < 0)
@@ -170,6 +169,19 @@ out:
 	return rc;
 }
 
+static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct file *lower_file = ecryptfs_file_to_lower(file);
+	/*
+	 * Don't allow mmap on top of file systems that don't support it
+	 * natively.  If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs
+	 * allows recursive mounting, this will need to be extended.
+	 */
+	if (!lower_file->f_op->mmap)
+		return -ENODEV;
+	return generic_file_mmap(file, vma);
+}
+
 /**
  * ecryptfs_open
  * @inode: inode speciying file to open
@@ -223,14 +235,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	}
 	ecryptfs_set_file_lower(
 		file, ecryptfs_inode_to_private(inode)->lower_file);
-	if (d_is_dir(ecryptfs_dentry)) {
-		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
-		mutex_lock(&crypt_stat->cs_mutex);
-		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
-		mutex_unlock(&crypt_stat->cs_mutex);
-		rc = 0;
-		goto out;
-	}
 	rc = read_or_initialize_metadata(ecryptfs_dentry);
 	if (rc)
 		goto out_put;
@@ -247,6 +251,45 @@ out:
 	return rc;
 }
 
+/**
+ * ecryptfs_dir_open
+ * @inode: inode speciying file to open
+ * @file: Structure to return filled in
+ *
+ * Opens the file specified by inode.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_dir_open(struct inode *inode, struct file *file)
+{
+	struct dentry *ecryptfs_dentry = file->f_path.dentry;
+	/* Private value of ecryptfs_dentry allocated in
+	 * ecryptfs_lookup() */
+	struct ecryptfs_file_info *file_info;
+	struct file *lower_file;
+
+	/* 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);
+	if (unlikely(!file_info)) {
+		ecryptfs_printk(KERN_ERR,
+				"Error attempting to allocate memory\n");
+		return -ENOMEM;
+	}
+	lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry),
+				 file->f_flags, current_cred());
+	if (IS_ERR(lower_file)) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the lower file for the dentry with name "
+			"[%pd]; rc = [%ld]\n", __func__,
+			ecryptfs_dentry, PTR_ERR(lower_file));
+		kmem_cache_free(ecryptfs_file_info_cache, file_info);
+		return PTR_ERR(lower_file);
+	}
+	ecryptfs_set_file_lower(file, lower_file);
+	return 0;
+}
+
 static int ecryptfs_flush(struct file *file, fl_owner_t td)
 {
 	struct file *lower_file = ecryptfs_file_to_lower(file);
@@ -267,6 +310,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int ecryptfs_dir_release(struct inode *inode, struct file *file)
+{
+	fput(ecryptfs_file_to_lower(file));
+	kmem_cache_free(ecryptfs_file_info_cache,
+			ecryptfs_file_to_private(file));
+	return 0;
+}
+
+static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence);
+}
+
 static int
 ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
@@ -346,25 +402,21 @@ const struct file_operations ecryptfs_dir_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.open = ecryptfs_open,
-	.flush = ecryptfs_flush,
-	.release = ecryptfs_release,
+	.open = ecryptfs_dir_open,
+	.release = ecryptfs_dir_release,
 	.fsync = ecryptfs_fsync,
-	.fasync = ecryptfs_fasync,
-	.splice_read = generic_file_splice_read,
-	.llseek = default_llseek,
+	.llseek = ecryptfs_dir_llseek,
 };
 
 const struct file_operations ecryptfs_main_fops = {
 	.llseek = generic_file_llseek,
 	.read_iter = ecryptfs_read_update_atime,
 	.write_iter = generic_file_write_iter,
-	.iterate = ecryptfs_readdir,
 	.unlocked_ioctl = ecryptfs_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..1b08556776ce 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -518,8 +518,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq)
 	wait_queue_head_t *whead;
 
 	rcu_read_lock();
-	/* If it is cleared by POLLFREE, it should be rcu-safe */
-	whead = rcu_dereference(pwq->whead);
+	/*
+	 * If it is cleared by POLLFREE, it should be rcu-safe.
+	 * If we read NULL we need a barrier paired with
+	 * smp_store_release() in ep_poll_callback(), otherwise
+	 * we rely on whead->lock.
+	 */
+	whead = smp_load_acquire(&pwq->whead);
 	if (whead)
 		remove_wait_queue(whead, &pwq->wait);
 	rcu_read_unlock();
@@ -1003,17 +1008,6 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
 
-	if ((unsigned long)key & POLLFREE) {
-		ep_pwq_from_wait(wait)->whead = NULL;
-		/*
-		 * whead = NULL above can race with ep_remove_wait_queue()
-		 * which can do another remove_wait_queue() after us, so we
-		 * can't use __remove_wait_queue(). whead->lock is held by
-		 * the caller.
-		 */
-		list_del_init(&wait->task_list);
-	}
-
 	spin_lock_irqsave(&ep->lock, flags);
 
 	/*
@@ -1078,6 +1072,23 @@ out_unlock:
 	if (pwake)
 		ep_poll_safewake(&ep->poll_wait);
 
+
+	if ((unsigned long)key & POLLFREE) {
+		/*
+		 * If we race with ep_remove_wait_queue() it can miss
+		 * ->whead = NULL and do another remove_wait_queue() after
+		 * us, so we can't use __remove_wait_queue().
+		 */
+		list_del_init(&wait->task_list);
+		/*
+		 * ->whead != NULL protects us from the race with ep_free()
+		 * or ep_remove(), ep_remove_wait_queue() takes whead->lock
+		 * held by the caller. Once we nullify it, nothing protects
+		 * ep/epi or even wait.
+		 */
+		smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+	}
+
 	return 1;
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index b06623a9347f..9c5ee2a880aa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -19,7 +19,7 @@
  * current->executable is only used by the procfs.  This allows a dispatch
  * table to check for several different types  of binary formats.  We keep
  * trying until we recognize the file or we run out of supported binary
- * formats. 
+ * formats.
  */
 
 #include <linux/slab.h>
@@ -56,6 +56,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
+#include <linux/user_namespace.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -205,7 +206,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 	if (write) {
 		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
-		struct rlimit *rlim;
+		unsigned long ptr_size, limit;
+
+		/*
+		 * Since the stack will hold pointers to the strings, we
+		 * must account for them as well.
+		 *
+		 * The size calculation is the entire vma while each arg page is
+		 * built, so each time we get here it's calculating how far it
+		 * is currently (rather than each call being just the newly
+		 * added size from the arg page).  As a result, we need to
+		 * always add the entire size of the pointers, so that on the
+		 * last call to get_arg_page() we'll actually have the entire
+		 * correct size.
+		 */
+		ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+		if (ptr_size > ULONG_MAX - size)
+			goto fail;
+		size += ptr_size;
 
 		acct_arg_size(bprm, size / PAGE_SIZE);
 
@@ -217,20 +235,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return page;
 
 		/*
-		 * Limit to 1/4-th the stack size for the argv+env strings.
+		 * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
+		 * (whichever is smaller) for the argv+env strings.
 		 * This ensures that:
 		 *  - the remaining binfmt code will not run out of stack space,
 		 *  - the program will have a reasonable amount of stack left
 		 *    to work from.
 		 */
-		rlim = current->signal->rlim;
-		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-			put_page(page);
-			return NULL;
-		}
+		limit = _STK_LIM / 4 * 3;
+		limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+		if (size > limit)
+			goto fail;
 	}
 
 	return page;
+
+fail:
+	put_page(page);
+	return NULL;
 }
 
 static void put_arg_page(struct page *page)
@@ -1114,6 +1136,13 @@ int flush_old_exec(struct linux_binprm * bprm)
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
 
+	/*
+	 * We have to apply CLOEXEC before we change whether the process is
+	 * dumpable (in setup_new_exec) to avoid a race with a process in userspace
+	 * trying to access the should-be-closed file descriptors of a process
+	 * undergoing exec(2).
+	 */
+	do_close_on_exec(current->files);
 	return 0;
 
 out:
@@ -1123,8 +1152,22 @@ EXPORT_SYMBOL(flush_old_exec);
 
 void would_dump(struct linux_binprm *bprm, struct file *file)
 {
-	if (inode_permission(file_inode(file), MAY_READ) < 0)
+	struct inode *inode = file_inode(file);
+	if (inode_permission(inode, MAY_READ) < 0) {
+		struct user_namespace *old, *user_ns;
 		bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
+
+		/* Ensure mm->user_ns contains the executable */
+		user_ns = old = bprm->mm->user_ns;
+		while ((user_ns != &init_user_ns) &&
+		       !privileged_wrt_inode_uidgid(user_ns, inode))
+			user_ns = user_ns->parent;
+
+		if (old != user_ns) {
+			bprm->mm->user_ns = get_user_ns(user_ns);
+			put_user_ns(old);
+		}
+	}
 }
 EXPORT_SYMBOL(would_dump);
 
@@ -1154,7 +1197,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	    !gid_eq(bprm->cred->gid, current_egid())) {
 		current->pdeath_signal = 0;
 	} else {
-		would_dump(bprm, bprm->file);
 		if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)
 			set_dumpable(current->mm, suid_dumpable);
 	}
@@ -1163,7 +1205,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	   group */
 	current->self_exec_id++;
 	flush_signal_handlers(current, 0);
-	do_close_on_exec(current->files);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
@@ -1254,7 +1295,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	unsigned n_fs;
 
 	if (p->ptrace) {
-		if (p->ptrace & PT_PTRACE_CAP)
+		if (ptracer_capable(p, current_user_ns()))
 			bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
 		else
 			bprm->unsafe |= LSM_UNSAFE_PTRACE;
@@ -1587,6 +1628,8 @@ static int do_execveat_common(int fd, struct filename *filename,
 	if (retval < 0)
 		goto out;
 
+	would_dump(bprm, bprm->file);
+
 	retval = exec_binprm(bprm);
 	if (retval < 0)
 		goto out;
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 27695e6f4e46..d6aeb84e90b6 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -193,15 +193,11 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		case ACL_TYPE_ACCESS:
 			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
 			if (acl) {
-				error = posix_acl_equiv_mode(acl, &inode->i_mode);
-				if (error < 0)
+				error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+				if (error)
 					return error;
-				else {
-					inode->i_ctime = CURRENT_TIME_SEC;
-					mark_inode_dirty(inode);
-					if (error == 0)
-						acl = NULL;
-				}
+				inode->i_ctime = CURRENT_TIME_SEC;
+				mark_inode_dirty(inode);
 			}
 			break;
 
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 69b1e73026a5..c3fe1e323951 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -196,15 +196,11 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 	case ACL_TYPE_ACCESS:
 		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
 		if (acl) {
-			error = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (error < 0)
+			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (error)
 				return error;
-			else {
-				inode->i_ctime = ext4_current_time(inode);
-				ext4_mark_inode_dirty(handle, inode);
-				if (error == 0)
-					acl = NULL;
-			}
+			inode->i_ctime = ext4_current_time(inode);
+			ext4_mark_inode_dirty(handle, inode);
 		}
 		break;
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index fe1f50fe764f..f97110461c19 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	memset(bh->b_data, 0, sb->s_blocksize);
 
 	bit_max = ext4_num_base_meta_clusters(sb, block_group);
+	if ((bit_max >> 3) >= bh->b_size)
+		return -EFSCORRUPTED;
+
 	for (bit = 0; bit < bit_max; bit++)
 		ext4_set_bit(bit, bh->b_data);
 
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index 1a0835073663..f240cef8b326 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -34,6 +34,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock_types.h>
+#include <linux/namei.h>
 
 #include "ext4_extents.h"
 #include "xattr.h"
@@ -93,7 +94,8 @@ void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
  * Return: An allocated and initialized encryption context on success; error
  * value or NULL otherwise.
  */
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+					    gfp_t gfp_flags)
 {
 	struct ext4_crypto_ctx *ctx = NULL;
 	int res = 0;
@@ -120,7 +122,7 @@ struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
 		list_del(&ctx->free_list);
 	spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
 	if (!ctx) {
-		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
+		ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, gfp_flags);
 		if (!ctx) {
 			res = -ENOMEM;
 			goto out;
@@ -257,7 +259,8 @@ static int ext4_page_crypto(struct inode *inode,
 			    ext4_direction_t rw,
 			    pgoff_t index,
 			    struct page *src_page,
-			    struct page *dest_page)
+			    struct page *dest_page,
+			    gfp_t gfp_flags)
 
 {
 	u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
@@ -268,7 +271,7 @@ static int ext4_page_crypto(struct inode *inode,
 	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = ablkcipher_request_alloc(tfm, gfp_flags);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 				   "%s: crypto_request_alloc() failed\n",
@@ -309,9 +312,10 @@ static int ext4_page_crypto(struct inode *inode,
 	return 0;
 }
 
-static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
+static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx,
+				      gfp_t gfp_flags)
 {
-	ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, GFP_NOWAIT);
+	ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, gfp_flags);
 	if (ctx->w.bounce_page == NULL)
 		return ERR_PTR(-ENOMEM);
 	ctx->flags |= EXT4_WRITE_PATH_FL;
@@ -334,7 +338,8 @@ static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
  * error value or NULL.
  */
 struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page)
+			  struct page *plaintext_page,
+			  gfp_t gfp_flags)
 {
 	struct ext4_crypto_ctx *ctx;
 	struct page *ciphertext_page = NULL;
@@ -342,17 +347,17 @@ struct page *ext4_encrypt(struct inode *inode,
 
 	BUG_ON(!PageLocked(plaintext_page));
 
-	ctx = ext4_get_crypto_ctx(inode);
+	ctx = ext4_get_crypto_ctx(inode, gfp_flags);
 	if (IS_ERR(ctx))
 		return (struct page *) ctx;
 
 	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx);
+	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
 	if (IS_ERR(ciphertext_page))
 		goto errout;
 	ctx->w.control_page = plaintext_page;
 	err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index,
-			       plaintext_page, ciphertext_page);
+			       plaintext_page, ciphertext_page, gfp_flags);
 	if (err) {
 		ciphertext_page = ERR_PTR(err);
 	errout:
@@ -380,8 +385,8 @@ int ext4_decrypt(struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 
-	return ext4_page_crypto(page->mapping->host,
-				EXT4_DECRYPT, page->index, page, page);
+	return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT,
+				page->index, page, page, GFP_NOFS);
 }
 
 int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
@@ -402,11 +407,11 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
 
 	BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
 
-	ctx = ext4_get_crypto_ctx(inode);
+	ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	ciphertext_page = alloc_bounce_page(ctx);
+	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
 	if (IS_ERR(ciphertext_page)) {
 		err = PTR_ERR(ciphertext_page);
 		goto errout;
@@ -414,11 +419,12 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
 
 	while (len--) {
 		err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk,
-				       ZERO_PAGE(0), ciphertext_page);
+				       ZERO_PAGE(0), ciphertext_page,
+				       GFP_NOFS);
 		if (err)
 			goto errout;
 
-		bio = bio_alloc(GFP_KERNEL, 1);
+		bio = bio_alloc(GFP_NOWAIT, 1);
 		if (!bio) {
 			err = -ENOMEM;
 			goto errout;
@@ -469,3 +475,61 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *dir;
+	struct ext4_crypt_info *ci;
+	int dir_has_key, cached_with_key;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	dir = dget_parent(dentry);
+	if (!ext4_encrypted_inode(d_inode(dir))) {
+		dput(dir);
+		return 0;
+	}
+	ci = EXT4_I(d_inode(dir))->i_crypt_info;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+	dput(dir);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
index 2fbef8a14760..2cfe3ffc276f 100644
--- a/fs/ext4/crypto_fname.c
+++ b/fs/ext4/crypto_fname.c
@@ -343,7 +343,7 @@ int _ext4_fname_disk_to_usr(struct inode *inode,
 		memcpy(buf+4, &hinfo->minor_hash, 4);
 	} else
 		memset(buf, 0, 8);
-	memcpy(buf + 8, iname->name + iname->len - 16, 16);
+	memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
 	oname->name[0] = '_';
 	ret = digest_encode(buf, 24, oname->name+1);
 	oname->len = ret + 1;
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
index 9a16d1e75a49..505f8afde57c 100644
--- a/fs/ext4/crypto_key.c
+++ b/fs/ext4/crypto_key.c
@@ -88,8 +88,6 @@ void ext4_free_crypt_info(struct ext4_crypt_info *ci)
 	if (!ci)
 		return;
 
-	if (ci->ci_keyring_key)
-		key_put(ci->ci_keyring_key);
 	crypto_free_ablkcipher(ci->ci_ctfm);
 	kmem_cache_free(ext4_crypt_info_cachep, ci);
 }
@@ -111,7 +109,7 @@ void ext4_free_encryption_info(struct inode *inode,
 	ext4_free_crypt_info(ci);
 }
 
-int _ext4_get_encryption_info(struct inode *inode)
+int ext4_get_encryption_info(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_crypt_info *crypt_info;
@@ -128,22 +126,15 @@ int _ext4_get_encryption_info(struct inode *inode)
 	char mode;
 	int res;
 
+	if (ei->i_crypt_info)
+		return 0;
+
 	if (!ext4_read_workqueue) {
 		res = ext4_init_crypto();
 		if (res)
 			return res;
 	}
 
-retry:
-	crypt_info = ACCESS_ONCE(ei->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-		    key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		ext4_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
 	res = ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
 				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
 				 &ctx, sizeof(ctx));
@@ -166,7 +157,6 @@ retry:
 	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
 	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
 	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
 	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
 	       sizeof(crypt_info->ci_master_key));
 	if (S_ISREG(inode->i_mode))
@@ -206,7 +196,6 @@ retry:
 		keyring_key = NULL;
 		goto out;
 	}
-	crypt_info->ci_keyring_key = keyring_key;
 	if (keyring_key->type != &key_type_logon) {
 		printk_once(KERN_WARNING
 			    "ext4: key type must be logon\n");
@@ -253,16 +242,13 @@ got_key:
 				       ext4_encryption_key_size(mode));
 	if (res)
 		goto out;
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) != NULL) {
-		ext4_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
 
+	if (cmpxchg(&ei->i_crypt_info, NULL, crypt_info) == NULL)
+		crypt_info = NULL;
 out:
 	if (res == -ENOKEY)
 		res = 0;
+	key_put(keyring_key);
 	ext4_free_crypt_info(crypt_info);
 	memzero_explicit(raw_key, sizeof(raw_key));
 	return res;
diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c
index ad050698143f..e4f4fc4e56ab 100644
--- a/fs/ext4/crypto_policy.c
+++ b/fs/ext4/crypto_policy.c
@@ -102,6 +102,9 @@ static int ext4_create_encryption_context_from_policy(
 int ext4_process_policy(const struct ext4_encryption_policy *policy,
 			struct inode *inode)
 {
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
 	if (policy->version != 0)
 		return -EINVAL;
 
@@ -145,20 +148,38 @@ int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
 int ext4_is_child_context_consistent_with_parent(struct inode *parent,
 						 struct inode *child)
 {
-	struct ext4_crypt_info *parent_ci, *child_ci;
+	const struct ext4_crypt_info *parent_ci, *child_ci;
+	struct ext4_encryption_context parent_ctx, child_ctx;
 	int res;
 
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		WARN_ON(1);	/* Should never happen */
-		return 0;
-	}
-	/* no restrictions if the parent directory is not encrypted */
+	/* No restrictions on file types which are never encrypted */
+	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+	    !S_ISLNK(child->i_mode))
+		return 1;
+
+	/* No restrictions if the parent directory is unencrypted */
 	if (!ext4_encrypted_inode(parent))
 		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
+
+	/* Encrypted directories must not contain unencrypted files */
 	if (!ext4_encrypted_inode(child))
 		return 0;
+
+	/*
+	 * Both parent and child are encrypted, so verify they use the same
+	 * encryption policy.  Compare the fscrypt_info structs if the keys are
+	 * available, otherwise retrieve and compare the fscrypt_contexts.
+	 *
+	 * Note that the fscrypt_context retrieval will be required frequently
+	 * when accessing an encrypted directory tree without the key.
+	 * Performance-wise this is not a big deal because we already don't
+	 * really optimize for file access without the key (to the extent that
+	 * such access is even possible), given that any attempted access
+	 * already causes a fscrypt_context retrieval and keyring search.
+	 *
+	 * In any case, if an unexpected error occurs, fall back to "forbidden".
+	 */
+
 	res = ext4_get_encryption_info(parent);
 	if (res)
 		return 0;
@@ -167,17 +188,35 @@ int ext4_is_child_context_consistent_with_parent(struct inode *parent,
 		return 0;
 	parent_ci = EXT4_I(parent)->i_crypt_info;
 	child_ci = EXT4_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
+	if (parent_ci && child_ci) {
+		return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+			      EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+			(parent_ci->ci_filename_mode ==
+			 child_ci->ci_filename_mode) &&
+			(parent_ci->ci_flags == child_ci->ci_flags);
+	}
+
+	res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+			     &parent_ctx, sizeof(parent_ctx));
+	if (res != sizeof(parent_ctx))
+		return 0;
+
+	res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION,
+			     EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+			     &child_ctx, sizeof(child_ctx));
+	if (res != sizeof(child_ctx))
 		return 0;
 
-	return (memcmp(parent_ci->ci_master_key,
-		       child_ci->ci_master_key,
-		       EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
+	return memcmp(parent_ctx.master_key_descriptor,
+		      child_ctx.master_key_descriptor,
+		      EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ctx.contents_encryption_mode ==
+		 child_ctx.contents_encryption_mode) &&
+		(parent_ctx.filenames_encryption_mode ==
+		 child_ctx.filenames_encryption_mode) &&
+		(parent_ctx.flags == child_ctx.flags);
 }
 
 /**
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..6d17f31a31d7 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index cc7ca4e87144..c8ad14c697c4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -221,6 +221,7 @@ struct ext4_io_submit {
 #define	EXT4_MAX_BLOCK_SIZE		65536
 #define EXT4_MIN_BLOCK_LOG_SIZE		10
 #define EXT4_MAX_BLOCK_LOG_SIZE		16
+#define EXT4_MAX_CLUSTER_LOG_SIZE	30
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
 #else
@@ -850,6 +851,29 @@ do {									       \
 #include "extents_status.h"
 
 /*
+ * Lock subclasses for i_data_sem in the ext4_inode_info structure.
+ *
+ * These are needed to avoid lockdep false positives when we need to
+ * allocate blocks to the quota inode during ext4_map_blocks(), while
+ * holding i_data_sem for a normal (non-quota) inode.  Since we don't
+ * do quota tracking for the quota inode, this avoids deadlock (as
+ * well as infinite recursion, since it isn't turtles all the way
+ * down...)
+ *
+ *  I_DATA_SEM_NORMAL - Used for most inodes
+ *  I_DATA_SEM_OTHER  - Used by move_inode.c for the second normal inode
+ *			  where the second inode has larger inode number
+ *			  than the first
+ *  I_DATA_SEM_QUOTA  - Used for quota inodes only
+ */
+enum {
+	I_DATA_SEM_NORMAL = 0,
+	I_DATA_SEM_OTHER,
+	I_DATA_SEM_QUOTA,
+};
+
+
+/*
  * fourth extended file system inode data in memory
  */
 struct ext4_inode_info {
@@ -910,6 +934,15 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
+	/*
+	 * i_mmap_sem is for serializing page faults with truncate / punch hole
+	 * operations. We have to make sure that new page cannot be faulted in
+	 * a section of the inode that is being punched. We cannot easily use
+	 * i_data_sem for this since we need protection for the whole punch
+	 * operation and i_data_sem ranks below transaction start so we have
+	 * to occasionally drop it.
+	 */
+	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -2228,13 +2261,16 @@ extern struct kmem_cache *ext4_crypt_info_cachep;
 bool ext4_valid_contents_enc_mode(uint32_t mode);
 uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
 extern struct workqueue_struct *ext4_read_workqueue;
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode);
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+					    gfp_t gfp_flags);
 void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
 void ext4_restore_control_page(struct page *data_page);
 struct page *ext4_encrypt(struct inode *inode,
-			  struct page *plaintext_page);
+			  struct page *plaintext_page,
+			  gfp_t gfp_flags);
 int ext4_decrypt(struct page *page);
 int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);
@@ -2297,23 +2333,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
 /* crypto_key.c */
 void ext4_free_crypt_info(struct ext4_crypt_info *ci);
 void ext4_free_encryption_info(struct inode *inode, struct ext4_crypt_info *ci);
-int _ext4_get_encryption_info(struct inode *inode);
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_has_encryption_key(struct inode *inode);
 
-static inline int ext4_get_encryption_info(struct inode *inode)
-{
-	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-
-	if (!ci ||
-	    (ci->ci_keyring_key &&
-	     (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					   (1 << KEY_FLAG_REVOKED) |
-					   (1 << KEY_FLAG_DEAD)))))
-		return _ext4_get_encryption_info(inode);
-	return 0;
-}
+int ext4_get_encryption_info(struct inode *inode);
 
 static inline struct ext4_crypt_info *ext4_encryption_info(struct inode *inode)
 {
@@ -2484,6 +2508,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
@@ -2848,6 +2873,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
 	return changed;
 }
 
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len);
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
index ac7d4e813796..1b17b05b9f4d 100644
--- a/fs/ext4/ext4_crypto.h
+++ b/fs/ext4/ext4_crypto.h
@@ -78,7 +78,6 @@ struct ext4_crypt_info {
 	char		ci_filename_mode;
 	char		ci_flags;
 	struct crypto_ablkcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
 	char		ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
 };
 
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5f5846211095..f817ed58f5ad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -395,17 +395,19 @@ static inline int ext4_inode_journal_mode(struct inode *inode)
 		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
 	/* We do not support data journalling with delayed allocation */
 	if (!S_ISREG(inode->i_mode) ||
-	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC))
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && ext4_encrypted_inode(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
 		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
 		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
 		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	else
-		BUG();
+	BUG();
 }
 
 static inline int ext4_should_journal_data(struct inode *inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 551353b1b17a..61d5bfc7318c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -376,9 +376,13 @@ 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 || lblock > last)
+	/*
+	 * We allow neither:
+	 *  - zero length
+	 *  - overflow/wrap-around
+	 */
+	if (lblock + len <= lblock)
 		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
@@ -469,6 +473,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 		error_msg = "invalid extent entries";
 		goto corrupted;
 	}
+	if (unlikely(depth > 32)) {
+		error_msg = "too large eh_depth";
+		goto corrupted;
+	}
 	/* Verify checksum on non-root extent tree nodes */
 	if (ext_depth(inode) != depth &&
 	    !ext4_extent_block_csum_verify(inode, eh)) {
@@ -4685,10 +4693,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	if (len <= EXT_UNWRITTEN_MAX_LEN)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
-
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
@@ -4752,8 +4756,6 @@ retry:
 		goto retry;
 	}
 
-	ext4_inode_resume_unlocked_dio(inode);
-
 	return ret > 0 ? ret2 : ret;
 }
 
@@ -4770,7 +4772,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
-	struct address_space *mapping = inode->i_mapping;
 	unsigned int blkbits = inode->i_blkbits;
 
 	trace_ext4_zero_range(inode, offset, len, mode);
@@ -4786,17 +4787,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		ret = filemap_write_and_wait_range(mapping, offset,
-						   offset + len - 1);
-		if (ret)
-			return ret;
-	}
-
-	/*
 	 * Round up offset. This is not fallocate, we neet to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
@@ -4839,6 +4829,10 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	/* Preallocate the range including the unaligned edges */
 	if (partial_begin || partial_end) {
 		ret = ext4_alloc_file_blocks(file,
@@ -4847,7 +4841,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 				 round_down(offset, 1 << blkbits)) >> blkbits,
 				new_size, flags, mode);
 		if (ret)
-			goto out_mutex;
+			goto out_dio;
 
 	}
 
@@ -4856,16 +4850,23 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
 			  EXT4_EX_NOCACHE);
 
-		/* Now release the pages and zero block aligned part of pages*/
+		/*
+		 * Prevent page faults from reinstantiating pages we have
+		 * released from page cache.
+		 */
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+		ret = ext4_update_disksize_before_punch(inode, offset, len);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_dio;
+		}
+		/* Now release the pages and zero block aligned part of pages */
 		truncate_pagecache_range(inode, start, end - 1);
 		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
-		/* Wait all existing dio workers, newcomers will block on i_mutex */
-		ext4_inode_block_unlocked_dio(inode);
-		inode_dio_wait(inode);
-
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags, mode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 		if (ret)
 			goto out_dio;
 	}
@@ -4901,6 +4902,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -4998,8 +5001,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 				     flags, mode);
+	ext4_inode_resume_unlocked_dio(inode);
 	if (ret)
 		goto out;
 
@@ -5356,7 +5364,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	ext4_lblk_t stop, *iterator, ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+				EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
@@ -5365,15 +5374,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	if (!extent)
 		goto out;
 
-	stop = le32_to_cpu(extent->ee_block) +
-			ext4_ext_get_actual_len(extent);
+	stop = le32_to_cpu(extent->ee_block);
 
        /*
 	 * In case of left shift, Don't start shifting extents until we make
 	 * sure the hole is big enough to accommodate the shift.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
-		path = ext4_find_extent(inode, start - 1, &path, 0);
+		path = ext4_find_extent(inode, start - 1, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5405,9 +5414,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	else
 		iterator = &stop;
 
-	/* Its safe to start updating extents */
-	while (start < stop) {
-		path = ext4_find_extent(inode, *iterator, &path, 0);
+	/*
+	 * Its safe to start updating extents.  Start and stop are unsigned, so
+	 * in case of right shift if extent with 0 block is reached, iterator
+	 * becomes NULL to indicate the end of the loop.
+	 */
+	while (iterator && start <= stop) {
+		path = ext4_find_extent(inode, *iterator, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5434,8 +5448,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					ext4_ext_get_actual_len(extent);
 		} else {
 			extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
-			*iterator =  le32_to_cpu(extent->ee_block) > 0 ?
-				le32_to_cpu(extent->ee_block) - 1 : 0;
+			if (le32_to_cpu(extent->ee_block) > 0)
+				*iterator = le32_to_cpu(extent->ee_block) - 1;
+			else
+				/* Beginning is reached, end of the loop */
+				iterator = NULL;
 			/* Update path extent in case we need to stop */
 			while (le32_to_cpu(extent->ee_block) < start)
 				extent++;
@@ -5494,21 +5511,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
-	/*
-	 * Need to round down offset to be aligned with page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   LLONG_MAX);
-	if (ret)
-		return ret;
-
-	/* Take mutex lock */
 	mutex_lock(&inode->i_mutex);
-
 	/*
 	 * There is no need to overlap collapse range with EOF, in which case
 	 * it is effectively a truncate operation
@@ -5524,17 +5527,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	truncate_pagecache(inode, ioffset);
-
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	/*
+	 * Need to round down offset to be aligned with page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+	/*
+	 * Write tail of the last page before removed range since it will get
+	 * removed from the page cache below.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	if (ret)
+		goto out_mmap;
+	/*
+	 * Write data that will be shifted to preserve them when discarding
+	 * page cache below. We are also protected from pages becoming dirty
+	 * by i_mmap_sem.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+					   LLONG_MAX);
+	if (ret)
+		goto out_mmap;
+	truncate_pagecache(inode, ioffset);
+
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_dio;
+		goto out_mmap;
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -5570,10 +5599,12 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
@@ -5627,21 +5658,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
-	/*
-	 * Need to round down to align start offset to page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-			LLONG_MAX);
-	if (ret)
-		return ret;
-
-	/* Take mutex lock */
 	mutex_lock(&inode->i_mutex);
-
 	/* Currently just for extent based files */
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		ret = -EOPNOTSUPP;
@@ -5660,17 +5677,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	truncate_pagecache(inode, ioffset);
-
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	/*
+	 * Need to round down to align start offset to page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+	/* Write out all dirty pages */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+			LLONG_MAX);
+	if (ret)
+		goto out_mmap;
+	truncate_pagecache(inode, ioffset);
+
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_dio;
+		goto out_mmap;
 	}
 
 	/* Expand file to avoid data loss if there is error while shifting */
@@ -5718,6 +5750,9 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 			up_write(&EXT4_I(inode)->i_data_sem);
 			goto out_stop;
 		}
+	} else {
+		ext4_ext_drop_refs(path);
+		kfree(path);
 	}
 
 	ret = ext4_es_remove_extent(inode, offset_lblk,
@@ -5738,10 +5773,13 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 113837e7ba98..45ef9975caec 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -209,15 +209,18 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
 	handle_t *handle = NULL;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 						EXT4_DATA_TRANS_BLOCKS(sb));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
@@ -228,8 +231,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -246,10 +251,12 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
 				ext4_chunk_trans_blocks(inode,
 							PMD_SIZE / PAGE_SIZE));
-	}
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
@@ -260,30 +267,71 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		if (!IS_ERR(handle))
 			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
-	}
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
 
 static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return dax_mkwrite(vma, vmf, ext4_get_block_dax,
-				ext4_end_io_unwritten);
+	int err;
+	struct inode *inode = file_inode(vma->vm_file);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = __dax_mkwrite(vma, vmf, ext4_get_block_dax,
+			    ext4_end_io_unwritten);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	sb_end_pagefault(inode->i_sb);
+
+	return err;
+}
+
+/*
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * handler we check for races agaist truncate. Note that since we cycle through
+ * i_mmap_sem, we are sure that also any hole punching that began before we
+ * were called is finished by now and so if it included part of the file we
+ * are working on, our pte will get unmapped and the check for pte_same() in
+ * wp_pfn_shared() fails. Thus fault gets retried and things work out as
+ * desired.
+ */
+static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
+				struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+	int ret = VM_FAULT_NOPAGE;
+	loff_t size;
+
+	sb_start_pagefault(sb);
+	file_update_time(vma->vm_file);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	sb_end_pagefault(sb);
+
+	return ret;
 }
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
 	.page_mkwrite	= ext4_dax_mkwrite,
-	.pfn_mkwrite	= dax_pfn_mkwrite,
+	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
 #define ext4_dax_vm_ops	ext4_file_vm_ops
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= ext4_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
@@ -415,47 +463,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
-			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -472,6 +500,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 				lastoff = page_offset(page);
 				bh = head = page_buffers(page);
 				do {
+					if (lastoff + bh->b_size <= startoff)
+						goto next;
 					if (buffer_uptodate(bh) ||
 					    buffer_unwritten(bh)) {
 						if (whence == SEEK_DATA)
@@ -486,6 +516,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 						unlock_page(page);
 						goto out;
 					}
+next:
 					lastoff += bh->b_size;
 					bh = bh->b_this_page;
 				} while (bh != head);
@@ -495,20 +526,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 53f2b98a69f3..5388207d2832 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1143,25 +1143,20 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
 	ext4_group_t block_group;
 	int bit;
-	struct buffer_head *bitmap_bh;
+	struct buffer_head *bitmap_bh = NULL;
 	struct inode *inode = NULL;
-	long err = -EIO;
+	int err = -EFSCORRUPTED;
 
-	/* Error cases - e2fsck has already cleaned up for us */
-	if (ino > max_ino) {
-		ext4_warning(sb, "bad orphan ino %lu!  e2fsck was run?", ino);
-		err = -EFSCORRUPTED;
-		goto error;
-	}
+	if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+		goto bad_orphan;
 
 	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
 	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
-		ext4_warning(sb, "inode bitmap error %ld for orphan %lu",
-			     ino, err);
-		goto error;
+		ext4_error(sb, "inode bitmap error %ld for orphan %lu",
+			   ino, PTR_ERR(bitmap_bh));
+		return (struct inode *) bitmap_bh;
 	}
 
 	/* Having the inode bit set should be a 100% indicator that this
@@ -1172,15 +1167,21 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 		goto bad_orphan;
 
 	inode = ext4_iget(sb, ino);
-	if (IS_ERR(inode))
-		goto iget_failed;
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
+			   ino, err);
+		return inode;
+	}
 
 	/*
-	 * If the orphans has i_nlinks > 0 then it should be able to be
-	 * truncated, otherwise it won't be removed from the orphan list
-	 * during processing and an infinite loop will result.
+	 * If the orphans has i_nlinks > 0 then it should be able to
+	 * be truncated, otherwise it won't be removed from the orphan
+	 * list during processing and an infinite loop will result.
+	 * Similarly, it must not be a bad inode.
 	 */
-	if (inode->i_nlink && !ext4_can_truncate(inode))
+	if ((inode->i_nlink && !ext4_can_truncate(inode)) ||
+	    is_bad_inode(inode))
 		goto bad_orphan;
 
 	if (NEXT_ORPHAN(inode) > max_ino)
@@ -1188,29 +1189,25 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	brelse(bitmap_bh);
 	return inode;
 
-iget_failed:
-	err = PTR_ERR(inode);
-	inode = NULL;
 bad_orphan:
-	ext4_warning(sb, "bad orphan inode %lu!  e2fsck was run?", ino);
-	printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
-	       bit, (unsigned long long)bitmap_bh->b_blocknr,
-	       ext4_test_bit(bit, bitmap_bh->b_data));
-	printk(KERN_WARNING "inode=%p\n", inode);
+	ext4_error(sb, "bad orphan inode %lu", ino);
+	if (bitmap_bh)
+		printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+		       bit, (unsigned long long)bitmap_bh->b_blocknr,
+		       ext4_test_bit(bit, bitmap_bh->b_data));
 	if (inode) {
-		printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
+		printk(KERN_ERR "is_bad_inode(inode)=%d\n",
 		       is_bad_inode(inode));
-		printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
+		printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n",
 		       NEXT_ORPHAN(inode));
-		printk(KERN_WARNING "max_ino=%lu\n", max_ino);
-		printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
+		printk(KERN_ERR "max_ino=%lu\n", max_ino);
+		printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink);
 		/* Avoid freeing blocks if we got a bad deleted inode */
 		if (inode->i_nlink == 0)
 			inode->i_blocks = 0;
 		iput(inode);
 	}
 	brelse(bitmap_bh);
-error:
 	return ERR_PTR(err);
 }
 
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index d884989cc83d..dad8e7bdf0a6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -336,8 +336,10 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 
 	len -= EXT4_MIN_INLINE_DATA_SIZE;
 	value = kzalloc(len, GFP_NOFS);
-	if (!value)
+	if (!value) {
+		error = -ENOMEM;
 		goto out;
+	}
 
 	error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
 				     value, len);
@@ -931,8 +933,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  struct page *page)
 {
 	int i_size_changed = 0;
+	int ret;
 
-	copied = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	if (ret < 0) {
+		unlock_page(page);
+		put_page(page);
+		return ret;
+	}
+	copied = ret;
 
 	/*
 	 * No need to use i_size_read() here, the i_size
@@ -1149,10 +1158,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	set_buffer_uptodate(dir_block);
 	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
 	if (err)
-		goto out;
+		return err;
 	set_buffer_verified(dir_block);
-out:
-	return err;
+	return ext4_mark_inode_dirty(handle, inode);
 }
 
 static int ext4_convert_inline_data_nolock(handle_t *handle,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 06bda0361e7c..1796d1bd9a1d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -51,25 +51,30 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u16 csum_lo;
-	__u16 csum_hi = 0;
 	__u32 csum;
+	__u16 dummy_csum = 0;
+	int offset = offsetof(struct ext4_inode, i_checksum_lo);
+	unsigned int csum_size = sizeof(dummy_csum);
 
-	csum_lo = le16_to_cpu(raw->i_checksum_lo);
-	raw->i_checksum_lo = 0;
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = le16_to_cpu(raw->i_checksum_hi);
-		raw->i_checksum_hi = 0;
-	}
-
-	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
-			   EXT4_INODE_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+	offset += csum_size;
+	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+			   EXT4_GOOD_OLD_INODE_SIZE - offset);
 
-	raw->i_checksum_lo = cpu_to_le16(csum_lo);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = cpu_to_le16(csum_hi);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		offset = offsetof(struct ext4_inode, i_checksum_hi);
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+				   EXT4_GOOD_OLD_INODE_SIZE,
+				   offset - EXT4_GOOD_OLD_INODE_SIZE);
+		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+					   csum_size);
+			offset += csum_size;
+		}
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+				   EXT4_INODE_SIZE(inode->i_sb) - offset);
+	}
 
 	return csum;
 }
@@ -205,9 +210,9 @@ void ext4_evict_inode(struct inode *inode)
 		 * Note that directories do not have this problem because they
 		 * don't use page cache.
 		 */
-		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
-		    inode->i_ino != EXT4_JOURNAL_INO) {
+		if (inode->i_ino != EXT4_JOURNAL_INO &&
+		    ext4_should_journal_data(inode) &&
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -1159,8 +1164,11 @@ static int ext4_write_end(struct file *file,
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto errout;
+		}
 		copied = ret;
 	} else
 		copied = block_write_end(file, mapping, pos,
@@ -1214,7 +1222,9 @@ errout:
  * set the buffer to be dirty, since in data=journalled mode we need
  * to call ext4_handle_dirty_metadata() instead.
  */
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct page *page,
+					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
@@ -1231,7 +1241,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
 					size = min(to, block_end) - start;
 
 					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
+					write_end_fn(handle, bh);
 				}
 				clear_buffer_new(bh);
 			}
@@ -1260,18 +1270,25 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode))
-		copied = ext4_write_inline_data_end(inode, pos, len,
-						    copied, page);
-	else {
-		if (copied < len) {
-			if (!PageUptodate(page))
-				copied = 0;
-			zero_new_buffers(page, from+copied, to);
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_write_inline_data_end(inode, pos, len,
+						 copied, page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			goto errout;
 		}
-
+		copied = ret;
+	} else if (unlikely(copied < len) && !PageUptodate(page)) {
+		copied = 0;
+		ext4_journalled_zero_new_buffers(handle, page, from, to);
+	} else {
+		if (unlikely(copied < len))
+			ext4_journalled_zero_new_buffers(handle, page,
+							 from + copied, to);
 		ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
-					     to, &partial, write_end_fn);
+					     from + copied, &partial,
+					     write_end_fn);
 		if (!partial)
 			SetPageUptodate(page);
 	}
@@ -1297,6 +1314,7 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
+errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -2026,7 +2044,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 {
 	struct inode *inode = mpd->inode;
 	int err;
-	ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
 	do {
@@ -2589,13 +2607,36 @@ retry:
 				done = true;
 			}
 		}
-		ext4_journal_stop(handle);
+		/*
+		 * Caution: If the handle is synchronous,
+		 * ext4_journal_stop() can wait for transaction commit
+		 * to finish which may depend on writeback of pages to
+		 * complete or on page lock to be released.  In that
+		 * case, we have to wait until after after we have
+		 * submitted all the IO, released page locks we hold,
+		 * and dropped io_end reference (for extent conversion
+		 * to be able to complete) before stopping the handle.
+		 */
+		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+			ext4_journal_stop(handle);
+			handle = NULL;
+		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
 		/* Unlock pages we didn't use */
 		mpage_release_unused_pages(&mpd, give_up_on_write);
-		/* Drop our io_end reference we got from init */
-		ext4_put_io_end(mpd.io_submit.io_end);
+		/*
+		 * Drop our io_end reference we got from init. We have
+		 * to be careful and use deferred io_end finishing if
+		 * we are still holding the transaction as we can
+		 * release the last reference to io_end which may end
+		 * up doing unwritten extent conversion.
+		 */
+		if (handle) {
+			ext4_put_io_end_defer(mpd.io_submit.io_end);
+			ext4_journal_stop(handle);
+		} else
+			ext4_put_io_end(mpd.io_submit.io_end);
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -3531,6 +3572,10 @@ static int ext4_block_truncate_page(handle_t *handle,
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
 
+	/* If we are processing an encrypted inode during orphan list handling */
+	if (ext4_encrypted_inode(inode) && !ext4_has_encryption_key(inode))
+		return 0;
+
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
 
@@ -3587,7 +3632,36 @@ int ext4_can_truncate(struct inode *inode)
 }
 
 /*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len)
+{
+	handle_t *handle;
+	loff_t size = i_size_read(inode);
+
+	WARN_ON(!mutex_is_locked(&inode->i_mutex));
+	if (offset > size || offset + len < size)
+		return 0;
+
+	if (EXT4_I(inode)->i_disksize >= size)
+		return 0;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ext4_update_i_disksize(inode, size);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
+	return 0;
+}
+
+/*
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
  *
  * @inode:  File inode
@@ -3616,7 +3690,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * Write out all dirty pages to avoid race conditions
 	 * Then release them.
 	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 		ret = filemap_write_and_wait_range(mapping, offset,
 						   offset + length - 1);
 		if (ret)
@@ -3651,17 +3725,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
 	/* Now release the pages and zero block aligned part of pages*/
-	if (last_block_offset > first_block_offset)
+	if (last_block_offset > first_block_offset) {
+		ret = ext4_update_disksize_before_punch(inode, offset, length);
+		if (ret)
+			goto out_dio;
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
-
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
+	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		credits = ext4_writepage_trans_blocks(inode);
@@ -3708,16 +3791,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	/* Now release the pages again to reduce race window */
-	if (last_block_offset > first_block_offset)
-		truncate_pagecache_range(inode, first_block_offset,
-					 last_block_offset);
-
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
@@ -4112,6 +4193,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	struct inode *inode;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
+	loff_t size;
 	int block;
 	uid_t i_uid;
 	gid_t i_gid;
@@ -4203,6 +4285,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ei->i_file_acl |=
 			((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
 	inode->i_size = ext4_isize(raw_inode);
+	if ((size = i_size_read(inode)) < 0) {
+		EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size);
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
@@ -4486,14 +4573,14 @@ static int ext4_do_update_inode(handle_t *handle,
  * Fix up interoperability with old kernels. Otherwise, old inodes get
  * re-used with the upper 16 bits of the uid/gid intact
  */
-		if (!ei->i_dtime) {
+		if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+			raw_inode->i_uid_high = 0;
+			raw_inode->i_gid_high = 0;
+		} else {
 			raw_inode->i_uid_high =
 				cpu_to_le16(high_16_bits(i_uid));
 			raw_inode->i_gid_high =
 				cpu_to_le16(high_16_bits(i_gid));
-		} else {
-			raw_inode->i_uid_high = 0;
-			raw_inode->i_gid_high = 0;
 		}
 	} else {
 		raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
@@ -4851,6 +4938,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			} else
 				ext4_wait_for_tail_page_commit(inode);
 		}
+		down_write(&EXT4_I(inode)->i_mmap_sem);
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
@@ -4858,6 +4946,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		truncate_pagecache(inode, inode->i_size);
 		if (shrink)
 			ext4_truncate(inode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
 	if (!rc) {
@@ -5075,8 +5164,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}
@@ -5109,6 +5199,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		return err;
 	if (ext4_handle_valid(handle) &&
 	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5125,8 +5217,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 						      sbi->s_want_extra_isize,
 						      iloc, handle);
 			if (ret) {
-				ext4_set_inode_state(inode,
-						     EXT4_STATE_NO_EXPAND);
 				if (mnt_count !=
 					le16_to_cpu(sbi->s_es->s_mnt_count)) {
 					ext4_warning(inode->i_sb,
@@ -5139,9 +5229,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 			}
 		}
 	}
-	if (!err)
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	return err;
+	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 
 /*
@@ -5306,6 +5394,13 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_convert_inline_data(inode);
+	if (ret)
+		goto out_ret;
+
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
@@ -5375,6 +5470,19 @@ retry_alloc:
 out_ret:
 	ret = block_page_mkwrite_return(ret);
 out:
+	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	int err;
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_fault(vma, vmf);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+
+	return err;
+}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5e872fd40e5e..bcd7c4788903 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -622,6 +622,9 @@ resizefs_out:
 		struct ext4_encryption_policy policy;
 		int err = 0;
 
+		if (!ext4_has_feature_encrypt(sb))
+			return -EOPNOTSUPP;
+
 		if (copy_from_user(&policy,
 				   (struct ext4_encryption_policy __user *)arg,
 				   sizeof(policy))) {
@@ -629,7 +632,17 @@ resizefs_out:
 			goto encryption_policy_out;
 		}
 
+		err = mnt_want_write_file(filp);
+		if (err)
+			goto encryption_policy_out;
+
+		mutex_lock(&inode->i_mutex);
+
 		err = ext4_process_policy(&policy, inode);
+
+		mutex_unlock(&inode->i_mutex);
+
+		mnt_drop_write_file(filp);
 encryption_policy_out:
 		return err;
 #else
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 61eaf74dca37..84cd77663e1f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -669,7 +669,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
 	ext4_grpblk_t min;
 	ext4_grpblk_t max;
 	ext4_grpblk_t chunk;
-	unsigned short border;
+	unsigned int border;
 
 	BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
 
@@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  * for this page; do not hold this lock when calling this routine!
  */
 
-static int ext4_mb_init_cache(struct page *page, char *incore)
+static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 {
 	ext4_group_t ngroups;
 	int blocksize;
@@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	/* allocate buffer_heads to read bitmaps */
 	if (groups_per_page > 1) {
 		i = sizeof(struct buffer_head *) * groups_per_page;
-		bh = kzalloc(i, GFP_NOFS);
+		bh = kzalloc(i, gfp);
 		if (bh == NULL) {
 			err = -ENOMEM;
 			goto out;
@@ -983,7 +983,7 @@ out:
  * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
  */
 static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
-		ext4_group_t group, struct ext4_buddy *e4b)
+		ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
 {
 	struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
 	int block, pnum, poff;
@@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 	block = group * 2;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 
 	block++;
 	pnum = block / blocks_per_page;
-	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, pnum, gfp);
 	if (!page)
 		return -ENOMEM;
 	BUG_ON(page->mapping != inode->i_mapping);
@@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
  * calling this routine!
  */
 static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 {
 
 	struct ext4_group_info *this_grp;
@@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	 * The call to ext4_mb_get_buddy_page_lock will mark the
 	 * page accessed.
 	 */
-	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp);
 	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
 		/*
 		 * somebody initialized the group
@@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 
 	page = e4b.bd_bitmap_page;
-	ret = ext4_mb_init_cache(page, NULL);
+	ret = ext4_mb_init_cache(page, NULL, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	}
 	/* init buddy cache */
 	page = e4b.bd_buddy_page;
-	ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+	ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
 	if (ret)
 		goto err;
 	if (!PageUptodate(page)) {
@@ -1109,8 +1109,8 @@ err:
  * calling this routine!
  */
 static noinline_for_stack int
-ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
-					struct ext4_buddy *e4b)
+ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
+		       struct ext4_buddy *e4b, gfp_t gfp)
 {
 	int blocks_per_page;
 	int block;
@@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 		 * we need full data about the group
 		 * to make a good selection
 		 */
-		ret = ext4_mb_init_group(sb, group);
+		ret = ext4_mb_init_group(sb, group, gfp);
 		if (ret)
 			return ret;
 	}
@@ -1168,11 +1168,11 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 			 * wait for it to initialize.
 			 */
 			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, NULL);
+				ret = ext4_mb_init_cache(page, NULL, gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1204,11 +1204,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 	if (page == NULL || !PageUptodate(page)) {
 		if (page)
 			page_cache_release(page);
-		page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+		page = find_or_create_page(inode->i_mapping, pnum, gfp);
 		if (page) {
 			BUG_ON(page->mapping != inode->i_mapping);
 			if (!PageUptodate(page)) {
-				ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+				ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+							 gfp);
 				if (ret) {
 					unlock_page(page);
 					goto err;
@@ -1247,6 +1248,12 @@ err:
 	return ret;
 }
 
+static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+			      struct ext4_buddy *e4b)
+{
+	return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS);
+}
+
 static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
 	if (e4b->bd_bitmap_page)
@@ -1259,6 +1266,7 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 {
 	int order = 1;
+	int bb_incr = 1 << (e4b->bd_blkbits - 1);
 	void *bb;
 
 	BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
@@ -1271,7 +1279,8 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 			/* this block is part of buddy of order 'order' */
 			return order;
 		}
-		bb += 1 << (e4b->bd_blkbits - order);
+		bb += bb_incr;
+		bb_incr >>= 1;
 		order++;
 	}
 	return 0;
@@ -2045,7 +2054,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		int ret = ext4_mb_init_group(ac->ac_sb, group);
+		int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -2278,7 +2287,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	struct ext4_group_info *grinfo;
 	struct sg {
 		struct ext4_group_info info;
-		ext4_grpblk_t counters[16];
+		ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
 	} sg;
 
 	group--;
@@ -2576,7 +2585,7 @@ int ext4_mb_init(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	unsigned i, j;
-	unsigned offset;
+	unsigned offset, offset_incr;
 	unsigned max;
 	int ret;
 
@@ -2605,11 +2614,13 @@ int ext4_mb_init(struct super_block *sb)
 
 	i = 1;
 	offset = 0;
+	offset_incr = 1 << (sb->s_blocksize_bits - 1);
 	max = sb->s_blocksize << 2;
 	do {
 		sbi->s_mb_offsets[i] = offset;
 		sbi->s_mb_maxs[i] = max;
-		offset += 1 << (sb->s_blocksize_bits - i);
+		offset += offset_incr;
+		offset_incr = offset_incr >> 1;
 		max = max >> 1;
 		i++;
 	} while (i <= sb->s_blocksize_bits + 1);
@@ -2928,7 +2939,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error
-		 * Fix the bitmap and repeat the block allocation
+		 * Fix the bitmap and return EFSCORRUPTED
 		 * We leak some of the blocks here.
 		 */
 		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
@@ -2937,7 +2948,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 		if (!err)
-			err = -EAGAIN;
+			err = -EFSCORRUPTED;
 		goto out_err;
 	}
 
@@ -3109,6 +3120,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ar->pright && start + size - 1 >= ar->lright)
 		size -= start + size - ar->lright;
 
+	/*
+	 * Trim allocation request for filesystems with artificially small
+	 * groups.
+	 */
+	if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+		size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
 	end = start + size;
 
 	/* check we don't cross already preallocated blocks */
@@ -4502,18 +4520,7 @@ repeat:
 	}
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
 		*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
-		if (*errp == -EAGAIN) {
-			/*
-			 * drop the reference that we took
-			 * in ext4_mb_use_best_found
-			 */
-			ext4_mb_release_context(ac);
-			ac->ac_b_ex.fe_group = 0;
-			ac->ac_b_ex.fe_start = 0;
-			ac->ac_b_ex.fe_len = 0;
-			ac->ac_status = AC_STATUS_CONTINUE;
-			goto repeat;
-		} else if (*errp) {
+		if (*errp) {
 			ext4_discard_allocated_blocks(ac);
 			goto errout;
 		} else {
@@ -4815,7 +4822,9 @@ do_more:
 #endif
 	trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
 
-	err = ext4_mb_load_buddy(sb, block_group, &e4b);
+	/* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+	err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+				     GFP_NOFS|__GFP_NOFAIL);
 	if (err)
 		goto error_return;
 
@@ -5217,7 +5226,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		grp = ext4_get_group_info(sb, group);
 		/* We only do this if the grp has never been initialized */
 		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-			ret = ext4_mb_init_group(sb, group);
+			ret = ext4_mb_init_group(sb, group, GFP_NOFS);
 			if (ret)
 				break;
 		}
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index e032a0423e35..05048fcfd602 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -60,10 +60,10 @@ ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
 {
 	if (first < second) {
 		down_write(&EXT4_I(first)->i_data_sem);
-		down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
+		down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER);
 	} else {
 		down_write(&EXT4_I(second)->i_data_sem);
-		down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
+		down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
 
 	}
 }
@@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 	if (PageUptodate(page))
 		return 0;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
 
@@ -390,6 +390,7 @@ data_copy:
 		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
 		if (*err < 0)
 			break;
+		bh = bh->b_this_page;
 	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
@@ -483,6 +484,13 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EBUSY;
 	}
 
+	if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
+		ext4_debug("ext4 move extent: The argument files should "
+			"not be quota files [ino:orig %lu, donor %lu]\n",
+			orig_inode->i_ino, donor_inode->i_ino);
+		return -EBUSY;
+	}
+
 	/* Ext4 move extent supports only extent based file */
 	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
 		ext4_debug("ext4 move extent: orig file is not extents "
@@ -590,6 +598,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		return -EOPNOTSUPP;
 	}
 
+	if (ext4_encrypted_inode(orig_inode) ||
+	    ext4_encrypted_inode(donor_inode)) {
+		ext4_msg(orig_inode->i_sb, KERN_ERR,
+			 "Online defrag not supported for encrypted files");
+		return -EOPNOTSUPP;
+	}
+
 	/* Protect orig and donor inodes against a truncate */
 	lock_two_nondirectories(orig_inode, donor_inode);
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a969ab39f302..1d007e853f5c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -420,15 +420,14 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	__u32 csum;
-	__le32 save_csum;
 	int size;
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct dx_tail, dt_checksum);
 
 	size = count_offset + (count * sizeof(struct dx_entry));
-	save_csum = t->dt_checksum;
-	t->dt_checksum = 0;
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
-	csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail));
-	t->dt_checksum = save_csum;
+	csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
 
 	return cpu_to_le32(csum);
 }
@@ -1244,9 +1243,9 @@ static inline int ext4_match(struct ext4_filename *fname,
 	if (unlikely(!name)) {
 		if (fname->usr_fname->name[0] == '_') {
 			int ret;
-			if (de->name_len < 16)
+			if (de->name_len <= 32)
 				return 0;
-			ret = memcmp(de->name + de->name_len - 16,
+			ret = memcmp(de->name + ((de->name_len - 17) & ~15),
 				     fname->crypto_buf.name + 8, 16);
 			return (ret == 0) ? 1 : 0;
 		}
@@ -1558,6 +1557,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -2018,33 +2035,31 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 	frame->entries = entries;
 	frame->at = entries;
 	frame->bh = bh;
-	bh = bh2;
 
 	retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
 	if (retval)
 		goto out_frames;	
-	retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+	retval = ext4_handle_dirty_dirent_node(handle, dir, bh2);
 	if (retval)
 		goto out_frames;	
 
-	de = do_split(handle,dir, &bh, frame, &fname->hinfo);
+	de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
 	if (IS_ERR(de)) {
 		retval = PTR_ERR(de);
 		goto out_frames;
 	}
-	dx_release(frames);
 
-	retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
-	brelse(bh);
-	return retval;
+	retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2);
 out_frames:
 	/*
 	 * Even if the block split failed, we have to properly write
 	 * out all the changes we did so far. Otherwise we can end up
 	 * with corrupted filesystem.
 	 */
-	ext4_mark_inode_dirty(handle, dir);
+	if (retval)
+		ext4_mark_inode_dirty(handle, dir);
 	dx_release(frames);
+	brelse(bh2);
 	return retval;
 }
 
@@ -2809,7 +2824,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 			 * list entries can cause panics at unmount time.
 			 */
 			mutex_lock(&sbi->s_orphan_lock);
-			list_del(&EXT4_I(inode)->i_orphan);
+			list_del_init(&EXT4_I(inode)->i_orphan);
 			mutex_unlock(&sbi->s_orphan_lock);
 		}
 	}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 17fbe3882b8e..6ca56f5f72b5 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/backing-dev.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -485,9 +486,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) &&
 	    nr_to_submit) {
-		data_page = ext4_encrypt(inode, page);
+		gfp_t gfp_flags = GFP_NOFS;
+
+	retry_encrypt:
+		data_page = ext4_encrypt(inode, page, gfp_flags);
 		if (IS_ERR(data_page)) {
 			ret = PTR_ERR(data_page);
+			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
+				if (io->io_bio) {
+					ext4_io_submit(io);
+					congestion_wait(BLK_RW_ASYNC, HZ/50);
+				}
+				gfp_flags |= __GFP_NOFAIL;
+				goto retry_encrypt;
+			}
 			data_page = NULL;
 			goto out;
 		}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 5dc5e95063de..bc7642f57dc8 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -279,7 +279,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 
 			if (ext4_encrypted_inode(inode) &&
 			    S_ISREG(inode->i_mode)) {
-				ctx = ext4_get_crypto_ctx(inode);
+				ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 			}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 34038e3598d5..74516efd874c 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1926,7 +1926,8 @@ retry:
 			n_desc_blocks = o_desc_blocks +
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
-			n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
+			n_blocks_count = (ext4_fsblk_t)n_group *
+				EXT4_BLOCKS_PER_GROUP(sb);
 			n_group--; /* set to last group number */
 		}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c9ab67da6e5a..68345a9e59b8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -793,6 +793,7 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	int aborted = 0;
 	int i, err;
 
 	ext4_unregister_li_request(sb);
@@ -802,9 +803,10 @@ static void ext4_put_super(struct super_block *sb)
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
+		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if (err < 0)
+		if ((err < 0) && !aborted)
 			ext4_abort(sb, "Couldn't clean up the journal");
 	}
 
@@ -816,7 +818,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
 
-	if (!(sb->s_flags & MS_RDONLY)) {
+	if (!(sb->s_flags & MS_RDONLY) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
@@ -958,6 +960,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
+	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 }
 
@@ -1292,9 +1295,9 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
 		return -1;
 	}
 	if (ext4_has_feature_quota(sb)) {
-		ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
-			 "when QUOTA feature is enabled");
-		return -1;
+		ext4_msg(sb, KERN_INFO, "Journaled quota options "
+			 "ignored when QUOTA feature is enabled");
+		return 1;
 	}
 	qname = match_strdup(args);
 	if (!qname) {
@@ -1657,10 +1660,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			return -1;
 		}
 		if (ext4_has_feature_quota(sb)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Cannot set journaled quota options "
+			ext4_msg(sb, KERN_INFO,
+				 "Quota format mount options ignored "
 				 "when QUOTA feature is enabled");
-			return -1;
+			return 1;
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
@@ -1721,11 +1724,11 @@ static int parse_options(char *options, struct super_block *sb,
 #ifdef CONFIG_QUOTA
 	if (ext4_has_feature_quota(sb) &&
 	    (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
-		ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
-			 "feature is enabled");
-		return 0;
-	}
-	if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+		ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota "
+			 "mount options ignored.");
+		clear_opt(sb, USRQUOTA);
+		clear_opt(sb, GRPQUOTA);
+	} else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
 		if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
 			clear_opt(sb, USRQUOTA);
 
@@ -2029,23 +2032,25 @@ failed:
 static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 				   struct ext4_group_desc *gdp)
 {
-	int offset;
+	int offset = offsetof(struct ext4_group_desc, bg_checksum);
 	__u16 crc = 0;
 	__le32 le_group = cpu_to_le32(block_group);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (ext4_has_metadata_csum(sbi->s_sb)) {
 		/* Use new metadata_csum algorithm */
-		__le16 save_csum;
 		__u32 csum32;
+		__u16 dummy_csum = 0;
 
-		save_csum = gdp->bg_checksum;
-		gdp->bg_checksum = 0;
 		csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
 				     sizeof(le_group));
-		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
-				     sbi->s_desc_size);
-		gdp->bg_checksum = save_csum;
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
+				     sizeof(dummy_csum));
+		offset += sizeof(dummy_csum);
+		if (offset < sbi->s_desc_size)
+			csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
+					     sbi->s_desc_size - offset);
 
 		crc = csum32 & 0xFFFF;
 		goto out;
@@ -2055,8 +2060,6 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 	if (!ext4_has_feature_gdt_csum(sb))
 		return 0;
 
-	offset = offsetof(struct ext4_group_desc, bg_checksum);
-
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
 	crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
 	crc = crc16(crc, (__u8 *)gdp, offset);
@@ -2092,6 +2095,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
 
 /* Called at mount-time, super-block is locked */
 static int ext4_check_descriptors(struct super_block *sb,
+				  ext4_fsblk_t sb_block,
 				  ext4_group_t *first_not_zeroed)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2122,6 +2126,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			grp = i;
 
 		block_bitmap = ext4_block_bitmap(sb, gdp);
+		if (block_bitmap == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Block bitmap for group %u overlaps "
+				 "superblock", i);
+		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
@@ -2129,6 +2138,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			return 0;
 		}
 		inode_bitmap = ext4_inode_bitmap(sb, gdp);
+		if (inode_bitmap == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode bitmap for group %u overlaps "
+				 "superblock", i);
+		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
@@ -2136,6 +2150,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			return 0;
 		}
 		inode_table = ext4_inode_table(sb, gdp);
+		if (inode_table == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode table for group %u overlaps "
+				 "superblock", i);
+		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2239,6 +2258,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	while (es->s_last_orphan) {
 		struct inode *inode;
 
+		/*
+		 * We may have encountered an error during cleanup; if
+		 * so, skip the rest.
+		 */
+		if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+			jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+			es->s_last_orphan = 0;
+			break;
+		}
+
 		inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
 		if (IS_ERR(inode)) {
 			es->s_last_orphan = 0;
@@ -3010,10 +3039,15 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp,
 			ext4_set_bit(s++, buf);
 			count++;
 		}
-		for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) {
-			ext4_set_bit(EXT4_B2C(sbi, s++), buf);
-			count++;
+		j = ext4_bg_num_gdb(sb, grp);
+		if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) {
+			ext4_error(sb, "Invalid number of block group "
+				   "descriptor blocks: %d", j);
+			j = EXT4_BLOCKS_PER_GROUP(sb) - s;
 		}
+		count += j;
+		for (; j > 0; j--)
+			ext4_set_bit(EXT4_B2C(sbi, s++), buf);
 	}
 	if (!count)
 		return 0;
@@ -3103,7 +3137,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
-	struct ext4_sb_info *sbi;
+	struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	ext4_fsblk_t block;
 	ext4_fsblk_t sb_block = get_sb_block(&data);
 	ext4_fsblk_t logical_sb_block;
@@ -3122,16 +3156,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	ext4_group_t first_not_zeroed;
 
-	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
-	if (!sbi)
-		goto out_free_orig;
+	if ((data && !orig_data) || !sbi)
+		goto out_free_base;
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
-	if (!sbi->s_blockgroup_lock) {
-		kfree(sbi);
-		goto out_free_orig;
-	}
+	if (!sbi->s_blockgroup_lock)
+		goto out_free_base;
+
 	sb->s_fs_info = sbi;
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
@@ -3277,11 +3309,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
-	if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
-			   &journal_devnum, &journal_ioprio, 0)) {
-		ext4_msg(sb, KERN_WARNING,
-			 "failed to parse options in superblock: %s",
-			 sbi->s_es->s_mount_opts);
+	if (sbi->s_es->s_mount_opts[0]) {
+		char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
+					      sizeof(sbi->s_es->s_mount_opts),
+					      GFP_KERNEL);
+		if (!s_mount_opts)
+			goto failed_mount;
+		if (!parse_options(s_mount_opts, sb, &journal_devnum,
+				   &journal_ioprio, 0)) {
+			ext4_msg(sb, KERN_WARNING,
+				 "failed to parse options in superblock: %s",
+				 s_mount_opts);
+		}
+		kfree(s_mount_opts);
 	}
 	sbi->s_def_mount_opt = sbi->s_mount_opt;
 	if (!parse_options((char *) data, sb, &journal_devnum,
@@ -3307,6 +3347,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and dax");
 			goto failed_mount;
 		}
+		if (ext4_has_feature_encrypt(sb)) {
+			ext4_msg(sb, KERN_WARNING,
+				 "encrypted files will use data=ordered "
+				 "instead of data journaling mode");
+		}
 		if (test_opt(sb, DELALLOC))
 			clear_opt(sb, DELALLOC);
 	} else {
@@ -3367,7 +3412,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
 	    blocksize > EXT4_MAX_BLOCK_SIZE) {
 		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d", blocksize);
+		       "Unsupported filesystem blocksize %d (%d log_block_size)",
+			 blocksize, le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+	if (le32_to_cpu(es->s_log_block_size) >
+	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log block size: %u",
+			 le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+
+	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Number of reserved GDT blocks insanely large: %d",
+			 le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
 		goto failed_mount;
 	}
 
@@ -3454,12 +3514,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
 	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
-	if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
-		goto cantfind_ext4;
 
 	sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
 	if (sbi->s_inodes_per_block == 0)
 		goto cantfind_ext4;
+	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+	    sbi->s_inodes_per_group > blocksize * 8) {
+		ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
+			 sbi->s_blocks_per_group);
+		goto failed_mount;
+	}
 	sbi->s_itb_per_group = sbi->s_inodes_per_group /
 					sbi->s_inodes_per_block;
 	sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
@@ -3499,6 +3563,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "block size (%d)", clustersize, blocksize);
 			goto failed_mount;
 		}
+		if (le32_to_cpu(es->s_log_cluster_size) >
+		    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Invalid log cluster size: %u",
+				 le32_to_cpu(es->s_log_cluster_size));
+			goto failed_mount;
+		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
 		sbi->s_clusters_per_group =
@@ -3535,13 +3606,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sbi->s_cluster_ratio = clustersize / blocksize;
 
-	if (sbi->s_inodes_per_group > blocksize * 8) {
-		ext4_msg(sb, KERN_ERR,
-		       "#inodes per group too big: %lu",
-		       sbi->s_inodes_per_group);
-		goto failed_mount;
-	}
-
 	/* Do we have standard group size of clustersize * 8 blocks ? */
 	if (sbi->s_blocks_per_group == clustersize << 3)
 		set_opt2(sb, STD_GROUP_SIZE);
@@ -3601,6 +3665,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
+	if (ext4_has_feature_meta_bg(sb)) {
+		if (le32_to_cpu(es->s_first_meta_bg) > db_count) {
+			ext4_msg(sb, KERN_WARNING,
+				 "first meta block group too large: %u "
+				 "(group descriptor block count %u)",
+				 le32_to_cpu(es->s_first_meta_bg), db_count);
+			goto failed_mount;
+		}
+	}
 	sbi->s_group_desc = ext4_kvmalloc(db_count *
 					  sizeof(struct buffer_head *),
 					  GFP_KERNEL);
@@ -3622,7 +3695,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		ret = -EFSCORRUPTED;
 		goto failed_mount2;
@@ -3675,7 +3748,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * root first: it may be modified in the journal!
 	 */
 	if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
-		if (ext4_load_journal(sb, es, journal_devnum))
+		err = ext4_load_journal(sb, es, journal_devnum);
+		if (err)
 			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 		   ext4_has_feature_journal_needs_recovery(sb)) {
@@ -3945,7 +4019,9 @@ no_journal:
 
 	if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
 		ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
-			 "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
+			 "Opts: %.*s%s%s", descr,
+			 (int) sizeof(sbi->s_es->s_mount_opts),
+			 sbi->s_es->s_mount_opts,
 			 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
 
 	if (es->s_error_count)
@@ -4015,8 +4091,8 @@ failed_mount:
 out_fail:
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
+out_free_base:
 	kfree(sbi);
-out_free_orig:
 	kfree(orig_data);
 	return err ? err : ret;
 }
@@ -4936,6 +5012,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
 					EXT4_SB(sb)->s_jquota_fmt, type);
 }
 
+static void lockdep_set_quota_inode(struct inode *inode, int subclass)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	/* The first argument of lockdep_set_subclass has to be
+	 * *exactly* the same as the argument to init_rwsem() --- in
+	 * this case, in init_once() --- or lockdep gets unhappy
+	 * because the name of the lock is set using the
+	 * stringification of the argument to init_rwsem().
+	 */
+	(void) ei;	/* shut up clang warning if !CONFIG_LOCKDEP */
+	lockdep_set_subclass(&ei->i_data_sem, subclass);
+}
+
 /*
  * Standard function to be called on quota_on
  */
@@ -4975,8 +5065,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			return err;
 	}
-
-	return dquot_quota_on(sb, type, format_id, path);
+	lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		lockdep_set_quota_inode(path->dentry->d_inode,
+					     I_DATA_SEM_NORMAL);
+	return err;
 }
 
 static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
@@ -5002,8 +5096,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 
 	/* Don't account quota for quota files to avoid recursion */
 	qf_inode->i_flags |= S_NOQUOTA;
+	lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
 	err = dquot_enable(qf_inode, type, format_id, flags);
 	iput(qf_inode);
+	if (err)
+		lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
 
 	return err;
 }
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 1420a3c614af..c2ee23acf359 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a,
 	int ret;
 
 	ret = kstrtoull(skip_spaces(buf), 0, &val);
-	if (!ret || val >= clusters)
+	if (ret || val >= clusters)
 		return -EINVAL;
 
 	atomic64_set(&sbi->s_resv_clusters, val);
@@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = {
 EXT4_ATTR_FEATURE(lazy_itable_init);
 EXT4_ATTR_FEATURE(batched_discard);
 EXT4_ATTR_FEATURE(meta_bg_resize);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 EXT4_ATTR_FEATURE(encryption);
+#endif
 EXT4_ATTR_FEATURE(metadata_csum_seed);
 
 static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(lazy_itable_init),
 	ATTR_LIST(batched_discard),
 	ATTR_LIST(meta_bg_resize),
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 	ATTR_LIST(encryption),
+#endif
 	ATTR_LIST(metadata_csum_seed),
 	NULL,
 };
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 011ba6670d99..c70d06a383e2 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -10,8 +10,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 }
 
 /*
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 6b6b3e751f8c..7c23363ecf19 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -123,17 +123,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	__u32 csum;
-	__le32 save_csum;
 	__le64 dsk_block_nr = cpu_to_le64(block_nr);
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct ext4_xattr_header, h_checksum);
 
-	save_csum = hdr->h_checksum;
-	hdr->h_checksum = 0;
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
 			   sizeof(dsk_block_nr));
-	csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
-			   EXT4_BLOCK_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
+	offset += sizeof(dummy_csum);
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
+			   EXT4_BLOCK_SIZE(inode->i_sb) - offset);
 
-	hdr->h_checksum = save_csum;
 	return cpu_to_le32(csum);
 }
 
@@ -232,6 +233,27 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 	return error;
 }
 
+static int
+__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
+			 void *end, const char *function, unsigned int line)
+{
+	struct ext4_xattr_entry *entry = IFIRST(header);
+	int error = -EFSCORRUPTED;
+
+	if (((void *) header >= end) ||
+	    (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
+		goto errout;
+	error = ext4_xattr_check_names(entry, end, entry);
+errout:
+	if (error)
+		__ext4_error_inode(inode, function, line, 0,
+				   "corrupted in-inode xattr");
+	return error;
+}
+
+#define xattr_check_inode(inode, header, end) \
+	__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
+
 static inline int
 ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
 {
@@ -343,7 +365,7 @@ 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, entry);
+	error = xattr_check_inode(inode, header, end);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -474,7 +496,7 @@ 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, IFIRST(header));
+	error = xattr_check_inode(inode, header, end);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -990,8 +1012,7 @@ 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,
-					       IFIRST(header));
+		error = xattr_check_inode(inode, header, is->s.end);
 		if (error)
 			return error;
 		/* Find the named attribute. */
@@ -1264,15 +1285,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	size_t min_offs, free;
 	int total_ino;
 	void *base, *start, *end;
-	int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+	int error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+	int isize_diff;	/* How much do we need to grow i_extra_isize */
 
 	down_write(&EXT4_I(inode)->xattr_sem);
+	/*
+	 * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+	 */
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 retry:
-	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
-		up_write(&EXT4_I(inode)->xattr_sem);
-		return 0;
-	}
+	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+		goto out;
 
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
@@ -1288,8 +1313,12 @@ retry:
 	last = entry;
 	total_ino = sizeof(struct ext4_xattr_ibody_header);
 
+	error = xattr_check_inode(inode, header, end);
+	if (error)
+		goto cleanup;
+
 	free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
-	if (free >= new_extra_isize) {
+	if (free >= isize_diff) {
 		entry = IFIRST(header);
 		ext4_xattr_shift_entries(entry,	EXT4_I(inode)->i_extra_isize
 				- new_extra_isize, (void *)raw_inode +
@@ -1297,8 +1326,7 @@ retry:
 				(void *)header, total_ino,
 				inode->i_sb->s_blocksize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
-		error = 0;
-		goto cleanup;
+		goto out;
 	}
 
 	/*
@@ -1321,7 +1349,7 @@ retry:
 		end = bh->b_data + bh->b_size;
 		min_offs = end - base;
 		free = ext4_xattr_free_space(first, &min_offs, base, NULL);
-		if (free < new_extra_isize) {
+		if (free < isize_diff) {
 			if (!tried_min_extra_isize && s_min_extra_isize) {
 				tried_min_extra_isize++;
 				new_extra_isize = s_min_extra_isize;
@@ -1335,7 +1363,7 @@ retry:
 		free = inode->i_sb->s_blocksize;
 	}
 
-	while (new_extra_isize > 0) {
+	while (isize_diff > 0) {
 		size_t offs, size, entry_size;
 		struct ext4_xattr_entry *small_entry = NULL;
 		struct ext4_xattr_info i = {
@@ -1366,7 +1394,7 @@ retry:
 			EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
 					EXT4_XATTR_LEN(last->e_name_len);
 			if (total_size <= free && total_size < min_total_size) {
-				if (total_size < new_extra_isize) {
+				if (total_size < isize_diff) {
 					small_entry = last;
 				} else {
 					entry = last;
@@ -1421,22 +1449,22 @@ retry:
 		error = ext4_xattr_ibody_set(handle, inode, &i, is);
 		if (error)
 			goto cleanup;
+		total_ino -= entry_size;
 
 		entry = IFIRST(header);
-		if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
-			shift_bytes = new_extra_isize;
+		if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+			shift_bytes = isize_diff;
 		else
-			shift_bytes = entry_size + size;
+			shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
 		/* Adjust the offsets and shift the remaining entries ahead */
-		ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
-			shift_bytes, (void *)raw_inode +
-			EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
-			(void *)header, total_ino - entry_size,
-			inode->i_sb->s_blocksize);
+		ext4_xattr_shift_entries(entry, -shift_bytes,
+			(void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+			EXT4_I(inode)->i_extra_isize + shift_bytes,
+			(void *)header, total_ino, inode->i_sb->s_blocksize);
 
-		extra_isize += shift_bytes;
-		new_extra_isize -= shift_bytes;
-		EXT4_I(inode)->i_extra_isize = extra_isize;
+		isize_diff -= shift_bytes;
+		EXT4_I(inode)->i_extra_isize += shift_bytes;
+		header = IHDR(inode, raw_inode);
 
 		i.name = b_entry_name;
 		i.value = buffer;
@@ -1458,6 +1486,8 @@ retry:
 		kfree(bs);
 	}
 	brelse(bh);
+out:
+	ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
 	up_write(&EXT4_I(inode)->xattr_sem);
 	return 0;
 
@@ -1469,6 +1499,10 @@ cleanup:
 	kfree(is);
 	kfree(bs);
 	brelse(bh);
+	/*
+	 * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+	 * size expansion failed.
+	 */
 	up_write(&EXT4_I(inode)->xattr_sem);
 	return error;
 }
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index c8f25f7241f0..83dcf7bfd7b8 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -213,13 +213,11 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl) {
-			error = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (error < 0)
+		if (acl && !ipage) {
+			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (error)
 				return error;
 			set_acl_inode(fi, inode->i_mode);
-			if (error == 0)
-				acl = NULL;
 		}
 		break;
 
diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c
index ab377d496a39..38349ed5ea51 100644
--- a/fs/f2fs/crypto_fname.c
+++ b/fs/f2fs/crypto_fname.c
@@ -333,7 +333,7 @@ int f2fs_fname_disk_to_usr(struct inode *inode,
 		memset(buf + 4, 0, 4);
 	} else
 		memset(buf, 0, 8);
-	memcpy(buf + 8, iname->name + iname->len - 16, 16);
+	memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
 	oname->name[0] = '_';
 	ret = digest_encode(buf, 24, oname->name + 1);
 	oname->len = ret + 1;
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
index 5de2d866a25c..18595d7a0efc 100644
--- a/fs/f2fs/crypto_key.c
+++ b/fs/f2fs/crypto_key.c
@@ -92,7 +92,6 @@ static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
 	if (!ci)
 		return;
 
-	key_put(ci->ci_keyring_key);
 	crypto_free_ablkcipher(ci->ci_ctfm);
 	kmem_cache_free(f2fs_crypt_info_cachep, ci);
 }
@@ -113,7 +112,7 @@ void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci)
 	f2fs_free_crypt_info(ci);
 }
 
-int _f2fs_get_encryption_info(struct inode *inode)
+int f2fs_get_encryption_info(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_crypt_info *crypt_info;
@@ -129,18 +128,12 @@ int _f2fs_get_encryption_info(struct inode *inode)
 	char mode;
 	int res;
 
+	if (fi->i_crypt_info)
+		return 0;
+
 	res = f2fs_crypto_initialize();
 	if (res)
 		return res;
-retry:
-	crypt_info = ACCESS_ONCE(fi->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		f2fs_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
 
 	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
 				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
@@ -159,7 +152,6 @@ retry:
 	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
 	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
 	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
 	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
 				sizeof(crypt_info->ci_master_key));
 	if (S_ISREG(inode->i_mode))
@@ -197,7 +189,6 @@ retry:
 		keyring_key = NULL;
 		goto out;
 	}
-	crypt_info->ci_keyring_key = keyring_key;
 	BUG_ON(keyring_key->type != &key_type_logon);
 	ukp = user_key_payload(keyring_key);
 	if (ukp->datalen != sizeof(struct f2fs_encryption_key)) {
@@ -230,17 +221,12 @@ retry:
 	if (res)
 		goto out;
 
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) {
-		f2fs_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
+	if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) == NULL)
+		crypt_info = NULL;
 out:
 	if (res == -ENOKEY && !S_ISREG(inode->i_mode))
 		res = 0;
-
+	key_put(keyring_key);
 	f2fs_free_crypt_info(crypt_info);
 	memzero_explicit(raw_key, sizeof(raw_key));
 	return res;
diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c
index d4a96af513c2..884f3f0fe29d 100644
--- a/fs/f2fs/crypto_policy.c
+++ b/fs/f2fs/crypto_policy.c
@@ -89,6 +89,9 @@ static int f2fs_create_encryption_context_from_policy(
 int f2fs_process_policy(const struct f2fs_encryption_policy *policy,
 			struct inode *inode)
 {
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
 	if (policy->version != 0)
 		return -EINVAL;
 
@@ -138,20 +141,38 @@ int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
 int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
 						struct inode *child)
 {
-	struct f2fs_crypt_info *parent_ci, *child_ci;
+	const struct f2fs_crypt_info *parent_ci, *child_ci;
+	struct f2fs_encryption_context parent_ctx, child_ctx;
 	int res;
 
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		BUG_ON(1);
-	}
+	/* No restrictions on file types which are never encrypted */
+	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+	    !S_ISLNK(child->i_mode))
+		return 1;
 
-	/* no restrictions if the parent directory is not encrypted */
+	/* No restrictions if the parent directory is unencrypted */
 	if (!f2fs_encrypted_inode(parent))
 		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
+
+	/* Encrypted directories must not contain unencrypted files */
 	if (!f2fs_encrypted_inode(child))
 		return 0;
+
+	/*
+	 * Both parent and child are encrypted, so verify they use the same
+	 * encryption policy.  Compare the fscrypt_info structs if the keys are
+	 * available, otherwise retrieve and compare the fscrypt_contexts.
+	 *
+	 * Note that the fscrypt_context retrieval will be required frequently
+	 * when accessing an encrypted directory tree without the key.
+	 * Performance-wise this is not a big deal because we already don't
+	 * really optimize for file access without the key (to the extent that
+	 * such access is even possible), given that any attempted access
+	 * already causes a fscrypt_context retrieval and keyring search.
+	 *
+	 * In any case, if an unexpected error occurs, fall back to "forbidden".
+	 */
+
 	res = f2fs_get_encryption_info(parent);
 	if (res)
 		return 0;
@@ -160,17 +181,35 @@ int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
 		return 0;
 	parent_ci = F2FS_I(parent)->i_crypt_info;
 	child_ci = F2FS_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
+	if (parent_ci && child_ci) {
+		return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+			      F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+			(parent_ci->ci_filename_mode ==
+			 child_ci->ci_filename_mode) &&
+			(parent_ci->ci_flags == child_ci->ci_flags);
+	}
+
+	res = f2fs_getxattr(parent, F2FS_XATTR_INDEX_ENCRYPTION,
+			    F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+			    &parent_ctx, sizeof(parent_ctx), NULL);
+	if (res != sizeof(parent_ctx))
+		return 0;
+
+	res = f2fs_getxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
+			    F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+			    &child_ctx, sizeof(child_ctx), NULL);
+	if (res != sizeof(child_ctx))
 		return 0;
 
-	return (memcmp(parent_ci->ci_master_key,
-			child_ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
+	return memcmp(parent_ctx.master_key_descriptor,
+		      child_ctx.master_key_descriptor,
+		      F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ctx.contents_encryption_mode ==
+		 child_ctx.contents_encryption_mode) &&
+		(parent_ctx.filenames_encryption_mode ==
+		 child_ctx.filenames_encryption_mode) &&
+		(parent_ctx.flags == child_ctx.flags);
 }
 
 /**
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 478e5d54154f..24d6a51b48d1 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -352,6 +352,7 @@ static int stat_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations stat_fops = {
+	.owner = THIS_MODULE,
 	.open = stat_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 7c1678ba8f92..60972a559685 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -124,19 +124,29 @@ struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
 
 		de = &d->dentry[bit_pos];
 
-		/* encrypted case */
+		if (de->hash_code != namehash)
+			goto not_match;
+
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
 
-		/* show encrypted name */
-		if (fname->hash) {
-			if (de->hash_code == fname->hash)
-				goto found;
-		} else if (de_name.len == name->len &&
-			de->hash_code == namehash &&
-			!memcmp(de_name.name, name->name, name->len))
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+		if (unlikely(!name->name)) {
+			if (fname->usr_fname->name[0] == '_') {
+				if (de_name.len > 32 &&
+					!memcmp(de_name.name + ((de_name.len - 17) & ~15),
+						fname->crypto_buf.name + 8, 16))
+					goto found;
+				goto not_match;
+			}
+			name->name = fname->crypto_buf.name;
+			name->len = fname->crypto_buf.len;
+		}
+#endif
+		if (de_name.len == name->len &&
+				!memcmp(de_name.name, name->name, name->len))
 			goto found;
-
+not_match:
 		if (max_slots && max_len > *max_slots)
 			*max_slots = max_len;
 		max_len = 0;
@@ -170,7 +180,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	int max_slots;
 	f2fs_hash_t namehash;
 
-	namehash = f2fs_dentry_hash(&name);
+	namehash = f2fs_dentry_hash(&name, fname);
 
 	f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
 
@@ -547,7 +557,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 
 	level = 0;
 	slots = GET_DENTRY_SLOTS(new_name.len);
-	dentry_hash = f2fs_dentry_hash(&new_name);
+	dentry_hash = f2fs_dentry_hash(&new_name, NULL);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9db5500d63d9..2871576fbca4 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1722,7 +1722,8 @@ void f2fs_msg(struct super_block *, const char *, const char *, ...);
 /*
  * hash.c
  */
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+				struct f2fs_filename *fname);
 
 /*
  * node.c
@@ -2149,7 +2150,6 @@ void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *);
 
 /* crypto_key.c */
 void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *);
-int _f2fs_get_encryption_info(struct inode *inode);
 
 /* crypto_fname.c */
 bool f2fs_valid_filenames_enc_mode(uint32_t);
@@ -2170,18 +2170,7 @@ void f2fs_exit_crypto(void);
 
 int f2fs_has_encryption_key(struct inode *);
 
-static inline int f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return _f2fs_get_encryption_info(inode);
-	return 0;
-}
+int f2fs_get_encryption_info(struct inode *inode);
 
 void f2fs_fname_crypto_free_buffer(struct f2fs_str *);
 int f2fs_fname_setup_filename(struct inode *, const struct qstr *,
diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h
index c2c1c2b63b25..f113f1a1e8c1 100644
--- a/fs/f2fs/f2fs_crypto.h
+++ b/fs/f2fs/f2fs_crypto.h
@@ -79,7 +79,6 @@ struct f2fs_crypt_info {
 	char		ci_filename_mode;
 	char		ci_flags;
 	struct crypto_ablkcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
 	char		ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
 };
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index a197215ad52b..4b449d263333 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1535,12 +1535,19 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 	struct f2fs_encryption_policy policy;
 	struct inode *inode = file_inode(filp);
+	int err;
 
 	if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg,
 				sizeof(policy)))
 		return -EFAULT;
 
-	return f2fs_process_policy(&policy, inode);
+	mutex_lock(&inode->i_mutex);
+
+	err = f2fs_process_policy(&policy, inode);
+
+	mutex_unlock(&inode->i_mutex);
+
+	return err;
 #else
 	return -EOPNOTSUPP;
 #endif
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 71b7206c431e..b238d2fec3e5 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -70,7 +70,8 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
 		*buf++ = pad;
 }
 
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+				struct f2fs_filename *fname)
 {
 	__u32 hash;
 	f2fs_hash_t f2fs_hash;
@@ -79,6 +80,10 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
 	const unsigned char *name = name_info->name;
 	size_t len = name_info->len;
 
+	/* encrypted bigname case */
+	if (fname && !fname->disk_name.name)
+		return cpu_to_le32(fname->hash);
+
 	if (is_dot_dotdot(name_info))
 		return 0;
 
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index bda7126466c0..ad80f916b64d 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -303,7 +303,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	if (IS_ERR(ipage))
 		return NULL;
 
-	namehash = f2fs_dentry_hash(&name);
+	namehash = f2fs_dentry_hash(&name, fname);
 
 	inline_dentry = inline_data_addr(ipage);
 
@@ -468,7 +468,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 
 	f2fs_wait_on_page_writeback(ipage, NODE);
 
-	name_hash = f2fs_dentry_hash(name);
+	name_hash = f2fs_dentry_hash(name, NULL);
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
 	f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3a65e0132352..4f666368aa85 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -918,6 +918,79 @@ static loff_t max_file_size(unsigned bits)
 	return result;
 }
 
+static inline bool sanity_check_area_boundary(struct super_block *sb,
+					struct f2fs_super_block *raw_super)
+{
+	u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+	u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
+	u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
+	u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr);
+	u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+	u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+	u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt);
+	u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit);
+	u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat);
+	u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa);
+	u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	u32 segment_count = le32_to_cpu(raw_super->segment_count);
+	u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+
+	if (segment0_blkaddr != cp_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+			segment0_blkaddr, cp_blkaddr);
+		return true;
+	}
+
+	if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) !=
+							sit_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong CP boundary, start(%u) end(%u) blocks(%u)",
+			cp_blkaddr, sit_blkaddr,
+			segment_count_ckpt << log_blocks_per_seg);
+		return true;
+	}
+
+	if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) !=
+							nat_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SIT boundary, start(%u) end(%u) blocks(%u)",
+			sit_blkaddr, nat_blkaddr,
+			segment_count_sit << log_blocks_per_seg);
+		return true;
+	}
+
+	if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) !=
+							ssa_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong NAT boundary, start(%u) end(%u) blocks(%u)",
+			nat_blkaddr, ssa_blkaddr,
+			segment_count_nat << log_blocks_per_seg);
+		return true;
+	}
+
+	if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) !=
+							main_blkaddr) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong SSA boundary, start(%u) end(%u) blocks(%u)",
+			ssa_blkaddr, main_blkaddr,
+			segment_count_ssa << log_blocks_per_seg);
+		return true;
+	}
+
+	if (main_blkaddr + (segment_count_main << log_blocks_per_seg) !=
+		segment0_blkaddr + (segment_count << log_blocks_per_seg)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)",
+			main_blkaddr,
+			segment0_blkaddr + (segment_count << log_blocks_per_seg),
+			segment_count_main << log_blocks_per_seg);
+		return true;
+	}
+
+	return false;
+}
+
 static int sanity_check_raw_super(struct super_block *sb,
 			struct f2fs_super_block *raw_super)
 {
@@ -947,6 +1020,14 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
+	/* check log blocks per segment */
+	if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid log blocks per segment (%u)\n",
+			le32_to_cpu(raw_super->log_blocks_per_seg));
+		return 1;
+	}
+
 	/* Currently, support 512/1024/2048/4096 bytes sector size */
 	if (le32_to_cpu(raw_super->log_sectorsize) >
 				F2FS_MAX_LOG_SECTOR_SIZE ||
@@ -965,6 +1046,30 @@ static int sanity_check_raw_super(struct super_block *sb,
 			le32_to_cpu(raw_super->log_sectorsize));
 		return 1;
 	}
+
+	/* check reserved ino info */
+	if (le32_to_cpu(raw_super->node_ino) != 1 ||
+		le32_to_cpu(raw_super->meta_ino) != 2 ||
+		le32_to_cpu(raw_super->root_ino) != 3) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)",
+			le32_to_cpu(raw_super->node_ino),
+			le32_to_cpu(raw_super->meta_ino),
+			le32_to_cpu(raw_super->root_ino));
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			le32_to_cpu(raw_super->segment_count));
+		return 1;
+	}
+
+	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
+	if (sanity_check_area_boundary(sb, raw_super))
+		return 1;
+
 	return 0;
 }
 
@@ -973,6 +1078,8 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int main_segs, blocks_per_seg;
+	int i;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -984,6 +1091,20 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	if (unlikely(fsmeta >= total))
 		return 1;
 
+	main_segs = le32_to_cpu(raw_super->segment_count_main);
+	blocks_per_seg = sbi->blocks_per_seg;
+
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 509411dd3698..cf644d52c0cf 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1269,6 +1269,16 @@ out:
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1713,12 +1723,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ee85cd4e136a..62376451bbce 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,16 +740,10 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
-		O_RDONLY	| O_WRONLY	| O_RDWR	|
-		O_CREAT		| O_EXCL	| O_NOCTTY	|
-		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
-		__O_SYNC	| O_DSYNC	| FASYNC	|
-		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
-		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
-		__FMODE_NONOTIFY
-		));
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+		HWEIGHT32(
+			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
+			__FMODE_EXEC | __FMODE_NONOTIFY));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
 		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
diff --git a/fs/fhandle.c b/fs/fhandle.c
index d59712dfa3e7..ca3c3dd01789 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -228,7 +228,7 @@ long do_handle_open(int mountdirfd,
 		path_put(&path);
 		return fd;
 	}
-	file = file_open_root(path.dentry, path.mnt, "", open_flag);
+	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		retval =  PTR_ERR(file);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 7a8ea1351584..60d6fc2e0e4b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -281,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct inode *inode)
 		wb_get(wb);
 		spin_unlock(&inode->i_lock);
 		spin_lock(&wb->list_lock);
-		wb_put(wb);		/* not gonna deref it anymore */
 
 		/* i_wb may have changed inbetween, can't use inode_to_wb() */
-		if (likely(wb == inode->i_wb))
-			return wb;	/* @inode already has ref */
+		if (likely(wb == inode->i_wb)) {
+			wb_put(wb);	/* @inode already has ref */
+			return wb;
+		}
 
 		spin_unlock(&wb->list_lock);
+		wb_put(wb);
 		cpu_relax();
 		spin_lock(&inode->i_lock);
 	}
@@ -1339,10 +1341,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
  * and does more profound writeback list handling in writeback_sb_inodes().
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+static int writeback_single_inode(struct inode *inode,
+				  struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb;
 	int ret = 0;
 
 	spin_lock(&inode->i_lock);
@@ -1380,7 +1382,8 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	ret = __writeback_single_inode(inode, wbc);
 
 	wbc_detach_inode(wbc);
-	spin_lock(&wb->list_lock);
+
+	wb = inode_to_wb_and_lock_list(inode);
 	spin_lock(&inode->i_lock);
 	/*
 	 * If inode is clean, remove it from writeback lists. Otherwise don't
@@ -1455,6 +1458,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
+		struct bdi_writeback *tmp_wb;
 
 		if (inode->i_sb != sb) {
 			if (work->sb) {
@@ -1545,15 +1549,23 @@ static long writeback_sb_inodes(struct super_block *sb,
 			cond_resched();
 		}
 
-
-		spin_lock(&wb->list_lock);
+		/*
+		 * Requeue @inode if still dirty.  Be careful as @inode may
+		 * have been switched to another wb in the meantime.
+		 */
+		tmp_wb = inode_to_wb_and_lock_list(inode);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
-		requeue_inode(inode, wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
+		if (unlikely(tmp_wb != wb)) {
+			spin_unlock(&tmp_wb->list_lock);
+			spin_lock(&wb->list_lock);
+		}
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
@@ -2340,7 +2352,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
@@ -2352,7 +2363,7 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	return writeback_single_inode(inode, wb, &wbc);
+	return writeback_single_inode(inode, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 
@@ -2369,7 +2380,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
+	return writeback_single_inode(inode, wbc);
 }
 EXPORT_SYMBOL(sync_inode);
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 4304072161aa..40d61077bead 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -542,6 +542,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
 			if (invalidate)
 				set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+			clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
 		}
 	} else {
@@ -560,6 +561,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
 				 TASK_UNINTERRUPTIBLE);
 
+	/* Make sure any pending writes are cancelled. */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+		fscache_invalidate_writes(cookie);
+
 	/* Reset the cookie state if it wasn't relinquished */
 	if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
 		atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 9b28649df3a1..a8aa00be4444 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -48,6 +48,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 	cookie->flags		= 1 << FSCACHE_COOKIE_ENABLED;
 
 	spin_lock_init(&cookie->lock);
+	spin_lock_init(&cookie->stores_lock);
 	INIT_HLIST_HEAD(&cookie->backing_objects);
 
 	/* check the netfs type is not already present */
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9e792e30f4db..7a182c87f378 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -30,6 +30,7 @@ static const struct fscache_state *fscache_look_up_object(struct fscache_object
 static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
 static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
 static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);
 
 #define __STATE_NAME(n) fscache_osm_##n
 #define STATE(n) (&__STATE_NAME(n))
@@ -91,7 +92,7 @@ static WORK_STATE(LOOKUP_FAILURE,	"LCFL", fscache_lookup_failure);
 static WORK_STATE(KILL_OBJECT,		"KILL", fscache_kill_object);
 static WORK_STATE(KILL_DEPENDENTS,	"KDEP", fscache_kill_dependents);
 static WORK_STATE(DROP_OBJECT,		"DROP", fscache_drop_object);
-static WORK_STATE(OBJECT_DEAD,		"DEAD", (void*)2UL);
+static WORK_STATE(OBJECT_DEAD,		"DEAD", fscache_object_dead);
 
 static WAIT_STATE(WAIT_FOR_INIT,	"?INI",
 		  TRANSIT_TO(INIT_OBJECT,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));
@@ -229,6 +230,10 @@ execute_work_state:
 	event = -1;
 	if (new_state == NO_TRANSIT) {
 		_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
+			_leave(" [dead]");
+			return;
+		}
 		fscache_enqueue_object(object);
 		event_mask = object->oob_event_mask;
 		goto unmask_events;
@@ -239,7 +244,7 @@ execute_work_state:
 	object->state = state = new_state;
 
 	if (state->work) {
-		if (unlikely(state->work == ((void *)2UL))) {
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
 			_leave(" [dead]");
 			return;
 		}
@@ -645,6 +650,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
 	fscache_mark_object_dead(object);
 	object->oob_event_mask = 0;
 
+	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+		/* Reject any new read/write ops and abort any that are pending. */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		fscache_cancel_all_ops(object);
+	}
+
 	if (list_empty(&object->dependents) &&
 	    object->n_ops == 0 &&
 	    object->n_children == 0)
@@ -1077,3 +1088,20 @@ void fscache_object_mark_killed(struct fscache_object *object,
 	}
 }
 EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead.  We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+						       int event)
+{
+	if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+			      &object->flags))
+		return NO_TRANSIT;
+
+	WARN(true, "FS-Cache object redispatched after death");
+	return NO_TRANSIT;
+}
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 8e3ee1936c7e..c5b6b7165489 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt)
 
 static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 
 	return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE);
@@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to)
 
 static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 {
-	struct fuse_io_priv io = { .async = 0, .file = kiocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp);
 	loff_t pos = 0;
 	/*
 	 * No locking or generic_write_checks(), the server is
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ebb5e37455a0..d0cf1f010fbe 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -418,6 +418,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->waitq.lock);
+	if (test_bit(FR_FINISHED, &req->flags)) {
+		spin_unlock(&fiq->waitq.lock);
+		return;
+	}
 	if (list_empty(&req->intr_entry)) {
 		list_add_tail(&req->intr_entry, &fiq->interrupts);
 		wake_up_locked(&fiq->waitq);
@@ -2083,7 +2087,6 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
 		struct fuse_req *req;
 		req = list_entry(head->next, struct fuse_req, list);
 		req->out.h.error = -ECONNABORTED;
-		clear_bit(FR_PENDING, &req->flags);
 		clear_bit(FR_SENT, &req->flags);
 		list_del_init(&req->list);
 		request_end(fc, req);
@@ -2161,6 +2164,8 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		spin_lock(&fiq->waitq.lock);
 		fiq->connected = 0;
 		list_splice_init(&fiq->pending, &to_end2);
+		list_for_each_entry(req, &to_end2, list)
+			clear_bit(FR_PENDING, &req->flags);
 		while (forget_pending(fiq))
 			kfree(dequeue_forget(fiq, 1, NULL));
 		wake_up_all_locked(&fiq->waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 5e2e08712d3b..4b5f2c4e69c8 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1697,14 +1697,46 @@ error:
 static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(entry);
+	struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL;
+	int ret;
 
 	if (!fuse_allow_current_process(get_fuse_conn(inode)))
 		return -EACCES;
 
-	if (attr->ia_valid & ATTR_FILE)
-		return fuse_do_setattr(inode, attr, attr->ia_file);
-	else
-		return fuse_do_setattr(inode, attr, NULL);
+	if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) {
+		int kill;
+
+		attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID |
+				    ATTR_MODE);
+		/*
+		 * ia_mode calculation may have used stale i_mode.  Refresh and
+		 * recalculate.
+		 */
+		ret = fuse_do_getattr(inode, NULL, file);
+		if (ret)
+			return ret;
+
+		attr->ia_mode = inode->i_mode;
+		kill = should_remove_suid(entry);
+		if (kill & ATTR_KILL_SUID) {
+			attr->ia_valid |= ATTR_MODE;
+			attr->ia_mode &= ~S_ISUID;
+		}
+		if (kill & ATTR_KILL_SGID) {
+			attr->ia_valid |= ATTR_MODE;
+			attr->ia_mode &= ~S_ISGID;
+		}
+	}
+	if (!attr->ia_valid)
+		return 0;
+
+	ret = fuse_do_setattr(inode, attr, file);
+	if (!ret) {
+		/* Directory mode changed, may need to revalidate access */
+		if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE))
+			fuse_invalidate_entry_cache(entry);
+	}
+	return ret;
 }
 
 static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
@@ -1797,6 +1829,23 @@ static ssize_t fuse_getxattr(struct dentry *entry, const char *name,
 	return ret;
 }
 
+static int fuse_verify_xattr_list(char *list, size_t size)
+{
+	size_t origsize = size;
+
+	while (size) {
+		size_t thislen = strnlen(list, size);
+
+		if (!thislen || thislen == size)
+			return -EIO;
+
+		size -= thislen + 1;
+		list += thislen + 1;
+	}
+
+	return origsize;
+}
+
 static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
 {
 	struct inode *inode = d_inode(entry);
@@ -1832,6 +1881,8 @@ static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
 	ret = fuse_simple_request(fc, &args);
 	if (!ret && !size)
 		ret = outarg.size;
+	if (ret > 0 && size)
+		ret = fuse_verify_xattr_list(list, ret);
 	if (ret == -ENOSYS) {
 		fc->no_listxattr = 1;
 		ret = -EOPNOTSUPP;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 570ca4053c80..1a063cbfe503 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
 {
 	struct fuse_file *ff;
 
-	ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
+	ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL);
 	if (unlikely(!ff))
 		return NULL;
 
@@ -100,6 +100,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync)
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else if (sync) {
+			__set_bit(FR_FORCE, &req->flags);
 			__clear_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send(ff->fc, req);
 			iput(req->misc.release.inode);
@@ -417,6 +418,15 @@ static int fuse_flush(struct file *file, fl_owner_t id)
 	fuse_sync_writes(inode);
 	mutex_unlock(&inode->i_mutex);
 
+	if (test_bit(AS_ENOSPC, &file->f_mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags))
+		err = -ENOSPC;
+	if (test_bit(AS_EIO, &file->f_mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &file->f_mapping->flags))
+		err = -EIO;
+	if (err)
+		return err;
+
 	req = fuse_get_req_nofail_nopages(fc, file);
 	memset(&inarg, 0, sizeof(inarg));
 	inarg.fh = ff->fh;
@@ -462,6 +472,21 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
 		goto out;
 
 	fuse_sync_writes(inode);
+
+	/*
+	 * Due to implementation of fuse writeback
+	 * filemap_write_and_wait_range() does not catch errors.
+	 * We have to do this directly after fuse_sync_writes()
+	 */
+	if (test_bit(AS_ENOSPC, &file->f_mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags))
+		err = -ENOSPC;
+	if (test_bit(AS_EIO, &file->f_mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &file->f_mapping->flags))
+		err = -EIO;
+	if (err)
+		goto out;
+
 	err = sync_inode_metadata(inode, 1);
 	if (err)
 		goto out;
@@ -516,18 +541,23 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
 	req->out.args[0].size = count;
 }
 
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
 {
 	unsigned i;
 
 	for (i = 0; i < req->num_pages; i++) {
 		struct page *page = req->pages[i];
-		if (write)
+		if (should_dirty)
 			set_page_dirty_lock(page);
 		put_page(page);
 	}
 }
 
+static void fuse_io_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct fuse_io_priv, refcnt));
+}
+
 static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
 {
 	if (io->err)
@@ -585,8 +615,9 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
 		}
 
 		io->iocb->ki_complete(io->iocb, res, 0);
-		kfree(io);
 	}
+
+	kref_put(&io->refcnt, fuse_io_release);
 }
 
 static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
@@ -613,6 +644,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
 		size_t num_bytes, struct fuse_io_priv *io)
 {
 	spin_lock(&io->lock);
+	kref_get(&io->refcnt);
 	io->size += num_bytes;
 	io->reqs++;
 	spin_unlock(&io->lock);
@@ -691,7 +723,7 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode,
 
 static int fuse_do_readpage(struct file *file, struct page *page)
 {
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	struct inode *inode = page->mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_req *req;
@@ -984,7 +1016,7 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
 	size_t res;
 	unsigned offset;
 	unsigned i;
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 
 	for (i = 0; i < req->num_pages; i++)
 		fuse_wait_on_page_writeback(inode, req->pages[i]->index);
@@ -1300,6 +1332,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
+	bool should_dirty = !write && iter_is_iovec(iter);
 	int cuse = flags & FUSE_DIO_CUSE;
 	struct file *file = io->file;
 	struct inode *inode = file->f_mapping->host;
@@ -1344,7 +1377,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			nres = fuse_send_read(req, io, pos, nbytes, owner);
 
 		if (!io->async)
-			fuse_release_user_pages(req, !write);
+			fuse_release_user_pages(req, should_dirty);
 		if (req->out.h.error) {
 			if (!res)
 				res = req->out.h.error;
@@ -1398,7 +1431,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
 
 static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	struct fuse_io_priv io = { .async = 0, .file = iocb->ki_filp };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp);
 	return __fuse_direct_read(&io, to, &iocb->ki_pos);
 }
 
@@ -1406,7 +1439,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file);
 	ssize_t res;
 
 	if (is_bad_inode(inode))
@@ -1965,6 +1998,10 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = page->mapping->host;
 
+	/* Haven't copied anything?  Skip zeroing, size extending, dirtying. */
+	if (!copied)
+		goto unlock;
+
 	if (!PageUptodate(page)) {
 		/* Zero any unwritten bytes at the end of the page */
 		size_t endoff = (pos + copied) & ~PAGE_CACHE_MASK;
@@ -1975,6 +2012,8 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
 
 	fuse_write_update_size(inode, pos + copied);
 	set_page_dirty(page);
+
+unlock:
 	unlock_page(page);
 	page_cache_release(page);
 
@@ -2786,6 +2825,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	loff_t i_size;
 	size_t count = iov_iter_count(iter);
 	struct fuse_io_priv *io;
+	bool is_sync = is_sync_kiocb(iocb);
 
 	pos = offset;
 	inode = file->f_mapping->host;
@@ -2806,6 +2846,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	if (!io)
 		return -ENOMEM;
 	spin_lock_init(&io->lock);
+	kref_init(&io->refcnt);
 	io->reqs = 1;
 	io->bytes = -1;
 	io->size = 0;
@@ -2825,12 +2866,18 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	 * to wait on real async I/O requests, so we must submit this request
 	 * synchronously.
 	 */
-	if (!is_sync_kiocb(iocb) && (offset + count > i_size) &&
+	if (!is_sync && (offset + count > i_size) &&
 	    iov_iter_rw(iter) == WRITE)
 		io->async = false;
 
-	if (io->async && is_sync_kiocb(iocb))
+	if (io->async && is_sync) {
+		/*
+		 * Additional reference to keep io around after
+		 * calling fuse_aio_complete()
+		 */
+		kref_get(&io->refcnt);
 		io->done = &wait;
+	}
 
 	if (iov_iter_rw(iter) == WRITE) {
 		ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
@@ -2843,14 +2890,14 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
 
 		/* we have a non-extending, async request, so return */
-		if (!is_sync_kiocb(iocb))
+		if (!is_sync)
 			return -EIOCBQUEUED;
 
 		wait_for_completion(&wait);
 		ret = fuse_get_res_by_io(io);
 	}
 
-	kfree(io);
+	kref_put(&io->refcnt, fuse_io_release);
 
 	if (iov_iter_rw(iter) == WRITE) {
 		if (ret > 0)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 405113101db8..604cd42dafef 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -22,6 +22,7 @@
 #include <linux/rbtree.h>
 #include <linux/poll.h>
 #include <linux/workqueue.h>
+#include <linux/kref.h>
 
 /** Max number of pages that can be used in a single read request */
 #define FUSE_MAX_PAGES_PER_REQ 32
@@ -243,6 +244,7 @@ struct fuse_args {
 
 /** The request IO state (for asynchronous processing) */
 struct fuse_io_priv {
+	struct kref refcnt;
 	int async;
 	spinlock_t lock;
 	unsigned reqs;
@@ -256,6 +258,13 @@ struct fuse_io_priv {
 	struct completion *done;
 };
 
+#define FUSE_IO_PRIV_SYNC(f) \
+{					\
+	.refcnt = { ATOMIC_INIT(1) },	\
+	.async = 0,			\
+	.file = f,			\
+}
+
 /**
  * Request flags
  *
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2913db2a5b99..0d5e8e59b390 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -926,7 +926,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
-		FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
+		FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
 		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
 	req->in.h.opcode = FUSE_INIT;
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 1be3b061c05c..ff0ac96a8e7b 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -79,17 +79,11 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	if (type == ACL_TYPE_ACCESS) {
 		umode_t mode = inode->i_mode;
 
-		error = posix_acl_equiv_mode(acl, &mode);
-		if (error < 0)
+		error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+		if (error)
 			return error;
-
-		if (error == 0)
-			acl = NULL;
-
-		if (mode != inode->i_mode) {
-			inode->i_mode = mode;
+		if (mode != inode->i_mode)
 			mark_inode_dirty(inode);
-		}
 	}
 
 	if (acl) {
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index ad8a5b757cc7..a443c6e54412 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -760,7 +760,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
 	int error;
 
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (!error)
+	if (!IS_ERR_VALUE(error))
 		error = get_leaf(dip, leaf_no, bh_out);
 
 	return error;
@@ -976,7 +976,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	index = name->hash >> (32 - dip->i_depth);
 	error = get_leaf_nr(dip, index, &leaf_no);
-	if (error)
+	if (IS_ERR_VALUE(error))
 		return error;
 
 	/*  Get the old leaf block  */
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 32e74710b1aa..070901e76653 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = {
 
 static struct rhashtable gl_hash_table;
 
-void gfs2_glock_free(struct gfs2_glock *gl)
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
 {
-	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
 
 	if (gl->gl_ops->go_flags & GLOF_ASPACE) {
 		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
@@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl)
 		kfree(gl->gl_lksb.sb_lvbptr);
 		kmem_cache_free(gfs2_glock_cachep, gl);
 	}
+}
+
+void gfs2_glock_free(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
 		wake_up(&sdp->sd_glock_wait);
 }
@@ -651,9 +658,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	struct kmem_cache *cachep;
 	int ret, tries = 0;
 
+	rcu_read_lock();
 	gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
 	if (gl && !lockref_get_not_dead(&gl->gl_lockref))
 		gl = NULL;
+	rcu_read_unlock();
 
 	*glp = gl;
 	if (gl)
@@ -721,15 +730,18 @@ again:
 
 	if (ret == -EEXIST) {
 		ret = 0;
+		rcu_read_lock();
 		tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
 		if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) {
 			if (++tries < 100) {
+				rcu_read_unlock();
 				cond_resched();
 				goto again;
 			}
 			tmp = NULL;
 			ret = -ENOMEM;
 		}
+		rcu_read_unlock();
 	} else {
 		WARN_ON_ONCE(ret);
 	}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index de7b4f97ac75..4a9077ec9313 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -207,7 +207,7 @@ struct lm_lockname {
 	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
 	unsigned int ln_type;
-};
+} __packed __aligned(sizeof(int));
 
 #define lm_name_equal(name1, name2) \
         (((name1)->ln_number == (name2)->ln_number) &&	\
@@ -367,6 +367,7 @@ struct gfs2_glock {
 			loff_t end;
 		} gl_vm;
 	};
+	struct rcu_head gl_rcu;
 	struct rhash_head gl_node;
 };
 
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
index df0c9af68d05..71b3087b7e32 100644
--- a/fs/hfsplus/posix_acl.c
+++ b/fs/hfsplus/posix_acl.c
@@ -68,8 +68,8 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
 	case ACL_TYPE_ACCESS:
 		xattr_name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			err = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (err < 0)
+			err = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (err)
 				return err;
 		}
 		err = 0;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 5a7b3229b956..f34d6f5a5aca 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -959,10 +959,11 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
 
 	if (S_ISLNK(root_inode->i_mode)) {
 		char *name = follow_link(host_root_path);
-		if (IS_ERR(name))
+		if (IS_ERR(name)) {
 			err = PTR_ERR(name);
-		else
-			err = read_name(root_inode, name);
+			goto out_put;
+		}
+		err = read_name(root_inode, name);
 		kfree(name);
 		if (err)
 			goto out_put;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index a561591896bd..3713fd52b44b 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/bitmap.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 
 /* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
 
@@ -453,10 +454,6 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 	int lowercase, eas, chk, errs, chkdsk, timeshift;
 	int o;
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
-	char *new_opts = kstrdup(data, GFP_KERNEL);
-
-	if (!new_opts)
-		return -ENOMEM;
 
 	sync_filesystem(s);
 
@@ -493,17 +490,44 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 
 	if (!(*flags & MS_RDONLY)) mark_dirty(s, 1);
 
-	replace_mount_options(s, new_opts);
-
 	hpfs_unlock(s);
 	return 0;
 
 out_err:
 	hpfs_unlock(s);
-	kfree(new_opts);
 	return -EINVAL;
 }
 
+static int hpfs_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct hpfs_sb_info *sbi = hpfs_sb(root->d_sb);
+
+	seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->sb_uid));
+	seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->sb_gid));
+	seq_printf(seq, ",umask=%03o", (~sbi->sb_mode & 0777));
+	if (sbi->sb_lowercase)
+		seq_printf(seq, ",case=lower");
+	if (!sbi->sb_chk)
+		seq_printf(seq, ",check=none");
+	if (sbi->sb_chk == 2)
+		seq_printf(seq, ",check=strict");
+	if (!sbi->sb_err)
+		seq_printf(seq, ",errors=continue");
+	if (sbi->sb_err == 2)
+		seq_printf(seq, ",errors=panic");
+	if (!sbi->sb_chkdsk)
+		seq_printf(seq, ",chkdsk=no");
+	if (sbi->sb_chkdsk == 2)
+		seq_printf(seq, ",chkdsk=always");
+	if (!sbi->sb_eas)
+		seq_printf(seq, ",eas=no");
+	if (sbi->sb_eas == 1)
+		seq_printf(seq, ",eas=ro");
+	if (sbi->sb_timeshift)
+		seq_printf(seq, ",timeshift=%d", sbi->sb_timeshift);
+	return 0;
+}
+
 /* Super operations */
 
 static const struct super_operations hpfs_sops =
@@ -514,7 +538,7 @@ static const struct super_operations hpfs_sops =
 	.put_super	= hpfs_put_super,
 	.statfs		= hpfs_statfs,
 	.remount_fs	= hpfs_remount_fs,
-	.show_options	= generic_show_options,
+	.show_options	= hpfs_show_options,
 };
 
 static int hpfs_fill_super(struct super_block *s, void *options, int silent)
@@ -537,8 +561,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 
 	int o;
 
-	save_mount_options(s, options);
-
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi) {
 		return -ENOMEM;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 595ebdb41846..a17da8b57fc6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -191,7 +191,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
diff --git a/fs/inode.c b/fs/inode.c
index 1be5f9003eb3..b0edef500590 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1733,8 +1733,8 @@ static int __remove_privs(struct dentry *dentry, int kill)
  */
 int file_remove_privs(struct file *file)
 {
-	struct dentry *dentry = file->f_path.dentry;
-	struct inode *inode = d_inode(dentry);
+	struct dentry *dentry = file_dentry(file);
+	struct inode *inode = file_inode(file);
 	int kill;
 	int error = 0;
 
@@ -1742,7 +1742,7 @@ int file_remove_privs(struct file *file)
 	if (IS_NOSEC(inode))
 		return 0;
 
-	kill = file_needs_remove_privs(file);
+	kill = dentry_needs_remove_privs(dentry);
 	if (kill < 0)
 		return kill;
 	if (kill)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d67a16f2a45d..350f67fb5b9c 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -690,6 +690,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 	pri_bh = NULL;
 
 root_found:
+	/* We don't support read-write mounts */
+	if (!(s->s_flags & MS_RDONLY)) {
+		error = -EACCES;
+		goto out_freebh;
+	}
 
 	if (joliet_level && (pri == NULL || !opt.rock)) {
 		/* This is the case of Joliet with the norock mount flag.
@@ -1503,9 +1508,6 @@ struct inode *__isofs_iget(struct super_block *sb,
 static struct dentry *isofs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	/* We don't support read-write mounts */
-	if (!(flags & MS_RDONLY))
-		return ERR_PTR(-EACCES);
 	return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
 }
 
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 735d7522a3a9..204659a5f6db 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de,
 	int retnamlen = 0;
 	int truncate = 0;
 	int ret = 0;
+	char *p;
+	int len;
 
 	if (!ISOFS_SB(inode->i_sb)->s_rock)
 		return 0;
@@ -267,12 +269,17 @@ repeat:
 					rr->u.NM.flags);
 				break;
 			}
-			if ((strlen(retname) + rr->len - 5) >= 254) {
+			len = rr->len - 5;
+			if (retnamlen + len >= 254) {
 				truncate = 1;
 				break;
 			}
-			strncat(retname, rr->u.NM.name, rr->len - 5);
-			retnamlen += rr->len - 5;
+			p = memchr(rr->u.NM.name, '\0', len);
+			if (unlikely(p))
+				len = p - rr->u.NM.name;
+			memcpy(retname + retnamlen, rr->u.NM.name, len);
+			retnamlen += len;
+			retname[retnamlen] = '\0';
 			break;
 		case SIG('R', 'E'):
 			kfree(rs.buffer);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 36345fefa3ff..2d964ce45606 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -124,7 +124,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	struct timespec now = current_kernel_time();
+	struct timespec64 now = current_kernel_time64();
 
 	*cbh = NULL;
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 81e622681c82..624a57a9c4aa 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1408,11 +1408,12 @@ out:
 /**
  * jbd2_mark_journal_empty() - Mark on disk journal as empty.
  * @journal: The journal to update.
+ * @write_op: With which operation should we write the journal sb
  *
  * Update a journal's dynamic superblock fields to show that journal is empty.
  * Write updated superblock to disk waiting for IO to complete.
  */
-static void jbd2_mark_journal_empty(journal_t *journal)
+static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
 
@@ -1430,7 +1431,7 @@ static void jbd2_mark_journal_empty(journal_t *journal)
 	sb->s_start    = cpu_to_be32(0);
 	read_unlock(&journal->j_state_lock);
 
-	jbd2_write_superblock(journal, WRITE_FUA);
+	jbd2_write_superblock(journal, write_op);
 
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
@@ -1716,7 +1717,13 @@ int jbd2_journal_destroy(journal_t *journal)
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
 			mutex_lock(&journal->j_checkpoint_mutex);
-			jbd2_mark_journal_empty(journal);
+
+			write_lock(&journal->j_state_lock);
+			journal->j_tail_sequence =
+				++journal->j_transaction_sequence;
+			write_unlock(&journal->j_state_lock);
+
+			jbd2_mark_journal_empty(journal, WRITE_FLUSH_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -1975,7 +1982,7 @@ int jbd2_journal_flush(journal_t *journal)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal);
+	jbd2_mark_journal_empty(journal, WRITE_FUA);
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);
@@ -2021,7 +2028,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal);
+		jbd2_mark_journal_empty(journal, WRITE_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index ca181e81c765..a2e724053919 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1156,6 +1156,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "file as BJ_Reserved");
 		spin_lock(&journal->j_list_lock);
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
+		spin_unlock(&journal->j_list_lock);
 	} else if (jh->b_transaction == journal->j_committing_transaction) {
 		/* first access by this transaction */
 		jh->b_modified = 0;
@@ -1163,8 +1164,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 		JBUFFER_TRACE(jh, "set next transaction");
 		spin_lock(&journal->j_list_lock);
 		jh->b_next_transaction = transaction;
+		spin_unlock(&journal->j_list_lock);
 	}
-	spin_unlock(&journal->j_list_lock);
 	jbd_unlock_bh_state(bh);
 
 	/*
@@ -1875,7 +1876,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
 	__blist_del_buffer(list, jh);
 	jh->b_jlist = BJ_None;
-	if (test_clear_buffer_jbddirty(bh))
+	if (transaction && is_journal_aborted(transaction->t_journal))
+		clear_buffer_jbddirty(bh);
+	else if (test_clear_buffer_jbddirty(bh))
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 2f7a3c090489..f9f86f87d32b 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -235,9 +235,10 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	case ACL_TYPE_ACCESS:
 		xprefix = JFFS2_XPREFIX_ACL_ACCESS;
 		if (acl) {
-			umode_t mode = inode->i_mode;
-			rc = posix_acl_equiv_mode(acl, &mode);
-			if (rc < 0)
+			umode_t mode;
+
+			rc = posix_acl_update_mode(inode, &mode, &acl);
+			if (rc)
 				return rc;
 			if (inode->i_mode != mode) {
 				struct iattr attr;
@@ -249,8 +250,6 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 				if (rc < 0)
 					return rc;
 			}
-			if (rc == 0)
-				acl = NULL;
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 0c8ca830b113..9fad9f4fe883 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -84,13 +84,11 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
 	case ACL_TYPE_ACCESS:
 		ea_name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			rc = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (rc < 0)
+			rc = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (rc)
 				return rc;
 			inode->i_ctime = CURRENT_TIME;
 			mark_inode_dirty(inode);
-			if (rc == 0)
-				acl = NULL;
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 8f9176caf098..c8d58c5ac8ae 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
 				sb->s_blocksize - offset : toread;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 0);
 		if (err)
 			return err;
@@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 1);
 		if (err)
 			goto out;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 7247252ee9b1..6e9a912d394c 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -833,21 +833,35 @@ repeat:
 	mutex_lock(&kernfs_mutex);
 
 	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
+		struct kernfs_node *parent;
 		struct inode *inode;
-		struct dentry *dentry;
 
+		/*
+		 * We want fsnotify_modify() on @kn but as the
+		 * modifications aren't originating from userland don't
+		 * have the matching @file available.  Look up the inodes
+		 * and generate the events manually.
+		 */
 		inode = ilookup(info->sb, kn->ino);
 		if (!inode)
 			continue;
 
-		dentry = d_find_any_alias(inode);
-		if (dentry) {
-			fsnotify_parent(NULL, dentry, FS_MODIFY);
-			fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
-				 NULL, 0);
-			dput(dentry);
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			struct inode *p_inode;
+
+			p_inode = ilookup(info->sb, parent->ino);
+			if (p_inode) {
+				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
+					 inode, FSNOTIFY_EVENT_INODE, kn->name, 0);
+				iput(p_inode);
+			}
+
+			kernfs_put(parent);
 		}
 
+		fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+			 kn->name, 0);
 		iput(inode);
 	}
 
diff --git a/fs/locks.c b/fs/locks.c
index 6333263b7bc8..8eddae23e10b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1602,7 +1602,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 {
 	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
diff --git a/fs/mount.h b/fs/mount.h
index 14db05d424f7..37c64bbe840c 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -13,6 +13,8 @@ struct mnt_namespace {
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	u64 event;
+	unsigned int		mounts; /* # of mounts in the namespace */
+	unsigned int		pending_mounts;
 };
 
 struct mnt_pcp {
@@ -55,6 +57,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
@@ -86,7 +89,6 @@ static inline int is_mounted(struct vfsmount *mnt)
 }
 
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
-extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern int __legitimize_mnt(struct vfsmount *, unsigned);
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
diff --git a/fs/mpage.c b/fs/mpage.c
index 1480d3a18037..6ade29b19494 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -111,7 +111,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 			SetPageUptodate(page);    
 			return;
 		}
-		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+		create_empty_buffers(page, i_blocksize(inode), 0);
 	}
 	head = page_buffers(page);
 	page_bh = head;
diff --git a/fs/namei.c b/fs/namei.c
index d8ee4da93650..3f96ae087488 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -887,6 +887,7 @@ static inline int may_follow_link(struct nameidata *nd)
 {
 	const struct inode *inode;
 	const struct inode *parent;
+	kuid_t puid;
 
 	if (!sysctl_protected_symlinks)
 		return 0;
@@ -902,7 +903,8 @@ static inline int may_follow_link(struct nameidata *nd)
 		return 0;
 
 	/* Allowed if parent directory and link owner match. */
-	if (uid_eq(parent->i_uid, inode->i_uid))
+	puid = parent->i_uid;
+	if (uid_valid(puid) && uid_eq(puid, inode->i_uid))
 		return 0;
 
 	if (nd->flags & LOOKUP_RCU)
@@ -2906,22 +2908,10 @@ no_open:
 		dentry = lookup_real(dir, dentry, nd->flags);
 		if (IS_ERR(dentry))
 			return PTR_ERR(dentry);
-
-		if (create_error) {
-			int open_flag = op->open_flag;
-
-			error = create_error;
-			if ((open_flag & O_EXCL)) {
-				if (!dentry->d_inode)
-					goto out;
-			} else if (!dentry->d_inode) {
-				goto out;
-			} else if ((open_flag & O_TRUNC) &&
-				   d_is_reg(dentry)) {
-				goto out;
-			}
-			/* will fail later, go on to get the right error */
-		}
+	}
+	if (create_error && !dentry->d_inode) {
+		error = create_error;
+		goto out;
 	}
 looked_up:
 	path->dentry = dentry;
@@ -4189,13 +4179,17 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	int error;
 	bool is_dir = d_is_dir(old_dentry);
-	const unsigned char *old_name;
 	struct inode *source = old_dentry->d_inode;
 	struct inode *target = new_dentry->d_inode;
 	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
+	struct name_snapshot old_name;
 
-	if (source == target)
+	/*
+	 * Check source == target.
+	 * On overlayfs need to look at underlying inodes.
+	 */
+	if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0))
 		return 0;
 
 	error = may_delete(old_dir, old_dentry, is_dir);
@@ -4243,7 +4237,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+	take_dentry_name_snapshot(&old_name, old_dentry);
 	dget(new_dentry);
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
@@ -4304,14 +4298,14 @@ out:
 		mutex_unlock(&target->i_mutex);
 	dput(new_dentry);
 	if (!error) {
-		fsnotify_move(old_dir, new_dir, old_name, is_dir,
+		fsnotify_move(old_dir, new_dir, old_name.name, is_dir,
 			      !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
 		if (flags & RENAME_EXCHANGE) {
 			fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
 				      new_is_dir, NULL, new_dentry);
 		}
 	}
-	fsnotify_oldname_free(old_name);
+	release_dentry_name_snapshot(&old_name);
 
 	return error;
 }
diff --git a/fs/namespace.c b/fs/namespace.c
index 0570729c87fd..ec4078d16eb7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,9 @@
 #include "pnode.h"
 #include "internal.h"
 
+/* Maximum number of mounts in a mount namespace */
+unsigned int sysctl_mount_max __read_mostly = 100000;
+
 static unsigned int m_hash_mask __read_mostly;
 static unsigned int m_hash_shift __read_mostly;
 static unsigned int mp_hash_mask __read_mostly;
@@ -234,6 +237,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
@@ -638,28 +642,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -743,26 +725,50 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
 	return NULL;
 }
 
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+static struct mountpoint *get_mountpoint(struct dentry *dentry)
 {
-	struct hlist_head *chain = mp_hash(dentry);
-	struct mountpoint *mp;
+	struct mountpoint *mp, *new = NULL;
 	int ret;
 
-	mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
-	if (!mp)
+	if (d_mountpoint(dentry)) {
+mountpoint:
+		read_seqlock_excl(&mount_lock);
+		mp = lookup_mountpoint(dentry);
+		read_sequnlock_excl(&mount_lock);
+		if (mp)
+			goto done;
+	}
+
+	if (!new)
+		new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
+	if (!new)
 		return ERR_PTR(-ENOMEM);
 
+
+	/* Exactly one processes may set d_mounted */
 	ret = d_set_mounted(dentry);
-	if (ret) {
-		kfree(mp);
-		return ERR_PTR(ret);
-	}
 
-	mp->m_dentry = dentry;
-	mp->m_count = 1;
-	hlist_add_head(&mp->m_hash, chain);
-	INIT_HLIST_HEAD(&mp->m_list);
+	/* Someone else set d_mounted? */
+	if (ret == -EBUSY)
+		goto mountpoint;
+
+	/* The dentry is not available as a mountpoint? */
+	mp = ERR_PTR(ret);
+	if (ret)
+		goto done;
+
+	/* Add the new mountpoint to the hash table */
+	read_seqlock_excl(&mount_lock);
+	new->m_dentry = dentry;
+	new->m_count = 1;
+	hlist_add_head(&new->m_hash, mp_hash(dentry));
+	INIT_HLIST_HEAD(&new->m_list);
+	read_sequnlock_excl(&mount_lock);
+
+	mp = new;
+	new = NULL;
+done:
+	kfree(new);
 	return mp;
 }
 
@@ -855,6 +861,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -863,28 +876,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -899,7 +929,10 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 
 	list_splice(&head, n->list.prev);
 
-	attach_shadowed(mnt, parent, shadows);
+	n->mounts += n->pending_mounts;
+	n->pending_mounts = 0;
+
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -1419,11 +1452,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		propagate_umount(&tmp_list);
 
 	while (!list_empty(&tmp_list)) {
+		struct mnt_namespace *ns;
 		bool disconnect;
 		p = list_first_entry(&tmp_list, struct mount, mnt_list);
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
-		__touch_mnt_namespace(p->mnt_ns);
+		ns = p->mnt_ns;
+		if (ns) {
+			ns->mounts--;
+			__touch_mnt_namespace(ns);
+		}
 		p->mnt_ns = NULL;
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
@@ -1557,11 +1595,12 @@ void __detach_mounts(struct dentry *dentry)
 	struct mount *mnt;
 
 	namespace_lock();
+	lock_mount_hash();
 	mp = lookup_mountpoint(dentry);
 	if (IS_ERR_OR_NULL(mp))
 		goto out_unlock;
 
-	lock_mount_hash();
+	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
@@ -1570,9 +1609,9 @@ void __detach_mounts(struct dentry *dentry)
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
-	unlock_mount_hash();
 	put_mountpoint(mp);
 out_unlock:
+	unlock_mount_hash();
 	namespace_unlock();
 }
 
@@ -1693,7 +1732,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1715,14 +1753,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1831,6 +1862,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse)
 	return 0;
 }
 
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
+{
+	unsigned int max = READ_ONCE(sysctl_mount_max);
+	unsigned int mounts = 0, old, pending, sum;
+	struct mount *p;
+
+	for (p = mnt; p; p = next_mnt(p, mnt))
+		mounts++;
+
+	old = ns->mounts;
+	pending = ns->pending_mounts;
+	sum = old + pending;
+	if ((old > sum) ||
+	    (pending > sum) ||
+	    (max < sum) ||
+	    (mounts > (max - sum)))
+		return -ENOSPC;
+
+	ns->pending_mounts = pending + mounts;
+	return 0;
+}
+
 /*
  *  @source_mnt : mount tree to be attached
  *  @nd         : place the mount tree @source_mnt is attached
@@ -1900,10 +1953,26 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			struct path *parent_path)
 {
 	HLIST_HEAD(tree_list);
+	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
+	/* Is there space to add these mounts to the mount namespace? */
+	if (!parent_path) {
+		err = count_mounts(ns, source_mnt);
+		if (err)
+			goto out;
+	}
+
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
@@ -1923,16 +1992,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -1940,11 +2012,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
  out_cleanup_ids:
 	while (!hlist_empty(&tree_list)) {
 		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		child->mnt_parent->mnt_ns->pending_mounts = 0;
 		umount_tree(child, UMOUNT_SYNC);
 	}
 	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
+	ns->pending_mounts = 0;
+
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }
 
@@ -1961,9 +2040,7 @@ retry:
 	namespace_lock();
 	mnt = lookup_mnt(path);
 	if (likely(!mnt)) {
-		struct mountpoint *mp = lookup_mountpoint(dentry);
-		if (!mp)
-			mp = new_mountpoint(dentry);
+		struct mountpoint *mp = get_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
 			mutex_unlock(&dentry->d_inode->i_mutex);
@@ -1982,7 +2059,11 @@ retry:
 static void unlock_mount(struct mountpoint *where)
 {
 	struct dentry *dentry = where->m_dentry;
+
+	read_seqlock_excl(&mount_lock);
 	put_mountpoint(where);
+	read_sequnlock_excl(&mount_lock);
+
 	namespace_unlock();
 	mutex_unlock(&dentry->d_inode->i_mutex);
 }
@@ -2401,8 +2482,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 		if (type->fs_flags & FS_USERNS_VISIBLE) {
-			if (!fs_fully_visible(type, &mnt_flags))
+			if (!fs_fully_visible(type, &mnt_flags)) {
+				put_filesystem(type);
 				return -EPERM;
+			}
 		}
 	}
 
@@ -2766,6 +2849,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 	init_waitqueue_head(&new_ns->poll);
 	new_ns->event = 0;
 	new_ns->user_ns = get_user_ns(user_ns);
+	new_ns->mounts = 0;
+	new_ns->pending_mounts = 0;
 	return new_ns;
 }
 
@@ -2815,6 +2900,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	q = new;
 	while (p) {
 		q->mnt_ns = new_ns;
+		new_ns->mounts++;
 		if (new_fs) {
 			if (&p->mnt == new_fs->root.mnt) {
 				new_fs->root.mnt = mntget(&q->mnt);
@@ -2853,6 +2939,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
 		struct mount *mnt = real_mount(m);
 		mnt->mnt_ns = new_ns;
 		new_ns->root = mnt;
+		new_ns->mounts++;
 		list_add(&mnt->mnt_list, &new_ns->list);
 	} else {
 		mntput(m);
@@ -3052,9 +3139,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
+	put_mountpoint(root_mp);
 	unlock_mount_hash();
 	chroot_fs_refs(&root, &new);
-	put_mountpoint(root_mp);
 	error = 0;
 out4:
 	unlock_mount(old_mp);
@@ -3236,6 +3323,10 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 		if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC)
 			mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC);
 
+		/* Don't miss readonly hidden in the superblock flags */
+		if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY)
+			mnt_flags |= MNT_LOCK_READONLY;
+
 		/* Verify the mount flags are equal to or more permissive
 		 * than the proposed new mount.
 		 */
@@ -3262,7 +3353,7 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
 			struct inode *inode = child->mnt_mountpoint->d_inode;
 			/* Only worry about locked mounts */
-			if (!(mnt_flags & MNT_LOCKED))
+			if (!(child->mnt.mnt_flags & MNT_LOCKED))
 				continue;
 			/* Is the directory permanetly empty? */
 			if (!is_empty_dir_inode(inode))
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f31fd0dd92c6..b1daeafbea92 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT
 config PNFS_BLOCK
 	tristate
 	depends on NFS_V4_1 && BLK_DEV_DM
+	depends on 64BIT || LBDAF
 	default NFS_V4
 
 config PNFS_OBJLAYOUT
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index a7f2e6e33305..48efe62e1302 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -261,7 +261,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	}
 
 	ret = -EPROTONOSUPPORT;
-	if (minorversion == 0)
+	if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0)
 		ret = nfs4_callback_up_net(serv, net);
 	else if (xprt->ops->bc_up)
 		ret = xprt->ops->bc_up(serv, net);
@@ -275,6 +275,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 err_socks:
 	svc_rpcb_cleanup(serv, net);
 err_bind:
+	nn->cb_users[minorversion]--;
 	dprintk("NFS: Couldn't create callback socket: err = %d; "
 			"net = %p\n", ret, net);
 	return ret;
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 646cdac73488..e2e857affbf2 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -912,7 +912,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	if (hdr_arg.minorversion == 0) {
 		cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
-			return rpc_drop_reply;
+			goto out_invalidcred;
 	}
 
 	cps.minorversion = hdr_arg.minorversion;
@@ -940,6 +940,10 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	nfs_put_client(cps.clp);
 	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
+
+out_invalidcred:
+	pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n");
+	return rpc_autherr_badcred;
 }
 
 /*
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5166adcfc0fb..7af5eeabc80e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -41,6 +41,17 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
 	set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags);
 }
 
+static bool
+nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
+		fmode_t flags)
+{
+	if (delegation != NULL && (delegation->type & flags) == flags &&
+	    !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
+	    !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+		return true;
+	return false;
+}
+
 static int
 nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 {
@@ -50,8 +61,7 @@ nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 	flags &= FMODE_READ|FMODE_WRITE;
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
-	if (delegation != NULL && (delegation->type & flags) == flags &&
-	    !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+	if (nfs4_is_valid_delegation(delegation, flags)) {
 		if (mark)
 			nfs_mark_delegation_referenced(delegation);
 		ret = 1;
@@ -892,7 +902,7 @@ bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
 	flags &= FMODE_READ|FMODE_WRITE;
 	rcu_read_lock();
 	delegation = rcu_dereference(nfsi->delegation);
-	ret = (delegation != NULL && (delegation->type & flags) == flags);
+	ret = nfs4_is_valid_delegation(delegation, flags);
 	if (ret) {
 		nfs4_stateid_copy(dst, &delegation->stateid);
 		nfs_mark_delegation_referenced(delegation);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ce5a21861074..348e0a05bd18 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -377,7 +377,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
  again:
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
-	error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages,
+	error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages,
 					  NFS_SERVER(inode)->dtsize, desc->plus);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
@@ -462,7 +462,7 @@ void nfs_force_use_readdirplus(struct inode *dir)
 {
 	if (!list_empty(&NFS_I(dir)->open_files)) {
 		nfs_advise_use_readdirplus(dir);
-		nfs_zap_mapping(dir, dir->i_mapping);
+		invalidate_mapping_pages(dir->i_mapping, 0, -1);
 	}
 }
 
@@ -560,7 +560,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 		count++;
 
 		if (desc->plus != 0)
-			nfs_prime_dcache(desc->file->f_path.dentry, entry);
+			nfs_prime_dcache(file_dentry(desc->file), entry);
 
 		status = nfs_readdir_add_to_array(entry, page);
 		if (status != 0)
@@ -847,24 +847,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
 	goto out;
 }
 
-static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
-{
-	struct nfs_inode *nfsi = NFS_I(dir);
-
-	if (nfs_attribute_cache_expired(dir))
-		return true;
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-		return true;
-	return false;
-}
-
 /* The file offset position represents the dirent entry number.  A
    last cookie cache takes care of the common case of reading the
    whole directory.
  */
 static int nfs_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct dentry	*dentry = file->f_path.dentry;
+	struct dentry	*dentry = file_dentry(file);
 	struct inode	*inode = d_inode(dentry);
 	nfs_readdir_descriptor_t my_desc,
 			*desc = &my_desc;
@@ -890,7 +879,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
 
 	nfs_block_sillyrename(dentry);
-	if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
+	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
 	if (res < 0)
 		goto out;
@@ -1146,11 +1135,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	/* Force a full look up iff the parent directory has changed */
 	if (!nfs_is_exclusive_create(dir, flags) &&
 	    nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
-
-		if (nfs_lookup_verify_inode(inode, flags)) {
+		error = nfs_lookup_verify_inode(inode, flags);
+		if (error) {
 			if (flags & LOOKUP_RCU)
 				return -ECHILD;
-			goto out_zap_parent;
+			if (error == -ESTALE)
+				goto out_zap_parent;
+			goto out_error;
 		}
 		goto out_valid;
 	}
@@ -1174,8 +1165,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
 	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
-	if (error)
+	if (error == -ESTALE || error == -ENOENT)
 		goto out_bad;
+	if (error)
+		goto out_error;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
 		goto out_bad;
 	if ((error = nfs_refresh_inode(inode, fattr)) != 0)
@@ -1531,9 +1524,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 		put_nfs_open_context(ctx);
+		d_drop(dentry);
 		switch (err) {
 		case -ENOENT:
-			d_drop(dentry);
 			d_add(dentry, NULL);
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
@@ -2432,6 +2425,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
 }
 EXPORT_SYMBOL_GPL(nfs_may_open);
 
+static int nfs_execute_ok(struct inode *inode, int mask)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		ret = nfs_revalidate_inode_rcu(server, inode);
+	else
+		ret = nfs_revalidate_inode(server, inode);
+	if (ret == 0 && !execute_ok(inode))
+		ret = -EACCES;
+	return ret;
+}
+
 int nfs_permission(struct inode *inode, int mask)
 {
 	struct rpc_cred *cred;
@@ -2449,6 +2456,9 @@ int nfs_permission(struct inode *inode, int mask)
 		case S_IFLNK:
 			goto out;
 		case S_IFREG:
+			if ((mask & MAY_OPEN) &&
+			   nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN))
+				return 0;
 			break;
 		case S_IFDIR:
 			/*
@@ -2481,8 +2491,8 @@ force_lookup:
 			res = PTR_ERR(cred);
 	}
 out:
-	if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
-		res = -EACCES;
+	if (!res && (mask & MAY_EXEC))
+		res = nfs_execute_ok(inode, mask);
 
 	dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 93e236429c5d..dc875cd0e11d 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -407,7 +407,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	 */
 	if (!PageUptodate(page)) {
 		unsigned pglen = nfs_page_length(page);
-		unsigned end = offset + len;
+		unsigned end = offset + copied;
 
 		if (pglen == 0) {
 			zero_user_segments(page, 0, offset,
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 02ec07973bc4..fd8da630fd22 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -374,8 +374,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
-	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
+	pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4946ef40ba87..85ef38f9765f 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -283,7 +283,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
 out_test_devid:
-	if (filelayout_test_devid_unavailable(devid))
+	if (ret->ds_clp == NULL ||
+	    filelayout_test_devid_unavailable(devid))
 		ret = NULL;
 out:
 	return ret;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 2a2e2d8ddee5..54313322ee5b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1414,8 +1414,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
-	if (data->verf.committed == NFS_UNSTABLE
-	    && ff_layout_need_layoutcommit(data->lseg))
+	if (ff_layout_need_layoutcommit(data->lseg))
 		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e125e55de86d..2603d7589946 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -30,6 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
 {
 	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
 	nfs4_pnfs_ds_put(mirror_ds->ds);
+	kfree(mirror_ds->ds_versions);
 	kfree_rcu(mirror_ds, id_node.rcu);
 }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 3e2071a177fd..668ac19af58f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -927,7 +927,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 {
 	struct nfs_open_context *ctx;
 
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 	nfs_file_set_open_context(filp, ctx);
@@ -1241,9 +1241,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 		return 0;
 	/* Has the inode gone and changed behind our back? */
 	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
-		return -EIO;
+		return -ESTALE;
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
-		return -EIO;
+		return -ESTALE;
 
 	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
 			inode->i_version != fattr->change_attr)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9dea85f7f918..578350fd96e1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -243,7 +243,6 @@ int nfs_iocounter_wait(struct nfs_io_counter *c);
 extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
 struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
 void nfs_pgio_header_free(struct nfs_pgio_header *);
-void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 6b1ce9825430..7f1a0fb8c493 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -269,6 +269,7 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 	task = rpc_run_task(&task_setup);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
+	rpc_put_task(task);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index db9b5fea5b3e..679e003818b1 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -26,7 +26,7 @@ static int
 nfs4_file_open(struct inode *inode, struct file *filp)
 {
 	struct nfs_open_context *ctx;
-	struct dentry *dentry = filp->f_path.dentry;
+	struct dentry *dentry = file_dentry(filp);
 	struct dentry *parent = NULL;
 	struct inode *dir;
 	unsigned openflags = filp->f_flags;
@@ -57,7 +57,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	parent = dget_parent(dentry);
 	dir = d_inode(parent);
 
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode);
 	err = PTR_ERR(ctx);
 	if (IS_ERR(ctx))
 		goto out;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 98a44157353a..8e425f2c5ddd 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2188,8 +2188,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
 		return 0;
 
-	/* even though OPEN succeeded, access is denied. Close the file */
-	nfs4_close_state(state, fmode);
 	return -EACCES;
 }
 
@@ -2422,7 +2420,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata,
 		sattr->ia_valid |= ATTR_MTIME;
 
 	/* Except MODE, it seems harmless of setting twice. */
-	if ((attrset[1] & FATTR4_WORD1_MODE))
+	if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
+		attrset[1] & FATTR4_WORD1_MODE)
 		sattr->ia_valid &= ~ATTR_MODE;
 
 	if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -2451,6 +2450,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	ret = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto out;
+	ctx->state = state;
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
@@ -2473,7 +2473,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	ctx->state = state;
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
 		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -2854,12 +2853,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 			call_close |= is_wronly;
 		else if (is_wronly)
 			calldata->arg.fmode |= FMODE_WRITE;
+		if (calldata->arg.fmode != (FMODE_READ|FMODE_WRITE))
+			call_close |= is_rdwr;
 	} 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);
@@ -4711,7 +4709,7 @@ out:
  */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
+	struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -4725,13 +4723,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1;
 	int ret = -ENOMEM, i;
 
-	/* As long as we're doing a round trip to the server anyway,
-	 * let's be prepared for a page of acl data. */
-	if (npages == 0)
-		npages = 1;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
 
@@ -7425,12 +7419,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_create_session(clp, status);
 
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EACCES:
+	case -EAGAIN:
+		goto out;
+	};
+
+	clp->cl_seqid++;
 	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
 		status = nfs4_verify_channel_attrs(&args, &res);
 		/* Increment the clientid slot sequence id */
-		if (clp->cl_seqid == res.seqid)
-			clp->cl_seqid++;
 		if (status)
 			goto out;
 		nfs4_update_session(session, &res);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d854693a15b0..e8d1d6c5000c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1072,6 +1072,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 		case -NFS4ERR_BADXDR:
 		case -NFS4ERR_RESOURCE:
 		case -NFS4ERR_NOFILEHANDLE:
+		case -NFS4ERR_MOVED:
 			/* Non-seqid mutating errors */
 			return;
 	};
@@ -1493,6 +1494,9 @@ restart:
 					__func__, status);
 			case -ENOENT:
 			case -ENOMEM:
+			case -EACCES:
+			case -EROFS:
+			case -EIO:
 			case -ESTALE:
 				/* Open state on this file cannot be recovered */
 				nfs4_state_mark_recovery_failed(state, status);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4e4441216804..1cb50bb898b0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2487,7 +2487,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 452a011ba0d8..8ebfdd00044b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -528,16 +528,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops)
 }
 EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc);
 
-/*
- * nfs_pgio_header_free - Free a read or write header
- * @hdr: The header to free
- */
-void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
-{
-	hdr->rw_ops->rw_free_header(hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
-
 /**
  * nfs_pgio_data_destroy - make @hdr suitable for reuse
  *
@@ -546,14 +536,24 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
  *
  * @hdr: A header that has had nfs_generic_pgio called
  */
-void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
+static void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
 {
 	if (hdr->args.context)
 		put_nfs_open_context(hdr->args.context);
 	if (hdr->page_array.pagevec != hdr->page_array.page_array)
 		kfree(hdr->page_array.pagevec);
 }
-EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy);
+
+/*
+ * nfs_pgio_header_free - Free a read or write header
+ * @hdr: The header to free
+ */
+void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
+{
+	nfs_pgio_data_destroy(hdr);
+	hdr->rw_ops->rw_free_header(hdr);
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
 
 /**
  * nfs_pgio_rpcsetup - Set up arguments for a pageio call
@@ -671,7 +671,6 @@ static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
 	u32 midx;
 
 	set_bit(NFS_IOHDR_REDO, &hdr->flags);
-	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
 	/* TODO: Make sure it's right to clean up all mirrors here
 	 *       and not just hdr->pgio_mirror_idx */
@@ -689,7 +688,6 @@ static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
 static void nfs_pgio_release(void *calldata)
 {
 	struct nfs_pgio_header *hdr = calldata;
-	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bec0384499f7..7af7bedd7c02 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -365,6 +365,9 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
 static bool
 pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
 {
+	/* Serialise LAYOUTGET/LAYOUTRETURN */
+	if (atomic_read(&lo->plh_outstanding) != 0)
+		return false;
 	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return false;
 	lo->plh_return_iomode = 0;
@@ -1182,13 +1185,11 @@ bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
 	 * i_lock */
         spin_lock(&ino->i_lock);
         lo = nfsi->layout;
-        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
                 sleep = true;
+	}
         spin_unlock(&ino->i_lock);
-
-        if (sleep)
-                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
-
         return sleep;
 }
 
@@ -1530,6 +1531,7 @@ pnfs_update_layout(struct inode *ino,
 		goto out;
 
 lookup_again:
+	nfs4_client_recover_expired_lease(clp);
 	first = false;
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
@@ -1941,7 +1943,6 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_write_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	nfs_pgio_data_destroy(hdr);
 	hdr->release(hdr);
 }
 
@@ -2057,7 +2058,6 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_read_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	nfs_pgio_data_destroy(hdr);
 	hdr->release(hdr);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7b9316406930..7a9b6e347249 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1261,6 +1261,9 @@ int nfs_updatepage(struct file *file, struct page *page,
 	dprintk("NFS:       nfs_updatepage(%pD2 %d@%lld)\n",
 		file, count, (long long)(page_file_offset(page) + offset));
 
+	if (!count)
+		goto out;
+
 	if (nfs_can_extend_write(file, page, inode)) {
 		count = max(count + offset, nfs_page_length(page));
 		offset = 0;
@@ -1271,7 +1274,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 		nfs_set_pageerror(page);
 	else
 		__set_page_dirty_nobuffers(page);
-
+out:
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
 	return status;
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index c29d9421bd5e..0976f8dad4ce 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -50,7 +50,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 {
 	struct nfsd4_layout_seg *seg = &args->lg_seg;
 	struct super_block *sb = inode->i_sb;
-	u32 block_size = (1 << inode->i_blkbits);
+	u32 block_size = i_blocksize(inode);
 	struct pnfs_block_extent *bex;
 	struct iomap iomap;
 	u32 device_generation = 0;
@@ -151,7 +151,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
 	int error;
 
 	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+			lcp->lc_up_len, &iomaps, i_blocksize(inode));
 	if (nr_iomaps < 0)
 		return nfserrno(nr_iomaps);
 
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 1580ea6fd64d..d08cd88155c7 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -104,22 +104,21 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
 		goto out;
 
 	inode = d_inode(fh->fh_dentry);
-	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
-		error = -EOPNOTSUPP;
-		goto out_errno;
-	}
 
 	error = fh_want_write(fh);
 	if (error)
 		goto out_errno;
 
-	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	fh_lock(fh);
+
+	error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
 	if (error)
-		goto out_drop_write;
-	error = inode->i_op->set_acl(inode, argp->acl_default,
-				     ACL_TYPE_DEFAULT);
+		goto out_drop_lock;
+	error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
 	if (error)
-		goto out_drop_write;
+		goto out_drop_lock;
+
+	fh_unlock(fh);
 
 	fh_drop_write(fh);
 
@@ -131,7 +130,8 @@ out:
 	posix_acl_release(argp->acl_access);
 	posix_acl_release(argp->acl_default);
 	return nfserr;
-out_drop_write:
+out_drop_lock:
+	fh_unlock(fh);
 	fh_drop_write(fh);
 out_errno:
 	nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 01df4cd7c753..0c890347cde3 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -95,22 +95,20 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
 		goto out;
 
 	inode = d_inode(fh->fh_dentry);
-	if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
-		error = -EOPNOTSUPP;
-		goto out_errno;
-	}
 
 	error = fh_want_write(fh);
 	if (error)
 		goto out_errno;
 
-	error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
+	fh_lock(fh);
+
+	error = set_posix_acl(inode, ACL_TYPE_ACCESS, argp->acl_access);
 	if (error)
-		goto out_drop_write;
-	error = inode->i_op->set_acl(inode, argp->acl_default,
-				     ACL_TYPE_DEFAULT);
+		goto out_drop_lock;
+	error = set_posix_acl(inode, ACL_TYPE_DEFAULT, argp->acl_default);
 
-out_drop_write:
+out_drop_lock:
+	fh_unlock(fh);
 	fh_drop_write(fh);
 out_errno:
 	nfserr = nfserrno(error);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 00575d776d91..7162ab7bc093 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -358,6 +358,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
+	struct kvec *head = rqstp->rq_arg.head;
 
 	p = decode_fh(p, &args->fh);
 	if (!p)
@@ -367,6 +368,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = ntohl(*p++);
 	args->stable = ntohl(*p++);
 	len = args->len = ntohl(*p++);
+	if ((void *)p > head->iov_base + head->iov_len)
+		return 0;
 	/*
 	 * The count must equal the amount of data passed.
 	 */
@@ -377,9 +380,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 	/*
 	 * Round the length of the data which was specified up to
 	 * the next multiple of XDR units and then compare that
@@ -396,7 +398,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		len = args->len = max_blocksize;
 	}
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
@@ -471,6 +473,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	/* first copy and check from the first page */
 	old = (char*)p;
 	vec = &rqstp->rq_arg.head[0];
+	if ((void *)old > vec->iov_base + vec->iov_len)
+		return 0;
 	avail = vec->iov_len - (old - (char*)vec->iov_base);
 	while (len && avail && *old) {
 		*new++ = *old++;
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 6adabd6049b7..71292a0d6f09 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -770,9 +770,6 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	inode = d_inode(dentry);
 
-	if (!inode->i_op->set_acl || !IS_POSIXACL(inode))
-		return nfserr_attrnotsupp;
-
 	if (S_ISDIR(inode->i_mode))
 		flags = NFS4_ACL_DIR;
 
@@ -782,16 +779,19 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_error < 0)
 		goto out_nfserr;
 
-	host_error = inode->i_op->set_acl(inode, pacl, ACL_TYPE_ACCESS);
+	fh_lock(fhp);
+
+	host_error = set_posix_acl(inode, ACL_TYPE_ACCESS, pacl);
 	if (host_error < 0)
-		goto out_release;
+		goto out_drop_lock;
 
 	if (S_ISDIR(inode->i_mode)) {
-		host_error = inode->i_op->set_acl(inode, dpacl,
-						  ACL_TYPE_DEFAULT);
+		host_error = set_posix_acl(inode, ACL_TYPE_DEFAULT, dpacl);
 	}
 
-out_release:
+out_drop_lock:
+	fh_unlock(fhp);
+
 	posix_acl_release(pacl);
 	posix_acl_release(dpacl);
 out_nfserr:
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index e7f50c4081d6..15bdc2d48cfe 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -710,22 +710,6 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 	}
 }
 
-static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
-{
-	struct rpc_xprt *xprt;
-
-	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
-		return rpc_create(args);
-
-	xprt = args->bc_xprt->xpt_bc_xprt;
-	if (xprt) {
-		xprt_get(xprt);
-		return rpc_create_xprt(args, xprt);
-	}
-
-	return rpc_create(args);
-}
-
 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);
@@ -768,7 +752,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
-	client = create_backchannel_client(&args);
+	client = rpc_create(&args);
 	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index c9d6c715c0fb..9eed219f57a5 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -189,10 +189,11 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	struct nfs4_layout_stateid *ls;
 	struct nfs4_stid *stp;
 
-	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache,
+					nfsd4_free_layout_stateid);
 	if (!stp)
 		return NULL;
-	stp->sc_free = nfsd4_free_layout_stateid;
+
 	get_nfs4_file(fp);
 	stp->sc_file = fp;
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a9f096c7e99f..209dbfc50cd4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -877,6 +877,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				    &exp, &dentry);
 	if (err)
 		return err;
+	fh_unlock(&cstate->current_fh);
 	if (d_really_is_negative(dentry)) {
 		exp_put(exp);
 		err = nfserr_noent;
@@ -1689,6 +1690,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			opdesc->op_get_currentstateid(cstate, &op->u);
 		op->status = opdesc->op_func(rqstp, cstate, &op->u);
 
+		/* Only from SEQUENCE */
+		if (cstate->status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			status = op->status;
+			goto out;
+		}
 		if (!op->status) {
 			if (opdesc->op_set_currentstateid)
 				opdesc->op_set_currentstateid(cstate, &op->u);
@@ -1699,14 +1706,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			if (need_wrongsec_check(rqstp))
 				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
 		}
-
 encode_op:
-		/* Only from SEQUENCE */
-		if (cstate->status == nfserr_replay_cache) {
-			dprintk("%s NFS4.1 replay from cache\n", __func__);
-			status = op->status;
-			goto out;
-		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(&resp->xdr, op);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6b800b5b8fed..c7f1ce41442a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -553,8 +553,8 @@ out:
 	return co;
 }
 
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
-					 struct kmem_cache *slab)
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *))
 {
 	struct nfs4_stid *stid;
 	int new_id;
@@ -570,6 +570,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 	idr_preload_end();
 	if (new_id < 0)
 		goto out_free;
+
+	stid->sc_free = sc_free;
 	stid->sc_client = cl;
 	stid->sc_stateid.si_opaque.so_id = new_id;
 	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
@@ -595,15 +597,12 @@ out_free:
 static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 {
 	struct nfs4_stid *stid;
-	struct nfs4_ol_stateid *stp;
 
-	stid = nfs4_alloc_stid(clp, stateid_slab);
+	stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
 	if (!stid)
 		return NULL;
 
-	stp = openlockstateid(stid);
-	stp->st_stid.sc_free = nfs4_free_ol_stateid;
-	return stp;
+	return openlockstateid(stid);
 }
 
 static void nfs4_free_deleg(struct nfs4_stid *stid)
@@ -701,11 +700,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh,
 		goto out_dec;
 	if (delegation_blocked(&current_fh->fh_handle))
 		goto out_dec;
-	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
+	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
 	if (dp == NULL)
 		goto out_dec;
 
-	dp->dl_stid.sc_free = nfs4_free_deleg;
 	/*
 	 * delegation seqid's are never incremented.  The 4.1 special
 	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -1200,27 +1198,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist)
 	}
 }
 
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-	struct nfs4_ol_stateid *stp;
-	struct list_head reaplist;
-
-	INIT_LIST_HEAD(&reaplist);
-
-	spin_lock(&clp->cl_lock);
-	unhash_lockowner_locked(lo);
-	while (!list_empty(&lo->lo_owner.so_stateids)) {
-		stp = list_first_entry(&lo->lo_owner.so_stateids,
-				struct nfs4_ol_stateid, st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
-		put_ol_stateid_locked(stp, &reaplist);
-	}
-	spin_unlock(&clp->cl_lock);
-	free_ol_stateid_reaplist(&reaplist);
-	nfs4_put_stateowner(&lo->lo_owner);
-}
-
 static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 				       struct list_head *reaplist)
 {
@@ -3452,6 +3429,10 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	struct nfs4_openowner *oo = open->op_openowner;
 	struct nfs4_ol_stateid *retstp = NULL;
 
+	/* We are moving these outside of the spinlocks to avoid the warnings */
+	mutex_init(&stp->st_mutex);
+	mutex_lock(&stp->st_mutex);
+
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
 
@@ -3467,13 +3448,17 @@ init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = 0;
 	stp->st_openstp = NULL;
-	init_rwsem(&stp->st_rwsem);
 	list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
 
 out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
+	if (retstp) {
+		mutex_lock(&retstp->st_mutex);
+		/* Not that we need to, just for neatness */
+		mutex_unlock(&stp->st_mutex);
+	}
 	return retstp;
 }
 
@@ -4300,32 +4285,34 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 */
 	if (stp) {
 		/* Stateid was found, this is an OPEN upgrade */
-		down_read(&stp->st_rwsem);
+		mutex_lock(&stp->st_mutex);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 	} else {
 		stp = open->op_stp;
 		open->op_stp = NULL;
+		/*
+		 * init_open_stateid() either returns a locked stateid
+		 * it found, or initializes and locks the new one we passed in
+		 */
 		swapstp = init_open_stateid(stp, fp, open);
 		if (swapstp) {
 			nfs4_put_stid(&stp->st_stid);
 			stp = swapstp;
-			down_read(&stp->st_rwsem);
 			status = nfs4_upgrade_open(rqstp, fp, current_fh,
 						stp, open);
 			if (status) {
-				up_read(&stp->st_rwsem);
+				mutex_unlock(&stp->st_mutex);
 				goto out;
 			}
 			goto upgrade_out;
 		}
-		down_read(&stp->st_rwsem);
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			up_read(&stp->st_rwsem);
+			mutex_unlock(&stp->st_mutex);
 			release_open_stateid(stp);
 			goto out;
 		}
@@ -4337,7 +4324,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	}
 upgrade_out:
 	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
-	up_read(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	if (nfsd4_has_session(&resp->cstate)) {
 		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
@@ -4872,6 +4859,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return nfs_ok;
 }
 
+static __be32
+nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
+{
+	struct nfs4_ol_stateid *stp = openlockstateid(s);
+	__be32 ret;
+
+	mutex_lock(&stp->st_mutex);
+
+	ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
+	if (ret)
+		goto out;
+
+	ret = nfserr_locks_held;
+	if (check_for_locks(stp->st_stid.sc_file,
+			    lockowner(stp->st_stateowner)))
+		goto out;
+
+	release_lock_stateid(stp);
+	ret = nfs_ok;
+
+out:
+	mutex_unlock(&stp->st_mutex);
+	nfs4_put_stid(s);
+	return ret;
+}
+
 __be32
 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   struct nfsd4_free_stateid *free_stateid)
@@ -4879,7 +4892,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	stateid_t *stateid = &free_stateid->fr_stateid;
 	struct nfs4_stid *s;
 	struct nfs4_delegation *dp;
-	struct nfs4_ol_stateid *stp;
 	struct nfs4_client *cl = cstate->session->se_client;
 	__be32 ret = nfserr_bad_stateid;
 
@@ -4898,18 +4910,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		ret = nfserr_locks_held;
 		break;
 	case NFS4_LOCK_STID:
-		ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
-		if (ret)
-			break;
-		stp = openlockstateid(s);
-		ret = nfserr_locks_held;
-		if (check_for_locks(stp->st_stid.sc_file,
-				    lockowner(stp->st_stateowner)))
-			break;
-		WARN_ON(!unhash_lock_stateid(stp));
+		atomic_inc(&s->sc_count);
 		spin_unlock(&cl->cl_lock);
-		nfs4_put_stid(s);
-		ret = nfs_ok;
+		ret = nfsd4_free_lock_stateid(stateid, s);
 		goto out;
 	case NFS4_REVOKED_DELEG_STID:
 		dp = delegstateid(s);
@@ -4950,12 +4953,12 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 		 * revoked delegations are kept only for free_stateid.
 		 */
 		return nfserr_bad_stateid;
-	down_write(&stp->st_rwsem);
+	mutex_lock(&stp->st_mutex);
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status == nfs_ok)
 		status = nfs4_check_fh(current_fh, &stp->st_stid);
 	if (status != nfs_ok)
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 	return status;
 }
 
@@ -5003,7 +5006,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 		return status;
 	oo = openowner(stp->st_stateowner);
 	if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 		nfs4_put_stid(&stp->st_stid);
 		return nfserr_bad_stateid;
 	}
@@ -5035,12 +5038,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	oo = openowner(stp->st_stateowner);
 	status = nfserr_bad_stateid;
 	if (oo->oo_flags & NFS4_OO_CONFIRMED) {
-		up_write(&stp->st_rwsem);
+		mutex_unlock(&stp->st_mutex);
 		goto put_stateid;
 	}
 	oo->oo_flags |= NFS4_OO_CONFIRMED;
 	nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
 		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid));
 
@@ -5116,7 +5119,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid);
 	status = nfs_ok;
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5169,7 +5172,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out; 
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 
 	nfsd4_close_open_stateid(stp);
 
@@ -5391,11 +5394,10 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
-	stp->st_stid.sc_free = nfs4_free_lock_stateid;
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
-	init_rwsem(&stp->st_rwsem);
+	mutex_init(&stp->st_mutex);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	spin_lock(&fp->fi_lock);
@@ -5434,7 +5436,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 	lst = find_lock_stateid(lo, fi);
 	if (lst == NULL) {
 		spin_unlock(&clp->cl_lock);
-		ns = nfs4_alloc_stid(clp, stateid_slab);
+		ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
 		if (ns == NULL)
 			return NULL;
 
@@ -5476,7 +5478,7 @@ static __be32
 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 			    struct nfs4_ol_stateid *ost,
 			    struct nfsd4_lock *lock,
-			    struct nfs4_ol_stateid **lst, bool *new)
+			    struct nfs4_ol_stateid **plst, bool *new)
 {
 	__be32 status;
 	struct nfs4_file *fi = ost->st_stid.sc_file;
@@ -5484,7 +5486,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 	struct nfs4_client *cl = oo->oo_owner.so_client;
 	struct inode *inode = d_inode(cstate->current_fh.fh_dentry);
 	struct nfs4_lockowner *lo;
+	struct nfs4_ol_stateid *lst;
 	unsigned int strhashval;
+	bool hashed;
 
 	lo = find_lockowner_str(cl, &lock->lk_new_owner);
 	if (!lo) {
@@ -5500,12 +5504,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
 			goto out;
 	}
 
-	*lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
-	if (*lst == NULL) {
+retry:
+	lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
+	if (lst == NULL) {
 		status = nfserr_jukebox;
 		goto out;
 	}
+
+	mutex_lock(&lst->st_mutex);
+
+	/* See if it's still hashed to avoid race with FREE_STATEID */
+	spin_lock(&cl->cl_lock);
+	hashed = !list_empty(&lst->st_perfile);
+	spin_unlock(&cl->cl_lock);
+
+	if (!hashed) {
+		mutex_unlock(&lst->st_mutex);
+		nfs4_put_stid(&lst->st_stid);
+		goto retry;
+	}
 	status = nfs_ok;
+	*plst = lst;
 out:
 	nfs4_put_stateowner(&lo->lo_owner);
 	return status;
@@ -5564,7 +5583,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 					&open_stp, nn);
 		if (status)
 			goto out;
-		up_write(&open_stp->st_rwsem);
+		mutex_unlock(&open_stp->st_mutex);
 		open_sop = openowner(open_stp->st_stateowner);
 		status = nfserr_bad_stateid;
 		if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid,
@@ -5572,8 +5591,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			goto out;
 		status = lookup_or_create_lock_state(cstate, open_stp, lock,
 							&lock_stp, &new);
-		if (status == nfs_ok)
-			down_write(&lock_stp->st_rwsem);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
 				       lock->lk_old_lock_seqid,
@@ -5677,7 +5694,7 @@ out:
 		    seqid_mutating_err(ntohl(status)))
 			lock_sop->lo_owner.so_seqid++;
 
-		up_write(&lock_stp->st_rwsem);
+		mutex_unlock(&lock_stp->st_mutex);
 
 		/*
 		 * If this is a new, never-before-used stateid, and we are
@@ -5847,7 +5864,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 fput:
 	fput(filp);
 put_stateid:
-	up_write(&stp->st_rwsem);
+	mutex_unlock(&stp->st_mutex);
 	nfs4_put_stid(&stp->st_stid);
 out:
 	nfsd4_bump_seqid(cstate, status);
@@ -5911,6 +5928,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfs4_client *clp;
+	LIST_HEAD (reaplist);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -5941,9 +5959,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		nfs4_get_stateowner(sop);
 		break;
 	}
+	if (!lo) {
+		spin_unlock(&clp->cl_lock);
+		return status;
+	}
+
+	unhash_lockowner_locked(lo);
+	while (!list_empty(&lo->lo_owner.so_stateids)) {
+		stp = list_first_entry(&lo->lo_owner.so_stateids,
+				       struct nfs4_ol_stateid,
+				       st_perstateowner);
+		WARN_ON(!unhash_lock_stateid(stp));
+		put_ol_stateid_locked(stp, &reaplist);
+	}
 	spin_unlock(&clp->cl_lock);
-	if (lo)
-		release_lockowner(lo);
+	free_ol_stateid_reaplist(&reaplist);
+	nfs4_put_stateowner(&lo->lo_owner);
+
 	return status;
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 51c9e9ca39a4..544672b440de 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -129,7 +129,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp)
 	argp->p = page_address(argp->pagelist[0]);
 	argp->pagelist++;
 	if (argp->pagelen < PAGE_SIZE) {
-		argp->end = argp->p + (argp->pagelen>>2);
+		argp->end = argp->p + XDR_QUADLEN(argp->pagelen);
 		argp->pagelen = 0;
 	} else {
 		argp->end = argp->p + (PAGE_SIZE>>2);
@@ -1072,8 +1072,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
 
 	READ_BUF(4);
 	rename->rn_snamelen = be32_to_cpup(p++);
-	READ_BUF(rename->rn_snamelen + 4);
+	READ_BUF(rename->rn_snamelen);
 	SAVEMEM(rename->rn_sname, rename->rn_snamelen);
+	READ_BUF(4);
 	rename->rn_tnamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_tnamelen);
 	SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
@@ -1155,13 +1156,14 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 	READ_BUF(8);
 	setclientid->se_callback_prog = be32_to_cpup(p++);
 	setclientid->se_callback_netid_len = be32_to_cpup(p++);
-
-	READ_BUF(setclientid->se_callback_netid_len + 4);
+	READ_BUF(setclientid->se_callback_netid_len);
 	SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
+	READ_BUF(4);
 	setclientid->se_callback_addr_len = be32_to_cpup(p++);
 
-	READ_BUF(setclientid->se_callback_addr_len + 4);
+	READ_BUF(setclientid->se_callback_addr_len);
 	SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
+	READ_BUF(4);
 	setclientid->se_callback_ident = be32_to_cpup(p++);
 
 	DECODE_TAIL;
@@ -1244,9 +1246,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 		argp->pagelen -= pages * PAGE_SIZE;
 		len -= pages * PAGE_SIZE;
 
-		argp->p = (__be32 *)page_address(argp->pagelist[0]);
-		argp->pagelist++;
-		argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
+		next_decode_page(argp);
 	}
 	argp->p += XDR_QUADLEN(len);
 
@@ -1815,8 +1815,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 
 	READ_BUF(4);
 	argp->taglen = be32_to_cpup(p++);
-	READ_BUF(argp->taglen + 8);
+	READ_BUF(argp->taglen);
 	SAVEMEM(argp->tag, argp->taglen);
+	READ_BUF(8);
 	argp->minorversion = be32_to_cpup(p++);
 	argp->opcnt = be32_to_cpup(p++);
 	max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);
@@ -2750,9 +2751,16 @@ out_acl:
 	}
 #endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
-		status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD1,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD2);
+		u32 supp[3];
+
+		supp[0] = nfsd_suppattrs0(minorversion);
+		supp[1] = nfsd_suppattrs1(minorversion);
+		supp[2] = nfsd_suppattrs2(minorversion);
+		supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0;
+		supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1;
+		supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2;
+
+		status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]);
 		if (status)
 			goto out;
 	}
@@ -4038,8 +4046,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_getdeviceinfo *gdev)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[gdev->gd_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	u32 starting_len = xdr->buf->len, needed_len;
 	__be32 *p;
 
@@ -4056,6 +4063,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	/* If maxcount is 0 then just update notifications */
 	if (gdev->gd_maxcount != 0) {
+		ops = nfsd4_layout_ops[gdev->gd_layout_type];
 		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
 		if (nfserr) {
 			/*
@@ -4108,8 +4116,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_layoutget *lgp)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[lgp->lg_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	__be32 *p;
 
 	dprintk("%s: err %d\n", __func__, nfserr);
@@ -4132,6 +4139,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
 	*p++ = cpu_to_be32(lgp->lg_layout_type);
 
+	ops = nfsd4_layout_ops[lgp->lg_layout_type];
 	nfserr = ops->encode_layoutget(xdr, lgp);
 out:
 	kfree(lgp->lg_content);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ad4e2377dd63..5be1fa6b676d 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -656,6 +656,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
 	return nfserr;
 }
 
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page.  The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases.  Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+				struct svc_procedure *proc)
+{
+	/*
+	 * The ACL code has more careful bounds-checking and is not
+	 * susceptible to this problem:
+	 */
+	if (rqstp->rq_prog != NFS_PROGRAM)
+		return false;
+	/*
+	 * Ditto NFSv4 (which can in theory have argument and reply both
+	 * more than a page):
+	 */
+	if (rqstp->rq_vers >= 4)
+		return false;
+	/* The reply will be small, we're OK: */
+	if (proc->pc_xdrressize > 0 &&
+	    proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+		return false;
+
+	return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
@@ -668,6 +699,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 				rqstp->rq_vers, rqstp->rq_proc);
 	proc = rqstp->rq_procinfo;
 
+	if (nfs_request_too_big(rqstp, proc)) {
+		dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+		*statp = rpc_garbage_args;
+		return 1;
+	}
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
 	 * (necessary in the NFSv4.0 compound case)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 79d964aa8079..bf913201a6ad 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd_writeargs *args)
 {
 	unsigned int len, hdr, dlen;
+	struct kvec *head = rqstp->rq_arg.head;
 	int v;
 
 	p = decode_fh(p, &args->fh);
@@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	if (hdr > head->iov_len)
+		return 0;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 
 	/*
 	 * Round the length of the data which was specified up to
@@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		return 0;
 
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 77fdf4de91ba..5134eedcb16c 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -535,7 +535,7 @@ struct nfs4_ol_stateid {
 	unsigned char			st_access_bmap;
 	unsigned char			st_deny_bmap;
 	struct nfs4_ol_stateid		*st_openstp;
-	struct rw_semaphore		st_rwsem;
+	struct mutex			st_mutex;
 };
 
 static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
@@ -583,8 +583,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
-		struct kmem_cache *slab);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *));
 void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 994d66fbb446..91e0c5429b4d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -369,7 +369,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	__be32		err;
 	int		host_err;
 	bool		get_write_count;
-	int		size_change = 0;
+	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -382,11 +382,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
-		goto out;
+		return err;
 	if (get_write_count) {
 		host_err = fh_want_write(fhp);
 		if (host_err)
-			return nfserrno(host_err);
+			goto out;
 	}
 
 	dentry = fhp->fh_dentry;
@@ -397,20 +397,28 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		iap->ia_valid &= ~ATTR_MODE;
 
 	if (!iap->ia_valid)
-		goto out;
+		return 0;
 
 	nfsd_sanitize_attrs(inode, iap);
 
+	if (check_guard && guardtime != inode->i_ctime.tv_sec)
+		return nfserr_notsync;
+
 	/*
 	 * The size case is special, it changes the file in addition to the
-	 * attributes.
+	 * attributes, and file systems don't expect it to be mixed with
+	 * "random" attribute changes.  We thus split out the size change
+	 * into a separate call to ->setattr, and do the rest as a separate
+	 * setattr call.
 	 */
-	if (iap->ia_valid & ATTR_SIZE) {
+	if (size_change) {
 		err = nfsd_get_write_access(rqstp, fhp, iap);
 		if (err)
-			goto out;
-		size_change = 1;
+			return err;
+	}
 
+	fh_lock(fhp);
+	if (size_change) {
 		/*
 		 * RFC5661, Section 18.30.4:
 		 *   Changing the size of a file with SETATTR indirectly
@@ -418,29 +426,36 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		 *
 		 * (and similar for the older RFCs)
 		 */
-		if (iap->ia_size != i_size_read(inode))
-			iap->ia_valid |= ATTR_MTIME;
-	}
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
 
-	iap->ia_valid |= ATTR_CTIME;
+		host_err = notify_change(dentry, &size_attr, NULL);
+		if (host_err)
+			goto out_unlock;
+		iap->ia_valid &= ~ATTR_SIZE;
 
-	if (check_guard && guardtime != inode->i_ctime.tv_sec) {
-		err = nfserr_notsync;
-		goto out_put_write_access;
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			goto out_unlock;
 	}
 
-	fh_lock(fhp);
+	iap->ia_valid |= ATTR_CTIME;
 	host_err = notify_change(dentry, iap, NULL);
-	fh_unlock(fhp);
-	err = nfserrno(host_err);
 
-out_put_write_access:
+out_unlock:
+	fh_unlock(fhp);
 	if (size_change)
 		put_write_access(inode);
-	if (!err)
-		err = nfserrno(commit_metadata(fhp));
 out:
-	return err;
+	if (!host_err)
+		host_err = commit_metadata(fhp);
+	return nfserrno(host_err);
 }
 
 #if defined(CONFIG_NFSD_V4)
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index a35ae35e6932..cd39b57288c2 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -55,7 +55,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 		brelse(bh);
 		BUG();
 	}
-	memset(bh->b_data, 0, 1 << inode->i_blkbits);
+	memset(bh->b_data, 0, i_blocksize(inode));
 	bh->b_bdev = inode->i_sb->s_bdev;
 	bh->b_blocknr = blocknr;
 	set_buffer_mapped(bh);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index ac2f64943ff4..00877ef0b120 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -55,7 +55,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_add_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_add(n, &root->blocks_count);
 }
@@ -64,7 +64,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_sub_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_sub(n, &root->blocks_count);
 }
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 1125f40233ff..612a2457243d 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -60,7 +60,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 	set_buffer_mapped(bh);
 
 	kaddr = kmap_atomic(bh->b_page);
-	memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits);
+	memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
 	if (init_block)
 		init_block(inode, bh, kaddr);
 	flush_dcache_page(bh->b_page);
@@ -503,7 +503,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size,
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
 
 	mi->mi_entry_size = entry_size;
-	mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size;
+	mi->mi_entries_per_block = i_blocksize(inode) / entry_size;
 	mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
 }
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 3b65adaae7e4..2f27c935bd57 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -719,7 +719,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 
 		lock_page(page);
 		if (!page_has_buffers(page))
-			create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+			create_empty_buffers(page, i_blocksize(inode), 0);
 		unlock_page(page);
 
 		bh = head = page_buffers(page);
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 69bd801afb53..37e49cb2ac4c 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -443,7 +443,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
 	if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC)
 		return 0;
 	bytes = le16_to_cpu(sbp->s_bytes);
-	if (bytes > BLOCK_SIZE)
+	if (bytes < sumoff + 4 || bytes > BLOCK_SIZE)
 		return 0;
 	crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp,
 		       sumoff);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d2f97ecca6a5..e0e5f7c3c99f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq, event->response ||
-				atomic_read(&group->fanotify_data.bypass_perm));
-
-	if (!event->response) {	/* bypass_perm set */
-		/*
-		 * Event was canceled because group is being destroyed. Remove
-		 * it from group's event list because we are responsible for
-		 * freeing the permission event.
-		 */
-		fsnotify_remove_event(group, &event->fae.fse);
-		return 0;
-	}
+	wait_event(group->fanotify_data.access_waitq, event->response);
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8e8e6bcd1d43..a64313868d3a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
+	struct fsnotify_event *fsn_event;
 
 	/*
-	 * There may be still new events arriving in the notification queue
-	 * but since userspace cannot use fanotify fd anymore, no event can
-	 * enter or leave access_list by now.
+	 * Stop new events from arriving in the notification queue. since
+	 * userspace cannot use fanotify fd anymore, no event can enter or
+	 * leave access_list by now either.
 	 */
-	spin_lock(&group->fanotify_data.access_lock);
-
-	atomic_inc(&group->fanotify_data.bypass_perm);
+	fsnotify_group_stop_queueing(group);
 
+	/*
+	 * Process all permission events on access_list and notification queue
+	 * and simulate reply from userspace.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
 				 fae.fse.list) {
 		pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	spin_unlock(&group->fanotify_data.access_lock);
 
 	/*
-	 * Since bypass_perm is set, newly queued events will not wait for
-	 * access response. Wake up the already sleeping ones now.
-	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
-	 * processes sleeping in fanotify_handle_event() waiting for access
-	 * response and thus also for all permission events to be freed.
+	 * Destroy all non-permission events. For permission events just
+	 * dequeue them and set the response. They will be freed once the
+	 * response is consumed and fanotify_get_response() returns.
 	 */
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		fsn_event = fsnotify_remove_first_event(group);
+		if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+			fsnotify_destroy_event(group, fsn_event);
+		else
+			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+	}
+	mutex_unlock(&group->notification_mutex);
+
+	/* Response for all permission events it set, wakeup waiters */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 
@@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index db39de2dd4cb..a64adc2fced9 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -104,16 +104,20 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 	if (unlikely(!fsnotify_inode_watches_children(p_inode)))
 		__fsnotify_update_child_dentry_flags(p_inode);
 	else if (p_inode->i_fsnotify_mask & mask) {
+		struct name_snapshot name;
+
 		/* we are notifying a parent so come up with the new mask which
 		 * specifies these are events which came from a child. */
 		mask |= FS_EVENT_ON_CHILD;
 
+		take_dentry_name_snapshot(&name, dentry);
 		if (path)
 			ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
-				       dentry->d_name.name, 0);
+				       name.name, 0);
 		else
 			ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
-				       dentry->d_name.name, 0);
+				       name.name, 0);
+		release_dentry_name_snapshot(&name);
 	}
 
 	dput(parent);
diff --git a/fs/notify/group.c b/fs/notify/group.c
index d16b62cb2854..18eb30c6bd8f 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 }
 
 /*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	mutex_lock(&group->notification_mutex);
+	group->shutdown = true;
+	mutex_unlock(&group->notification_mutex);
+}
+
+/*
  * Trying to get rid of a group. Remove all marks, flush all events and release
  * the group reference.
  * Note that another thread calling fsnotify_clear_marks_by_group() may still
@@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
  */
 void fsnotify_destroy_group(struct fsnotify_group *group)
 {
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
 	/* clear all inode marks for this group */
 	fsnotify_clear_marks_by_group(group);
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index a95d8e037aeb..e455e83ceeeb 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
  * added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
  */
 int fsnotify_add_event(struct fsnotify_group *group,
 		       struct fsnotify_event *event,
@@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group,
 
 	mutex_lock(&group->notification_mutex);
 
+	if (group->shutdown) {
+		mutex_unlock(&group->notification_mutex);
+		return 2;
+	}
+
 	if (group->q_len >= group->max_events) {
 		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
@@ -126,21 +132,6 @@ queue:
 }
 
 /*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
-			   struct fsnotify_event *event)
-{
-	mutex_lock(&group->notification_mutex);
-	if (!list_empty(&event->list)) {
-		list_del_init(&event->list);
-		group->q_len--;
-	}
-	mutex_unlock(&group->notification_mutex);
-}
-
-/*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event
  */
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 0cdf497c91ef..164307b99405 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -241,13 +241,11 @@ int ocfs2_set_acl(handle_t *handle,
 	case ACL_TYPE_ACCESS:
 		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
 		if (acl) {
-			umode_t mode = inode->i_mode;
-			ret = posix_acl_equiv_mode(acl, &mode);
-			if (ret < 0)
-				return ret;
+			umode_t mode;
 
-			if (ret == 0)
-				acl = NULL;
+			ret = posix_acl_update_mode(inode, &mode, &acl);
+			if (ret)
+				return ret;
 
 			ret = ocfs2_acl_set_mode(inode, di_bh,
 						 handle, mode);
@@ -322,3 +320,90 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 	brelse(di_bh);
 	return acl;
 }
+
+int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl;
+	int ret;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return 0;
+
+	acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
+	if (IS_ERR(acl) || !acl)
+		return PTR_ERR(acl);
+	ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+	if (ret)
+		return ret;
+	ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
+			    acl, NULL, NULL);
+	posix_acl_release(acl);
+	return ret;
+}
+
+/*
+ * Initialize the ACLs of a new inode. If parent directory has default ACL,
+ * then clone to new inode. Called from ocfs2_mknod.
+ */
+int ocfs2_init_acl(handle_t *handle,
+		   struct inode *inode,
+		   struct inode *dir,
+		   struct buffer_head *di_bh,
+		   struct buffer_head *dir_bh,
+		   struct ocfs2_alloc_context *meta_ac,
+		   struct ocfs2_alloc_context *data_ac)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl = NULL;
+	int ret = 0, ret2;
+	umode_t mode;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+			acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
+						   dir_bh);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+		if (!acl) {
+			mode = inode->i_mode & ~current_umask();
+			ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+			if (ret) {
+				mlog_errno(ret);
+				goto cleanup;
+			}
+		}
+	}
+	if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
+		if (S_ISDIR(inode->i_mode)) {
+			ret = ocfs2_set_acl(handle, inode, di_bh,
+					    ACL_TYPE_DEFAULT, acl,
+					    meta_ac, data_ac);
+			if (ret)
+				goto cleanup;
+		}
+		mode = inode->i_mode;
+		ret = __posix_acl_create(&acl, GFP_NOFS, &mode);
+		if (ret < 0)
+			return ret;
+
+		ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+		if (ret2) {
+			mlog_errno(ret2);
+			ret = ret2;
+			goto cleanup;
+		}
+		if (ret > 0) {
+			ret = ocfs2_set_acl(handle, inode,
+					    di_bh, ACL_TYPE_ACCESS,
+					    acl, meta_ac, data_ac);
+		}
+	}
+cleanup:
+	posix_acl_release(acl);
+	return ret;
+}
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 3fce68d08625..2783a75b3999 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -35,5 +35,10 @@ int ocfs2_set_acl(handle_t *handle,
 			 struct posix_acl *acl,
 			 struct ocfs2_alloc_context *meta_ac,
 			 struct ocfs2_alloc_context *data_ac);
+extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);
+extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
+			  struct buffer_head *, struct buffer_head *,
+			  struct ocfs2_alloc_context *,
+			  struct ocfs2_alloc_context *);
 
 #endif /* OCFS2_ACL_H */
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index e6795c7c76a8..e4184bd2a954 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1103,7 +1103,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 	int ret = 0;
 	struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
 	unsigned int block_end, block_start;
-	unsigned int bsize = 1 << inode->i_blkbits;
+	unsigned int bsize = i_blocksize(inode);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, bsize, 0);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 709fbbd44c65..acebc350e98d 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2070,13 +2070,13 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
 		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	unsigned long tmp;
@@ -2125,11 +2125,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
 
 }
 
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
 CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_dead_threshold,
 	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index e36d63ff1783..2e11658676eb 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -287,6 +287,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		status = DLM_DENIED;
 		goto bail;
 	}
+
+	if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+		mlog(0, "last convert request returned DLM_RECOVERING, but "
+		     "owner has already queued and sent ast to me. res %.*s, "
+		     "(cookie=%u:%llu, type=%d, conv=%d)\n",
+		     res->lockname.len, res->lockname.name,
+		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+		     lock->ml.type, lock->ml.convert_type);
+		status = DLM_NORMAL;
+		goto bail;
+	}
+
 	res->state |= DLM_LOCK_RES_IN_PROGRESS;
 	/* move lock to local convert queue */
 	/* do not alter lock refcount.  switching lists. */
@@ -315,13 +328,22 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
-	lock->convert_pending = 0;
-	/* if it failed, move it back to granted queue */
+	/* if it failed, move it back to granted queue.
+	 * if master returns DLM_NORMAL and then down before sending ast,
+	 * it may have already been moved to granted queue, reset to
+	 * DLM_RECOVERING and retry convert */
 	if (status != DLM_NORMAL) {
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
+	} else if (!lock->convert_pending) {
+		mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+				"to granted list, retry convert.\n",
+				dlm->name, res->lockname.len, res->lockname.name);
+		status = DLM_RECOVERING;
 	}
+
+	lock->convert_pending = 0;
 bail:
 	spin_unlock(&res->spinlock);
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 42f0cae93a0a..4a338803e7e9 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2064,7 +2064,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm,
 			dlm_lock_get(lock);
 			if (lock->convert_pending) {
 				/* move converting lock back to granted */
-				BUG_ON(i != DLM_CONVERTING_LIST);
 				mlog(0, "node died with convert pending "
 				     "on %.*s. move back to granted list.\n",
 				     res->lockname.len, res->lockname.name);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b002acf50203..60a5f1548cd9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3321,6 +3321,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name,
 	     lockres->l_level, new_level);
 
+	/*
+	 * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always
+	 * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that
+	 * we can recover correctly from node failure. Otherwise, we may get
+	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
+	 */
+	if (!ocfs2_is_o2cb_active() &&
+	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
+		lvb = 1;
+
 	if (lvb)
 		dlm_flags |= DLM_LKF_VALBLK;
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0e5b4515f92e..1d738723a41a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	/* We know that zero_from is block aligned */
 	for (block_start = zero_from; block_start < zero_to;
 	     block_start = block_end) {
-		block_end = block_start + (1 << inode->i_blkbits);
+		block_end = block_start + i_blocksize(inode);
 
 		/*
 		 * block_start is block-aligned.  Bump it by one to force
@@ -1268,20 +1268,20 @@ bail_unlock_rw:
 	if (size_change)
 		ocfs2_rw_unlock(inode, 1);
 bail:
-	brelse(bh);
 
 	/* Release quota pointers in case we acquired them */
 	for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++)
 		dqput(transfer_to[qtype]);
 
 	if (!status && attr->ia_valid & ATTR_MODE) {
-		status = posix_acl_chmod(inode, inode->i_mode);
+		status = ocfs2_acl_chmod(inode, bh);
 		if (status < 0)
 			mlog_errno(status);
 	}
 	if (inode_locked)
 		ocfs2_inode_unlock(inode, 1);
 
+	brelse(bh);
 	return status;
 }
 
@@ -1536,7 +1536,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 				       u64 start, u64 len)
 {
 	int ret = 0;
-	u64 tmpend, end = start + len;
+	u64 tmpend = 0;
+	u64 end = start + len;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	unsigned int csize = osb->s_clustersize;
 	handle_t *handle;
@@ -1568,18 +1569,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 	}
 
 	/*
-	 * We want to get the byte offset of the end of the 1st cluster.
+	 * If start is on a cluster boundary and end is somewhere in another
+	 * cluster, we have not COWed the cluster starting at start, unless
+	 * end is also within the same cluster. So, in this case, we skip this
+	 * first call to ocfs2_zero_range_for_truncate() truncate and move on
+	 * to the next one.
 	 */
-	tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
-	if (tmpend > end)
-		tmpend = end;
+	if ((start & (csize - 1)) != 0) {
+		/*
+		 * We want to get the byte offset of the end of the 1st
+		 * cluster.
+		 */
+		tmpend = (u64)osb->s_clustersize +
+			(start & ~(osb->s_clustersize - 1));
+		if (tmpend > end)
+			tmpend = end;
 
-	trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
-						 (unsigned long long)tmpend);
+		trace_ocfs2_zero_partial_clusters_range1(
+			(unsigned long long)start,
+			(unsigned long long)tmpend);
 
-	ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
-	if (ret)
-		mlog_errno(ret);
+		ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+						    tmpend);
+		if (ret)
+			mlog_errno(ret);
+	}
 
 	if (tmpend < end) {
 		/*
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3123408da935..62af9554541d 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -259,7 +259,6 @@ static int ocfs2_mknod(struct inode *dir,
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 	sigset_t oldset;
 	int did_block_signals = 0;
-	struct posix_acl *default_acl = NULL, *acl = NULL;
 	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
@@ -367,12 +366,6 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
-	status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
-	if (status) {
-		mlog_errno(status);
-		goto leave;
-	}
-
 	handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
 							    S_ISDIR(mode),
 							    xattr_credits));
@@ -421,16 +414,8 @@ static int ocfs2_mknod(struct inode *dir,
 		inc_nlink(dir);
 	}
 
-	if (default_acl) {
-		status = ocfs2_set_acl(handle, inode, new_fe_bh,
-				       ACL_TYPE_DEFAULT, default_acl,
-				       meta_ac, data_ac);
-	}
-	if (!status && acl) {
-		status = ocfs2_set_acl(handle, inode, new_fe_bh,
-				       ACL_TYPE_ACCESS, acl,
-				       meta_ac, data_ac);
-	}
+	status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh,
+			 meta_ac, data_ac);
 
 	if (status < 0) {
 		mlog_errno(status);
@@ -472,10 +457,6 @@ static int ocfs2_mknod(struct inode *dir,
 	d_instantiate(dentry, inode);
 	status = 0;
 leave:
-	if (default_acl)
-		posix_acl_release(default_acl);
-	if (acl)
-		posix_acl_release(acl);
 	if (status < 0 && did_quota_inode)
 		dquot_free_inode(inode);
 	if (handle)
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 252119860e6c..6a0c55d7dff0 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4248,20 +4248,12 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *old_bh = NULL;
 	struct inode *new_orphan_inode = NULL;
-	struct posix_acl *default_acl, *acl;
-	umode_t mode;
 
 	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
 		return -EOPNOTSUPP;
 
-	mode = inode->i_mode;
-	error = posix_acl_create(dir, &mode, &default_acl, &acl);
-	if (error) {
-		mlog_errno(error);
-		return error;
-	}
 
-	error = ocfs2_create_inode_in_orphan(dir, mode,
+	error = ocfs2_create_inode_in_orphan(dir, inode->i_mode,
 					     &new_orphan_inode);
 	if (error) {
 		mlog_errno(error);
@@ -4300,16 +4292,11 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 	/* If the security isn't preserved, we need to re-initialize them. */
 	if (!preserve) {
 		error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
-						    &new_dentry->d_name,
-						    default_acl, acl);
+						    &new_dentry->d_name);
 		if (error)
 			mlog_errno(error);
 	}
 out:
-	if (default_acl)
-		posix_acl_release(default_acl);
-	if (acl)
-		posix_acl_release(acl);
 	if (!error) {
 		error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode,
 						       new_dentry);
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 5d965e83bd43..783bcdce5666 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
+inline int ocfs2_is_o2cb_active(void)
+{
+	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
+}
+EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
+
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 66334a30cea8..e1b30931974d 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,4 +298,7 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
+int ocfs2_is_o2cb_active(void);
+
 #endif  /* STACKGLUE_H */
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e9164f09841b..877830b05e12 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7197,12 +7197,10 @@ out:
  */
 int ocfs2_init_security_and_acl(struct inode *dir,
 				struct inode *inode,
-				const struct qstr *qstr,
-				struct posix_acl *default_acl,
-				struct posix_acl *acl)
+				const struct qstr *qstr)
 {
-	struct buffer_head *dir_bh = NULL;
 	int ret = 0;
+	struct buffer_head *dir_bh = NULL;
 
 	ret = ocfs2_init_security_get(inode, dir, qstr, NULL);
 	if (ret) {
@@ -7215,11 +7213,9 @@ int ocfs2_init_security_and_acl(struct inode *dir,
 		mlog_errno(ret);
 		goto leave;
 	}
-
-	if (!ret && default_acl)
-		ret = ocfs2_iop_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
-	if (!ret && acl)
-		ret = ocfs2_iop_set_acl(inode, acl, ACL_TYPE_ACCESS);
+	ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL);
+	if (ret)
+		mlog_errno(ret);
 
 	ocfs2_inode_unlock(dir, 0);
 	brelse(dir_bh);
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index f10d5b93c366..1633cc15ea1f 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -94,7 +94,5 @@ int ocfs2_reflink_xattrs(struct inode *old_inode,
 			 bool preserve_security);
 int ocfs2_init_security_and_acl(struct inode *dir,
 				struct inode *inode,
-				const struct qstr *qstr,
-				struct posix_acl *default_acl,
-				struct posix_acl *acl);
+				const struct qstr *qstr);
 #endif /* OCFS2_XATTR_H */
diff --git a/fs/open.c b/fs/open.c
index b6f1e96a7c0b..fbc5c7b230b3 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -840,16 +840,12 @@ EXPORT_SYMBOL(file_path);
 int vfs_open(const struct path *path, struct file *file,
 	     const struct cred *cred)
 {
-	struct dentry *dentry = path->dentry;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = vfs_select_inode(path->dentry, file->f_flags);
 
-	file->f_path = *path;
-	if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
-		inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
-		if (IS_ERR(inode))
-			return PTR_ERR(inode);
-	}
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
+	file->f_path = *path;
 	return do_dentry_open(file, inode, NULL, cred);
 }
 
@@ -889,6 +885,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 	int lookup_flags = 0;
 	int acc_mode;
 
+	/*
+	 * Clear out all open flags we don't know about so that we don't report
+	 * them in fcntl(F_GETFD) or similar interfaces.
+	 */
+	flags &= VALID_OPEN_FLAGS;
+
 	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
 	else
@@ -995,14 +997,12 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 EXPORT_SYMBOL(filp_open);
 
 struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
-			    const char *filename, int flags)
+			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int err = build_open_flags(flags, 0, &op);
+	int err = build_open_flags(flags, mode, &op);
 	if (err)
 		return ERR_PTR(err);
-	if (flags & O_CREAT)
-		return ERR_PTR(-EINVAL);
 	return do_file_open_root(dentry, mnt, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index eff6319d5037..63a0d0ba36de 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -25,6 +25,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 	ssize_t list_size, size, value_size = 0;
 	char *buf, *name, *value = NULL;
 	int uninitialized_var(error);
+	size_t slen;
 
 	if (!old->d_inode->i_op->getxattr ||
 	    !new->d_inode->i_op->getxattr)
@@ -47,7 +48,18 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 		goto out;
 	}
 
-	for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+	for (name = buf; list_size; name += slen) {
+		slen = strnlen(name, list_size) + 1;
+
+		/* underlying fs providing us with an broken xattr list? */
+		if (WARN_ON(slen > list_size)) {
+			error = -EIO;
+			break;
+		}
+		list_size -= slen;
+
+		if (ovl_is_private_xattr(name))
+			continue;
 retry:
 		size = vfs_getxattr(old, name, value, value_size);
 		if (size == -ERANGE)
@@ -127,6 +139,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		len -= bytes;
 	}
 
+	if (!error)
+		error = vfs_fsync(new_file, 0);
 	fput(new_file);
 out_fput:
 	fput(old_file);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index a2b1d7ce3e1a..327177df03a5 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -12,6 +12,7 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/cred.h>
+#include <linux/atomic.h>
 #include "overlayfs.h"
 
 void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
@@ -35,8 +36,10 @@ struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
 {
 	struct dentry *temp;
 	char name[20];
+	static atomic_t temp_id = ATOMIC_INIT(0);
 
-	snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry);
+	/* counter is allowed to wrap, since temp dentries are ephemeral */
+	snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
 
 	temp = lookup_one_len(name, workdir, strlen(name));
 	if (!IS_ERR(temp) && temp->d_inode) {
@@ -511,6 +514,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	struct dentry *upper;
 	struct dentry *opaquedir = NULL;
 	int err;
+	int flags = 0;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
@@ -540,46 +544,39 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	if (err)
 		goto out_dput;
 
-	whiteout = ovl_whiteout(workdir, dentry);
-	err = PTR_ERR(whiteout);
-	if (IS_ERR(whiteout))
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
 		goto out_unlock;
 
-	upper = ovl_dentry_upper(dentry);
-	if (!upper) {
-		upper = lookup_one_len(dentry->d_name.name, upperdir,
-				       dentry->d_name.len);
-		err = PTR_ERR(upper);
-		if (IS_ERR(upper))
-			goto kill_whiteout;
-
-		err = ovl_do_rename(wdir, whiteout, udir, upper, 0);
-		dput(upper);
-		if (err)
-			goto kill_whiteout;
-	} else {
-		int flags = 0;
+	err = -ESTALE;
+	if ((opaquedir && upper != opaquedir) ||
+	    (!opaquedir && ovl_dentry_upper(dentry) &&
+	     upper != ovl_dentry_upper(dentry))) {
+		goto out_dput_upper;
+	}
 
-		if (opaquedir)
-			upper = opaquedir;
-		err = -ESTALE;
-		if (upper->d_parent != upperdir)
-			goto kill_whiteout;
+	whiteout = ovl_whiteout(workdir, dentry);
+	err = PTR_ERR(whiteout);
+	if (IS_ERR(whiteout))
+		goto out_dput_upper;
 
-		if (is_dir)
-			flags |= RENAME_EXCHANGE;
+	if (d_is_dir(upper))
+		flags = RENAME_EXCHANGE;
 
-		err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
-		if (err)
-			goto kill_whiteout;
+	err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+	if (err)
+		goto kill_whiteout;
+	if (flags)
+		ovl_cleanup(wdir, upper);
 
-		if (is_dir)
-			ovl_cleanup(wdir, upper);
-	}
 	ovl_dentry_version_inc(dentry->d_parent);
 out_d_drop:
 	d_drop(dentry);
 	dput(whiteout);
+out_dput_upper:
+	dput(upper);
 out_unlock:
 	unlock_rename(workdir, upperdir);
 out_dput:
@@ -596,21 +593,25 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
-	struct dentry *upper = ovl_dentry_upper(dentry);
+	struct dentry *upper;
 	int err;
 
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	upper = lookup_one_len(dentry->d_name.name, upperdir,
+			       dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (IS_ERR(upper))
+		goto out_unlock;
+
 	err = -ESTALE;
-	if (upper->d_parent == upperdir) {
-		/* Don't let d_delete() think it can reset d_inode */
-		dget(upper);
+	if (upper == ovl_dentry_upper(dentry)) {
 		if (is_dir)
 			err = vfs_rmdir(dir, upper);
 		else
 			err = vfs_unlink(dir, upper, NULL);
-		dput(upper);
 		ovl_dentry_version_inc(dentry->d_parent);
 	}
+	dput(upper);
 
 	/*
 	 * Keeping this dentry hashed would mean having to release
@@ -620,6 +621,7 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 */
 	if (!err)
 		d_drop(dentry);
+out_unlock:
 	mutex_unlock(&dir->i_mutex);
 
 	return err;
@@ -840,29 +842,39 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 	trap = lock_rename(new_upperdir, old_upperdir);
 
-	olddentry = ovl_dentry_upper(old);
-	newdentry = ovl_dentry_upper(new);
-	if (newdentry) {
+
+	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+				   old->d_name.len);
+	err = PTR_ERR(olddentry);
+	if (IS_ERR(olddentry))
+		goto out_unlock;
+
+	err = -ESTALE;
+	if (olddentry != ovl_dentry_upper(old))
+		goto out_dput_old;
+
+	newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+				   new->d_name.len);
+	err = PTR_ERR(newdentry);
+	if (IS_ERR(newdentry))
+		goto out_dput_old;
+
+	err = -ESTALE;
+	if (ovl_dentry_upper(new)) {
 		if (opaquedir) {
-			newdentry = opaquedir;
-			opaquedir = NULL;
+			if (newdentry != opaquedir)
+				goto out_dput;
 		} else {
-			dget(newdentry);
+			if (newdentry != ovl_dentry_upper(new))
+				goto out_dput;
 		}
 	} else {
 		new_create = true;
-		newdentry = lookup_one_len(new->d_name.name, new_upperdir,
-					   new->d_name.len);
-		err = PTR_ERR(newdentry);
-		if (IS_ERR(newdentry))
-			goto out_unlock;
+		if (!d_is_negative(newdentry) &&
+		    (!new_opaque || !ovl_is_whiteout(newdentry)))
+			goto out_dput;
 	}
 
-	err = -ESTALE;
-	if (olddentry->d_parent != old_upperdir)
-		goto out_dput;
-	if (newdentry->d_parent != new_upperdir)
-		goto out_dput;
 	if (olddentry == trap)
 		goto out_dput;
 	if (newdentry == trap)
@@ -925,6 +937,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 
 out_dput:
 	dput(newdentry);
+out_dput_old:
+	dput(olddentry);
 out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 05ac9a95e881..220b04f04523 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -63,6 +63,9 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	if (!err) {
 		upperdentry = ovl_dentry_upper(dentry);
 
+		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
+			attr->ia_valid &= ~ATTR_MODE;
+
 		mutex_lock(&upperdentry->d_inode->i_mutex);
 		err = notify_change(upperdentry, attr, NULL);
 		if (!err)
@@ -216,7 +219,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
 }
 
 
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
 {
 	return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
 }
@@ -274,7 +277,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 	struct path realpath;
 	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
 	ssize_t res;
-	int off;
+	size_t len;
+	char *s;
 
 	res = vfs_listxattr(realpath.dentry, list, size);
 	if (res <= 0 || size == 0)
@@ -284,17 +288,19 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 		return res;
 
 	/* filter out private xattrs */
-	for (off = 0; off < res;) {
-		char *s = list + off;
-		size_t slen = strlen(s) + 1;
+	for (s = list, len = res; len;) {
+		size_t slen = strnlen(s, len) + 1;
 
-		BUG_ON(off + slen > res);
+		/* underlying fs providing us with an broken xattr list? */
+		if (WARN_ON(slen > len))
+			return -EIO;
 
+		len -= slen;
 		if (ovl_is_private_xattr(s)) {
 			res -= slen;
-			memmove(s, s + slen, res - off);
+			memmove(s, s + slen, len);
 		} else {
-			off += slen;
+			s += slen;
 		}
 	}
 
@@ -412,12 +418,11 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 	if (!inode)
 		return NULL;
 
-	mode &= S_IFMT;
-
 	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_flags |= S_NOATIME | S_NOCMTIME;
 
+	mode &= S_IFMT;
 	switch (mode) {
 	case S_IFDIR:
 		inode->i_private = oe;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index e17154aeaae4..c319d5eaabcf 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -174,6 +174,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
 struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
+bool ovl_is_private_xattr(const char *name);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);
@@ -181,6 +182,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to)
 {
 	to->i_uid = from->i_uid;
 	to->i_gid = from->i_gid;
+	to->i_mode = from->i_mode;
 }
 
 /* dir.c */
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 000b2ed05c29..d70208c0de84 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -276,6 +276,37 @@ static void ovl_dentry_release(struct dentry *dentry)
 	}
 }
 
+static struct dentry *ovl_d_real(struct dentry *dentry, struct inode *inode)
+{
+	struct dentry *real;
+
+	if (d_is_dir(dentry)) {
+		if (!inode || inode == d_inode(dentry))
+			return dentry;
+		goto bug;
+	}
+
+	real = ovl_dentry_upper(dentry);
+	if (real && (!inode || inode == d_inode(real)))
+		return real;
+
+	real = ovl_dentry_lower(dentry);
+	if (!real)
+		goto bug;
+
+	if (!inode || inode == d_inode(real))
+		return real;
+
+	/* Handle recursion */
+	if (real->d_flags & DCACHE_OP_REAL)
+		return real->d_op->d_real(real, inode);
+
+bug:
+	WARN(1, "ovl_d_real(%pd4, %s:%lu\n): real dentry not found\n", dentry,
+	     inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
+	return dentry;
+}
+
 static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -320,11 +351,13 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
 	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 };
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_release = ovl_dentry_release,
 	.d_select_inode = ovl_d_select_inode,
+	.d_real = ovl_d_real,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
@@ -343,7 +376,8 @@ static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
 static bool ovl_dentry_remote(struct dentry *dentry)
 {
 	return dentry->d_flags &
-		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
+		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
+		 DCACHE_OP_REAL);
 }
 
 static bool ovl_dentry_weird(struct dentry *dentry)
@@ -729,6 +763,10 @@ retry:
 		struct kstat stat = {
 			.mode = S_IFDIR | 0,
 		};
+		struct iattr attr = {
+			.ia_valid = ATTR_MODE,
+			.ia_mode = stat.mode,
+		};
 
 		if (work->d_inode) {
 			err = -EEXIST;
@@ -744,6 +782,21 @@ retry:
 		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
 		if (err)
 			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		/* Clear any inherited mode bits */
+		inode_lock(work->d_inode);
+		err = notify_change(work, &attr, NULL);
+		inode_unlock(work->d_inode);
+		if (err)
+			goto out_dput;
 	}
 out_unlock:
 	mutex_unlock(&dir->i_mutex);
diff --git a/fs/pipe.c b/fs/pipe.c
index 42cf8ddf0e55..ab8dad3ccb6a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -38,6 +38,12 @@ unsigned int pipe_max_size = 1048576;
  */
 unsigned int pipe_min_size = PAGE_SIZE;
 
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
 /*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
@@ -583,20 +589,49 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+                                 unsigned long old, unsigned long new)
+{
+	atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+	return pipe_user_pages_soft &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+	return pipe_user_pages_hard &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
 struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
 	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
 	if (pipe) {
-		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+		struct user_struct *user = get_current_user();
+
+		if (!too_many_pipe_buffers_hard(user)) {
+			if (too_many_pipe_buffers_soft(user))
+				pipe_bufs = 1;
+			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+		}
+
 		if (pipe->bufs) {
 			init_waitqueue_head(&pipe->wait);
 			pipe->r_counter = pipe->w_counter = 1;
-			pipe->buffers = PIPE_DEF_BUFFERS;
+			pipe->buffers = pipe_bufs;
+			pipe->user = user;
+			account_pipe_buffers(pipe, 0, pipe_bufs);
 			mutex_init(&pipe->mutex);
 			return pipe;
 		}
+		free_uid(user);
 		kfree(pipe);
 	}
 
@@ -607,6 +642,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
+	account_pipe_buffers(pipe, pipe->buffers, 0);
+	free_uid(pipe->user);
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
@@ -998,6 +1035,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
+	account_pipe_buffers(pipe, pipe->buffers, nr_pages);
 	pipe->curbuf = 0;
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
@@ -1069,6 +1107,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
+		} else if ((too_many_pipe_buffers_hard(pipe->user) ||
+			    too_many_pipe_buffers_soft(pipe->user)) &&
+		           !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;
diff --git a/fs/pnode.c b/fs/pnode.c
index 6367e1e435c6..d15c63e97ef1 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p)
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
+static inline struct mount *last_slave(struct mount *p)
+{
+	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -164,6 +169,19 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
+static struct mount *skip_propagation_subtree(struct mount *m,
+						struct mount *origin)
+{
+	/*
+	 * Advance m such that propagation_next will not return
+	 * the slaves of m.
+	 */
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+		m = last_slave(m);
+
+	return m;
+}
+
 static struct mount *next_group(struct mount *m, struct mount *origin)
 {
 	while (1) {
@@ -198,10 +216,15 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 
 /* all accesses are serialized by namespace_sem */
 static struct user_namespace *user_ns;
-static struct mount *last_dest, *last_source, *dest_master;
+static struct mount *last_dest, *first_source, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
+static inline bool peers(struct mount *m1, struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
 static int propagate_one(struct mount *m)
 {
 	struct mount *child;
@@ -212,24 +235,26 @@ static int propagate_one(struct mount *m)
 	/* skip if mountpoint isn't covered by it */
 	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	if (m->mnt_group_id == last_dest->mnt_group_id) {
+	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
 		struct mount *n, *p;
+		bool done;
 		for (n = m; ; n = p) {
 			p = n->mnt_master;
-			if (p == dest_master || IS_MNT_MARKED(p)) {
-				while (last_dest->mnt_master != p) {
-					last_source = last_source->mnt_master;
-					last_dest = last_source->mnt_parent;
-				}
-				if (n->mnt_group_id != last_dest->mnt_group_id) {
-					last_source = last_source->mnt_master;
-					last_dest = last_source->mnt_parent;
-				}
+			if (p == dest_master || IS_MNT_MARKED(p))
 				break;
-			}
 		}
+		do {
+			struct mount *parent = last_source->mnt_parent;
+			if (last_source == first_source)
+				break;
+			done = parent->mnt_master == p;
+			if (done && peers(n, parent))
+				break;
+			last_source = last_source->mnt_master;
+		} while (!done);
+
 		type = CL_SLAVE;
 		/* beginning of peer group among the slaves? */
 		if (IS_MNT_SHARED(m))
@@ -252,7 +277,7 @@ static int propagate_one(struct mount *m)
 		read_sequnlock_excl(&mount_lock);
 	}
 	hlist_add_head(&child->mnt_hash, list);
-	return 0;
+	return count_mounts(m->mnt_ns, child);
 }
 
 /*
@@ -281,6 +306,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 	 */
 	user_ns = current->nsproxy->mnt_ns->user_ns;
 	last_dest = dest_mnt;
+	first_source = source_mnt;
 	last_source = source_mnt;
 	mp = dest_mp;
 	list = tree_list;
@@ -316,6 +342,21 @@ out:
 	return ret;
 }
 
+static struct mount *find_topper(struct mount *mnt)
+{
+	/* If there is exactly one mount covering mnt completely return it. */
+	struct mount *child;
+
+	if (!list_is_singular(&mnt->mnt_mounts))
+		return NULL;
+
+	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
+	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
+		return NULL;
+
+	return child;
+}
+
 /*
  * return true if the refcount is greater than count
  */
@@ -336,9 +377,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child;
+	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
-	int ret = 0;
 
 	if (mnt == parent)
 		return do_refcount_check(mnt, refcnt);
@@ -353,12 +393,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 
 	for (m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-		if (child && list_empty(&child->mnt_mounts) &&
-		    (ret = do_refcount_check(child, 1)))
-			break;
+		int count = 1;
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
+		if (!child)
+			continue;
+
+		/* Is there exactly one mount on the child that covers
+		 * it completely whose reference should be ignored?
+		 */
+		topper = find_topper(child);
+		if (topper)
+			count += 1;
+		else if (!list_empty(&child->mnt_mounts))
+			continue;
+
+		if (do_refcount_check(child, count))
+			return 1;
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -375,63 +427,113 @@ void propagate_mount_unlock(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 		if (child)
 			child->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
 }
 
-/*
- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
- */
-static void mark_umount_candidates(struct mount *mnt)
+static void umount_one(struct mount *mnt, struct list_head *to_umount)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
-
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt_last(&m->mnt,
-						mnt->mnt_mountpoint);
-		if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
-			SET_MNT_MARK(child);
-		}
-	}
+	CLEAR_MNT_MARK(mnt);
+	mnt->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&mnt->mnt_child);
+	list_del_init(&mnt->mnt_umounting);
+	list_move_tail(&mnt->mnt_list, to_umount);
 }
 
 /*
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt)
+static bool __propagate_umount(struct mount *mnt,
+			       struct list_head *to_umount,
+			       struct list_head *to_restore)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
+	bool progress = false;
+	struct mount *child;
 
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
+	/*
+	 * The state of the parent won't change if this mount is
+	 * already unmounted or marked as without children.
+	 */
+	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
+		goto out;
 
-		struct mount *child = __lookup_mnt_last(&m->mnt,
-						mnt->mnt_mountpoint);
-		/*
-		 * umount the child only if the child has no children
-		 * and the child is marked safe to unmount.
-		 */
-		if (!child || !IS_MNT_MARKED(child))
+	/* Verify topper is the only grandchild that has not been
+	 * speculatively unmounted.
+	 */
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
 			continue;
-		CLEAR_MNT_MARK(child);
-		if (list_empty(&child->mnt_mounts)) {
-			list_del_init(&child->mnt_child);
-			child->mnt.mnt_flags |= MNT_UMOUNT;
-			list_move_tail(&child->mnt_list, &mnt->mnt_list);
+		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
+			continue;
+		/* Found a mounted child */
+		goto children;
+	}
+
+	/* Mark mounts that can be unmounted if not locked */
+	SET_MNT_MARK(mnt);
+	progress = true;
+
+	/* If a mount is without children and not locked umount it. */
+	if (!IS_MNT_LOCKED(mnt)) {
+		umount_one(mnt, to_umount);
+	} else {
+children:
+		list_move_tail(&mnt->mnt_umounting, to_restore);
+	}
+out:
+	return progress;
+}
+
+static void umount_list(struct list_head *to_umount,
+			struct list_head *to_restore)
+{
+	struct mount *mnt, *child, *tmp;
+	list_for_each_entry(mnt, to_umount, mnt_list) {
+		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
+			/* topper? */
+			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+				list_move_tail(&child->mnt_umounting, to_restore);
+			else
+				umount_one(child, to_umount);
 		}
 	}
 }
 
+static void restore_mounts(struct list_head *to_restore)
+{
+	/* Restore mounts to a clean working state */
+	while (!list_empty(to_restore)) {
+		struct mount *mnt, *parent;
+		struct mountpoint *mp;
+
+		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
+		CLEAR_MNT_MARK(mnt);
+		list_del_init(&mnt->mnt_umounting);
+
+		/* Should this mount be reparented? */
+		mp = mnt->mnt_mp;
+		parent = mnt->mnt_parent;
+		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+			mp = parent->mnt_mp;
+			parent = parent->mnt_parent;
+		}
+		if (parent != mnt->mnt_parent)
+			mnt_change_mountpoint(parent, mp, mnt);
+	}
+}
+
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+	while (!list_empty(visited)) {
+		struct mount *mnt =
+			list_first_entry(visited, struct mount, mnt_umounting);
+		list_del_init(&mnt->mnt_umounting);
+	}
+}
+
 /*
  * collect all mounts that receive propagation from the mount in @list,
  * and return these additional mounts in the same list.
@@ -442,11 +544,68 @@ static void __propagate_umount(struct mount *mnt)
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
+	LIST_HEAD(to_restore);
+	LIST_HEAD(to_umount);
+	LIST_HEAD(visited);
+
+	/* Find candidates for unmounting */
+	list_for_each_entry_reverse(mnt, list, mnt_list) {
+		struct mount *parent = mnt->mnt_parent;
+		struct mount *m;
+
+		/*
+		 * If this mount has already been visited it is known that it's
+		 * entire peer group and all of their slaves in the propagation
+		 * tree for the mountpoint has already been visited and there is
+		 * no need to visit them again.
+		 */
+		if (!list_empty(&mnt->mnt_umounting))
+			continue;
+
+		list_add_tail(&mnt->mnt_umounting, &visited);
+		for (m = propagation_next(parent, parent); m;
+		     m = propagation_next(m, parent)) {
+			struct mount *child = __lookup_mnt(&m->mnt,
+							   mnt->mnt_mountpoint);
+			if (!child)
+				continue;
+
+			if (!list_empty(&child->mnt_umounting)) {
+				/*
+				 * If the child has already been visited it is
+				 * know that it's entire peer group and all of
+				 * their slaves in the propgation tree for the
+				 * mountpoint has already been visited and there
+				 * is no need to visit this subtree again.
+				 */
+				m = skip_propagation_subtree(m, parent);
+				continue;
+			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+				/*
+				 * We have come accross an partially unmounted
+				 * mount in list that has not been visited yet.
+				 * Remember it has been visited and continue
+				 * about our merry way.
+				 */
+				list_add_tail(&child->mnt_umounting, &visited);
+				continue;
+			}
+
+			/* Check the child and parents while progress is made */
+			while (__propagate_umount(child,
+						  &to_umount, &to_restore)) {
+				/* Is the parent a umount candidate? */
+				child = child->mnt_parent;
+				if (list_empty(&child->mnt_umounting))
+					break;
+			}
+		}
+	}
 
-	list_for_each_entry_reverse(mnt, list, mnt_list)
-		mark_umount_candidates(mnt);
+	umount_list(&to_umount, &to_restore);
+	restore_mounts(&to_restore);
+	cleanup_umount_visitations(&visited);
+	list_splice_tail(&to_umount, list);
 
-	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt);
 	return 0;
 }
diff --git a/fs/pnode.h b/fs/pnode.h
index 0fcdbe7ca648..dc87e65becd2 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -49,7 +49,10 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
 unsigned int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
 #endif /* _LINUX_PNODE_H */
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 4adde1e2cbec..993bb3b5f4d5 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -592,6 +592,37 @@ no_mem:
 }
 EXPORT_SYMBOL_GPL(posix_acl_create);
 
+/**
+ * posix_acl_update_mode  -  update mode in set_acl
+ *
+ * Update the file mode when setting an ACL: compute the new file permission
+ * bits based on the ACL.  In addition, if the ACL is equivalent to the new
+ * file mode, set *acl to NULL to indicate that no ACL should be set.
+ *
+ * As with chmod, clear the setgit bit if the caller is not in the owning group
+ * or capable of CAP_FSETID (see inode_change_ok).
+ *
+ * Called from set_acl inode operations.
+ */
+int posix_acl_update_mode(struct inode *inode, umode_t *mode_p,
+			  struct posix_acl **acl)
+{
+	umode_t mode = inode->i_mode;
+	int error;
+
+	error = posix_acl_equiv_mode(*acl, &mode);
+	if (error < 0)
+		return error;
+	if (error == 0)
+		*acl = NULL;
+	if (!in_group_p(inode->i_gid) &&
+	    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+		mode &= ~S_ISGID;
+	*mode_p = mode;
+	return 0;
+}
+EXPORT_SYMBOL(posix_acl_update_mode);
+
 /*
  * Fix up the uids and gids in posix acl extended attributes in place.
  */
@@ -788,6 +819,28 @@ posix_acl_xattr_get(const struct xattr_handler *handler,
 	return error;
 }
 
+int
+set_posix_acl(struct inode *inode, int type, struct posix_acl *acl)
+{
+	if (!IS_POSIXACL(inode))
+		return -EOPNOTSUPP;
+	if (!inode->i_op->set_acl)
+		return -EOPNOTSUPP;
+
+	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
+		return acl ? -EACCES : 0;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+
+	if (acl) {
+		int ret = posix_acl_valid(acl);
+		if (ret)
+			return ret;
+	}
+	return inode->i_op->set_acl(inode, acl, type);
+}
+EXPORT_SYMBOL(set_posix_acl);
+
 static int
 posix_acl_xattr_set(const struct xattr_handler *handler,
 		    struct dentry *dentry, const char *name,
@@ -799,30 +852,13 @@ posix_acl_xattr_set(const struct xattr_handler *handler,
 
 	if (strcmp(name, "") != 0)
 		return -EINVAL;
-	if (!IS_POSIXACL(inode))
-		return -EOPNOTSUPP;
-	if (!inode->i_op->set_acl)
-		return -EOPNOTSUPP;
-
-	if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
-		return value ? -EACCES : 0;
-	if (!inode_owner_or_capable(inode))
-		return -EPERM;
 
 	if (value) {
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
-
-		if (acl) {
-			ret = posix_acl_valid(acl);
-			if (ret)
-				goto out;
-		}
 	}
-
-	ret = inode->i_op->set_acl(inode, acl, handler->flags);
-out:
+	ret = set_posix_acl(inode, handler->flags, acl);
 	posix_acl_release(acl);
 	return ret;
 }
@@ -867,11 +903,10 @@ int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	int error;
 
 	if (type == ACL_TYPE_ACCESS) {
-		error = posix_acl_equiv_mode(acl, &inode->i_mode);
-		if (error < 0)
-			return 0;
-		if (error == 0)
-			acl = NULL;
+		error = posix_acl_update_mode(inode,
+				&inode->i_mode, &acl);
+		if (error)
+			return error;
 	}
 
 	inode->i_ctime = CURRENT_TIME;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b7de324bec11..dd732400578e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -954,7 +954,8 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	int ret = 0;
 	struct mm_struct *mm = file->private_data;
 
-	if (!mm)
+	/* Ensure the process spawned far enough to have an environment. */
+	if (!mm || !mm->env_end)
 		return 0;
 
 	page = (char *)__get_free_page(GFP_TEMPORARY);
@@ -1544,18 +1545,13 @@ static const struct file_operations proc_pid_set_comm_operations = {
 static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 {
 	struct task_struct *task;
-	struct mm_struct *mm;
 	struct file *exe_file;
 
 	task = get_proc_task(d_inode(dentry));
 	if (!task)
 		return -ENOENT;
-	mm = get_task_mm(task);
+	exe_file = get_task_exe_file(task);
 	put_task_struct(task);
-	if (!mm)
-		return -ENOENT;
-	exe_file = get_mm_exe_file(mm);
-	mmput(mm);
 	if (exe_file) {
 		*exe_path = exe_file->f_path;
 		path_get(&exe_file->f_path);
@@ -3062,6 +3058,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
 		char name[PROC_NUMBUF];
 		int len;
+
+		cond_resched();
 		if (!has_pid_permissions(ns, iter.task, 2))
 			continue;
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index ff3ffc76a937..3773335791da 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -469,6 +469,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 		ent->data = NULL;
 		ent->proc_fops = NULL;
 		ent->proc_iops = NULL;
+		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
 			kfree(ent);
 			parent->nlink--;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index fe5b6e6c4671..4dbe1e2daeca 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -703,7 +703,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 	ctl_dir = container_of(head, struct ctl_dir, header);
 
 	if (!dir_emit_dots(file, ctx))
-		return 0;
+		goto out;
 
 	pos = 2;
 
@@ -713,6 +713,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 	}
+out:
 	sysctl_head_finish(head);
 	return 0;
 }
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 361ab4ee42fc..ec649c92d270 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -121,6 +121,13 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+
 	if (!proc_parse_options(options, ns)) {
 		deactivate_locked_super(sb);
 		return ERR_PTR(-EINVAL);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 09cd3edde08a..07ef85e19fbc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -248,23 +248,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	int stack = 0;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 static void
@@ -289,11 +295,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (stack_guard_page_start(vma, start))
-		start += PAGE_SIZE;
 	end = vma->vm_end;
-	if (stack_guard_page_end(vma, end))
-		end -= PAGE_SIZE;
 
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
@@ -324,8 +326,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -337,21 +337,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 done:
@@ -812,7 +799,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+	pmd_t pmd = *pmdp;
+
+	/* See comment in change_huge_pmd() */
+	pmdp_invalidate(vma, addr, pmdp);
+	if (pmd_dirty(*pmdp))
+		pmd = pmd_mkdirty(pmd);
+	if (pmd_young(*pmdp))
+		pmd = pmd_mkyoung(pmd);
 
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
@@ -1435,6 +1429,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 	return page;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
+					      struct vm_area_struct *vma,
+					      unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pmd_present(pmd))
+		return NULL;
+
+	page = vm_normal_page_pmd(vma, addr, pmd);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_MEMORY]))
+		return NULL;
+
+	return page;
+}
+#endif
+
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
@@ -1444,13 +1464,13 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, vma, addr);
+		page = can_gather_numa_stats_pmd(*pmd, vma, addr);
 		if (page)
-			gather_stats(page, md, pte_dirty(huge_pte),
+			gather_stats(page, md, pmd_dirty(*pmd),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(ptl);
 		return 0;
@@ -1458,6 +1478,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
+#endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, vma, addr);
@@ -1539,19 +1560,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	if (is_vm_hugetlb_page(vma))
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index e0d64c92e4f6..faacb0c0d857 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
-
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	struct mm_struct *mm = vma->vm_mm;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 /*
@@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	if (file) {
 		seq_pad(m, ' ');
 		seq_file_path(m, file, "");
-	} else if (mm) {
-		pid_t tid = pid_of_stack(priv, vma, is_pid);
-
-		if (tid != 0) {
-			seq_pad(m, ' ');
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_printf(m, "[stack]");
-			else
-				seq_printf(m, "[stack:%d]", tid);
-		}
+	} else if (mm && is_stack(priv, vma, is_pid)) {
+		seq_pad(m, ' ');
+		seq_printf(m, "[stack]");
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 8ebd9a334085..87645955990d 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -197,6 +197,8 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
 	if (sb->s_op->show_devname) {
 		seq_puts(m, "device ");
 		err = sb->s_op->show_devname(m, mnt_path.dentry);
+		if (err)
+			goto out;
 	} else {
 		if (r->mnt_devname) {
 			seq_puts(m, "device ");
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d8c439d813ce..ac6c78fe19cf 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -178,7 +178,6 @@ static loff_t pstore_file_llseek(struct file *file, loff_t off, int whence)
 }
 
 static const struct file_operations pstore_file_operations = {
-	.owner		= THIS_MODULE,
 	.open		= pstore_file_open,
 	.read		= pstore_file_read,
 	.llseek		= pstore_file_llseek,
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 319c3a60cfa5..59d93acc29c7 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -375,13 +375,14 @@ static void ramoops_free_przs(struct ramoops_context *cxt)
 {
 	int i;
 
-	cxt->max_dump_cnt = 0;
 	if (!cxt->przs)
 		return;
 
-	for (i = 0; !IS_ERR_OR_NULL(cxt->przs[i]); i++)
+	for (i = 0; i < cxt->max_dump_cnt; i++)
 		persistent_ram_free(cxt->przs[i]);
+
 	kfree(cxt->przs);
+	cxt->max_dump_cnt = 0;
 }
 
 static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
@@ -406,17 +407,22 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 			     GFP_KERNEL);
 	if (!cxt->przs) {
 		dev_err(dev, "failed to initialize a prz array for dumps\n");
-		goto fail_prz;
+		goto fail_mem;
 	}
 
 	for (i = 0; i < cxt->max_dump_cnt; i++) {
 		cxt->przs[i] = persistent_ram_new(*paddr, cxt->record_size, 0,
 						  &cxt->ecc_info,
-						  cxt->memtype);
+						  cxt->memtype, 0);
 		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",
 				cxt->record_size, (unsigned long long)*paddr, err);
+
+			while (i > 0) {
+				i--;
+				persistent_ram_free(cxt->przs[i]);
+			}
 			goto fail_prz;
 		}
 		*paddr += cxt->record_size;
@@ -424,7 +430,9 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 
 	return 0;
 fail_prz:
-	ramoops_free_przs(cxt);
+	kfree(cxt->przs);
+fail_mem:
+	cxt->max_dump_cnt = 0;
 	return err;
 }
 
@@ -442,7 +450,8 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 		return -ENOMEM;
 	}
 
-	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
+	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info,
+				  cxt->memtype, 0);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
@@ -583,7 +592,6 @@ static int ramoops_remove(struct platform_device *pdev)
 	struct ramoops_context *cxt = &oops_cxt;
 
 	pstore_unregister(&cxt->pstore);
-	cxt->max_dump_cnt = 0;
 
 	kfree(cxt->pstore.buf);
 	cxt->pstore.bufsize = 0;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 76c3f80efdfa..27300533c2dd 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -48,48 +48,14 @@ static inline size_t buffer_start(struct persistent_ram_zone *prz)
 }
 
 /* increase and wrap the start pointer, returning the old value */
-static size_t buffer_start_add_atomic(struct persistent_ram_zone *prz, size_t a)
+static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a)
 {
 	int old;
 	int new;
+	unsigned long flags = 0;
 
-	do {
-		old = atomic_read(&prz->buffer->start);
-		new = old + a;
-		while (unlikely(new >= prz->buffer_size))
-			new -= prz->buffer_size;
-	} while (atomic_cmpxchg(&prz->buffer->start, old, new) != old);
-
-	return old;
-}
-
-/* increase the size counter until it hits the max size */
-static void buffer_size_add_atomic(struct persistent_ram_zone *prz, size_t a)
-{
-	size_t old;
-	size_t new;
-
-	if (atomic_read(&prz->buffer->size) == prz->buffer_size)
-		return;
-
-	do {
-		old = atomic_read(&prz->buffer->size);
-		new = old + a;
-		if (new > prz->buffer_size)
-			new = prz->buffer_size;
-	} while (atomic_cmpxchg(&prz->buffer->size, old, new) != old);
-}
-
-static DEFINE_RAW_SPINLOCK(buffer_lock);
-
-/* increase and wrap the start pointer, returning the old value */
-static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a)
-{
-	int old;
-	int new;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&buffer_lock, flags);
+	if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+		raw_spin_lock_irqsave(&prz->buffer_lock, flags);
 
 	old = atomic_read(&prz->buffer->start);
 	new = old + a;
@@ -97,19 +63,21 @@ static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a)
 		new -= prz->buffer_size;
 	atomic_set(&prz->buffer->start, new);
 
-	raw_spin_unlock_irqrestore(&buffer_lock, flags);
+	if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+		raw_spin_unlock_irqrestore(&prz->buffer_lock, flags);
 
 	return old;
 }
 
 /* increase the size counter until it hits the max size */
-static void buffer_size_add_locked(struct persistent_ram_zone *prz, size_t a)
+static void buffer_size_add(struct persistent_ram_zone *prz, size_t a)
 {
 	size_t old;
 	size_t new;
-	unsigned long flags;
+	unsigned long flags = 0;
 
-	raw_spin_lock_irqsave(&buffer_lock, flags);
+	if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+		raw_spin_lock_irqsave(&prz->buffer_lock, flags);
 
 	old = atomic_read(&prz->buffer->size);
 	if (old == prz->buffer_size)
@@ -121,12 +89,10 @@ static void buffer_size_add_locked(struct persistent_ram_zone *prz, size_t a)
 	atomic_set(&prz->buffer->size, new);
 
 exit:
-	raw_spin_unlock_irqrestore(&buffer_lock, flags);
+	if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+		raw_spin_unlock_irqrestore(&prz->buffer_lock, flags);
 }
 
-static size_t (*buffer_start_add)(struct persistent_ram_zone *, size_t) = buffer_start_add_atomic;
-static void (*buffer_size_add)(struct persistent_ram_zone *, size_t) = buffer_size_add_atomic;
-
 static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz,
 	uint8_t *data, size_t len, uint8_t *ecc)
 {
@@ -299,7 +265,7 @@ static void notrace persistent_ram_update(struct persistent_ram_zone *prz,
 	const void *s, unsigned int start, unsigned int count)
 {
 	struct persistent_ram_buffer *buffer = prz->buffer;
-	memcpy(buffer->data + start, s, count);
+	memcpy_toio(buffer->data + start, s, count);
 	persistent_ram_update_ecc(prz, start, count);
 }
 
@@ -322,8 +288,8 @@ void persistent_ram_save_old(struct persistent_ram_zone *prz)
 	}
 
 	prz->old_log_size = size;
-	memcpy(prz->old_log, &buffer->data[start], size - start);
-	memcpy(prz->old_log + size - start, &buffer->data[0], start);
+	memcpy_fromio(prz->old_log, &buffer->data[start], size - start);
+	memcpy_fromio(prz->old_log + size - start, &buffer->data[0], start);
 }
 
 int notrace persistent_ram_write(struct persistent_ram_zone *prz,
@@ -426,9 +392,6 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size,
 		return NULL;
 	}
 
-	buffer_start_add = buffer_start_add_locked;
-	buffer_size_add = buffer_size_add_locked;
-
 	if (memtype)
 		va = ioremap(start, size);
 	else
@@ -487,6 +450,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
 			 prz->buffer->sig);
 	}
 
+	/* Rewind missing or invalid memory area. */
 	prz->buffer->sig = sig;
 	persistent_ram_zap(prz);
 
@@ -513,7 +477,7 @@ 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,
-			unsigned int memtype)
+			unsigned int memtype, u32 flags)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
@@ -524,6 +488,10 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
+	/* Initialize general buffer state. */
+	raw_spin_lock_init(&prz->buffer_lock);
+	prz->flags = flags;
+
 	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 ef0d64b2a6d9..353ff31dcee1 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1398,7 +1398,7 @@ static int dquot_active(const struct inode *inode)
 static int __dquot_initialize(struct inode *inode, int type)
 {
 	int cnt, init_needed = 0;
-	struct dquot **dquots, *got[MAXQUOTAS];
+	struct dquot **dquots, *got[MAXQUOTAS] = {};
 	struct super_block *sb = inode->i_sb;
 	qsize_t rsv;
 	int ret = 0;
@@ -1415,7 +1415,6 @@ static int __dquot_initialize(struct inode *inode, int type)
 		int rc;
 		struct dquot *dquot;
 
-		got[cnt] = NULL;
 		if (type != -1 && cnt != type)
 			continue;
 		/*
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 96a1bcf33db4..38187300a2b4 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 	int ret = 0;
 
 	th.t_trans_id = 0;
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 
 	if (logit) {
 		reiserfs_write_lock(s);
@@ -260,10 +260,10 @@ const struct file_operations reiserfs_file_operations = {
 
 const struct inode_operations reiserfs_file_inode_operations = {
 	.setattr = reiserfs_setattr,
-	.setxattr = reiserfs_setxattr,
-	.getxattr = reiserfs_getxattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
 	.listxattr = reiserfs_listxattr,
-	.removexattr = reiserfs_removexattr,
+	.removexattr = generic_removexattr,
 	.permission = reiserfs_permission,
 	.get_acl = reiserfs_get_acl,
 	.set_acl = reiserfs_set_acl,
diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c
index b751eea32e20..5db6f45b3fed 100644
--- a/fs/reiserfs/ibalance.c
+++ b/fs/reiserfs/ibalance.c
@@ -1153,8 +1153,9 @@ int balance_internal(struct tree_balance *tb,
 				       insert_ptr);
 	}
 
-	memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE);
 	insert_ptr[0] = new_insert_ptr;
+	if (new_insert_ptr)
+		memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE);
 
 	return order;
 }
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 3d8e7e671d5b..60ba35087d12 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -524,7 +524,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 	 * referenced in convert_tail_for_hole() that may be called from
 	 * reiserfs_get_block()
 	 */
-	bh_result->b_size = (1 << inode->i_blkbits);
+	bh_result->b_size = i_blocksize(inode);
 
 	ret = reiserfs_get_block(inode, iblock, bh_result,
 				 create | GET_BLOCK_NO_DANGLE);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 47f96988fdd4..3ebc70167e41 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -1649,10 +1649,10 @@ const struct inode_operations reiserfs_dir_inode_operations = {
 	.mknod = reiserfs_mknod,
 	.rename = reiserfs_rename,
 	.setattr = reiserfs_setattr,
-	.setxattr = reiserfs_setxattr,
-	.getxattr = reiserfs_getxattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
 	.listxattr = reiserfs_listxattr,
-	.removexattr = reiserfs_removexattr,
+	.removexattr = generic_removexattr,
 	.permission = reiserfs_permission,
 	.get_acl = reiserfs_get_acl,
 	.set_acl = reiserfs_set_acl,
@@ -1667,10 +1667,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = {
 	.follow_link = page_follow_link_light,
 	.put_link = page_put_link,
 	.setattr = reiserfs_setattr,
-	.setxattr = reiserfs_setxattr,
-	.getxattr = reiserfs_getxattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
 	.listxattr = reiserfs_listxattr,
-	.removexattr = reiserfs_removexattr,
+	.removexattr = generic_removexattr,
 	.permission = reiserfs_permission,
 };
 
@@ -1679,10 +1679,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = {
  */
 const struct inode_operations reiserfs_special_inode_operations = {
 	.setattr = reiserfs_setattr,
-	.setxattr = reiserfs_setxattr,
-	.getxattr = reiserfs_getxattr,
+	.setxattr = generic_setxattr,
+	.getxattr = generic_getxattr,
 	.listxattr = reiserfs_listxattr,
-	.removexattr = reiserfs_removexattr,
+	.removexattr = generic_removexattr,
 	.permission = reiserfs_permission,
 	.get_acl = reiserfs_get_acl,
 	.set_acl = reiserfs_set_acl,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 4a62fe8cc3bf..f9f3be50081a 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -190,7 +190,15 @@ static int remove_save_link_only(struct super_block *s,
 static int reiserfs_quota_on_mount(struct super_block *, int);
 #endif
 
-/* look for uncompleted unlinks and truncates and complete them */
+/*
+ * Look for uncompleted unlinks and truncates and complete them
+ *
+ * Called with superblock write locked.  If quotas are enabled, we have to
+ * release/retake lest we call dquot_quota_on_mount(), proceed to
+ * schedule_on_each_cpu() in invalidate_bdev() and deadlock waiting for the per
+ * cpu worklets to complete flush_async_commits() that in turn wait for the
+ * superblock write lock.
+ */
 static int finish_unfinished(struct super_block *s)
 {
 	INITIALIZE_PATH(path);
@@ -237,7 +245,9 @@ static int finish_unfinished(struct super_block *s)
 				quota_enabled[i] = 0;
 				continue;
 			}
+			reiserfs_write_unlock(s);
 			ret = reiserfs_quota_on_mount(s, i);
+			reiserfs_write_lock(s);
 			if (ret < 0)
 				reiserfs_warning(s, "reiserfs-2500",
 						 "cannot turn on journaled "
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 66b26fdfff8d..a8dbc93e45eb 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -763,60 +763,6 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers,
 	return xah;
 }
 
-
-/*
- * Inode operation getxattr()
- */
-ssize_t
-reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
-		  size_t size)
-{
-	const struct xattr_handler *handler;
-
-	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
-	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
-		return -EOPNOTSUPP;
-
-	return handler->get(handler, dentry, name, buffer, size);
-}
-
-/*
- * Inode operation setxattr()
- *
- * d_inode(dentry)->i_mutex down
- */
-int
-reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags)
-{
-	const struct xattr_handler *handler;
-
-	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
-	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
-		return -EOPNOTSUPP;
-
-	return handler->set(handler, dentry, name, value, size, flags);
-}
-
-/*
- * Inode operation removexattr()
- *
- * d_inode(dentry)->i_mutex down
- */
-int reiserfs_removexattr(struct dentry *dentry, const char *name)
-{
-	const struct xattr_handler *handler;
-
-	handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
-
-	if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1)
-		return -EOPNOTSUPP;
-
-	return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
-}
-
 struct listxattr_buf {
 	struct dir_context ctx;
 	size_t size;
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 15dde6262c00..613ff5aef94e 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -2,6 +2,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/rwsem.h>
+#include <linux/xattr.h>
 
 struct inode;
 struct dentry;
@@ -18,12 +19,7 @@ int reiserfs_permission(struct inode *inode, int mask);
 
 #ifdef CONFIG_REISERFS_FS_XATTR
 #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir)
-ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name,
-			  void *buffer, size_t size);
-int reiserfs_setxattr(struct dentry *dentry, const char *name,
-		      const void *value, size_t size, int flags);
 ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int reiserfs_removexattr(struct dentry *dentry, const char *name);
 
 int reiserfs_xattr_get(struct inode *, const char *, void *, size_t);
 int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int);
@@ -92,10 +88,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
 
 #else
 
-#define reiserfs_getxattr NULL
-#define reiserfs_setxattr NULL
 #define reiserfs_listxattr NULL
-#define reiserfs_removexattr NULL
 
 static inline void reiserfs_init_xattr_rwsem(struct inode *inode)
 {
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 4b34b9dc03dd..9b1824f35501 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -246,13 +246,9 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			error = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (error < 0)
+			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (error)
 				return error;
-			else {
-				if (error == 0)
-					acl = NULL;
-			}
 		}
 		break;
 	case ACL_TYPE_DEFAULT:
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index ac659af431ae..60de069225ba 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -12,26 +12,24 @@ static int
 security_get(const struct xattr_handler *handler, struct dentry *dentry,
 	     const char *name, void *buffer, size_t size)
 {
-	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
-		return -EINVAL;
-
 	if (IS_PRIVATE(d_inode(dentry)))
 		return -EPERM;
 
-	return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+	return reiserfs_xattr_get(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size);
 }
 
 static int
 security_set(const struct xattr_handler *handler, struct dentry *dentry,
 	     const char *name, const void *buffer, size_t size, int flags)
 {
-	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
-		return -EINVAL;
-
 	if (IS_PRIVATE(d_inode(dentry)))
 		return -EPERM;
 
-	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+	return reiserfs_xattr_set(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size, flags);
 }
 
 static size_t security_list(const struct xattr_handler *handler,
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index a338adf1b8b4..ebba1ebf28ad 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -11,26 +11,24 @@ static int
 trusted_get(const struct xattr_handler *handler, struct dentry *dentry,
 	    const char *name, void *buffer, size_t size)
 {
-	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
-		return -EINVAL;
-
 	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
 		return -EPERM;
 
-	return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+	return reiserfs_xattr_get(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size);
 }
 
 static int
 trusted_set(const struct xattr_handler *handler, struct dentry *dentry,
 	    const char *name, const void *buffer, size_t size, int flags)
 {
-	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
-		return -EINVAL;
-
 	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry)))
 		return -EPERM;
 
-	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+	return reiserfs_xattr_set(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size, flags);
 }
 
 static size_t trusted_list(const struct xattr_handler *handler,
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 39c9667191c5..6ac8a8c8bd9c 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -10,24 +10,22 @@ static int
 user_get(const struct xattr_handler *handler, struct dentry *dentry,
 	 const char *name, void *buffer, size_t size)
 {
-
-	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
-		return -EINVAL;
 	if (!reiserfs_xattrs_user(dentry->d_sb))
 		return -EOPNOTSUPP;
-	return reiserfs_xattr_get(d_inode(dentry), name, buffer, size);
+	return reiserfs_xattr_get(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size);
 }
 
 static int
 user_set(const struct xattr_handler *handler, struct dentry *dentry,
 	 const char *name, const void *buffer, size_t size, int flags)
 {
-	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
-		return -EINVAL;
-
 	if (!reiserfs_xattrs_user(dentry->d_sb))
 		return -EOPNOTSUPP;
-	return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags);
+	return reiserfs_xattr_set(d_inode(dentry),
+				  xattr_full_name(handler, name),
+				  buffer, size, flags);
 }
 
 static size_t user_list(const struct xattr_handler *handler,
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 268733cda397..5f4f1882dc7d 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/major.h>
 #include "internal.h"
 
 static struct kmem_cache *romfs_inode_cachep;
@@ -415,7 +416,22 @@ static void romfs_destroy_inode(struct inode *inode)
 static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	u64 id = 0;
+
+	/* When calling huge_encode_dev(),
+	 * use sb->s_bdev->bd_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK defined
+	 * use sb->s_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD defined
+	 * leave id as 0 when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD undefined
+	 */
+	if (sb->s_bdev)
+		id = huge_encode_dev(sb->s_bdev->bd_dev);
+	else if (sb->s_dev)
+		id = huge_encode_dev(sb->s_dev);
 
 	buf->f_type = ROMFS_MAGIC;
 	buf->f_namelen = ROMFS_MAXFN;
@@ -488,6 +504,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags |= MS_RDONLY | MS_NOATIME;
 	sb->s_op = &romfs_super_ops;
 
+#ifdef CONFIG_ROMFS_ON_MTD
+	/* Use same dev ID from the underlying mtdblock device */
+	if (sb->s_mtd)
+		sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
 	/* read the image superblock and check it */
 	rsb = kmalloc(512, GFP_KERNEL);
 	if (!rsb)
diff --git a/fs/seq_file.c b/fs/seq_file.c
index e85664b7c7d9..6dc4296eed62 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -72,9 +72,10 @@ int seq_open(struct file *file, const struct seq_operations *op)
 
 	mutex_init(&p->lock);
 	p->op = op;
-#ifdef CONFIG_USER_NS
-	p->user_ns = file->f_cred->user_ns;
-#endif
+
+	// No refcounting: the lifetime of 'p' is constrained
+	// to the lifetime of the file.
+	p->file = file;
 
 	/*
 	 * Wrappers around seq_open(e.g. swaps_open) need to be
@@ -222,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 		size -= n;
 		buf += n;
 		copied += n;
-		if (!m->count)
+		if (!m->count) {
+			m->from = 0;
 			m->index++;
+		}
 		if (!size)
 			goto Done;
 	}
diff --git a/fs/splice.c b/fs/splice.c
index 4cf700d50b40..8398974e1538 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	unsigned int spd_pages = spd->nr_pages;
 	int ret, do_wakeup, page_nr;
 
+	if (!spd_pages)
+		return 0;
+
 	ret = 0;
 	do_wakeup = 0;
 	page_nr = 0;
@@ -208,6 +211,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 			buf->len = spd->partial[page_nr].len;
 			buf->private = spd->partial[page_nr].private;
 			buf->ops = spd->ops;
+			buf->flags = 0;
 			if (spd->flags & SPLICE_F_GIFT)
 				buf->flags |= PIPE_BUF_FLAG_GIFT;
 
diff --git a/fs/stat.c b/fs/stat.c
index d4a61d8dc021..004dd77c3b93 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->atime = inode->i_atime;
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
-	stat->blksize = (1 << inode->i_blkbits);
+	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
 }
 
@@ -454,6 +454,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes)
 		inode->i_bytes -= 512;
 	}
 }
+EXPORT_SYMBOL(__inode_add_bytes);
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/super.c b/fs/super.c
index f5f4b328f860..d4d2591b77c8 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1326,8 +1326,8 @@ int freeze_super(struct super_block *sb)
 		}
 	}
 	/*
-	 * This is just for debugging purposes so that fs can warn if it
-	 * sees write activity when frozen is set to SB_FREEZE_COMPLETE.
+	 * For debugging purposes so that fs can warn if it sees write activity
+	 * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
 	 */
 	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 	up_write(&sb->s_umount);
@@ -1346,7 +1346,7 @@ int thaw_super(struct super_block *sb)
 	int error;
 
 	down_write(&sb->s_umount);
-	if (sb->s_writers.frozen == SB_UNFROZEN) {
+	if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) {
 		up_write(&sb->s_umount);
 		return -EINVAL;
 	}
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index f35523d4fa3a..39c75a86c67f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,16 +108,24 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	struct kobject *kobj = of->kn->parent->priv;
-	size_t len;
+	ssize_t len;
 
 	/*
 	 * If buf != of->prealloc_buf, we don't know how
 	 * large it is, so cannot safely pass it to ->show
 	 */
-	if (pos || WARN_ON_ONCE(buf != of->prealloc_buf))
+	if (WARN_ON_ONCE(buf != of->prealloc_buf))
 		return 0;
 	len = ops->show(kobj, of->kn->priv, buf);
-	return min(count, len);
+	if (len < 0)
+		return len;
+	if (pos) {
+		if (len <= pos)
+			return 0;
+		len -= pos;
+		memmove(buf, buf + pos, len);
+	}
+	return min_t(ssize_t, count, len);
 }
 
 /* kernfs write callback for regular sysfs files */
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 053818dd6c18..1327a02ec778 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@ struct timerfd_ctx {
 	short unsigned settime_flags;	/* to show in fdinfo */
 	struct rcu_head rcu;
 	struct list_head clist;
+	spinlock_t cancel_lock;
 	bool might_cancel;
 };
 
@@ -112,7 +113,7 @@ void timerfd_clock_was_set(void)
 	rcu_read_unlock();
 }
 
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
 {
 	if (ctx->might_cancel) {
 		ctx->might_cancel = false;
@@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
 	}
 }
 
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+	spin_lock(&ctx->cancel_lock);
+	__timerfd_remove_cancel(ctx);
+	spin_unlock(&ctx->cancel_lock);
+}
+
 static bool timerfd_canceled(struct timerfd_ctx *ctx)
 {
 	if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX)
@@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
 
 static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 {
+	spin_lock(&ctx->cancel_lock);
 	if ((ctx->clockid == CLOCK_REALTIME ||
 	     ctx->clockid == CLOCK_REALTIME_ALARM) &&
 	    (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 			list_add_rcu(&ctx->clist, &cancel_list);
 			spin_unlock(&cancel_lock);
 		}
-	} else if (ctx->might_cancel) {
-		timerfd_remove_cancel(ctx);
+	} else {
+		__timerfd_remove_cancel(ctx);
 	}
+	spin_unlock(&ctx->cancel_lock);
 }
 
 static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -395,6 +405,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 		return -ENOMEM;
 
 	init_waitqueue_head(&ctx->wqh);
+	spin_lock_init(&ctx->cancel_lock);
 	ctx->clockid = clockid;
 
 	if (isalarm(ctx))
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index e49bd2808bf3..f5d5ee43ae6e 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -350,7 +350,7 @@ static unsigned int vfs_dent_type(uint8_t type)
  */
 static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 {
-	int err;
+	int err = 0;
 	struct qstr nm;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent;
@@ -452,14 +452,20 @@ out:
 	kfree(file->private_data);
 	file->private_data = NULL;
 
-	if (err != -ENOENT) {
+	if (err != -ENOENT)
 		ubifs_err(c, "cannot find next direntry, error %d", err);
-		return err;
-	}
+	else
+		/*
+		 * -ENOENT is a non-fatal error in this context, the TNC uses
+		 * it to indicate that the cursor moved past the current directory
+		 * and readdir() has to stop.
+		 */
+		err = 0;
+
 
 	/* 2 is a special value indicating that there are no more direntries */
 	ctx->pos = 2;
-	return 0;
+	return err;
 }
 
 /* Free saved readdir() state when the directory is closed */
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 0edc12856147..b895af7d8d80 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -52,6 +52,7 @@
 #include "ubifs.h"
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/migrate.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
 		      struct ubifs_data_node *dn)
@@ -1452,6 +1453,26 @@ static int ubifs_set_page_dirty(struct page *page)
 	return ret;
 }
 
+#ifdef CONFIG_MIGRATION
+static int ubifs_migrate_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	int rc;
+
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (rc != MIGRATEPAGE_SUCCESS)
+		return rc;
+
+	if (PagePrivate(page)) {
+		ClearPagePrivate(page);
+		SetPagePrivate(newpage);
+	}
+
+	migrate_page_copy(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
 static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
 {
 	/*
@@ -1591,6 +1612,9 @@ const struct address_space_operations ubifs_file_address_operations = {
 	.write_end      = ubifs_write_end,
 	.invalidatepage = ubifs_invalidatepage,
 	.set_page_dirty = ubifs_set_page_dirty,
+#ifdef CONFIG_MIGRATION
+	.migratepage	= ubifs_migrate_page,
+#endif
 	.releasepage    = ubifs_releasepage,
 };
 
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index fa9a20cc60d6..fe5e8d4970ae 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -34,6 +34,11 @@
 #include <linux/slab.h>
 #include "ubifs.h"
 
+static int try_read_node(const struct ubifs_info *c, void *buf, int type,
+			 int len, int lnum, int offs);
+static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
+			      struct ubifs_zbranch *zbr, void *node);
+
 /*
  * Returned codes of 'matches_name()' and 'fallible_matches_name()' functions.
  * @NAME_LESS: name corresponding to the first argument is less than second
@@ -402,7 +407,19 @@ static int tnc_read_node_nm(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 		return 0;
 	}
 
-	err = ubifs_tnc_read_node(c, zbr, node);
+	if (c->replaying) {
+		err = fallible_read_node(c, &zbr->key, zbr, node);
+		/*
+		 * When the node was not found, return -ENOENT, 0 otherwise.
+		 * Negative return codes stay as-is.
+		 */
+		if (err == 0)
+			err = -ENOENT;
+		else if (err == 1)
+			err = 0;
+	} else {
+		err = ubifs_tnc_read_node(c, zbr, node);
+	}
 	if (err)
 		return err;
 
@@ -2766,7 +2783,11 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c,
 	if (nm->name) {
 		if (err) {
 			/* Handle collisions */
-			err = resolve_collision(c, key, &znode, &n, nm);
+			if (c->replaying)
+				err = fallible_resolve_collision(c, key, &znode, &n,
+							 nm, 0);
+			else
+				err = resolve_collision(c, key, &znode, &n, nm);
 			dbg_tnc("rc returned %d, znode %p, n %d",
 				err, znode, n);
 			if (unlikely(err < 0))
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index b45345d701e7..51157da3f76e 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 
 	p = c->gap_lebs;
 	do {
-		ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+		ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
 		written = layout_leb_in_gaps(c, p);
 		if (written < 0) {
 			err = written;
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index e8b01b721e99..b5bf23b34241 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -173,6 +173,7 @@ out_cancel:
 	host_ui->xattr_cnt -= 1;
 	host_ui->xattr_size -= CALC_DENT_SIZE(nm->len);
 	host_ui->xattr_size -= CALC_XATTR_BYTES(size);
+	host_ui->xattr_names -= nm->len;
 	mutex_unlock(&host_ui->ui_mutex);
 out_free:
 	make_bad_inode(inode);
@@ -533,6 +534,7 @@ out_cancel:
 	host_ui->xattr_cnt += 1;
 	host_ui->xattr_size += CALC_DENT_SIZE(nm->len);
 	host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
+	host_ui->xattr_names += nm->len;
 	mutex_unlock(&host_ui->ui_mutex);
 	ubifs_release_budget(c, &req);
 	make_bad_inode(inode);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 566df9b5a6cb..0e659d9c69a1 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1206,7 +1206,7 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 {
 	int err;
 	struct udf_inode_info *iinfo;
-	int bsize = 1 << inode->i_blkbits;
+	int bsize = i_blocksize(inode);
 
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	      S_ISLNK(inode->i_mode)))
@@ -1235,8 +1235,8 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 			return err;
 		}
 set_size:
-		truncate_setsize(inode, newsize);
 		up_write(&iinfo->i_data_sem);
+		truncate_setsize(inode, newsize);
 	} else {
 		if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 			down_write(&iinfo->i_data_sem);
@@ -1253,9 +1253,9 @@ set_size:
 					  udf_get_block);
 		if (err)
 			return err;
+		truncate_setsize(inode, newsize);
 		down_write(&iinfo->i_data_sem);
 		udf_clear_extent_cache(inode);
-		truncate_setsize(inode, newsize);
 		udf_truncate_extents(inode);
 		up_write(&iinfo->i_data_sem);
 	}
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index dc5fae601c24..637e17cb0edd 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -81,7 +81,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 			ufs_error (sb, "ufs_free_fragments",
 				   "bit already cleared for fragment %u", i);
 	}
-	
+
+	inode_sub_bytes(inode, count << uspi->s_fshift);
 	fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
 	uspi->cs_total.cs_nffree += count;
 	fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
@@ -183,6 +184,7 @@ do_more:
 			ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
 		}
 		ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+		inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
 		if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
 			ufs_clusteracct (sb, ucpi, blkno, 1);
 
@@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	return 0;
 }		
 
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+	unsigned size = frags * i_blocksize(inode);
+	spin_lock(&inode->i_lock);
+	__inode_add_bytes(inode, size);
+	if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+		__inode_sub_bytes(inode, size);
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	spin_unlock(&inode->i_lock);
+	return true;
+}
+
 static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 			     unsigned oldcount, unsigned newcount)
 {
@@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 	for (i = oldcount; i < newcount; i++)
 		if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
 			return 0;
+
+	if (!try_add_frags(inode, count))
+		return 0;
 	/*
 	 * Block can be extended
 	 */
@@ -647,6 +666,7 @@ cg_found:
 			ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
 		i = uspi->s_fpb - count;
 
+		inode_sub_bytes(inode, i << uspi->s_fshift);
 		fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
 		uspi->cs_total.cs_nffree += i;
 		fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
@@ -657,6 +677,8 @@ cg_found:
 	result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
 	if (result == INVBLOCK)
 		return 0;
+	if (!try_add_frags(inode, count))
+		return 0;
 	for (i = 0; i < count; i++)
 		ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
 	
@@ -716,6 +738,8 @@ norot:
 		return INVBLOCK;
 	ucpi->c_rotor = result;
 gotit:
+	if (!try_add_frags(inode, uspi->s_fpb))
+		return 0;
 	blkno = ufs_fragstoblks(result);
 	ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
 	if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index a064cf44b143..1f69bb9b1e9d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
 
 	p = ufs_get_direct_data_ptr(uspi, ufsi, block);
 	tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
-				new_size, err, locked_page);
+				new_size - (lastfrag & uspi->s_fpbmask), err,
+				locked_page);
 	return tmp != 0;
 }
 
@@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
 			goal += uspi->s_fpb;
 	}
 	tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
-				goal, uspi->s_fpb, err, locked_page);
+				goal, nfrags, err, locked_page);
 
 	if (!tmp) {
 		*err = -ENOSPC;
@@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
 
 	if (!create) {
 		phys64 = ufs_frag_map(inode, offsets, depth);
-		goto out;
+		if (phys64)
+			map_bh(bh_result, sb, phys64 + frag);
+		return 0;
 	}
 
         /* This code entered only while writing ....? */
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f6390eec02ca..10f364490833 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb)
 	return;
 }
 
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+	int bits = uspi->s_apbshift;
+	u64 res;
+
+	if (bits > 21)
+		res = ~0ULL;
+	else
+		res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+			(1LL << (3*bits));
+
+	if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+		return MAX_LFS_FILESIZE;
+	return res << uspi->s_bshift;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -1212,6 +1229,7 @@ magic_found:
 			    "fast symlink size (%u)\n", uspi->s_maxsymlinklen);
 		uspi->s_maxsymlinklen = maxsymlen;
 	}
+	sb->s_maxbytes = ufs_max_bytes(sb);
 	sb->s_max_links = UFS_LINK_MAX;
 
 	inode = ufs_iget(sb, UFS_ROOTINO);
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 954175928240..3f9463f8cf2f 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_(
 static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
 	struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
 {
+	u8 mask;
 	switch (uspi->s_fpb) {
 	case 8:
 	    	return (*ubh_get_addr (ubh, begin + block) == 0xff);
 	case 4:
-		return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+		mask = 0x0f << ((block & 0x01) << 2);
+		return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
 	case 2:
-		return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+		mask = 0x03 << ((block & 0x03) << 1);
+		return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
 	case 1:
-		return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+		mask = 0x01 << (block & 0x07);
+		return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
 	}
 	return 0;	
 }
diff --git a/fs/utimes.c b/fs/utimes.c
index aa138d64560a..cb771c30d102 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -87,20 +87,7 @@ static int utimes_common(struct path *path, struct timespec *times)
 		 */
 		newattrs.ia_valid |= ATTR_TIMES_SET;
 	} else {
-		/*
-		 * If times is NULL (or both times are UTIME_NOW),
-		 * then we need to check permissions, because
-		 * inode_change_ok() won't do it.
-		 */
-		error = -EACCES;
-                if (IS_IMMUTABLE(inode))
-			goto mnt_drop_write_and_out;
-
-		if (!inode_owner_or_capable(inode)) {
-			error = inode_permission(inode, MAY_WRITE);
-			if (error)
-				goto mnt_drop_write_and_out;
-		}
+		newattrs.ia_valid |= ATTR_TOUCH;
 	}
 retry_deleg:
 	mutex_lock(&inode->i_mutex);
@@ -112,7 +99,6 @@ retry_deleg:
 			goto retry_deleg;
 	}
 
-mnt_drop_write_and_out:
 	mnt_drop_write(path->mnt);
 out:
 	return error;
diff --git a/fs/xattr.c b/fs/xattr.c
index 9b932b95d74e..f0da9d24e9ca 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -442,7 +442,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 			size = XATTR_SIZE_MAX;
 		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!kvalue) {
-			vvalue = vmalloc(size);
+			vvalue = vzalloc(size);
 			if (!vvalue)
 				return -ENOMEM;
 			kvalue = vvalue;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3479294c1d58..e1e7fe3b5424 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -535,6 +535,7 @@ xfs_agfl_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agfl_buf_ops = {
+	.name = "xfs_agfl",
 	.verify_read = xfs_agfl_read_verify,
 	.verify_write = xfs_agfl_write_verify,
 };
@@ -2339,6 +2340,7 @@ xfs_agf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agf_buf_ops = {
+	.name = "xfs_agf",
 	.verify_read = xfs_agf_read_verify,
 	.verify_write = xfs_agf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 90de071dd4c2..eb8bbfe85484 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -379,6 +379,7 @@ xfs_allocbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_allocbt_buf_ops = {
+	.name = "xfs_allocbt",
 	.verify_read = xfs_allocbt_read_verify,
 	.verify_write = xfs_allocbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index aa187f7ba2dd..01a5ecfedfcf 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -328,6 +328,7 @@ xfs_attr3_leaf_read_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_leaf_buf_ops = {
+	.name = "xfs_attr3_leaf",
 	.verify_read = xfs_attr3_leaf_read_verify,
 	.verify_write = xfs_attr3_leaf_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 5ab95ffa4ae9..f3ed9bf0b065 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -201,6 +201,7 @@ xfs_attr3_rmt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = {
+	.name = "xfs_attr3_rmt",
 	.verify_read = xfs_attr3_rmt_read_verify,
 	.verify_write = xfs_attr3_rmt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 119c2422aac7..75884aecf920 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2179,8 +2179,10 @@ xfs_bmap_add_extent_delay_real(
 		}
 		temp = xfs_bmap_worst_indlen(bma->ip, temp);
 		temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
-		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
-			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
+		diff = (int)(temp + temp2 -
+			     (startblockval(PREV.br_startblock) -
+			      (bma->cur ?
+			       bma->cur->bc_private.b.allocated : 0)));
 		if (diff > 0) {
 			error = xfs_mod_fdblocks(bma->ip->i_mount,
 						 -((int64_t)diff), false);
@@ -2232,7 +2234,6 @@ xfs_bmap_add_extent_delay_real(
 		temp = da_new;
 		if (bma->cur)
 			temp += bma->cur->bc_private.b.allocated;
-		ASSERT(temp <= da_old);
 		if (temp < da_old)
 			xfs_mod_fdblocks(bma->ip->i_mount,
 					(int64_t)(da_old - temp), false);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 6b0cf6546a82..1637c37bfbaa 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -720,6 +720,7 @@ xfs_bmbt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_bmbt_buf_ops = {
+	.name = "xfs_bmbt",
 	.verify_read = xfs_bmbt_read_verify,
 	.verify_write = xfs_bmbt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index af1bbee5586e..28bc5e78b110 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4064,7 +4064,7 @@ xfs_btree_change_owner(
 			xfs_btree_readahead_ptr(cur, ptr, 1);
 
 			/* save for the next iteration of the loop */
-			lptr = *ptr;
+			xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
 		}
 
 		/* for each buffer in the level */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e89a0f8f827c..097bf7717d80 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -245,6 +245,7 @@ xfs_da3_node_read_verify(
 }
 
 const struct xfs_buf_ops xfs_da3_node_buf_ops = {
+	.name = "xfs_da3_node",
 	.verify_read = xfs_da3_node_read_verify,
 	.verify_write = xfs_da3_node_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 9c10e2b8cfcb..aa17cb788946 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -123,6 +123,7 @@ xfs_dir3_block_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
+	.name = "xfs_dir3_block",
 	.verify_read = xfs_dir3_block_read_verify,
 	.verify_write = xfs_dir3_block_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index af71a84f343c..725fc7841fde 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -305,11 +305,13 @@ xfs_dir3_data_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
+	.name = "xfs_dir3_data",
 	.verify_read = xfs_dir3_data_read_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
 
 static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
+	.name = "xfs_dir3_data_reada",
 	.verify_read = xfs_dir3_data_reada_verify,
 	.verify_write = xfs_dir3_data_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 3923e1f94697..b887fb2a2bcf 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -245,11 +245,13 @@ xfs_dir3_leafn_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops = {
+	.name = "xfs_dir3_leaf1",
 	.verify_read = xfs_dir3_leaf1_read_verify,
 	.verify_write = xfs_dir3_leaf1_write_verify,
 };
 
 const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
+	.name = "xfs_dir3_leafn",
 	.verify_read = xfs_dir3_leafn_read_verify,
 	.verify_write = xfs_dir3_leafn_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 70b0cb2fd556..63ee03db796c 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -150,6 +150,7 @@ xfs_dir3_free_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
+	.name = "xfs_dir3_free",
 	.verify_read = xfs_dir3_free_read_verify,
 	.verify_write = xfs_dir3_free_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 5331b7f0460c..ac9a003dd29a 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -54,7 +54,7 @@ xfs_dqcheck(
 	xfs_dqid_t	 id,
 	uint		 type,	  /* used only when IO_dorepair is true */
 	uint		 flags,
-	char		 *str)
+	const char	 *str)
 {
 	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
 	int		errs = 0;
@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(
-					XFS_BB_TO_FSB(mp, bp->b_length));
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
@@ -207,7 +206,8 @@ xfs_dquot_buf_verify_crc(
 STATIC bool
 xfs_dquot_buf_verify(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	int			warn)
 {
 	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
 	xfs_dqid_t		id = 0;
@@ -240,8 +240,7 @@ xfs_dquot_buf_verify(
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
-				       "xfs_dquot_buf_verify");
+		error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__);
 		if (error)
 			return false;
 	}
@@ -256,7 +255,7 @@ xfs_dquot_buf_read_verify(
 
 	if (!xfs_dquot_buf_verify_crc(mp, bp))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
-	else if (!xfs_dquot_buf_verify(mp, bp))
+	else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -264,6 +263,25 @@ xfs_dquot_buf_read_verify(
 }
 
 /*
+ * readahead errors are silent and simply leave the buffer as !done so a real
+ * read will then be run with the xfs_dquot_buf_ops verifier. See
+ * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than
+ * reporting the failure.
+ */
+static void
+xfs_dquot_buf_readahead_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify_crc(mp, bp) ||
+	    !xfs_dquot_buf_verify(mp, bp, 0)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+	}
+}
+
+/*
  * we don't calculate the CRC here as that is done when the dquot is flushed to
  * the buffer after the update is done. This ensures that the dquot in the
  * buffer always has an up-to-date CRC value.
@@ -274,7 +292,7 @@ xfs_dquot_buf_write_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	if (!xfs_dquot_buf_verify(mp, bp)) {
+	if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) {
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 		xfs_verifier_error(bp);
 		return;
@@ -282,7 +300,13 @@ xfs_dquot_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_dquot_buf_ops = {
+	.name = "xfs_dquot",
 	.verify_read = xfs_dquot_buf_read_verify,
 	.verify_write = xfs_dquot_buf_write_verify,
 };
 
+const struct xfs_buf_ops xfs_dquot_buf_ra_ops = {
+	.name = "xfs_dquot_ra",
+	.verify_read = xfs_dquot_buf_readahead_verify,
+	.verify_write = xfs_dquot_buf_write_verify,
+};
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 70c1db99f6a7..66d702e6b9ff 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2572,6 +2572,7 @@ xfs_agi_write_verify(
 }
 
 const struct xfs_buf_ops xfs_agi_buf_ops = {
+	.name = "xfs_agi",
 	.verify_read = xfs_agi_read_verify,
 	.verify_write = xfs_agi_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index f39b285beb19..6dd44f9ea727 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -304,6 +304,7 @@ xfs_inobt_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inobt_buf_ops = {
+	.name = "xfs_inobt",
 	.verify_read = xfs_inobt_read_verify,
 	.verify_write = xfs_inobt_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 65485cfc4ade..7183b7ea065b 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -68,6 +68,8 @@ xfs_inobp_check(
  * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
  * because all we want to do is say readahead failed; there is no-one to report
  * the error to, so this will distinguish it from a non-ra verifier failure.
+ * Changes to this readahead error behavour also need to be reflected in
+ * xfs_dquot_buf_readahead_verify().
  */
 static void
 xfs_inode_buf_verify(
@@ -134,11 +136,13 @@ xfs_inode_buf_write_verify(
 }
 
 const struct xfs_buf_ops xfs_inode_buf_ops = {
+	.name = "xfs_inode",
 	.verify_read = xfs_inode_buf_read_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
 
 const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
+	.name = "xxfs_inode_ra",
 	.verify_read = xfs_inode_buf_readahead_verify,
 	.verify_write = xfs_inode_buf_write_verify,
 };
@@ -295,6 +299,14 @@ xfs_dinode_verify(
 	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
 		return false;
 
+	/* don't allow invalid i_size */
+	if (be64_to_cpu(dip->di_size) & (1ULL << 63))
+		return false;
+
+	/* No zero-length symlinks. */
+	if (S_ISLNK(be16_to_cpu(dip->di_mode)) && dip->di_size == 0)
+		return false;
+
 	/* only version 3 or greater inodes are extensively verified here */
 	if (dip->di_version < 3)
 		return true;
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 1b0a08379759..f51078f1e92a 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -153,7 +153,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
-		       xfs_dqid_t id, uint type, uint flags, char *str);
+		       xfs_dqid_t id, uint type, uint flags, const char *str);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index a0b071d881a0..7088be6afb3c 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -581,7 +581,8 @@ xfs_sb_verify(
 	 * Only check the in progress field for the primary superblock as
 	 * mkfs.xfs doesn't clear it from secondary superblocks.
 	 */
-	return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR,
+	return xfs_mount_validate_sb(mp, &sb,
+				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
 				     check_version);
 }
 
@@ -679,11 +680,13 @@ xfs_sb_write_verify(
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
+	.name = "xfs_sb",
 	.verify_read = xfs_sb_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
 
 const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
+	.name = "xfs_sb_quiet",
 	.verify_read = xfs_sb_quiet_read_verify,
 	.verify_write = xfs_sb_write_verify,
 };
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 5be529707903..15c3ceb845b9 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -49,6 +49,7 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index cb6fd20a4d3d..2e2c6716b623 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -168,6 +168,7 @@ xfs_symlink_write_verify(
 }
 
 const struct xfs_buf_ops xfs_symlink_buf_ops = {
+	.name = "xfs_symlink",
 	.verify_read = xfs_symlink_read_verify,
 	.verify_write = xfs_symlink_write_verify,
 };
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 6bb470fbb8e8..c5101a3295d8 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -288,16 +288,11 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		return error;
 
 	if (type == ACL_TYPE_ACCESS) {
-		umode_t mode = inode->i_mode;
-		error = posix_acl_equiv_mode(acl, &mode);
-
-		if (error <= 0) {
-			acl = NULL;
-
-			if (error < 0)
-				return error;
-		}
+		umode_t mode;
 
+		error = posix_acl_update_mode(inode, &mode, &acl);
+		if (error)
+			return error;
 		error = xfs_set_mode(inode, mode);
 		if (error)
 			return error;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 29e7e5dd5178..a9063ac50c4e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -288,7 +288,7 @@ xfs_map_blocks(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			count = 1 << inode->i_blkbits;
+	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			error = 0;
 	int			bmapi_flags = XFS_BMAPI_ENTIRE;
@@ -921,7 +921,7 @@ xfs_aops_discard_page(
 			break;
 		}
 next_buffer:
-		offset += 1 << inode->i_blkbits;
+		offset += i_blocksize(inode);
 
 	} while ((bh = bh->b_this_page) != head);
 
@@ -1363,7 +1363,7 @@ xfs_map_trim_size(
 	    offset + mapping_size >= i_size_read(inode)) {
 		/* limit mapping to block that spans EOF */
 		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  1 << inode->i_blkbits);
+					  i_blocksize(inode));
 	}
 	if (mapping_size > LONG_MAX)
 		mapping_size = LONG_MAX;
@@ -1395,7 +1395,7 @@ __xfs_get_blocks(
 		return -EIO;
 
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
+	ASSERT(bh_result->b_size >= i_blocksize(inode));
 	size = bh_result->b_size;
 
 	if (!create && direct && offset >= i_size_read(inode))
@@ -1426,6 +1426,26 @@ __xfs_get_blocks(
 	if (error)
 		goto out_unlock;
 
+	/*
+	 * The only time we can ever safely find delalloc blocks on direct I/O
+	 * is a dio write to post-eof speculative preallocation. All other
+	 * scenarios are indicative of a problem or misuse (such as mixing
+	 * direct and mapped I/O).
+	 *
+	 * The file may be unmapped by the time we get here so we cannot
+	 * reliably fail the I/O based on mapping. Instead, fail the I/O if this
+	 * is a read or a write within eof. Otherwise, carry on but warn as a
+	 * precuation if the file happens to be mapped.
+	 */
+	if (direct && imap.br_startblock == DELAYSTARTBLOCK) {
+	        if (!create || offset < i_size_read(VFS_I(ip))) {
+	                WARN_ON_ONCE(1);
+	                error = -EIO;
+	                goto out_unlock;
+	        }
+	        WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping));
+	}
+
 	/* for DAX, we convert unwritten extents directly */
 	if (create &&
 	    (!nimaps ||
@@ -1525,7 +1545,6 @@ __xfs_get_blocks(
 		set_buffer_new(bh_result);
 
 	if (imap.br_startblock == DELAYSTARTBLOCK) {
-		BUG_ON(direct);
 		if (create) {
 			set_buffer_uptodate(bh_result);
 			set_buffer_mapped(bh_result);
@@ -1968,7 +1987,7 @@ xfs_vm_set_page_dirty(
 			if (offset < end_offset)
 				set_buffer_dirty(bh);
 			bh = bh->b_this_page;
-			offset += 1 << inode->i_blkbits;
+			offset += i_blocksize(inode);
 		} while (bh != head);
 	}
 	/*
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index dd4824589470..234331227c0c 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -112,6 +112,7 @@ typedef struct attrlist_cursor_kern {
  *========================================================================*/
 
 
+/* Return 0 on success, or -errno; other state communicated via *context */
 typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int,
 			      unsigned char *, int, int, unsigned char *);
 
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 0ef7c2ed3f8a..c8be331a3196 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -108,16 +108,14 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 					   (int)sfe->namelen,
 					   (int)sfe->valuelen,
 					   &sfe->nameval[sfe->namelen]);
-
+			if (error)
+				return error;
 			/*
 			 * Either search callback finished early or
 			 * didn't fit it all in the buffer after all.
 			 */
 			if (context->seen_enough)
 				break;
-
-			if (error)
-				return error;
 			sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
 		}
 		trace_xfs_attr_list_sf_all(context);
@@ -202,8 +200,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 					sbp->namelen,
 					sbp->valuelen,
 					&sbp->name[sbp->namelen]);
-		if (error)
+		if (error) {
+			kmem_free(sbuf);
 			return error;
+		}
 		if (context->seen_enough)
 			break;
 		cursor->offset++;
@@ -454,14 +454,13 @@ xfs_attr3_leaf_list_int(
 				args.rmtblkcnt = xfs_attr3_rmt_blocks(
 							args.dp->i_mount, valuelen);
 				retval = xfs_attr_rmtval_get(&args);
-				if (retval)
-					return retval;
-				retval = context->put_listent(context,
-						entry->flags,
-						name_rmt->name,
-						(int)name_rmt->namelen,
-						valuelen,
-						args.value);
+				if (!retval)
+					retval = context->put_listent(context,
+							entry->flags,
+							name_rmt->name,
+							(int)name_rmt->namelen,
+							valuelen,
+							args.value);
 				kmem_free(args.value);
 			} else {
 				retval = context->put_listent(context,
@@ -580,7 +579,7 @@ xfs_attr_put_listent(
 		trace_xfs_attr_list_full(context);
 		alist->al_more = 1;
 		context->seen_enough = 1;
-		return 1;
+		return 0;
 	}
 
 	aep = (attrlist_ent_t *)&context->alist[context->firstu];
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index dbae6490a79a..863e1bff403b 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -682,7 +682,7 @@ xfs_getbmap(
 			 * extents.
 			 */
 			if (map[i].br_startblock == DELAYSTARTBLOCK &&
-			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+			    map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
 				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
 
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
@@ -1713,6 +1713,7 @@ xfs_swap_extents(
 	xfs_trans_t	*tp;
 	xfs_bstat_t	*sbp = &sxp->sx_stat;
 	xfs_ifork_t	*tempifp, *ifp, *tifp;
+	xfs_extnum_t	nextents;
 	int		src_log_flags, target_log_flags;
 	int		error = 0;
 	int		aforkblks = 0;
@@ -1899,7 +1900,8 @@ xfs_swap_extents(
 		 * pointer.  Otherwise it's already NULL or
 		 * pointing to the extent.
 		 */
-		if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+		nextents = ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+		if (nextents <= XFS_INLINE_EXTS) {
 			ifp->if_u1.if_extents =
 				ifp->if_u2.if_inline_ext;
 		}
@@ -1918,7 +1920,8 @@ xfs_swap_extents(
 		 * pointer.  Otherwise it's already NULL or
 		 * pointing to the extent.
 		 */
-		if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
+		nextents = tip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+		if (nextents <= XFS_INLINE_EXTS) {
 			tifp->if_u1.if_extents =
 				tifp->if_u2.if_inline_ext;
 		}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 39090fc56f09..dcb70969ff1c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -375,6 +375,7 @@ retry:
 out_free_pages:
 	for (i = 0; i < bp->b_page_count; i++)
 		__free_page(bp->b_pages[i]);
+	bp->b_flags &= ~_XBF_PAGES;
 	return error;
 }
 
@@ -978,6 +979,8 @@ void
 xfs_buf_unlock(
 	struct xfs_buf		*bp)
 {
+	ASSERT(xfs_buf_islocked(bp));
+
 	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
 
@@ -1535,7 +1538,7 @@ xfs_wait_buftarg(
 	 * ensure here that all reference counts have been dropped before we
 	 * start walking the LRU list.
 	 */
-	drain_workqueue(btp->bt_mount->m_buf_workqueue);
+	flush_workqueue(btp->bt_mount->m_buf_workqueue);
 
 	/* loop until there is nothing left on the lru list. */
 	while (list_lru_count(&btp->bt_lru)) {
@@ -1712,6 +1715,28 @@ error:
 }
 
 /*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+	struct list_head	*list)
+{
+	struct xfs_buf		*bp;
+
+	while (!list_empty(list)) {
+		bp = list_first_entry(list, struct xfs_buf, b_list);
+
+		xfs_buf_lock(bp);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
+		list_del_init(&bp->b_list);
+		xfs_buf_relse(bp);
+	}
+}
+
+/*
  * Add a buffer to the delayed write list.
  *
  * This queues a buffer for writeout if it hasn't already been.  Note that
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c79b717d9b88..149bbd451731 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -132,6 +132,7 @@ struct xfs_buf_map {
 	struct xfs_buf_map (map) = { .bm_bn = (blkno), .bm_len = (numblk) };
 
 struct xfs_buf_ops {
+	char *name;
 	void (*verify_read)(struct xfs_buf *);
 	void (*verify_write)(struct xfs_buf *);
 };
@@ -303,6 +304,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 extern void *xfs_buf_offset(struct xfs_buf *, size_t);
 
 /* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 642d55d10075..2fbf643fa10a 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -406,6 +406,7 @@ xfs_dir2_leaf_readbuf(
 
 	/*
 	 * Do we need more readahead?
+	 * Each loop tries to process 1 full dir blk; last may be partial.
 	 */
 	blk_start_plug(&plug);
 	for (mip->ra_index = mip->ra_offset = i = 0;
@@ -416,7 +417,8 @@ xfs_dir2_leaf_readbuf(
 		 * Read-ahead a contiguous directory block.
 		 */
 		if (i > mip->ra_current &&
-		    map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+		    (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
+		    geo->fsbcount) {
 			xfs_dir3_data_readahead(dp,
 				map[mip->ra_index].br_startoff + mip->ra_offset,
 				XFS_FSB_TO_DADDR(dp->i_mount,
@@ -437,14 +439,19 @@ xfs_dir2_leaf_readbuf(
 		}
 
 		/*
-		 * Advance offset through the mapping table.
+		 * Advance offset through the mapping table, processing a full
+		 * dir block even if it is fragmented into several extents.
+		 * But stop if we have consumed all valid mappings, even if
+		 * it's not yet a full directory block.
 		 */
-		for (j = 0; j < geo->fsbcount; j += length ) {
+		for (j = 0;
+		     j < geo->fsbcount && mip->ra_index < mip->map_valid;
+		     j += length ) {
 			/*
 			 * The rest of this extent but not more than a dir
 			 * block.
 			 */
-			length = min_t(int, geo->fsbcount,
+			length = min_t(int, geo->fsbcount - j,
 					map[mip->ra_index].br_blockcount -
 							mip->ra_offset);
 			mip->ra_offset += length;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 74d0e5966ebc..88693a98fac5 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -164,9 +164,9 @@ xfs_verifier_error(
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 
-	xfs_alert(mp, "Metadata %s detected at %pF, block 0x%llx",
+	xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
 		  bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
-		  __return_address, bp->b_bn);
+		  __return_address, bp->b_ops->name, bp->b_bn);
 
 	xfs_alert(mp, "Unmount and run xfs_repair");
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f5392ab2def1..3dd47307363f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -947,7 +947,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		if (offset & blksize_mask || len & blksize_mask) {
 			error = -EINVAL;
@@ -969,7 +969,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_INSERT_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		new_size = i_size_read(inode) + len;
 		if (offset & blksize_mask || len & blksize_mask) {
@@ -1208,7 +1208,7 @@ xfs_find_get_desired_pgoff(
 		unsigned	nr_pages;
 		unsigned int	i;
 
-		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  want);
 		/*
@@ -1235,17 +1235,6 @@ xfs_find_get_desired_pgoff(
 			break;
 		}
 
-		/*
-		 * At lease we found one page.  If this is the first time we
-		 * step into the loop, and if the first page index offset is
-		 * greater than the given search offset, a hole was found.
-		 */
-		if (type == HOLE_OFF && lastoff == startoff &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = true;
-			break;
-		}
-
 		for (i = 0; i < nr_pages; i++) {
 			struct page	*page = pvec.pages[i];
 			loff_t		b_offset;
@@ -1257,18 +1246,18 @@ xfs_find_get_desired_pgoff(
 			 * file mapping. However, page->index will not change
 			 * because we have a reference on the page.
 			 *
-			 * Searching done if the page index is out of range.
-			 * If the current offset is not reaches the end of
-			 * the specified search range, there should be a hole
-			 * between them.
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
 			 */
-			if (page->index > end) {
-				if (type == HOLE_OFF && lastoff < endoff) {
-					*offset = lastoff;
-					found = true;
-				}
+			if (type == HOLE_OFF && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
+				found = true;
+				*offset = lastoff;
 				goto out;
 			}
+			/* Searching done if the page index is out of range. */
+			if (page->index > end)
+				goto out;
 
 			lock_page(page);
 			/*
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ee3aaa0a5317..ca0d3eb44925 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -243,8 +243,8 @@ xfs_growfs_data_private(
 		agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
 		agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
 		agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
-		agf->agf_flfirst = 0;
-		agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
+		agf->agf_flfirst = cpu_to_be32(1);
+		agf->agf_fllast = 0;
 		agf->agf_flcount = 0;
 		tmpsize = agsize - XFS_PREALLOC_BLOCKS(mp);
 		agf->agf_freeblks = cpu_to_be32(tmpsize);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d7a490f24ead..adbc1f59969a 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -210,14 +210,17 @@ xfs_iget_cache_hit(
 
 		error = inode_init_always(mp->m_super, inode);
 		if (error) {
+			bool wake;
 			/*
 			 * Re-initializing the inode failed, and we are in deep
 			 * trouble.  Try to re-add it to the reclaim list.
 			 */
 			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
-
+			wake = !!__xfs_iflags_test(ip, XFS_INEW);
 			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+			if (wake)
+				wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 			trace_xfs_iget_reclaim_fail(ip);
 			goto out_error;
@@ -363,6 +366,22 @@ out_destroy:
 	return error;
 }
 
+static void
+xfs_inew_wait(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+	do {
+		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		if (!xfs_iflags_test(ip, XFS_INEW))
+			break;
+		schedule();
+	} while (true);
+	finish_wait(wq, &wait.wait);
+}
+
 /*
  * Look up an inode by number in the given file system.
  * The inode is looked up in the cache held in each AG.
@@ -467,9 +486,11 @@ out_error_or_again:
 
 STATIC int
 xfs_inode_ag_walk_grab(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	bool			newinos = !!(flags & XFS_AGITER_INEW_WAIT);
 
 	ASSERT(rcu_read_lock_held());
 
@@ -487,7 +508,8 @@ xfs_inode_ag_walk_grab(
 		goto out_unlock_noent;
 
 	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+	if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+	    __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
 		goto out_unlock_noent;
 	spin_unlock(&ip->i_flags_lock);
 
@@ -515,7 +537,8 @@ xfs_inode_ag_walk(
 					   void *args),
 	int			flags,
 	void			*args,
-	int			tag)
+	int			tag,
+	int			iter_flags)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
@@ -557,7 +580,7 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			struct xfs_inode *ip = batch[i];
 
-			if (done || xfs_inode_ag_walk_grab(ip))
+			if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
 				batch[i] = NULL;
 
 			/*
@@ -585,6 +608,9 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
 				continue;
+			if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+			    xfs_iflags_test(batch[i], XFS_INEW))
+				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
 			IRELE(batch[i]);
 			if (error == -EAGAIN) {
@@ -637,12 +663,13 @@ xfs_eofblocks_worker(
 }
 
 int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
-	void			*args)
+	void			*args,
+	int			iter_flags)
 {
 	struct xfs_perag	*pag;
 	int			error = 0;
@@ -652,7 +679,8 @@ xfs_inode_ag_iterator(
 	ag = 0;
 	while ((pag = xfs_perag_get(mp, ag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+					  iter_flags);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
@@ -664,6 +692,17 @@ xfs_inode_ag_iterator(
 }
 
 int
+xfs_inode_ag_iterator(
+	struct xfs_mount	*mp,
+	int			(*execute)(struct xfs_inode *ip, int flags,
+					   void *args),
+	int			flags,
+	void			*args)
+{
+	return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
+int
 xfs_inode_ag_iterator_tag(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
@@ -680,7 +719,8 @@ xfs_inode_ag_iterator_tag(
 	ag = 0;
 	while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+					  0);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 62f1f91c32cb..147a79212e63 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -48,6 +48,11 @@ struct xfs_eofblocks {
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
 
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT	0x1	/* wait on new inodes */
+
 int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
 	     uint flags, uint lock_flags, xfs_inode_t **ipp);
 
@@ -72,6 +77,9 @@ void xfs_eofblocks_worker(struct work_struct *);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
+	int flags, void *args, int iter_flags);
 int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args, int tag);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8ee393996b7d..f0ce28cd311d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3220,13 +3220,14 @@ xfs_iflush_cluster(
 		 * We need to check under the i_flags_lock for a valid inode
 		 * here. Skip it if it is not valid or the wrong inode.
 		 */
-		spin_lock(&ip->i_flags_lock);
-		if (!ip->i_ino ||
+		spin_lock(&iq->i_flags_lock);
+		if (!iq->i_ino ||
+		    __xfs_iflags_test(iq, XFS_ISTALE) ||
 		    (XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index) {
-			spin_unlock(&ip->i_flags_lock);
+			spin_unlock(&iq->i_flags_lock);
 			continue;
 		}
-		spin_unlock(&ip->i_flags_lock);
+		spin_unlock(&iq->i_flags_lock);
 
 		/*
 		 * Do an un-protected check to see if the inode is dirty and
@@ -3342,7 +3343,7 @@ xfs_iflush(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_buf		*bp;
+	struct xfs_buf		*bp = NULL;
 	struct xfs_dinode	*dip;
 	int			error;
 
@@ -3384,14 +3385,22 @@ xfs_iflush(
 	}
 
 	/*
-	 * Get the buffer containing the on-disk inode.
+	 * Get the buffer containing the on-disk inode. We are doing a try-lock
+	 * operation here, so we may get  an EAGAIN error. In that case, we
+	 * simply want to return with the inode still dirty.
+	 *
+	 * If we get any other error, we effectively have a corruption situation
+	 * and we cannot flush the inode, so we treat it the same as failing
+	 * xfs_iflush_int().
 	 */
 	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
 			       0);
-	if (error || !bp) {
+	if (error == -EAGAIN) {
 		xfs_ifunlock(ip);
 		return error;
 	}
+	if (error)
+		goto corrupt_out;
 
 	/*
 	 * First flush out the inode that xfs_iflush was called with.
@@ -3419,7 +3428,8 @@ xfs_iflush(
 	return 0;
 
 corrupt_out:
-	xfs_buf_relse(bp);
+	if (bp)
+		xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 cluster_corrupt_out:
 	error = -EFSCORRUPTED;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ca9e11989cbd..ae1a49845744 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -208,7 +208,8 @@ xfs_get_initial_prid(struct xfs_inode *dp)
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
-#define XFS_INEW		(1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT		3	 /* inode has just been allocated */
+#define XFS_INEW		(1 << __XFS_INEW_BIT)
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
@@ -453,6 +454,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
 	xfs_iflags_clear(ip, XFS_INEW);
 	barrier();
 	unlock_new_inode(VFS_I(ip));
+	wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 }
 
 static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d42738deec6d..e4a4f82ea13f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -403,6 +403,7 @@ xfs_attrlist_by_handle(
 {
 	int			error = -ENOMEM;
 	attrlist_cursor_kern_t	*cursor;
+	struct xfs_fsop_attrlist_handlereq __user	*p = arg;
 	xfs_fsop_attrlist_handlereq_t al_hreq;
 	struct dentry		*dentry;
 	char			*kbuf;
@@ -435,6 +436,11 @@ xfs_attrlist_by_handle(
 	if (error)
 		goto out_kfree;
 
+	if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
+		error = -EFAULT;
+		goto out_kfree;
+	}
+
 	if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
 		error = -EFAULT;
 
@@ -1379,10 +1385,11 @@ xfs_ioc_getbmap(
 	unsigned int		cmd,
 	void			__user *arg)
 {
-	struct getbmapx		bmx;
+	struct getbmapx		bmx = { 0 };
 	int			error;
 
-	if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+	/* struct getbmap is a strict subset of struct getbmapx. */
+	if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
 		return -EFAULT;
 
 	if (bmx.bmv_count < 2)
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index ec0e239a0fa9..201aae0b2662 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -369,7 +369,14 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
 #endif /* DEBUG */
 
 #ifdef CONFIG_XFS_RT
-#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME)
+
+/*
+ * make sure we ignore the inode flag if the filesystem doesn't have a
+ * configured realtime device.
+ */
+#define XFS_IS_REALTIME_INODE(ip)			\
+	(((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) &&	\
+	 (ip)->i_mount->m_rtdev_targp)
 #else
 #define XFS_IS_REALTIME_INODE(ip) (0)
 #endif
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index c5ecaacdd218..8cab78eeb0c2 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3204,6 +3204,7 @@ xlog_recover_dquot_ra_pass2(
 	struct xfs_disk_dquot	*recddq;
 	struct xfs_dq_logformat	*dq_f;
 	uint			type;
+	int			len;
 
 
 	if (mp->m_qflags == 0)
@@ -3224,8 +3225,12 @@ xlog_recover_dquot_ra_pass2(
 	ASSERT(dq_f);
 	ASSERT(dq_f->qlf_len == 1);
 
-	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno,
-			  XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL);
+	len = XFS_FSB_TO_BB(mp, dq_f->qlf_len);
+	if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0))
+		return;
+
+	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len,
+			  &xfs_dquot_buf_ra_ops);
 }
 
 STATIC void
@@ -3975,6 +3980,7 @@ xlog_recover_clear_agi_bucket(
 	agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
 	offset = offsetof(xfs_agi_t, agi_unlinked) +
 		 (sizeof(xfs_agino_t) * bucket);
+	xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
 	xfs_trans_log_buf(tp, agibp, offset,
 			  (offset + sizeof(xfs_agino_t) - 1));
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 532ab79d38fe..572b64a135b3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1355,12 +1355,7 @@ xfs_qm_quotacheck(
 	mp->m_qflags |= flags;
 
  error_return:
-	while (!list_empty(&buffer_list)) {
-		struct xfs_buf *bp =
-			list_first_entry(&buffer_list, struct xfs_buf, b_list);
-		list_del_init(&bp->b_list);
-		xfs_buf_relse(bp);
-	}
+	xfs_buf_delwri_cancel(&buffer_list);
 
 	if (error) {
 		xfs_warn(mp,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3640c6e896af..4d334440bd94 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -764,5 +764,6 @@ xfs_qm_dqrele_all_inodes(
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+	xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+				    XFS_AGITER_INEW_WAIT);
 }
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 36bd8825bfb0..ef64a1e1a66a 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1233,6 +1233,16 @@ xfs_fs_remount(
 			return -EINVAL;
 		}
 
+		if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+		    xfs_sb_has_ro_compat_feature(sbp,
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+			xfs_warn(mp,
+"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
+				(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+			return -EINVAL;
+		}
+
 		mp->m_flags &= ~XFS_MOUNT_RDONLY;
 
 		/*
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 839b35ca21c6..9beaf192b4bb 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -180,7 +180,8 @@ xfs_xattr_put_listent(
 	arraytop = context->count + prefix_len + namelen + 1;
 	if (arraytop > context->firstu) {
 		context->count = -1;	/* insufficient space */
-		return 1;
+		context->seen_enough = 1;
+		return 0;
 	}
 	offset = (char *)context->alist + context->count;
 	strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
@@ -222,12 +223,15 @@ list_one_attr(const char *name, const size_t len, void *data,
 }
 
 ssize_t
-xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
+xfs_vn_listxattr(
+	struct dentry	*dentry,
+	char		*data,
+	size_t		size)
 {
 	struct xfs_attr_list_context context;
 	struct attrlist_cursor_kern cursor = { 0 };
-	struct inode		*inode = d_inode(dentry);
-	int			error;
+	struct inode	*inode = d_inode(dentry);
+	int		error;
 
 	/*
 	 * First read the regular on-disk attributes.
@@ -245,7 +249,9 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
 	else
 		context.put_listent = xfs_xattr_put_listent_sizes;
 
-	xfs_attr_list_int(&context);
+	error = xfs_attr_list_int(&context);
+	if (error)
+		return error;
 	if (context.count < 0)
 		return -ERANGE;
 
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index c30266e94806..8ef0ccbf8167 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -29,16 +29,16 @@ do {					\
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
- * This operation is like clear_bit_unlock, however it is not atomic.
- * It does provide release barrier semantics so it can be used to unlock
- * a bit lock, however it would only be used if no other CPU can modify
- * any bits in the memory until the lock is released (a good example is
- * if the bit lock itself protects access to the other bits in the word).
+ * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
+ * the bits in the word are protected by this lock some archs can use weaker
+ * ops to safely unlock.
+ *
+ * See for example x86's implementation.
  */
 #define __clear_bit_unlock(nr, addr)	\
 do {					\
-	smp_mb();			\
-	__clear_bit(nr, addr);		\
+	smp_mb__before_atomic();	\
+	clear_bit(nr, addr);		\
 } while (0)
 
 #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index e56272c919b5..bf2d34c9d804 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -108,11 +108,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	u32 val;
 
 	preempt_disable();
-	if (unlikely(get_user(val, uaddr) != 0))
+	if (unlikely(get_user(val, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
-	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
 	*uval = val;
 	preempt_enable();
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index e2aadbc7151f..1885fc44b1bc 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -21,14 +21,33 @@
 #include <asm-generic/qspinlock_types.h>
 
 /**
+ * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+#ifndef queued_spin_unlock_wait
+extern void queued_spin_unlock_wait(struct qspinlock *lock);
+#endif
+
+/**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
  */
+#ifndef queued_spin_is_locked
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
+	/*
+	 * See queued_spin_unlock_wait().
+	 *
+	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
+	 * isn't immediately observable.
+	 */
 	return atomic_read(&lock->val);
 }
+#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -98,19 +117,6 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
-/**
- * queued_spin_unlock_wait - wait until current lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-static inline void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-}
-
 #ifndef virt_spin_lock
 static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 3d1a3af5cf59..a2508a8f9a9c 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -17,21 +17,6 @@
 struct siginfo;
 void do_schedule_next_timer(struct siginfo *info);
 
-#ifndef HAVE_ARCH_COPY_SIGINFO
-
-#include <linux/string.h>
-
-static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
-{
-	if (from->si_code < 0)
-		memcpy(to, from, sizeof(*to));
-	else
-		/* _sigchld is currently the largest know union member */
-		memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
-}
-
-#endif
-
 extern int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from);
 
 #endif
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index fc824e2828f3..5d2add1a6c96 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -48,7 +48,11 @@
 #define parent_node(node)	((void)(node),0)
 #endif
 #ifndef cpumask_of_node
-#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+  #ifdef CONFIG_NEED_MULTIPLE_NODES
+    #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
+  #else
+    #define cpumask_of_node(node)	((void)node, cpu_online_mask)
+  #endif
 #endif
 #ifndef pcibus_to_node
 #define pcibus_to_node(bus)	((void)(bus), -1)
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 1bfa602958f2..32901d11f8c4 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -230,14 +230,18 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 	might_fault();						\
 	access_ok(VERIFY_READ, __p, sizeof(*ptr)) ?		\
 		__get_user((x), (__typeof__(*(ptr)) *)__p) :	\
-		-EFAULT;					\
+		((x) = (__typeof__(*(ptr)))0,-EFAULT);		\
 })
 
 #ifndef __get_user_fn
 static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 {
-	size = __copy_from_user(x, ptr, size);
-	return size ? -EFAULT : size;
+	size_t n = __copy_from_user(x, ptr, size);
+	if (unlikely(n)) {
+		memset(x + (size - n), 0, n);
+		return -EFAULT;
+	}
+	return 0;
 }
 
 #define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
@@ -257,11 +261,13 @@ extern int __get_user_bad(void) __attribute__((noreturn));
 static inline long copy_from_user(void *to,
 		const void __user * from, unsigned long n)
 {
+	unsigned long res = n;
 	might_fault();
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_from_user(to, from, n);
-	else
-		return n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
 static inline long copy_to_user(void __user *to,
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 772c784ba763..71581125e604 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -532,15 +532,19 @@
 
 #define INIT_TEXT							\
 	*(.init.text)							\
+	*(.text.startup)						\
 	MEM_DISCARD(init.text)
 
 #define EXIT_DATA							\
 	*(.exit.data)							\
+	*(.fini_array)							\
+	*(.dtors)							\
 	MEM_DISCARD(exit.data)						\
 	MEM_DISCARD(exit.rodata)
 
 #define EXIT_TEXT							\
 	*(.exit.text)							\
+	*(.text.exit)							\
 	MEM_DISCARD(exit.text)
 
 #define EXIT_CALL							\
diff --git a/include/crypto/ghash.h b/include/crypto/ghash.h
new file mode 100644
index 000000000000..2a61c9bbab8f
--- /dev/null
+++ b/include/crypto/ghash.h
@@ -0,0 +1,23 @@
+/*
+ * Common values for GHASH algorithms
+ */
+
+#ifndef __CRYPTO_GHASH_H__
+#define __CRYPTO_GHASH_H__
+
+#include <linux/types.h>
+#include <crypto/gf128mul.h>
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+struct ghash_ctx {
+	struct gf128mul_4k *gf128;
+};
+
+struct ghash_desc_ctx {
+	u8 buffer[GHASH_BLOCK_SIZE];
+	u32 bytes;
+};
+
+#endif
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 3b4af1d7c7e9..a25414ce2898 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -173,6 +173,16 @@ static inline struct ahash_instance *ahash_alloc_instance(
 	return crypto_alloc_instance2(name, alg, ahash_instance_headroom());
 }
 
+static inline void ahash_request_complete(struct ahash_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline u32 ahash_request_flags(struct ahash_request *req)
+{
+	return req->base.flags;
+}
+
 static inline struct crypto_ahash *crypto_spawn_ahash(
 	struct crypto_ahash_spawn *spawn)
 {
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0a271ca1f7c7..a31976c860f6 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1029,7 +1029,8 @@ static inline int drm_debugfs_remove_files(const struct drm_info_list *files,
 #endif
 
 extern struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
-		struct drm_gem_object *obj, int flags);
+					    struct drm_gem_object *obj,
+					    int flags);
 extern int drm_gem_prime_handle_to_fd(struct drm_device *dev,
 		struct drm_file *file_priv, uint32_t handle, uint32_t flags,
 		int *prime_fd);
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index 461a0558bca4..cebecff536a3 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -39,6 +39,8 @@ static inline bool drm_arch_can_wc_memory(void)
 {
 #if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
 	return false;
+#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
+	return false;
 #else
 	return true;
 #endif
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 17c445612e01..2cdc723d750f 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -277,7 +277,9 @@
 	INTEL_VGA_DEVICE(0x191D, info)  /* WKS GT2 */
 
 #define INTEL_SKL_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x1923, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \
+	INTEL_VGA_DEVICE(0x1927, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \
 	INTEL_VGA_DEVICE(0x192A, info) /* SRV GT3 */ \
 
@@ -289,6 +291,8 @@
 #define INTEL_BXT_IDS(info) \
 	INTEL_VGA_DEVICE(0x0A84, info), \
 	INTEL_VGA_DEVICE(0x1A84, info), \
-	INTEL_VGA_DEVICE(0x5A84, info)
+	INTEL_VGA_DEVICE(0x1A85, info), \
+	INTEL_VGA_DEVICE(0x5A84, info), /* APL HD Graphics 505 */ \
+	INTEL_VGA_DEVICE(0x5A85, info)  /* APL HD Graphics 500 */
 
 #endif /* _I915_PCIIDS_H */
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index c768ddfbe53c..b7bfa513e6ed 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -316,6 +316,20 @@ ttm_bo_reference(struct ttm_buffer_object *bo)
  */
 extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool lazy,
 		       bool interruptible, bool no_wait);
+
+/**
+ * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo
+ *
+ * @placement:  Return immediately if buffer is busy.
+ * @mem:  The struct ttm_mem_reg indicating the region where the bo resides
+ * @new_flags: Describes compatible placement found
+ *
+ * Returns true if the placement is compatible
+ */
+extern bool ttm_bo_mem_compat(struct ttm_placement *placement,
+			      struct ttm_mem_reg *mem,
+			      uint32_t *new_flags);
+
 /**
  * ttm_bo_validate
  *
diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h
index ed953f98f0e1..1487011fe057 100644
--- a/include/drm/ttm/ttm_object.h
+++ b/include/drm/ttm/ttm_object.h
@@ -229,6 +229,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
  * @ref_type: The type of reference.
  * @existed: Upon completion, indicates that an identical reference object
  * already existed, and the refcount was upped on that object instead.
+ * @require_existed: Fail with -EPERM if an identical ref object didn't
+ * already exist.
  *
  * Checks that the base object is shareable and adds a ref object to it.
  *
@@ -243,7 +245,8 @@ extern void ttm_base_object_unref(struct ttm_base_object **p_base);
  */
 extern int ttm_ref_object_add(struct ttm_object_file *tfile,
 			      struct ttm_base_object *base,
-			      enum ttm_ref_type ref_type, bool *existed);
+			      enum ttm_ref_type ref_type, bool *existed,
+			      bool require_existed);
 
 extern bool ttm_ref_object_exists(struct ttm_object_file *tfile,
 				  struct ttm_base_object *base);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1991aea2ec4c..3672893b275e 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -920,7 +920,7 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 	return NULL;
 }
 
-#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \
+#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \
 	static const void * __acpi_table_##name[]			\
 		__attribute__((unused))					\
 		 = { (void *) table_id,					\
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 1b4d69f68c33..140c29635069 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -163,6 +163,7 @@ struct backing_dev_info {
 	wait_queue_head_t wb_waitq;
 
 	struct device *dev;
+	struct device *owner;
 
 	struct timer_list laptop_mode_wb_timer;
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c82794f20110..89d3de3e096b 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -24,6 +24,7 @@ __printf(3, 4)
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
 void bdi_unregister(struct backing_dev_info *bdi);
 
 int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 3feb1b2d75d8..14cd6f77e284 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -156,6 +156,7 @@ struct bcma_host_ops {
 #define BCMA_CORE_DEFAULT		0xFFF
 
 #define BCMA_MAX_NR_CORES		16
+#define BCMA_CORE_SIZE			0x1000
 
 /* Chip IDs of PCIe devices */
 #define BCMA_CHIP_ID_BCM4313	0x4313
diff --git a/include/linux/bio.h b/include/linux/bio.h
index fbe47bc700bd..42e4e3cbb001 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -527,11 +527,14 @@ extern unsigned int bvec_nr_vecs(unsigned short idx);
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_current(struct bio *bio);
 void bio_disassociate_task(struct bio *bio);
+void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
 static inline int bio_associate_blkcg(struct bio *bio,
 			struct cgroup_subsys_state *blkcg_css) { return 0; }
 static inline int bio_associate_current(struct bio *bio) { return -ENOENT; }
 static inline void bio_disassociate_task(struct bio *bio) { }
+static inline void bio_clone_blkcg_association(struct bio *dst,
+			struct bio *src) { }
 #endif	/* CONFIG_BLK_CGROUP */
 
 #ifdef CONFIG_HIGHMEM
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 168755791ec8..fe14382f9664 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -890,7 +890,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
+	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 83d1926c61e4..4f6d29c8e3d8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -165,12 +165,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
-void bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
@@ -197,6 +198,10 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
+
+static inline void bpf_prog_put_rcu(struct bpf_prog *prog)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 /* verifier prototypes for helper functions called from eBPF programs */
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index a0875001b13c..df08a41d5be5 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,10 +45,9 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-extern int  can_rx_register(struct net_device *dev, canid_t can_id,
-			    canid_t mask,
-			    void (*func)(struct sk_buff *, void *),
-			    void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+		    void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk);
 
 extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 			      canid_t mask,
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 735f9f8c4e43..5f5270941ba0 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -32,6 +32,7 @@ enum can_mode {
  * CAN common private data
  */
 struct can_priv {
+	struct net_device *dev;
 	struct can_device_stats can_stats;
 
 	struct can_bittiming bittiming, data_bittiming;
@@ -40,11 +41,14 @@ struct can_priv {
 	struct can_clock clock;
 
 	enum can_state state;
-	u32 ctrlmode;
-	u32 ctrlmode_supported;
+
+	/* CAN controller features - see include/uapi/linux/can/netlink.h */
+	u32 ctrlmode;		/* current options setting */
+	u32 ctrlmode_supported;	/* options that can be modified by netlink */
+	u32 ctrlmode_static;	/* static enabled options for driver/hardware */
 
 	int restart_ms;
-	struct timer_list restart_timer;
+	struct delayed_work restart_work;
 
 	int (*do_set_bittiming)(struct net_device *dev);
 	int (*do_set_data_bittiming)(struct net_device *dev);
@@ -108,6 +112,21 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb)
 	return skb->len == CANFD_MTU;
 }
 
+/* helper to define static CAN controller features at device creation time */
+static inline void can_set_static_ctrlmode(struct net_device *dev,
+					   u32 static_mode)
+{
+	struct can_priv *priv = netdev_priv(dev);
+
+	/* alloc_candev() succeeded => netdev_priv() is valid at this point */
+	priv->ctrlmode = static_mode;
+	priv->ctrlmode_static = static_mode;
+
+	/* override MTU which was set by default in can_setup()? */
+	if (static_mode & CAN_CTRLMODE_FD)
+		dev->mtu = CANFD_MTU;
+}
+
 /* get data length from can_dlc with sanitized can_dlc */
 u8 can_dlc2len(u8 can_dlc);
 
diff --git a/include/linux/capability.h b/include/linux/capability.h
index af9f0b9e80e6..b20ffe23a09b 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -40,8 +40,6 @@ struct inode;
 struct dentry;
 struct user_namespace;
 
-struct user_namespace *current_user_ns(void);
-
 extern const kernel_cap_t __cap_empty_set;
 extern const kernel_cap_t __cap_init_eff_set;
 
@@ -214,6 +212,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 				      struct user_namespace *ns, int cap);
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
+extern bool ns_capable_noaudit(struct user_namespace *ns, int cap);
 #else
 static inline bool has_capability(struct task_struct *t, int cap)
 {
@@ -241,9 +240,15 @@ static inline bool ns_capable(struct user_namespace *ns, int cap)
 {
 	return true;
 }
+static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+	return true;
+}
 #endif /* CONFIG_MULTIUSER */
+extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode);
 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);
+extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e55c08bc3a96..0abc56140c83 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -49,7 +49,7 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
 	case CEPH_POOL_TYPE_EC:
 		return false;
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 }
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8e30faeab183..8da263299754 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -216,6 +216,9 @@ struct css_set {
 	/* all css_task_iters currently walking this cset */
 	struct list_head task_iters;
 
+	/* dead and being drained, ignore for migration */
+	bool dead;
+
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
 };
@@ -431,6 +434,7 @@ struct cgroup_subsys {
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);
+	void (*post_attach)(void);
 	int (*can_fork)(struct task_struct *task, void **priv_p);
 	void (*cancel_fork)(struct task_struct *task, void *priv);
 	void (*fork)(struct task_struct *task, void *priv);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index cb91b44f5f78..210ccc4ea44b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -340,6 +340,26 @@ static inline bool css_tryget_online(struct cgroup_subsys_state *css)
 }
 
 /**
+ * css_is_dying - test whether the specified css is dying
+ * @css: target css
+ *
+ * Test whether @css is in the process of offlining or already offline.  In
+ * most cases, ->css_online() and ->css_offline() callbacks should be
+ * enough; however, the actual offline operations are RCU delayed and this
+ * test returns %true also when @css is scheduled to be offlined.
+ *
+ * This is useful, for example, when the use case requires synchronous
+ * behavior with respect to cgroup removal.  cgroup removal schedules css
+ * offlining but the css can seem alive while the operation is being
+ * delayed.  If the delay affects user visible semantics, this test can be
+ * used to resolve the situation.
+ */
+static inline bool css_is_dying(struct cgroup_subsys_state *css)
+{
+	return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
+}
+
+/**
  * css_put - put a css reference
  * @css: target css
  *
@@ -528,6 +548,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
+static inline void cgroup_init_kthreadd(void)
+{
+	/*
+	 * kthreadd is inherited by all kthreads, keep it in the root so
+	 * that the new kthreads are guaranteed to stay in the root until
+	 * initialization is finished.
+	 */
+	current->no_cgroup_migration = 1;
+}
+
+static inline void cgroup_kthread_ready(void)
+{
+	/*
+	 * This kthread finished initialization.  The creator should have
+	 * set PF_NO_SETAFFINITY if this kthread should stay in the root.
+	 */
+	current->no_cgroup_migration = 0;
+}
+
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
@@ -551,6 +590,8 @@ static inline void cgroup_free(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
+static inline void cgroup_init_kthreadd(void) {}
+static inline void cgroup_kthread_ready(void) {}
 
 #endif /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index c56988ac63f7..7cd0171963ae 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -384,6 +384,7 @@ struct clk_divider {
 #define CLK_DIVIDER_MAX_AT_ZERO		BIT(6)
 
 extern const struct clk_ops clk_divider_ops;
+extern const struct clk_ops clk_divider_ro_ops;
 
 unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate,
 		unsigned int val, const struct clk_div_table *table,
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 22ab246feed3..287e698c28de 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -199,7 +199,7 @@
 #define unreachable() __builtin_unreachable()
 
 /* Mark a function definition as prohibited from being cloned. */
-#define __noclone	__attribute__((__noclone__))
+#define __noclone	__attribute__((__noclone__, __optimize__("no-tracer")))
 
 #endif /* GCC_VERSION >= 40500 */
 
@@ -251,7 +251,9 @@
 #endif
 #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
 
-#if GCC_VERSION >= 50000
+#if GCC_VERSION >= 70000
+#define KASAN_ABI_VERSION 5
+#elif GCC_VERSION >= 50000
 #define KASAN_ABI_VERSION 4
 #elif GCC_VERSION >= 40902
 #define KASAN_ABI_VERSION 3
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index d016a121a8c4..28ffa94aed6b 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -14,6 +14,7 @@ struct coredump_params;
 extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
+extern void dump_truncate(struct coredump_params *cprm);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const siginfo_t *siginfo);
 #else
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index d2ca8c38f9c4..3ea9aae2387d 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -131,22 +131,16 @@ enum {
 		{ .notifier_call = fn, .priority = pri };	\
 	__register_cpu_notifier(&fn##_nb);			\
 }
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
 
-#ifdef CONFIG_HOTPLUG_CPU
 extern int register_cpu_notifier(struct notifier_block *nb);
 extern int __register_cpu_notifier(struct notifier_block *nb);
 extern void unregister_cpu_notifier(struct notifier_block *nb);
 extern void __unregister_cpu_notifier(struct notifier_block *nb);
-#else
 
-#ifndef MODULE
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-#else
+#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
+
 static inline int register_cpu_notifier(struct notifier_block *nb)
 {
 	return 0;
@@ -156,7 +150,6 @@ static inline int __register_cpu_notifier(struct notifier_block *nb)
 {
 	return 0;
 }
-#endif
 
 static inline void unregister_cpu_notifier(struct notifier_block *nb)
 {
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 59915ea5373c..a91b3b75da0f 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -556,7 +556,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
 static inline int cpumask_parse_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
-	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -571,7 +571,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
-				     nr_cpu_ids);
+				     nr_cpumask_bits);
 }
 
 /**
@@ -586,7 +586,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 	char *nl = strchr(buf, '\n');
 	unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
 
-	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -598,7 +598,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  */
 static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
-	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index fea160ee5803..8397dc235e84 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -16,6 +16,7 @@
 
 #ifdef CONFIG_CPUSETS
 
+extern struct static_key cpusets_pre_enable_key;
 extern struct static_key cpusets_enabled_key;
 static inline bool cpusets_enabled(void)
 {
@@ -30,12 +31,14 @@ static inline int nr_cpusets(void)
 
 static inline void cpuset_inc(void)
 {
+	static_key_slow_inc(&cpusets_pre_enable_key);
 	static_key_slow_inc(&cpusets_enabled_key);
 }
 
 static inline void cpuset_dec(void)
 {
 	static_key_slow_dec(&cpusets_enabled_key);
+	static_key_slow_dec(&cpusets_pre_enable_key);
 }
 
 extern int cpuset_init(void);
@@ -104,7 +107,7 @@ extern void cpuset_print_current_mems_allowed(void);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
-	if (!cpusets_enabled())
+	if (!static_key_false(&cpusets_pre_enable_key))
 		return 0;
 
 	return read_seqcount_begin(&current->mems_allowed_seq);
@@ -118,7 +121,7 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	if (!cpusets_enabled())
+	if (!static_key_false(&cpusets_enabled_key))
 		return false;
 
 	return read_seqcount_retry(&current->mems_allowed_seq, seq);
@@ -137,8 +140,6 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
-extern void cpuset_post_attach_flush(void);
-
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -245,10 +246,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
-static inline void cpuset_post_attach_flush(void)
-{
-}
-
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 8d70e1361ecd..257db64562e5 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -377,7 +377,10 @@ extern struct user_namespace init_user_ns;
 #ifdef CONFIG_USER_NS
 #define current_user_ns()	(current_cred_xxx(user_ns))
 #else
-#define current_user_ns()	(&init_user_ns)
+static inline struct user_namespace *current_user_ns(void)
+{
+	return &init_user_ns;
+}
 #endif
 
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 8a2e009c8a5a..d516847e0fae 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -161,6 +161,7 @@ struct dentry_operations {
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(struct dentry *, bool);
 	struct inode *(*d_select_inode)(struct dentry *, unsigned);
+	struct dentry *(*d_real)(struct dentry *, struct inode *);
 } ____cacheline_aligned;
 
 /*
@@ -227,6 +228,7 @@ struct dentry_operations {
 #define DCACHE_MAY_FREE			0x00800000
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
 #define DCACHE_OP_SELECT_INODE		0x02000000 /* Unioned entry: dcache op selects inode */
+#define DCACHE_OP_REAL			0x08000000
 
 extern seqlock_t rename_lock;
 
@@ -582,4 +584,42 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper)
 	return upper;
 }
 
+static inline struct dentry *d_real(struct dentry *dentry)
+{
+	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
+		return dentry->d_op->d_real(dentry, NULL);
+	else
+		return dentry;
+}
+
+static inline struct inode *vfs_select_inode(struct dentry *dentry,
+					     unsigned open_flags)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (inode && unlikely(dentry->d_flags & DCACHE_OP_SELECT_INODE))
+		inode = dentry->d_op->d_select_inode(dentry, open_flags);
+
+	return inode;
+}
+
+/**
+ * d_real_inode - Return the real inode
+ * @dentry: The dentry to query
+ *
+ * If dentry is on an union/overlay, then return the underlying, real inode.
+ * Otherwise return d_inode().
+ */
+static inline struct inode *d_real_inode(struct dentry *dentry)
+{
+	return d_backing_inode(d_real(dentry));
+}
+
+struct name_snapshot {
+	const char *name;
+	char inline_name[DNAME_INLINE_LEN];
+};
+void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
+void release_dentry_name_snapshot(struct name_snapshot *);
+
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042bbbf60..68449293c4b6 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h
index 0a83a1e648b0..4db00b02ca3f 100644
--- a/include/linux/devfreq-event.h
+++ b/include/linux/devfreq-event.h
@@ -148,11 +148,6 @@ static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev)
 	return -EINVAL;
 }
 
-static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
 					struct device *dev, int index)
 {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ec1c61c87d89..899ab9f8549e 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -124,6 +124,8 @@ struct dm_dev {
 	char name[16];
 };
 
+dev_t dm_get_dev_t(const char *path);
+
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
diff --git a/include/linux/device.h b/include/linux/device.h
index b8f411b57dcb..7075a2485ed3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -368,6 +368,7 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @suspend:	Used to put the device to sleep mode, usually to a low power
  *		state.
  * @resume:	Used to bring the device from the sleep mode.
+ * @shutdown:	Called at shut-down time to quiesce the device.
  * @ns_type:	Callbacks so sysfs can detemine namespaces.
  * @namespace:	Namespace of the device belongs to this class.
  * @pm:		The default device power management operations of this class.
@@ -396,6 +397,7 @@ struct class {
 
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
+	int (*shutdown)(struct device *dev);
 
 	const struct kobj_ns_type_operations *ns_type;
 	const void *(*namespace)(struct device *dev);
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index e0ee0b3000b2..358a4db72a27 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,38 +15,24 @@
 
 #include <linux/errno.h>
 
+struct pts_fs_info;
+
 #ifdef CONFIG_UNIX98_PTYS
 
-int devpts_new_index(struct inode *ptmx_inode);
-void devpts_kill_index(struct inode *ptmx_inode, int idx);
-void devpts_add_ref(struct inode *ptmx_inode);
-void devpts_del_ref(struct inode *ptmx_inode);
+/* Look up a pts fs info and get a ref to it */
+struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
+void devpts_put_ref(struct pts_fs_info *);
+
+int devpts_new_index(struct pts_fs_info *);
+void devpts_kill_index(struct pts_fs_info *, int);
+
 /* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
-		void *priv);
+struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *);
 /* get private structure */
 void *devpts_get_priv(struct inode *pts_inode);
 /* unlink */
 void devpts_pty_kill(struct inode *inode);
 
-#else
-
-/* Dummy stubs in the no-pty case */
-static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
-static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline void devpts_add_ref(struct inode *ptmx_inode) { }
-static inline void devpts_del_ref(struct inode *ptmx_inode) { }
-static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
-		dev_t device, int index, void *priv)
-{
-	return ERR_PTR(-EINVAL);
-}
-static inline void *devpts_get_priv(struct inode *pts_inode)
-{
-	return NULL;
-}
-static inline void devpts_pty_kill(struct inode *inode) { }
-
 #endif
 
 
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 25c6324a0dd0..3d6e6ce44c5c 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -284,6 +284,12 @@ struct f2fs_nat_block {
 #define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry))
 
 /*
+ * F2FS uses 4 bytes to represent block address. As a result, supported size of
+ * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments.
+ */
+#define F2FS_MAX_SEGMENT       ((16 * 1024 * 1024) / 2)
+
+/*
  * Note that f2fs_sit_entry->vblocks has the following bit-field information.
  * [15:10] : allocation type such as CURSEG_XXXX_TYPE
  * [9:0] : valid block count
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 76ce329e656d..1b48d9c9a561 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -3,6 +3,12 @@
 
 #include <uapi/linux/fcntl.h>
 
+/* list of all valid flags for the open/openat flags argument: */
+#define VALID_OPEN_FLAGS \
+	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
+	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
+	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
+	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
 
 #ifndef force_o_largefile
 #define force_o_largefile() (BITS_PER_LONG != 32)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5972ffe5719a..ccb98b459c59 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -421,7 +421,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 }
 #endif /* CONFIG_DEBUG_SET_MODULE_RONX */
 
-int sk_filter(struct sock *sk, struct sk_buff *skb);
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
+static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
+{
+	return sk_filter_trim_cap(sk, skb, 1);
+}
 
 int bpf_prog_select_runtime(struct bpf_prog *fp);
 void bpf_prog_free(struct bpf_prog *fp);
@@ -446,8 +450,12 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
+int __sk_detach_filter(struct sock *sk, bool locked);
+
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3aa514254161..c8decb7075d6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -226,6 +226,7 @@ typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
 #define ATTR_KILL_PRIV	(1 << 14)
 #define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
 #define ATTR_TIMES_SET	(1 << 16)
+#define ATTR_TOUCH	(1 << 17)
 
 /*
  * Whiteout is represented by a char device.  The following constants define the
@@ -679,6 +680,11 @@ struct inode {
 	void			*i_private; /* fs or device private pointer */
 };
 
+static inline unsigned int i_blocksize(const struct inode *node)
+{
+	return (1 << node->i_blkbits);
+}
+
 static inline int inode_unhashed(struct inode *inode)
 {
 	return hlist_unhashed(&inode->i_hash);
@@ -710,6 +716,31 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT2,
 };
 
+static inline void inode_lock(struct inode *inode)
+{
+	mutex_lock(&inode->i_mutex);
+}
+
+static inline void inode_unlock(struct inode *inode)
+{
+	mutex_unlock(&inode->i_mutex);
+}
+
+static inline int inode_trylock(struct inode *inode)
+{
+	return mutex_trylock(&inode->i_mutex);
+}
+
+static inline int inode_is_locked(struct inode *inode)
+{
+	return mutex_is_locked(&inode->i_mutex);
+}
+
+static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
+{
+	mutex_lock_nested(&inode->i_mutex, subclass);
+}
+
 void lock_two_nondirectories(struct inode *, struct inode*);
 void unlock_two_nondirectories(struct inode *, struct inode*);
 
@@ -1207,6 +1238,16 @@ static inline struct inode *file_inode(const struct file *f)
 	return f->f_inode;
 }
 
+static inline struct dentry *file_dentry(const struct file *file)
+{
+	struct dentry *dentry = file->f_path.dentry;
+
+	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
+		return dentry->d_op->d_real(dentry, file_inode(file));
+	else
+		return dentry;
+}
+
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 {
 	return locks_lock_inode_wait(file_inode(filp), fl);
@@ -2217,7 +2258,7 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags,
 extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
-				   const char *, int);
+				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
@@ -3019,8 +3060,8 @@ static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
 }
 static inline bool dir_relax(struct inode *inode)
 {
-	mutex_unlock(&inode->i_mutex);
-	mutex_lock(&inode->i_mutex);
+	inode_unlock(inode);
+	inode_lock(inode);
 	return !IS_DEADDIR(inode);
 }
 
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 604e1526cd00..eb19bf2b2a81 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -360,6 +360,7 @@ struct fscache_object {
 #define FSCACHE_OBJECT_IS_AVAILABLE	5	/* T if object has become active */
 #define FSCACHE_OBJECT_RETIRED		6	/* T if object was retired on relinquishment */
 #define FSCACHE_OBJECT_KILLED_BY_CACHE	7	/* T if object was killed by the cache */
+#define FSCACHE_OBJECT_RUN_AFTER_DEAD	8	/* T if object has been dispatched after death */
 
 	struct list_head	cache_link;	/* link in cache->object_list */
 	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 7ee1774edee5..a7789559078b 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -310,35 +310,4 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 	}
 }
 
-#if defined(CONFIG_FSNOTIFY)	/* notify helpers */
-
-/*
- * fsnotify_oldname_init - save off the old filename before we change it
- */
-static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name)
-{
-	return kstrdup(name, GFP_KERNEL);
-}
-
-/*
- * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init
- */
-static inline void fsnotify_oldname_free(const unsigned char *old_name)
-{
-	kfree(old_name);
-}
-
-#else	/* CONFIG_FSNOTIFY */
-
-static inline const char *fsnotify_oldname_init(const unsigned char *name)
-{
-	return NULL;
-}
-
-static inline void fsnotify_oldname_free(const unsigned char *old_name)
-{
-}
-
-#endif	/*  CONFIG_FSNOTIFY */
-
 #endif	/* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 533c4408529a..850d8822e8ff 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -148,6 +148,7 @@ struct fsnotify_group {
 	#define FS_PRIO_1	1 /* fanotify content based access control */
 	#define FS_PRIO_2	2 /* fanotify pre-content access */
 	unsigned int priority;
+	bool shutdown;		/* group is being shut down, don't queue more events */
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
@@ -179,7 +180,6 @@ struct fsnotify_group {
 			spinlock_t access_lock;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
-			atomic_t bypass_perm;
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
 			int f_flags;
 			unsigned int max_marks;
@@ -308,6 +308,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op
 extern void fsnotify_get_group(struct fsnotify_group *group);
 /* drop reference on a group from fsnotify_alloc_group */
 extern void fsnotify_put_group(struct fsnotify_group *group);
+/* group destruction begins, stop queuing new events */
+extern void fsnotify_group_stop_queueing(struct fsnotify_group *group);
 /* destroy group */
 extern void fsnotify_destroy_group(struct fsnotify_group *group);
 /* fasync handler function */
@@ -320,8 +322,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
 			      int (*merge)(struct list_head *,
 					   struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
 /* true if the group notification queue is empty */
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 847cc1d91634..5012fcdb4c9e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -742,11 +742,9 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 extern void blk_integrity_add(struct gendisk *);
 extern void blk_integrity_del(struct gendisk *);
-extern void blk_integrity_revalidate(struct gendisk *);
 #else	/* CONFIG_BLK_DEV_INTEGRITY */
 static inline void blk_integrity_add(struct gendisk *disk) { }
 static inline void blk_integrity_del(struct gendisk *disk) { }
-static inline void blk_integrity_revalidate(struct gendisk *disk) { }
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
 
 #else /* CONFIG_BLOCK */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 1afde47e1528..79c52fa81cac 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -32,12 +32,28 @@
 #error Wordsize not 32 or 64
 #endif
 
+/*
+ * The above primes are actively bad for hashing, since they are
+ * too sparse. The 32-bit one is mostly ok, the 64-bit one causes
+ * real problems. Besides, the "prime" part is pointless for the
+ * multiplicative hash.
+ *
+ * Although a random odd number will do, it turns out that the golden
+ * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
+ * properties.
+ *
+ * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2.
+ * (See Knuth vol 3, section 6.4, exercise 9.)
+ */
+#define GOLDEN_RATIO_32 0x61C88647
+#define GOLDEN_RATIO_64 0x61C8864680B583EBull
+
 static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
-#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
-	hash = hash * GOLDEN_RATIO_PRIME_64;
+#if BITS_PER_LONG == 64
+	hash = hash * GOLDEN_RATIO_64;
 #else
 	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
 	u64 n = hash;
diff --git a/include/linux/i8042.h b/include/linux/i8042.h
index 0f9bafa17a02..d98780ca9604 100644
--- a/include/linux/i8042.h
+++ b/include/linux/i8042.h
@@ -62,7 +62,6 @@ struct serio;
 void i8042_lock_chip(void);
 void i8042_unlock_chip(void);
 int i8042_command(unsigned char *param, int command);
-bool i8042_check_port_owner(const struct serio *);
 int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
 					struct serio *serio));
 int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
@@ -83,11 +82,6 @@ static inline int i8042_command(unsigned char *param, int command)
 	return -ENODEV;
 }
 
-static inline bool i8042_check_port_owner(const struct serio *serio)
-{
-	return false;
-}
-
 static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
 					struct serio *serio))
 {
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index a338a688ee4a..dcb89e3515db 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -46,10 +46,6 @@ struct br_ip_list {
 #define BR_LEARNING_SYNC	BIT(9)
 #define BR_PROXYARP_WIFI	BIT(10)
 
-/* values as per ieee8021QBridgeFdbAgingTime */
-#define BR_MIN_AGEING_TIME	(10 * HZ)
-#define BR_MAX_AGEING_TIME	(1000000 * HZ)
-
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 67ce5bd3b56a..19db03dbbd00 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -616,15 +616,16 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
 						    netdev_features_t features)
 {
-	if (skb_vlan_tagged_multi(skb))
-		features = netdev_intersect_features(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);
-
+	if (skb_vlan_tagged_multi(skb)) {
+		/* In the case of multi-tagged packets, use a direct mask
+		 * instead of using netdev_interesect_features(), to make
+		 * sure that only devices supporting NETIF_F_HW_CSUM will
+		 * have checksum offloading support.
+		 */
+		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+			    NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
+			    NETIF_F_HW_VLAN_STAG_TX;
+	}
 	return features;
 }
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2d9b650047a5..23e129ef6726 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -153,8 +153,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
 #define DMA_TLB_DSI_FLUSH (((u64)2) << 60)
 #define DMA_TLB_PSI_FLUSH (((u64)3) << 60)
-#define DMA_TLB_IIRG(type) ((type >> 60) & 7)
-#define DMA_TLB_IAIG(val) (((val) >> 57) & 7)
+#define DMA_TLB_IIRG(type) ((type >> 60) & 3)
+#define DMA_TLB_IAIG(val) (((val) >> 57) & 3)
 #define DMA_TLB_READ_DRAIN (((u64)1) << 49)
 #define DMA_TLB_WRITE_DRAIN (((u64)1) << 48)
 #define DMA_TLB_DID(id)	(((u64)((id) & 0xffff)) << 32)
@@ -164,9 +164,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 
 /* INVALID_DESC */
 #define DMA_CCMD_INVL_GRANU_OFFSET  61
-#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 3)
-#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 3)
-#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 3)
+#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 4)
+#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 4)
+#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 4)
 #define DMA_ID_TLB_READ_DRAIN	(((u64)1) << 7)
 #define DMA_ID_TLB_WRITE_DRAIN	(((u64)1) << 6)
 #define DMA_ID_TLB_DID(id)	(((u64)((id & 0xffff) << 16)))
@@ -316,8 +316,8 @@ enum {
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
 #define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
 #define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
-#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 32)
-#define QI_DEV_EIOTLB_QDEP(qd)	(((qd) & 0x1f) << 16)
+#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
+#define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_MAX_INVS	32
 
 #define QI_PGRP_IDX(idx)	(((u64)(idx)) << 55)
@@ -429,6 +429,7 @@ struct intel_iommu {
 	struct page_req_dsc *prq;
 	unsigned char prq_name[16];    /* Name for PRQ interrupt */
 	struct idr pasid_idr;
+	u32 pasid_max;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 *iommu_state; /* Store iommu states between suspend and resume.*/
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3c1c96786248..f7cade00c525 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -916,6 +916,16 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
 static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
 #endif
 
+/*
+ * The irqsave variants are for usage in non interrupt code. Do not use
+ * them in irq_chip callbacks. Use irq_gc_lock() instead.
+ */
+#define irq_gc_lock_irqsave(gc, flags)	\
+	raw_spin_lock_irqsave(&(gc)->lock, flags)
+
+#define irq_gc_unlock_irqrestore(gc, flags)	\
+	raw_spin_unlock_irqrestore(&(gc)->lock, flags)
+
 static inline void irq_reg_writel(struct irq_chip_generic *gc,
 				  u32 val, int reg_offset)
 {
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index d5d798b35c1f..54048f336a1f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -218,7 +218,7 @@
 #define GITS_BASER_TYPE_SHIFT		(56)
 #define GITS_BASER_TYPE(r)		(((r) >> GITS_BASER_TYPE_SHIFT) & 7)
 #define GITS_BASER_ENTRY_SIZE_SHIFT	(48)
-#define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
+#define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
 #define GITS_BASER_NonShareable		(0UL << 10)
 #define GITS_BASER_InnerShareable	(1UL << 10)
 #define GITS_BASER_OuterShareable	(2UL << 10)
@@ -301,7 +301,7 @@
 #define ICC_SGI1R_AFFINITY_1_SHIFT	16
 #define ICC_SGI1R_AFFINITY_1_MASK	(0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
 #define ICC_SGI1R_SGI_ID_SHIFT		24
-#define ICC_SGI1R_SGI_ID_MASK		(0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_SGI_ID_MASK		(0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
 #define ICC_SGI1R_AFFINITY_2_SHIFT	32
 #define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
 #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT	40
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 0536524bb9eb..68904469fba1 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -117,13 +117,18 @@ struct module;
 
 #include <linux/atomic.h>
 
+#ifdef HAVE_JUMP_LABEL
+
 static inline int static_key_count(struct static_key *key)
 {
-	return atomic_read(&key->enabled);
+	/*
+	 * -1 means the first static_key_slow_inc() is in progress.
+	 *  static_key_enabled() must return true, so return 1 here.
+	 */
+	int n = atomic_read(&key->enabled);
+	return n >= 0 ? n : 1;
 }
 
-#ifdef HAVE_JUMP_LABEL
-
 #define JUMP_TYPE_FALSE	0UL
 #define JUMP_TYPE_TRUE	1UL
 #define JUMP_TYPE_MASK	1UL
@@ -162,6 +167,11 @@ extern void jump_label_apply_nops(struct module *mod);
 
 #else  /* !HAVE_JUMP_LABEL */
 
+static inline int static_key_count(struct static_key *key)
+{
+	return atomic_read(&key->enabled);
+}
+
 static __always_inline void jump_label_init(void)
 {
 	static_key_initialized = true;
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index 089f70f83e97..23da3af459fe 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -14,6 +14,7 @@ struct static_key_deferred {
 
 #ifdef HAVE_JUMP_LABEL
 extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
+extern void static_key_deferred_flush(struct static_key_deferred *key);
 extern void
 jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
 
@@ -26,6 +27,10 @@ static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 	STATIC_KEY_CHECK_USE();
 	static_key_slow_dec(&key->key);
 }
+static inline void static_key_deferred_flush(struct static_key_deferred *key)
+{
+	STATIC_KEY_CHECK_USE();
+}
 static inline void
 jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 350dfb08aee3..50220cab738c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -202,26 +202,26 @@ extern int _cond_resched(void);
 
 /**
  * abs - return absolute value of an argument
- * @x: the value.  If it is unsigned type, it is converted to signed type first
- *   (s64, long or int depending on its size).
+ * @x: the value.  If it is unsigned type, it is converted to signed type first.
+ *     char is treated as if it was signed (regardless of whether it really is)
+ *     but the macro's return type is preserved as char.
  *
- * Return: an absolute value of x.  If x is 64-bit, macro's return type is s64,
- *   otherwise it is signed long.
+ * Return: an absolute value of x.
  */
-#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({	\
-		s64 __x = (x);						\
-		(__x < 0) ? -__x : __x;					\
-	}), ({								\
-		long ret;						\
-		if (sizeof(x) == sizeof(long)) {			\
-			long __x = (x);					\
-			ret = (__x < 0) ? -__x : __x;			\
-		} else {						\
-			int __x = (x);					\
-			ret = (__x < 0) ? -__x : __x;			\
-		}							\
-		ret;							\
-	}))
+#define abs(x)	__abs_choose_expr(x, long long,				\
+		__abs_choose_expr(x, long,				\
+		__abs_choose_expr(x, int,				\
+		__abs_choose_expr(x, short,				\
+		__abs_choose_expr(x, char,				\
+		__builtin_choose_expr(					\
+			__builtin_types_compatible_p(typeof(x), char),	\
+			(char)({ signed char __x = (x); __x<0?-__x:__x; }), \
+			((void)0)))))))
+
+#define __abs_choose_expr(x, type, other) __builtin_choose_expr(	\
+	__builtin_types_compatible_p(typeof(x),   signed type) ||	\
+	__builtin_types_compatible_p(typeof(x), unsigned type),		\
+	({ signed type __x = (x); __x < 0 ? -__x : __x; }), other)
 
 /**
  * reciprocal_scale - "scale" a value into range [0, ep_ro)
@@ -356,6 +356,7 @@ int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
 int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
 int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
 int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
+int __must_check kstrtobool(const char *s, bool *res);
 
 int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
 int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
@@ -367,6 +368,7 @@ int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigne
 int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
 int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
 int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
+int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res);
 
 static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
 {
@@ -607,7 +609,7 @@ do {							\
 
 #define do_trace_printk(fmt, args...)					\
 do {									\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(fmt) ? fmt : NULL;			\
 									\
@@ -651,7 +653,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...);
  */
 
 #define trace_puts(str) ({						\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(str) ? str : NULL;			\
 									\
@@ -673,7 +675,7 @@ extern void trace_dump_stack(int skip);
 #define ftrace_vprintk(fmt, vargs)					\
 do {									\
 	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
+		static const char *trace_printk_fmt __used		\
 		  __attribute__((section("__trace_printk_fmt"))) =	\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 8f6849084248..e23392517db9 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -330,7 +330,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table,
 					     int write, void __user *buffer,
 					     size_t *length, loff_t *ppos);
 #endif
-
+extern void wait_for_kprobe_optimizer(void);
+#else
+static inline void wait_for_kprobe_optimizer(void) { }
 #endif /* CONFIG_OPTPROBES */
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c923350ca20a..d7ce4e3280db 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -182,8 +182,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val);
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev);
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			      struct kvm_io_device *dev);
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			       struct kvm_io_device *dev);
 
 #ifdef CONFIG_KVM_ASYNC_PF
 struct kvm_async_pf {
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 3f021dc5da8c..30201b9be7bc 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -83,6 +83,8 @@ struct nd_cmd_desc {
 
 struct nd_interleave_set {
 	u64 cookie;
+	/* compatibility with initial buggy Linux implementation */
+	u64 altcookie;
 };
 
 struct nd_region_desc {
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 034117b3be5f..4bc4b1b13193 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -1,6 +1,8 @@
 #ifndef NVM_H
 #define NVM_H
 
+#include <linux/types.h>
+
 enum {
 	NVM_IO_OK = 0,
 	NVM_IO_REQUEUE = 1,
@@ -11,10 +13,71 @@ enum {
 	NVM_IOTYPE_GC = 1,
 };
 
+#define NVM_BLK_BITS (16)
+#define NVM_PG_BITS  (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS  (8)
+#define NVM_LUN_BITS (8)
+#define NVM_CH_BITS  (8)
+
+struct ppa_addr {
+	/* Generic structure for all addresses */
+	union {
+		struct {
+			u64 blk		: NVM_BLK_BITS;
+			u64 pg		: NVM_PG_BITS;
+			u64 sec		: NVM_SEC_BITS;
+			u64 pl		: NVM_PL_BITS;
+			u64 lun		: NVM_LUN_BITS;
+			u64 ch		: NVM_CH_BITS;
+		} g;
+
+		u64 ppa;
+	};
+};
+
+struct nvm_rq;
+struct nvm_id;
+struct nvm_dev;
+
+typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
+typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
+typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
+				nvm_l2p_update_fn *, void *);
+typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
+				nvm_bb_update_fn *, void *);
+typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
+typedef void (nvm_destroy_dma_pool_fn)(void *);
+typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
+								dma_addr_t *);
+typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
+
+struct nvm_dev_ops {
+	nvm_id_fn		*identity;
+	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
+	nvm_op_bb_tbl_fn	*get_bb_tbl;
+	nvm_op_set_bb_fn	*set_bb_tbl;
+
+	nvm_submit_io_fn	*submit_io;
+	nvm_erase_blk_fn	*erase_block;
+
+	nvm_create_dma_pool_fn	*create_dma_pool;
+	nvm_destroy_dma_pool_fn	*destroy_dma_pool;
+	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
+	nvm_dev_dma_free_fn	*dev_dma_free;
+
+	unsigned int		max_phys_sect;
+};
+
+
+
 #ifdef CONFIG_NVM
 
 #include <linux/blkdev.h>
-#include <linux/types.h>
 #include <linux/file.h>
 #include <linux/dmapool.h>
 
@@ -58,8 +121,9 @@ enum {
 	/* Block Types */
 	NVM_BLK_T_FREE		= 0x0,
 	NVM_BLK_T_BAD		= 0x1,
-	NVM_BLK_T_DEV		= 0x2,
-	NVM_BLK_T_HOST		= 0x4,
+	NVM_BLK_T_GRWN_BAD	= 0x2,
+	NVM_BLK_T_DEV		= 0x4,
+	NVM_BLK_T_HOST		= 0x8,
 };
 
 struct nvm_id_group {
@@ -125,29 +189,6 @@ struct nvm_tgt_instance {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
-#define NVM_BLK_BITS (16)
-#define NVM_PG_BITS  (16)
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (8)
-#define NVM_LUN_BITS (8)
-#define NVM_CH_BITS  (8)
-
-struct ppa_addr {
-	/* Generic structure for all addresses */
-	union {
-		struct {
-			u64 blk		: NVM_BLK_BITS;
-			u64 pg		: NVM_PG_BITS;
-			u64 sec		: NVM_SEC_BITS;
-			u64 pl		: NVM_PL_BITS;
-			u64 lun		: NVM_LUN_BITS;
-			u64 ch		: NVM_CH_BITS;
-		} g;
-
-		u64 ppa;
-	};
-};
-
 struct nvm_rq {
 	struct nvm_tgt_instance *ins;
 	struct nvm_dev *dev;
@@ -181,39 +222,6 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 
 struct nvm_block;
 
-typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
-typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
-				nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
-				nvm_bb_update_fn *, void *);
-typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
-typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
-typedef void (nvm_destroy_dma_pool_fn)(void *);
-typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
-								dma_addr_t *);
-typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
-
-struct nvm_dev_ops {
-	nvm_id_fn		*identity;
-	nvm_get_l2p_tbl_fn	*get_l2p_tbl;
-	nvm_op_bb_tbl_fn	*get_bb_tbl;
-	nvm_op_set_bb_fn	*set_bb_tbl;
-
-	nvm_submit_io_fn	*submit_io;
-	nvm_erase_blk_fn	*erase_block;
-
-	nvm_create_dma_pool_fn	*create_dma_pool;
-	nvm_destroy_dma_pool_fn	*destroy_dma_pool;
-	nvm_dev_dma_alloc_fn	*dev_dma_alloc;
-	nvm_dev_dma_free_fn	*dev_dma_free;
-
-	unsigned int		max_phys_sect;
-};
-
 struct nvm_lun {
 	int id;
 
@@ -302,6 +310,7 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
 {
 	struct ppa_addr l;
 
+	l.ppa = 0;
 	/*
 	 * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
 	 */
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 2a6b9947aaa3..743b34f56f2b 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -44,6 +44,7 @@ struct list_lru_node {
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	*memcg_lrus;
 #endif
+	long nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index c15373894a42..b37dee3acaba 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -355,7 +355,8 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
 static inline int nlm_compare_locks(const struct file_lock *fl1,
 				    const struct file_lock *fl2)
 {
-	return	fl1->fl_pid   == fl2->fl_pid
+	return file_inode(fl1->fl_file) == file_inode(fl2->fl_file)
+	     && fl1->fl_pid   == fl2->fl_pid
 	     && fl1->fl_owner == fl2->fl_owner
 	     && fl1->fl_start == fl2->fl_start
 	     && fl1->fl_end   == fl2->fl_end
diff --git a/include/linux/log2.h b/include/linux/log2.h
index fd7ff3d91e6a..c373295f359f 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -16,12 +16,6 @@
 #include <linux/bitops.h>
 
 /*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
  *   more efficiently than using fls() and fls64()
@@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\
@@ -203,6 +194,17 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
  *  ... and so on.
  */
 
-#define order_base_2(n) ilog2(roundup_pow_of_two(n))
+static inline __attribute_const__
+int __order_base_2(unsigned long n)
+{
+	return n > 1 ? ilog2(n - 1) + 1 : 0;
+}
 
+#define order_base_2(n)				\
+(						\
+	__builtin_constant_p(n) ? (		\
+		((n) == 0 || (n) == 1) ? 0 :	\
+		ilog2((n) - 1) + 1) :		\
+	__order_base_2(n)			\
+)
 #endif /* _LINUX_LOG2_H */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 24daf8fc4d7c..76b502c6258f 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -408,12 +408,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end)
 }
 #endif
 
+extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+		phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
 	return 0;
 }
 
+static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
+		phys_addr_t end_addr)
+{
+	return 0;
+}
+
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index cd0e2413c358..435fd8426b8a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -174,6 +174,11 @@ struct mem_cgroup_thresholds {
 	struct mem_cgroup_threshold_ary *spare;
 };
 
+struct mem_cgroup_id {
+	int id;
+	atomic_t ref;
+};
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -183,6 +188,9 @@ struct mem_cgroup_thresholds {
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
 
+	/* Private memcg ID. Used to ID objects that outlive the cgroup */
+	struct mem_cgroup_id id;
+
 	/* Accounted resources */
 	struct page_counter memory;
 	struct page_counter memsw;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 2ea574ff9714..538488bd1d3d 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
 extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long, unsigned long);
+extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+	unsigned long *valid_start, unsigned long *valid_end);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h
index d409ceb2231e..c118a7ec94d6 100644
--- a/include/linux/mfd/88pm80x.h
+++ b/include/linux/mfd/88pm80x.h
@@ -350,7 +350,7 @@ static inline int pm80x_dev_suspend(struct device *dev)
 	int irq = platform_get_irq(pdev, 0);
 
 	if (device_may_wakeup(dev))
-		set_bit((1 << irq), &chip->wu_flag);
+		set_bit(irq, &chip->wu_flag);
 
 	return 0;
 }
@@ -362,7 +362,7 @@ static inline int pm80x_dev_resume(struct device *dev)
 	int irq = platform_get_irq(pdev, 0);
 
 	if (device_may_wakeup(dev))
-		clear_bit((1 << irq), &chip->wu_flag);
+		clear_bit(irq, &chip->wu_flag);
 
 	return 0;
 }
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 494682ce4bf3..3ab3cede28ea 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -224,6 +224,21 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
 		     struct cros_ec_command *msg);
 
 /**
+ * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC
+ *
+ * This function is identical to cros_ec_cmd_xfer, except it returns success
+ * status only if both the command was transmitted successfully and the EC
+ * replied with success status. It's not necessary to check msg->result when
+ * using this function.
+ *
+ * @ec_dev: EC device
+ * @msg: Message to write
+ * @return: Num. of bytes transferred on success, <0 on failure
+ */
+int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
+			    struct cros_ec_command *msg);
+
+/**
  * cros_ec_remove - Remove a ChromeOS EC
  *
  * Call this to deregister a ChromeOS EC, then clean up any private data.
diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h
index b288965e8101..2c14eeca46f0 100644
--- a/include/linux/mfd/samsung/s2mps11.h
+++ b/include/linux/mfd/samsung/s2mps11.h
@@ -173,10 +173,12 @@ enum s2mps11_regulators {
 
 #define S2MPS11_LDO_VSEL_MASK	0x3F
 #define S2MPS11_BUCK_VSEL_MASK	0xFF
+#define S2MPS11_BUCK9_VSEL_MASK	0x1F
 #define S2MPS11_ENABLE_MASK	(0x03 << S2MPS11_ENABLE_SHIFT)
 #define S2MPS11_ENABLE_SHIFT	0x06
 #define S2MPS11_LDO_N_VOLTAGES	(S2MPS11_LDO_VSEL_MASK + 1)
 #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1)
+#define S2MPS11_BUCK9_N_VOLTAGES (S2MPS11_BUCK9_VSEL_MASK + 1)
 #define S2MPS11_RAMP_DELAY	25000		/* uV/us */
 
 #define S2MPS11_CTRL1_PWRHOLD_MASK	BIT(4)
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index 1fd50dcfe47c..175c82699e9d 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -138,16 +138,16 @@
 /*
  * time in us for processing a single channel, calculated as follows:
  *
- * num cycles = open delay + (sample delay + conv time) * averaging
+ * max num cycles = open delay + (sample delay + conv time) * averaging
  *
- * num cycles: 152 + (1 + 13) * 16 = 376
+ * max num cycles: 262143 + (255 + 13) * 16 = 266431
  *
  * clock frequency: 26MHz / 8 = 3.25MHz
  * clock period: 1 / 3.25MHz = 308ns
  *
- * processing time: 376 * 308ns = 116us
+ * max processing time: 266431 * 308ns = 83ms(approx)
  */
-#define IDLE_TIMEOUT 116 /* microsec */
+#define IDLE_TIMEOUT 83 /* milliseconds */
 
 #define TSCADC_CELLS		2
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0b473cbfa7ef..a91b67b18a73 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -334,6 +334,17 @@ enum {
 	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
 };
 
+enum {
+	/*
+	 * Max wqe size for rdma read is 512 bytes, so this
+	 * limits our max_sge_rd as the wqe needs to fit:
+	 * - ctrl segment (16 bytes)
+	 * - rdma segment (16 bytes)
+	 * - scatter elements (16 bytes each)
+	 */
+	MLX5_MAX_SGE_RD	= (512 - 16 - 16) / 16
+};
+
 struct mlx5_inbox_hdr {
 	__be16		opcode;
 	u8		rsvd[4];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af3efd9157f0..412aa988c6ad 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -792,9 +792,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
 
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index f079fb1a31f7..a8786d27ab81 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -160,6 +160,7 @@ enum {
 enum {
 	MLX5_FENCE_MODE_NONE			= 0 << 5,
 	MLX5_FENCE_MODE_INITIATOR_SMALL		= 1 << 5,
+	MLX5_FENCE_MODE_FENCE			= 2 << 5,
 	MLX5_FENCE_MODE_STRONG_ORDERING		= 3 << 5,
 	MLX5_FENCE_MODE_SMALL_AND_FENCE		= 4 << 5,
 };
@@ -534,9 +535,9 @@ struct mlx5_destroy_qp_mbox_out {
 struct mlx5_modify_qp_mbox_in {
 	struct mlx5_inbox_hdr	hdr;
 	__be32			qpn;
-	u8			rsvd1[4];
-	__be32			optparam;
 	u8			rsvd0[4];
+	__be32			optparam;
+	u8			rsvd1[4];
 	struct mlx5_qp_context	ctx;
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 00bad7793788..55f950afb60d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1084,6 +1084,8 @@ struct zap_details {
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		pte_t pte);
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd);
 
 int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size);
@@ -1276,41 +1278,12 @@ int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
-/* Is the vma a continuation of the stack vma above it? */
-static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
-{
-	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
-}
-
 static inline bool vma_is_anonymous(struct vm_area_struct *vma)
 {
 	return !vma->vm_ops;
 }
 
-static inline int stack_guard_page_start(struct vm_area_struct *vma,
-					     unsigned long addr)
-{
-	return (vma->vm_flags & VM_GROWSDOWN) &&
-		(vma->vm_start == addr) &&
-		!vma_growsdown(vma->vm_prev, addr);
-}
-
-/* Is the vma a continuation of the stack vma below it? */
-static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
-{
-	return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
-}
-
-static inline int stack_guard_page_end(struct vm_area_struct *vma,
-					   unsigned long addr)
-{
-	return (vma->vm_flags & VM_GROWSUP) &&
-		(vma->vm_end == addr) &&
-		!vma_growsup(vma->vm_next, addr);
-}
-
-extern struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group);
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
@@ -1694,7 +1667,7 @@ extern void free_highmem_page(struct page *page);
 extern void adjust_managed_page_count(struct page *page, long count);
 extern void mem_init_print_info(const char *str);
 
-extern void reserve_bootmem_region(unsigned long start, unsigned long end);
+extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void __free_reserved_page(struct page *page)
@@ -1897,6 +1870,7 @@ extern void mm_drop_all_locks(struct mm_struct *mm);
 
 extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
+extern struct file *get_task_exe_file(struct task_struct *task);
 
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
 extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
@@ -2010,6 +1984,7 @@ void page_cache_async_readahead(struct address_space *mapping,
 				pgoff_t offset,
 				unsigned long size);
 
+extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
@@ -2038,6 +2013,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
 	return vma;
 }
 
+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+{
+	unsigned long vm_start = vma->vm_start;
+
+	if (vma->vm_flags & VM_GROWSDOWN) {
+		vm_start -= stack_guard_gap;
+		if (vm_start > vma->vm_start)
+			vm_start = 0;
+	}
+	return vm_start;
+}
+
+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+{
+	unsigned long vm_end = vma->vm_end;
+
+	if (vma->vm_flags & VM_GROWSUP) {
+		vm_end += stack_guard_gap;
+		if (vm_end < vma->vm_end)
+			vm_end = -PAGE_SIZE;
+	}
+	return vm_end;
+}
+
 static inline unsigned long vma_pages(struct vm_area_struct *vma)
 {
 	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
@@ -2110,6 +2109,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_MLOCK	0x1000	/* lock present pages */
+#define FOLL_COW	0x4000	/* internal GUP flag */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f8d1492a114f..36f4695aa604 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -469,6 +469,7 @@ struct mm_struct {
 	 */
 	struct task_struct __rcu *owner;
 #endif
+	struct user_namespace *user_ns;
 
 	/* store ref to file /proc/<pid>/exe symlink points to */
 	struct file __rcu *exe_file;
@@ -503,6 +504,10 @@ struct mm_struct {
 	 */
 	bool tlb_flush_pending;
 #endif
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	/* See flush_tlb_batched_pending() */
+	bool tlb_flush_batched;
+#endif
 	struct uprobes_state uprobes_state;
 #ifdef CONFIG_X86_INTEL_MPX
 	/* address of the bounds directory */
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index f67b2ec18e6d..7776afb0ffa5 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -172,7 +172,7 @@ struct dw_mci {
 	/* For edmac */
 	struct dw_mci_dma_slave *dms;
 	/* Registers's physical base address */
-	void                    *phy_regs;
+	resource_size_t		phy_regs;
 
 	u32			cmd_status;
 	u32			data_status;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e23a9e704536..5b609a3ce3d7 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -688,6 +688,7 @@ typedef struct pglist_data {
 	 * is the first PFN that needs to be initialised.
 	 */
 	unsigned long first_deferred_pfn;
+	unsigned long static_init_size;
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 } pg_data_t;
 
diff --git a/include/linux/mount.h b/include/linux/mount.h
index f822c3c11377..dc6cd800cd5d 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -95,4 +95,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts);
 
 extern dev_t name_to_dev_t(const char *name);
 
+extern unsigned int sysctl_mount_max;
+
 #endif /* _LINUX_MOUNT_H */
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 79aaa9fc1a15..d5277fc3ce2e 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -103,5 +103,5 @@ struct mfc_cache {
 struct rtmsg;
 extern int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			  __be32 saddr, __be32 daddr,
-			  struct rtmsg *rtm, int nowait);
+			  struct rtmsg *rtm, int nowait, u32 portid);
 #endif
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index 66982e764051..f831155dc7d1 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -115,7 +115,7 @@ struct mfc6_cache {
 
 struct rtmsg;
 extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
-			   struct rtmsg *rtm, int nowait);
+			   struct rtmsg *rtm, int nowait, u32 portid);
 
 #ifdef CONFIG_IPV6_MROUTE
 extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index f71a25e5fd25..f0f43ec45ee7 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -254,12 +254,12 @@ enum {
 	 * callbacks.
 	 */
 	MSI_FLAG_USE_DEF_CHIP_OPS	= (1 << 1),
-	/* Build identity map between hwirq and irq */
-	MSI_FLAG_IDENTITY_MAP		= (1 << 2),
 	/* Support multiple PCI MSI interrupts */
-	MSI_FLAG_MULTI_PCI_MSI		= (1 << 3),
+	MSI_FLAG_MULTI_PCI_MSI		= (1 << 2),
 	/* Support PCI MSIX interrupts */
-	MSI_FLAG_PCI_MSIX		= (1 << 4),
+	MSI_FLAG_PCI_MSIX		= (1 << 3),
+	/* Needs early activate, required for PCI */
+	MSI_FLAG_ACTIVATE_EARLY		= (1 << 4),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 366cf77953b5..806d0ab845e0 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -122,18 +122,13 @@
 #endif
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_32
-# ifdef map_bankwidth
-#  undef map_bankwidth
-#  define map_bankwidth(map) ((map)->bankwidth)
-#  undef map_bankwidth_is_large
-#  define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8)
-#  undef map_words
-#  define map_words(map) map_calc_words(map)
-# else
-#  define map_bankwidth(map) 32
-#  define map_bankwidth_is_large(map) (1)
-#  define map_words(map) map_calc_words(map)
-# endif
+/* always use indirect access for 256-bit to preserve kernel stack */
+# undef map_bankwidth
+# define map_bankwidth(map) ((map)->bankwidth)
+# undef map_bankwidth_is_large
+# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8)
+# undef map_words
+# define map_words(map) map_calc_words(map)
 #define map_bankwidth_is_32(map) (map_bankwidth(map) == 32)
 #undef MAX_MAP_BANKWIDTH
 #define MAX_MAP_BANKWIDTH 32
diff --git a/include/linux/net.h b/include/linux/net.h
index 0b4ac7da583a..c00b8d182226 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -245,7 +245,16 @@ do {								\
 	net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG)
+#define net_dbg_ratelimited(fmt, ...)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
+	    net_ratelimit())						\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt),		\
+		                   ##__VA_ARGS__);			\
+} while (0)
+#elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
 #else
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3143c847bddb..4035bbe40971 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -265,6 +265,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -510,7 +511,6 @@ static inline void napi_enable(struct napi_struct *n)
 	clear_bit(NAPI_STATE_NPSVC, &n->state);
 }
 
-#ifdef CONFIG_SMP
 /**
  *	napi_synchronize - wait until NAPI is not running
  *	@n: napi context
@@ -521,12 +521,12 @@ static inline void napi_enable(struct napi_struct *n)
  */
 static inline void napi_synchronize(const struct napi_struct *n)
 {
-	while (test_bit(NAPI_STATE_SCHED, &n->state))
-		msleep(1);
+	if (IS_ENABLED(CONFIG_SMP))
+		while (test_bit(NAPI_STATE_SCHED, &n->state))
+			msleep(1);
+	else
+		barrier();
 }
-#else
-# define napi_synchronize(n)	barrier()
-#endif
 
 enum netdev_queue_state_t {
 	__QUEUE_STATE_DRV_XOFF,
@@ -1398,8 +1398,8 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length, which means that this is the
- *			  minimum size of a packet.
+ *	@hard_header_len: Maximum hardware header length.
+ *	@min_header_len:  Minimum hardware header length
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1620,6 +1620,7 @@ struct net_device {
 	unsigned int		mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
+	unsigned short		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -1987,8 +1988,8 @@ struct napi_gro_cb {
 	/* This is non-zero if the packet may be of the same flow. */
 	u8	same_flow:1;
 
-	/* Used in udp_gro_receive */
-	u8	udp_mark:1;
+	/* Used in tunnel GRO receive */
+	u8	encap_mark:1;
 
 	/* GRO checksum is valid */
 	u8	csum_valid:1;
@@ -2004,7 +2005,10 @@ struct napi_gro_cb {
 	/* Used in foo-over-udp, set in udp[46]_gro_receive */
 	u8	is_ipv6:1;
 
-	/* 7 bit hole */
+	/* Number of gro_receive callbacks this packet already went through */
+	u8 recursion_counter:4;
+
+	/* 3 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2015,6 +2019,25 @@ struct napi_gro_cb {
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
 
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+						struct sk_buff **head,
+						struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	struct net_device	*dev;	/* NULL is wildcarded here	     */
@@ -2060,6 +2083,22 @@ struct udp_offload {
 	struct udp_offload_callbacks callbacks;
 };
 
+typedef struct sk_buff **(*gro_receive_udp_t)(struct sk_buff **,
+					      struct sk_buff *,
+					      struct udp_offload *);
+static inline struct sk_buff **call_gro_receive_udp(gro_receive_udp_t cb,
+						    struct sk_buff **head,
+						    struct sk_buff *skb,
+						    struct udp_offload *uoff)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb, uoff);
+}
+
 /* often modified stats are per cpu, other are shared (netdev->stats) */
 struct pcpu_sw_netstats {
 	u64     rx_packets;
@@ -2288,14 +2327,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
 	return NAPI_GRO_CB(skb)->frag0_len < hlen;
 }
 
+static inline void skb_gro_frag0_invalidate(struct sk_buff *skb)
+{
+	NAPI_GRO_CB(skb)->frag0 = NULL;
+	NAPI_GRO_CB(skb)->frag0_len = 0;
+}
+
 static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
 					unsigned int offset)
 {
 	if (!pskb_may_pull(skb, hlen))
 		return NULL;
 
-	NAPI_GRO_CB(skb)->frag0 = NULL;
-	NAPI_GRO_CB(skb)->frag0_len = 0;
+	skb_gro_frag0_invalidate(skb);
 	return skb->data + offset;
 }
 
@@ -2493,6 +2537,26 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+	if (len < dev->min_header_len)
+		return false;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
@@ -3019,6 +3083,7 @@ static inline void napi_free_frags(struct napi_struct *napi)
 	napi->skb = NULL;
 }
 
+bool netdev_is_rx_handler_busy(struct net_device *dev);
 int netdev_rx_handler_register(struct net_device *dev,
 			       rx_handler_func_t *rx_handler,
 			       void *rx_handler_data);
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index c5577410c25d..04078e8a4803 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -239,11 +239,18 @@ void xt_unregister_match(struct xt_match *target);
 int xt_register_matches(struct xt_match *match, unsigned int n);
 void xt_unregister_matches(struct xt_match *match, unsigned int n);
 
+int xt_check_entry_offsets(const void *base, const char *elems,
+			   unsigned int target_offset,
+			   unsigned int next_offset);
+
 int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
 		   bool inv_proto);
 int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
 		    bool inv_proto);
 
+void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
+				 struct xt_counters_info *info, bool compat);
+
 struct xt_table *xt_register_table(struct net *net,
 				   const struct xt_table *table,
 				   struct xt_table_info *bootstrap,
@@ -478,7 +485,7 @@ void xt_compat_init_offsets(u_int8_t af, unsigned int number);
 int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
 
 int xt_compat_match_offset(const struct xt_match *match);
-int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 			      unsigned int *size);
 int xt_compat_match_to_user(const struct xt_entry_match *m,
 			    void __user **dstptr, unsigned int *size);
@@ -488,6 +495,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 				unsigned int *size);
 int xt_compat_target_to_user(const struct xt_entry_target *t,
 			     void __user **dstptr, unsigned int *size);
+int xt_compat_check_entry_offsets(const void *base, const char *elems,
+				  unsigned int target_offset,
+				  unsigned int next_offset);
 
 #endif /* CONFIG_COMPAT */
 #endif /* _X_TABLES_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e7e78537aea2..63a817631f06 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -266,7 +266,7 @@ enum nfsstat4 {
 
 static inline bool seqid_mutating_err(u32 err)
 {
-	/* rfc 3530 section 8.1.5: */
+	/* See RFC 7530, section 9.1.7 */
 	switch (err) {
 	case NFS4ERR_STALE_CLIENTID:
 	case NFS4ERR_STALE_STATEID:
@@ -275,6 +275,7 @@ static inline bool seqid_mutating_err(u32 err)
 	case NFS4ERR_BADXDR:
 	case NFS4ERR_RESOURCE:
 	case NFS4ERR_NOFILEHANDLE:
+	case NFS4ERR_MOVED:
 		return false;
 	};
 	return true;
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 9bb77d3ed6e0..c2256d746543 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -74,7 +74,7 @@ static inline void nvmem_cell_put(struct nvmem_cell *cell)
 {
 }
 
-static inline char *nvmem_cell_read(struct nvmem_cell *cell, size_t *len)
+static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 26eabf5ec718..fbfadba81c5a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -601,56 +601,56 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size)
  */
 static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
 {
-	int ret = 0;
 	char __user *end = uaddr + size - 1;
 
 	if (unlikely(size == 0))
-		return ret;
+		return 0;
 
+	if (unlikely(uaddr > end))
+		return -EFAULT;
 	/*
 	 * Writing zeroes into userspace here is OK, because we know that if
 	 * the zero gets there, we'll be overwriting it.
 	 */
-	while (uaddr <= end) {
-		ret = __put_user(0, uaddr);
-		if (ret != 0)
-			return ret;
+	do {
+		if (unlikely(__put_user(0, uaddr) != 0))
+			return -EFAULT;
 		uaddr += PAGE_SIZE;
-	}
+	} while (uaddr <= end);
 
 	/* Check whether the range spilled into the next page. */
 	if (((unsigned long)uaddr & PAGE_MASK) ==
 			((unsigned long)end & PAGE_MASK))
-		ret = __put_user(0, end);
+		return __put_user(0, end);
 
-	return ret;
+	return 0;
 }
 
 static inline int fault_in_multipages_readable(const char __user *uaddr,
 					       int size)
 {
 	volatile char c;
-	int ret = 0;
 	const char __user *end = uaddr + size - 1;
 
 	if (unlikely(size == 0))
-		return ret;
+		return 0;
 
-	while (uaddr <= end) {
-		ret = __get_user(c, uaddr);
-		if (ret != 0)
-			return ret;
+	if (unlikely(uaddr > end))
+		return -EFAULT;
+
+	do {
+		if (unlikely(__get_user(c, uaddr) != 0))
+			return -EFAULT;
 		uaddr += PAGE_SIZE;
-	}
+	} while (uaddr <= end);
 
 	/* Check whether the range spilled into the next page. */
 	if (((unsigned long)uaddr & PAGE_MASK) ==
 			((unsigned long)end & PAGE_MASK)) {
-		ret = __get_user(c, end);
-		(void)c;
+		return __get_user(c, end);
 	}
 
-	return ret;
+	return 0;
 }
 
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6ae25aae88fd..5f37614f2451 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -359,6 +359,7 @@ struct pci_dev {
 	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
 	unsigned int	irq_managed:1;
 	unsigned int	has_secondary_link:1;
+	unsigned int	non_compliant_bars:1;	/* broken BARs; ignore them */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
@@ -988,23 +989,6 @@ static inline int pci_is_managed(struct pci_dev *pdev)
 	return pdev->is_managed;
 }
 
-static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq)
-{
-	pdev->irq = irq;
-	pdev->irq_managed = 1;
-}
-
-static inline void pci_reset_managed_irq(struct pci_dev *pdev)
-{
-	pdev->irq = 0;
-	pdev->irq_managed = 0;
-}
-
-static inline bool pci_has_managed_irq(struct pci_dev *pdev)
-{
-	return pdev->irq_managed && pdev->irq > 0;
-}
-
 void pci_disable_device(struct pci_dev *dev);
 
 extern unsigned int pcibios_max_latency;
@@ -1818,6 +1802,20 @@ static inline int pci_pcie_type(const struct pci_dev *dev)
 	return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4;
 }
 
+static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev)
+{
+	while (1) {
+		if (!pci_is_pcie(dev))
+			break;
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			return dev;
+		if (!dev->bus->self)
+			break;
+		dev = dev->bus->self;
+	}
+	return NULL;
+}
+
 void pci_request_acs(void);
 bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
 bool pci_acs_path_enabled(struct pci_dev *start,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index d9ba49cedc5d..1af616138d1d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -573,6 +573,7 @@
 #define PCI_DEVICE_ID_AMD_CS5536_EHC    0x2095
 #define PCI_DEVICE_ID_AMD_CS5536_UDC    0x2096
 #define PCI_DEVICE_ID_AMD_CS5536_UOC    0x2097
+#define PCI_DEVICE_ID_AMD_CS5536_DEV_IDE    0x2092
 #define PCI_DEVICE_ID_AMD_CS5536_IDE    0x209A
 #define PCI_DEVICE_ID_AMD_LX_VIDEO  0x2081
 #define PCI_DEVICE_ID_AMD_LX_AES    0x2082
@@ -2495,6 +2496,13 @@
 #define PCI_DEVICE_ID_KORENIX_JETCARDF2	0x1700
 #define PCI_DEVICE_ID_KORENIX_JETCARDF3	0x17ff
 
+#define PCI_VENDOR_ID_NETRONOME		0x19ee
+#define PCI_DEVICE_ID_NETRONOME_NFP3200	0x3200
+#define PCI_DEVICE_ID_NETRONOME_NFP3240	0x3240
+#define PCI_DEVICE_ID_NETRONOME_NFP4000	0x4000
+#define PCI_DEVICE_ID_NETRONOME_NFP6000	0x6000
+#define PCI_DEVICE_ID_NETRONOME_NFP6000_VF	0x6003
+
 #define PCI_VENDOR_ID_QMI		0x1a32
 
 #define PCI_VENDOR_ID_AZWAVE		0x1a3b
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 12c9b485beb7..abd7c01c84db 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -206,7 +206,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count;
-	int ret;
+	bool ret;
 
 	rcu_read_lock_sched();
 
@@ -240,7 +240,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count;
-	int ret = false;
+	bool ret = false;
 
 	rcu_read_lock_sched();
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a48f16a..6cdd50f7f52d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -121,6 +121,7 @@ struct hw_perf_event {
 		struct { /* intel_cqm */
 			int			cqm_state;
 			u32			cqm_rmid;
+			int			is_group_event;
 			struct list_head	cqm_events_entry;
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 05fde31b6dc6..b64825d6ad26 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -785,6 +785,10 @@ int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
 int genphy_soft_reset(struct phy_device *phydev);
+static inline int genphy_no_soft_reset(struct phy_device *phydev)
+{
+	return 0;
+}
 void phy_driver_unregister(struct phy_driver *drv);
 void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver);
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 23705a53abba..97b745ddece5 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -8,7 +8,9 @@ enum pid_type
 	PIDTYPE_PID,
 	PIDTYPE_PGID,
 	PIDTYPE_SID,
-	PIDTYPE_MAX
+	PIDTYPE_MAX,
+	/* only valid to __task_pid_nr_ns() */
+	__PIDTYPE_TGID
 };
 
 /*
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index eb8b8ac6df3c..24f5470d3944 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -42,6 +42,7 @@ struct pipe_buffer {
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
+ *	@user: the user who created this pipe
  **/
 struct pipe_inode_info {
 	struct mutex mutex;
@@ -57,6 +58,7 @@ struct pipe_inode_info {
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
+	struct user_struct *user;
 };
 
 /*
@@ -123,6 +125,8 @@ void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
 extern unsigned int pipe_max_size, pipe_min_size;
+extern unsigned long pipe_user_pages_hard;
+extern unsigned long pipe_user_pages_soft;
 int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 
 
diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h
index 5e0bc779e6c5..33f88b4479e4 100644
--- a/include/linux/platform_data/asoc-s3c.h
+++ b/include/linux/platform_data/asoc-s3c.h
@@ -39,6 +39,10 @@ struct samsung_i2s {
  */
 struct s3c_audio_pdata {
 	int (*cfg_gpio)(struct platform_device *);
+	void *dma_playback;
+	void *dma_capture;
+	void *dma_play_sec;
+	void *dma_capture_mic;
 	union {
 		struct samsung_i2s i2s;
 	} type;
diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h
index 3e96a6a76103..d1a8ad7e5ae4 100644
--- a/include/linux/posix_acl.h
+++ b/include/linux/posix_acl.h
@@ -95,6 +95,7 @@ extern int set_posix_acl(struct inode *, int, struct posix_acl *);
 extern int posix_acl_chmod(struct inode *, umode_t);
 extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **,
 		struct posix_acl **);
+extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **);
 
 extern int simple_set_acl(struct inode *, struct posix_acl *, int);
 extern int simple_acl_create(struct inode *, struct inode *);
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9c9d6c154c8e..6f4520a82197 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -23,6 +23,13 @@
 #include <linux/types.h>
 #include <linux/init.h>
 
+/*
+ * Choose whether access to the RAM zone requires locking or not.  If a zone
+ * can be written to from different CPUs like with ftrace for example, then
+ * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required.
+ */
+#define PRZ_FLAG_NO_LOCK	BIT(0)
+
 struct persistent_ram_buffer;
 struct rs_control;
 
@@ -39,6 +46,8 @@ struct persistent_ram_zone {
 	void *vaddr;
 	struct persistent_ram_buffer *buffer;
 	size_t buffer_size;
+	u32 flags;
+	raw_spinlock_t buffer_lock;
 
 	/* ECC correction */
 	char *par_buffer;
@@ -54,7 +63,7 @@ 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,
-			unsigned int memtype);
+			unsigned int memtype, u32 flags);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 504c98a278d4..81fdf4b8aba4 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -19,7 +19,6 @@
 #define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
 #define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
-#define PT_PTRACE_CAP	0x00000004	/* ptracer can follow suid-exec */
 
 #define PT_OPT_FLAG_SHIFT	3
 /* PT_TRACE_* event enable flags */
@@ -51,7 +50,8 @@ extern int ptrace_request(struct task_struct *child, long request,
 			  unsigned long addr, unsigned long data);
 extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
-			  struct task_struct *new_parent);
+			  struct task_struct *new_parent,
+			  const struct cred *ptracer_cred);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_READ	0x01
@@ -203,7 +203,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 
 	if (unlikely(ptrace) && current->ptrace) {
 		child->ptrace = current->ptrace;
-		__ptrace_link(child, current->parent);
+		__ptrace_link(child, current->parent, current->ptracer_cred);
 
 		if (child->ptrace & PT_SEIZED)
 			task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
@@ -212,6 +212,8 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 
 		set_tsk_thread_flag(child, TIF_SIGPENDING);
 	}
+	else
+		child->ptracer_cred = NULL;
 }
 
 /**
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index cfc3ed46cad2..aa8736d5b2f3 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -331,6 +331,7 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num)
 #ifdef CONFIG_PWM_SYSFS
 void pwmchip_sysfs_export(struct pwm_chip *chip);
 void pwmchip_sysfs_unexport(struct pwm_chip *chip);
+void pwmchip_sysfs_unexport_children(struct pwm_chip *chip);
 #else
 static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
 {
@@ -339,6 +340,10 @@ static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
 static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip)
 {
 }
+
+static inline void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
+{
+}
 #endif /* CONFIG_PWM_SYSFS */
 
 #endif /* __LINUX_PWM_H */
diff --git a/include/linux/random.h b/include/linux/random.h
index a75840c1aa71..9c29122037f9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops;
 #endif
 
 unsigned int get_random_int(void);
+unsigned long get_random_long(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 21a6e9649012..e887c8d6f395 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -801,6 +801,16 @@ struct signal_struct {
 
 #define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
 
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+			  SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+					 unsigned int flags)
+{
+	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
+}
+
 /* If true, all threads except ->group_exit_task have pending SIGKILL */
 static inline int signal_group_exit(const struct signal_struct *sig)
 {
@@ -831,6 +841,7 @@ struct user_struct {
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
@@ -1474,6 +1485,10 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+#ifdef CONFIG_CGROUPS
+	/* disallow userland-initiated cgroup migration */
+	unsigned no_cgroup_migration:1;
+#endif
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
@@ -1539,6 +1554,7 @@ struct task_struct {
 	struct list_head cpu_timers[3];
 
 /* process credentials */
+	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
 	const struct cred __rcu *real_cred; /* objective and real subjective task
 					 * credentials (COW) */
 	const struct cred __rcu *cred;	/* effective (overridable) subjective task
@@ -1933,31 +1949,8 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk)
 	return tsk->tgid;
 }
 
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return pid_vnr(task_tgid(tsk));
-}
-
 
 static inline int pid_alive(const struct task_struct *p);
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
 
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
 					struct pid_namespace *ns)
@@ -1982,6 +1975,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk)
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 /* obsolete, do not use */
 static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 {
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 976ce3a19f1b..d0efd6e6c20a 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -21,6 +21,7 @@ struct sem_array {
 	struct list_head	list_id;	/* undo requests on this array */
 	int			sem_nsems;	/* no. of semaphores in array */
 	int			complex_count;	/* pending complex operations */
+	bool			complex_mode;	/* no parallel simple ops */
 };
 
 #ifdef CONFIG_SYSVIPC
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index dde00defbaa5..f3d45dd42695 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -7,13 +7,10 @@
 #include <linux/mutex.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
+#include <linux/fs.h>
+#include <linux/cred.h>
 
 struct seq_operations;
-struct file;
-struct path;
-struct inode;
-struct dentry;
-struct user_namespace;
 
 struct seq_file {
 	char *buf;
@@ -27,9 +24,7 @@ struct seq_file {
 	struct mutex lock;
 	const struct seq_operations *op;
 	int poll_event;
-#ifdef CONFIG_USER_NS
-	struct user_namespace *user_ns;
-#endif
+	const struct file *file;
 	void *private;
 };
 
@@ -147,7 +142,7 @@ int seq_release_private(struct inode *, struct file *);
 static inline struct user_namespace *seq_user_ns(struct seq_file *seq)
 {
 #ifdef CONFIG_USER_NS
-	return seq->user_ns;
+	return seq->file->f_cred->user_ns;
 #else
 	extern struct user_namespace init_user_ns;
 	return &init_user_ns;
diff --git a/include/linux/serio.h b/include/linux/serio.h
index df4ab5de1586..c733cff44e18 100644
--- a/include/linux/serio.h
+++ b/include/linux/serio.h
@@ -31,7 +31,8 @@ struct serio {
 
 	struct serio_device_id id;
 
-	spinlock_t lock;		/* protects critical sections from port's interrupt handler */
+	/* Protects critical sections from port's interrupt handler */
+	spinlock_t lock;
 
 	int (*write)(struct serio *, unsigned char);
 	int (*open)(struct serio *);
@@ -40,16 +41,29 @@ struct serio {
 	void (*stop)(struct serio *);
 
 	struct serio *parent;
-	struct list_head child_node;	/* Entry in parent->children list */
+	/* Entry in parent->children list */
+	struct list_head child_node;
 	struct list_head children;
-	unsigned int depth;		/* level of nesting in serio hierarchy */
+	/* Level of nesting in serio hierarchy */
+	unsigned int depth;
 
-	struct serio_driver *drv;	/* accessed from interrupt, must be protected by serio->lock and serio->sem */
-	struct mutex drv_mutex;		/* protects serio->drv so attributes can pin driver */
+	/*
+	 * serio->drv is accessed from interrupt handlers; when modifying
+	 * caller should acquire serio->drv_mutex and serio->lock.
+	 */
+	struct serio_driver *drv;
+	/* Protects serio->drv so attributes can pin current driver */
+	struct mutex drv_mutex;
 
 	struct device dev;
 
 	struct list_head node;
+
+	/*
+	 * For use by PS/2 layer when several ports share hardware and
+	 * may get indigestion when exposed to concurrent access (i8042).
+	 */
+	struct mutex *ps2_cmd_mutex;
 };
 #define to_serio_port(d)	container_of(d, struct serio, dev)
 
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 92557bbce7e7..d80259afb9e5 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -28,6 +28,21 @@ struct sigpending {
 	sigset_t signal;
 };
 
+#ifndef HAVE_ARCH_COPY_SIGINFO
+
+#include <linux/string.h>
+
+static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
+{
+	if (from->si_code < 0)
+		memcpy(to, from, sizeof(*to));
+	else
+		/* _sigchld is currently the largest know union member */
+		memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld));
+}
+
+#endif
+
 /*
  * Define some primitives to manipulate sigset_t.
  */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 75f136a22a5e..3f61c647fc5c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -982,6 +982,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
@@ -1083,9 +1084,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
 
 static inline void skb_sender_cpu_clear(struct sk_buff *skb)
 {
-#ifdef CONFIG_XPS
-	skb->sender_cpu = 0;
-#endif
 }
 
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
@@ -1908,6 +1906,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 #define ENCAP_TYPE_ETHER	0
 #define ENCAP_TYPE_IPPROTO	1
 
@@ -2540,6 +2562,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len
 	       skb_headroom(skb) + len <= skb->hdr_len;
 }
 
+static inline int skb_try_make_writable(struct sk_buff *skb,
+					unsigned int write_len)
+{
+	return skb_cloned(skb) && !skb_clone_writable(skb, write_len) &&
+	       pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
 static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
 			    int cloned)
 {
@@ -2724,6 +2753,42 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
 
+static inline void skb_postpush_rcsum(struct sk_buff *skb,
+				      const void *start, unsigned int len)
+{
+	/* For performing the reverse operation to skb_postpull_rcsum(),
+	 * we can instead of ...
+	 *
+	 *   skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
+	 *
+	 * ... just use this equivalent version here to save a few
+	 * instructions. Feeding csum of 0 in csum_partial() and later
+	 * on adding skb->csum is equivalent to feed skb->csum in the
+	 * first place.
+	 */
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_partial(start, len, skb->csum);
+}
+
+/**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 2037a861e367..8a2a9ffaf5de 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -203,7 +203,7 @@ size_t ksize(const void *);
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
@@ -216,7 +216,7 @@ size_t ksize(const void *);
  * be allocated from the same page.
  */
 #define KMALLOC_SHIFT_HIGH	PAGE_SHIFT
-#define KMALLOC_SHIFT_MAX	30
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h
index 76199b75d584..e302c447e057 100644
--- a/include/linux/smc91x.h
+++ b/include/linux/smc91x.h
@@ -1,6 +1,16 @@
 #ifndef __SMC91X_H__
 #define __SMC91X_H__
 
+/*
+ * These bits define which access sizes a platform can support, rather
+ * than the maximal access size.  So, if your platform can do 16-bit
+ * and 32-bit accesses to the SMC91x device, but not 8-bit, set both
+ * SMC91X_USE_16BIT and SMC91X_USE_32BIT.
+ *
+ * The SMC91x driver requires at least one of SMC91X_USE_8BIT or
+ * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is
+ * an invalid configuration.
+ */
 #define SMC91X_USE_8BIT (1 << 0)
 #define SMC91X_USE_16BIT (1 << 1)
 #define SMC91X_USE_32BIT (1 << 2)
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index fddebc617469..8ff34ed1ae8a 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -35,6 +35,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 {
 	switch (sk->sk_family) {
 	case AF_INET:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET_TCP_DESTROY;
@@ -44,6 +47,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 			return SKNLGRP_NONE;
 		}
 	case AF_INET6:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET6_TCP_DESTROY;
diff --git a/include/linux/string.h b/include/linux/string.h
index 9ef7795e65e4..aa30789b0f65 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -127,7 +127,11 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
 extern void argv_free(char **argv);
 
 extern bool sysfs_streq(const char *s1, const char *s2);
-extern int strtobool(const char *s, bool *res);
+extern int kstrtobool(const char *s, bool *res);
+static inline int strtobool(const char *s, bool *res)
+{
+	return kstrtobool(s, res);
+}
 
 #ifdef CONFIG_BINARY_PRINTF
 int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 131032f15cc1..316a5525b730 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -135,8 +135,6 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
-					struct rpc_xprt *xprt);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt);
@@ -182,5 +180,6 @@ const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 int		rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t);
 
 const char *rpc_proc_name(const struct rpc_task *task);
+void rpc_cleanup_clids(void);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7ba7dccaf0e7..d8ca2eaa3a8b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -266,6 +266,7 @@ static inline void workingset_node_pages_inc(struct radix_tree_node *node)
 
 static inline void workingset_node_pages_dec(struct radix_tree_node *node)
 {
+	VM_WARN_ON_ONCE(!workingset_node_pages(node));
 	node->count--;
 }
 
@@ -281,6 +282,7 @@ static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
 
 static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
 {
+	VM_WARN_ON_ONCE(!workingset_node_shadows(node));
 	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
 }
 
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index fa7bc29925c9..ef17db6caaed 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -41,6 +41,8 @@ extern int proc_dostring(struct ctl_table *, int,
 			 void __user *, size_t *, loff_t *);
 extern int proc_dointvec(struct ctl_table *, int,
 			 void __user *, size_t *, loff_t *);
+extern int proc_douintvec(struct ctl_table *, int,
+			 void __user *, size_t *, loff_t *);
 extern int proc_dointvec_minmax(struct ctl_table *, int,
 				void __user *, size_t *, loff_t *);
 extern int proc_dointvec_jiffies(struct ctl_table *, int,
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b386361ba3e8..318c24612458 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -56,8 +56,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 
 /* TCP Fast Open Cookie as stored in memory */
 struct tcp_fastopen_cookie {
+	union {
+		u8	val[TCP_FASTOPEN_COOKIE_MAX];
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr addr;
+#endif
+	};
 	s8	len;
-	u8	val[TCP_FASTOPEN_COOKIE_MAX];
 	bool	exp;	/* In RFC6994 experimental option format */
 };
 
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index e13a1ace50e9..4a849f19e6c9 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -156,6 +156,7 @@ struct thermal_attr {
  * @trip_hyst_attrs:	attributes for trip points for sysfs: trip hysteresis
  * @devdata:	private pointer for device private data
  * @trips:	number of trip points the thermal zone supports
+ * @trips_disabled;	bitmap for disabled trips
  * @passive_delay:	number of milliseconds to wait between polls when
  *			performing passive cooling.
  * @polling_delay:	number of milliseconds to wait between polls when
@@ -191,6 +192,7 @@ struct thermal_zone_device {
 	struct thermal_attr *trip_hyst_attrs;
 	void *devdata;
 	int trips;
+	unsigned long trips_disabled;	/* bitmap for disabled trips */
 	int passive_delay;
 	int polling_delay;
 	int temperature;
diff --git a/include/linux/time.h b/include/linux/time.h
index beebe3a02d43..297f09f23896 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -125,6 +125,32 @@ static inline bool timeval_valid(const struct timeval *tv)
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 
+/*
+ * Validates if a timespec/timeval used to inject a time offset is valid.
+ * Offsets can be postive or negative. The value of the timeval/timespec
+ * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must
+ * always be non-negative.
+ */
+static inline bool timeval_inject_offset_valid(const struct timeval *tv)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more microseconds then a second */
+	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+		return false;
+	return true;
+}
+
+static inline bool timespec_inject_offset_valid(const struct timespec *ts)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more nanoseconds then a second */
+	if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC)
+		return false;
+	return true;
+}
+
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
 
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 25247220b4b7..f0f1793cfa49 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -29,7 +29,6 @@
  */
 struct tk_read_base {
 	struct clocksource	*clock;
-	cycle_t			(*read)(struct clocksource *cs);
 	cycle_t			mask;
 	cycle_t			cycle_last;
 	u32			mult;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 6b6e811f4575..83b264c52898 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -338,7 +338,6 @@ struct tty_file_private {
 #define TTY_EXCLUSIVE 		3	/* Exclusive open mode */
 #define TTY_DEBUG 		4	/* Debugging */
 #define TTY_DO_WRITE_WAKEUP 	5	/* Call write_wakeup after queuing new */
-#define TTY_OTHER_DONE		6	/* Closed pty has completed input processing */
 #define TTY_LDISC_OPEN	 	11	/* Line discipline is open */
 #define TTY_PTY_LOCK 		16	/* pty private */
 #define TTY_NO_WRITE_SPLIT 	17	/* Preserve write boundaries to driver */
@@ -469,6 +468,7 @@ extern void tty_buffer_init(struct tty_port *port);
 extern void tty_buffer_set_lock_subclass(struct tty_port *port);
 extern bool tty_buffer_restart_work(struct tty_port *port);
 extern bool tty_buffer_cancel_work(struct tty_port *port);
+extern void tty_buffer_flush_work(struct tty_port *port);
 extern speed_t tty_termios_baud_rate(struct ktermios *termios);
 extern speed_t tty_termios_input_baud_rate(struct ktermios *termios);
 extern void tty_termios_encode_baud_rate(struct ktermios *termios,
@@ -594,7 +594,7 @@ static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p,
 		count = ld->ops->receive_buf2(ld->tty, p, f, count);
 	else {
 		count = min_t(int, count, ld->tty->receive_room);
-		if (count)
+		if (count && ld->ops->receive_buf)
 			ld->ops->receive_buf(ld->tty, p, f, count);
 	}
 	return count;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 8b01e1c3c614..e2225109b816 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -76,7 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes);
+#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
@@ -101,12 +101,12 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 
-static inline size_t iov_iter_count(struct iov_iter *i)
+static inline size_t iov_iter_count(const struct iov_iter *i)
 {
 	return i->count;
 }
 
-static inline bool iter_is_iovec(struct iov_iter *i)
+static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return !(i->type & (ITER_BVEC | ITER_KVEC));
 }
diff --git a/include/linux/usb.h b/include/linux/usb.h
index b79925dd2b41..8c75af6b7d5b 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -371,14 +371,13 @@ struct usb_bus {
 
 	int devnum_next;		/* Next open device number in
 					 * round-robin allocation */
+	struct mutex devnum_next_mutex; /* devnum_next mutex */
 
 	struct usb_devmap devmap;	/* device address allocation map */
 	struct usb_device *root_hub;	/* Root hub */
 	struct usb_bus *hs_companion;	/* Companion EHCI bus, if any */
 	struct list_head bus_list;	/* list of busses */
 
-	struct mutex usb_address0_mutex; /* unaddressed device mutex */
-
 	int bandwidth_allocated;	/* on this bus: how much of the time
 					 * reserved for periodic (intr/iso)
 					 * requests is used, on average?
@@ -1068,7 +1067,7 @@ struct usbdrv_wrap {
  *	for interfaces bound to this driver.
  * @soft_unbind: if set to 1, the USB core will not kill URBs and disable
  *	endpoints before calling the driver's disconnect method.
- * @disable_hub_initiated_lpm: if set to 0, the USB core will not allow hubs
+ * @disable_hub_initiated_lpm: if set to 1, the USB core will not allow hubs
  *	to initiate lower power link state transitions when an idle timeout
  *	occurs.  Device-initiated USB 3.0 link PM will still be allowed.
  *
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index 5dd75fa47dd8..f9be467d6695 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -14,6 +14,7 @@ struct ci_hdrc;
  * struct ci_hdrc_cable - structure for external connector cable state tracking
  * @state: current state of the line
  * @changed: set to true when extcon event happen
+ * @enabled: set to true if we've enabled the vbus or id interrupt
  * @edev: device which generate events
  * @ci: driver state of the chipidea device
  * @nb: hold event notification callback
@@ -22,6 +23,7 @@ struct ci_hdrc;
 struct ci_hdrc_cable {
 	bool				state;
 	bool				changed;
+	bool				enabled;
 	struct extcon_dev		*edev;
 	struct ci_hdrc			*ci;
 	struct notifier_block		nb;
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index 966889a20ea3..e479033bd782 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -180,11 +180,11 @@ struct ehci_regs {
  * PORTSCx
  */
 	/* HOSTPC: offset 0x84 */
-	u32		hostpc[1];	/* HOSTPC extension */
+	u32		hostpc[0];	/* HOSTPC extension */
 #define HOSTPC_PHCD	(1<<22)		/* Phy clock disable */
 #define HOSTPC_PSPD	(3<<25)		/* Port speed detection */
 
-	u32		reserved5[16];
+	u32		reserved5[17];
 
 	/* USBMODE_EX: offset 0xc8 */
 	u32		usbmode_ex;	/* USB Device mode extension */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index f89c24bd53a4..757c554408ce 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -180,6 +180,7 @@ struct usb_hcd {
 	 * bandwidth_mutex should be dropped after a successful control message
 	 * to the device, or resetting the bandwidth after a failed attempt.
 	 */
+	struct mutex		*address0_mutex;
 	struct mutex		*bandwidth_mutex;
 	struct usb_hcd		*shared_hcd;
 	struct usb_hcd		*primary_hcd;
@@ -559,9 +560,9 @@ extern void usb_ep0_reinit(struct usb_device *);
 	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
 
 #define EndpointRequest \
-	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
+	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8)
 #define EndpointOutRequest \
-	((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
+	((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8)
 
 /* class requests from the USB 2.0 hub spec, table 11-15 */
 /* GetBusState and SetHubDescriptor are optional, omitted */
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 1d0043dc34e4..de2a722fe3cf 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -50,4 +50,10 @@
 /* device can't handle Link Power Management */
 #define USB_QUIRK_NO_LPM			BIT(10)
 
+/*
+ * Device reports its bInterval as linear frames instead of the
+ * USB 2.0 calculation.
+ */
+#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL	BIT(11)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 7f5f78bd15ad..245f57dbbb61 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -79,6 +79,8 @@
 		/* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */	\
 	US_FLAG(MAX_SECTORS_240,	0x08000000)		\
 		/* Sets max_sectors to 240 */			\
+	US_FLAG(NO_REPORT_LUNS,	0x10000000)			\
+		/* Cannot handle REPORT_LUNS */			\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index ddb440975382..34851bf2e2c8 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -85,6 +85,8 @@ extern void vfio_unregister_iommu_driver(
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
+extern bool vfio_external_group_match_file(struct vfio_group *group,
+					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0197358f1e81..217abe56e711 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -408,7 +409,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
+			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 647ebfe5174f..d4227a8a2a23 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -363,6 +363,7 @@ struct vb2_ops {
 };
 
 struct vb2_buf_ops {
+	int (*verify_planes_array)(struct vb2_buffer *vb, const void *pb);
 	int (*fill_user_buffer)(struct vb2_buffer *vb, void *pb);
 	int (*fill_vb2_buffer)(struct vb2_buffer *vb, const void *pb,
 				struct vb2_plane *planes);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 78003dfb8539..18dd7a3caf2f 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -19,6 +19,8 @@
 #define ADDRCONF_TIMER_FUZZ		(HZ / 4)
 #define ADDRCONF_TIMER_FUZZ_MAX		(HZ)
 
+#define ADDRCONF_NOTIFY_PRIORITY	0
+
 #include <linux/in.h>
 #include <linux/in6.h>
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 9b4c418bebd8..fd60eccb59a6 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -52,7 +52,7 @@ struct unix_sock {
 	struct sock		sk;
 	struct unix_address     *addr;
 	struct path		path;
-	struct mutex		readlock;
+	struct mutex		iolock, bindlock;
 	struct sock		*peer;
 	struct list_head	link;
 	atomic_long_t		inflight;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index c1740a2794a3..93abe5f6188d 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -214,6 +214,7 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
+	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2c7bdb81d30c..b5f3693fe5b6 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4258,6 +4258,17 @@ void cfg80211_rx_assoc_resp(struct net_device *dev,
 void cfg80211_assoc_timeout(struct net_device *dev, struct cfg80211_bss *bss);
 
 /**
+ * cfg80211_abandon_assoc - notify cfg80211 of abandoned association attempt
+ * @dev: network device
+ * @bss: The BSS entry with which association was abandoned.
+ *
+ * Call this whenever - for reasons reported through other API, like deauth RX,
+ * an association attempt was abandoned.
+ * This function may sleep. The caller must hold the corresponding wdev's mutex.
+ */
+void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss);
+
+/**
  * cfg80211_tx_mlme_mgmt - notification of transmitted deauth/disassoc frame
  * @dev: network device
  * @buf: 802.11 frame (header + body)
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 3ebb168b9afc..a34b141f125f 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto out;
+		}
 		tag_len = opt[opt_iter + 1];
 		if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;
diff --git a/include/net/codel.h b/include/net/codel.h
index 267e70210061..d168aca115cc 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -162,12 +162,14 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  * ce_mark:	number of packets CE marked because sojourn time was above ce_threshold
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 	u32		ce_mark;
 };
@@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 
diff --git a/include/net/dst.h b/include/net/dst.h
index c7329dcd90cc..e4f450617919 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -110,10 +110,16 @@ struct dst_entry {
 	};
 };
 
+struct dst_metrics {
+	u32		metrics[RTAX_MAX];
+	atomic_t	refcnt;
+};
+extern const struct dst_metrics dst_default_metrics;
+
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-extern const u32 dst_default_metrics[];
 
 #define DST_METRICS_READ_ONLY		0x1UL
+#define DST_METRICS_REFCOUNTED		0x2UL
 #define DST_METRICS_FLAGS		0x3UL
 #define __DST_METRICS_PTR(Y)	\
 	((u32 *)((Y) & ~DST_METRICS_FLAGS))
diff --git a/include/net/ip.h b/include/net/ip.h
index 1a98f1ca1638..7476bb10ff37 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -314,7 +314,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
@@ -327,7 +327,7 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
@@ -553,7 +553,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct net *net, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -575,7 +575,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 
 static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 {
-	ip_cmsg_recv_offset(msg, skb, 0);
+	ip_cmsg_recv_offset(msg, skb, 0, 0);
 }
 
 bool icmp_global_allow(void);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 295d291269e2..b8a8d4239e85 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -21,6 +21,7 @@ struct route_info {
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
+#include <net/lwtunnel.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/route.h>
@@ -77,6 +78,7 @@ static inline struct dst_entry *ip6_route_output(struct net *net,
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags);
 
+void ip6_route_init_special_entries(void);
 int ip6_route_init(void);
 void ip6_route_cleanup(void);
 
@@ -207,4 +209,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
 		return daddr;
 }
 
+static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
+{
+	return a->dst.dev == b->dst.dev &&
+	       a->rt6i_idev == b->rt6i_idev &&
+	       ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
+	       !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
+}
 #endif
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index ff788b665277..9c2c044153f6 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -86,6 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	struct net_device_stats *stats = &dev->stats;
 	int pkt_len, err;
 
+	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
 
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 3f98233388fb..bda1721e9622 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -112,11 +112,11 @@ struct fib_info {
 	unsigned char		fib_type;
 	__be32			fib_prefsrc;
 	u32			fib_priority;
-	u32			*fib_metrics;
-#define fib_mtu fib_metrics[RTAX_MTU-1]
-#define fib_window fib_metrics[RTAX_WINDOW-1]
-#define fib_rtt fib_metrics[RTAX_RTT-1]
-#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
+	struct dst_metrics	*fib_metrics;
+#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
+#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
+#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
+#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			fib_weight;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 62a750a6a8f8..86a7bdd61d1a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4);
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
@@ -282,6 +283,22 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
 					 int gso_type_mask);
 
+static inline int iptunnel_pull_offloads(struct sk_buff *skb)
+{
+	if (skb_is_gso(skb)) {
+		int err;
+
+		err = skb_unclone(skb, GFP_ATOMIC);
+		if (unlikely(err))
+			return err;
+		skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >>
+					       NETIF_F_GSO_SHIFT);
+	}
+
+	skb->encapsulation = 0;
+	return 0;
+}
+
 static inline void iptunnel_xmit_stats(int err,
 				       struct net_device_stats *err_stats,
 				       struct pcpu_sw_netstats __percpu *stats)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 0816c872b689..a6cc576fd467 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 }
 #endif /* CONFIG_IP_VS_NFCT */
 
+/* Really using conntrack? */
+static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
+					     struct sk_buff *skb)
+{
+#ifdef CONFIG_IP_VS_NFCT
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (!(cp->flags & IP_VS_CONN_F_NFCT))
+		return false;
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct && !nf_ct_is_untracked(ct))
+		return true;
+#endif
+	return false;
+}
+
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 9a5c9f013784..7a8066b90289 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -744,6 +744,11 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 {
 	u32 hash;
 
+	/* @flowlabel may include more than a flow label, eg, the traffic class.
+	 * Here we want only the flow label value.
+	 */
+	flowlabel &= IPV6_FLOWLABEL_MASK;
+
 	if (flowlabel ||
 	    net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
 	    (!autolabel &&
@@ -958,6 +963,7 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
  */
 extern const struct proto_ops inet6_stream_ops;
 extern const struct proto_ops inet6_dgram_ops;
+extern const struct proto_ops inet6_sockraw_ops;
 
 struct group_source_req;
 struct group_filter;
diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index e0f4109e64c6..c2aa73e5e6bb 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -556,7 +556,8 @@ iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends,
 		memcpy(stream + lcp_len,
 		       ((char *) &iwe->u) + IW_EV_POINT_OFF,
 		       IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN);
-		memcpy(stream + point_len, extra, iwe->u.data.length);
+		if (iwe->u.data.length && extra)
+			memcpy(stream + point_len, extra, iwe->u.data.length);
 		stream += event_len;
 	}
 	return stream;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 760bc4d5a2cf..4e51f9a5a177 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1662,6 +1662,9 @@ struct ieee80211_sta_rates {
  * @supp_rates: Bitmap of supported rates (per band)
  * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
  * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
+ * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU
+ *	that this station is allowed to transmit to us.
+ *	Can be modified by driver.
  * @wme: indicates whether the STA supports QoS/WME (if local devices does,
  *	otherwise always false)
  * @drv_priv: data area for driver use, will always be aligned to
@@ -1688,6 +1691,7 @@ struct ieee80211_sta {
 	u16 aid;
 	struct ieee80211_sta_ht_cap ht_cap;
 	struct ieee80211_sta_vht_cap vht_cap;
+	u8 max_rx_aggregation_subframes;
 	bool wme;
 	u8 uapsd_queues;
 	u8 max_sp;
@@ -2674,6 +2678,33 @@ enum ieee80211_ampdu_mlme_action {
 };
 
 /**
+ * struct ieee80211_ampdu_params - AMPDU action parameters
+ *
+ * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action.
+ * @sta: peer of this AMPDU session
+ * @tid: tid of the BA session
+ * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When
+ *	action is set to %IEEE80211_AMPDU_RX_START the driver passes back the
+ *	actual ssn value used to start the session and writes the value here.
+ * @buf_size: reorder buffer size  (number of subframes). Valid only when the
+ *	action is set to %IEEE80211_AMPDU_RX_START or
+ *	%IEEE80211_AMPDU_TX_OPERATIONAL
+ * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU.
+ *	valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL
+ * @timeout: BA session timeout. Valid only when the action is set to
+ *	%IEEE80211_AMPDU_RX_START
+ */
+struct ieee80211_ampdu_params {
+	enum ieee80211_ampdu_mlme_action action;
+	struct ieee80211_sta *sta;
+	u16 tid;
+	u16 ssn;
+	u8 buf_size;
+	bool amsdu;
+	u16 timeout;
+};
+
+/**
  * enum ieee80211_frame_release_type - frame release reason
  * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll
  * @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to
@@ -3017,13 +3048,9 @@ enum ieee80211_reconfig_type {
  * @ampdu_action: Perform a certain A-MPDU action
  * 	The RA/TID combination determines the destination and TID we want
  * 	the ampdu action to be performed for. The action is defined through
- * 	ieee80211_ampdu_mlme_action. Starting sequence number (@ssn)
- * 	is the first frame we expect to perform the action on. Notice
- * 	that TX/RX_STOP can pass NULL for this parameter.
- *	The @buf_size parameter is only valid when the action is set to
- *	%IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder
- *	buffer size (number of subframes) for this session -- the driver
- *	may neither send aggregates containing more subframes than this
+ *	ieee80211_ampdu_mlme_action.
+ *	When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver
+ *	may neither send aggregates containing more subframes than @buf_size
  *	nor send aggregates in a way that lost frames would exceed the
  *	buffer size. If just limiting the aggregate size, this would be
  *	possible with a buf_size of 8:
@@ -3034,9 +3061,6 @@ enum ieee80211_reconfig_type {
  *	buffer size of 8. Correct ways to retransmit #1 would be:
  *	 - TX:       1 or 18 or 81
  *	Even "189" would be wrong since 1 could be lost again.
- *	The @amsdu parameter is valid when the action is set to
- *	%IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability
- *	to receive A-MSDU within A-MPDU.
  *
  *	Returns a negative error code on failure.
  *	The callback can sleep.
@@ -3378,9 +3402,7 @@ struct ieee80211_ops {
 	int (*tx_last_beacon)(struct ieee80211_hw *hw);
 	int (*ampdu_action)(struct ieee80211_hw *hw,
 			    struct ieee80211_vif *vif,
-			    enum ieee80211_ampdu_mlme_action action,
-			    struct ieee80211_sta *sta, u16 tid, u16 *ssn,
-			    u8 buf_size, bool amsdu);
+			    struct ieee80211_ampdu_params *params);
 	int (*get_survey)(struct ieee80211_hw *hw, int idx,
 		struct survey_info *survey);
 	void (*rfkill_poll)(struct ieee80211_hw *hw);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index b2a8e6338576..7a5d6a073165 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -396,7 +396,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -407,6 +408,15 @@ bool tcf_destroy(struct tcf_proto *tp, bool force);
 void tcf_destroy_chain(struct tcf_proto __rcu **fl);
 int skb_do_redirect(struct sk_buff *);
 
+static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return G_TC_AT(skb->tc_verd) & AT_INGRESS;
+#else
+	return false;
+#endif
+}
+
 /* Reset all TX qdiscs greater then index of a device.  */
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
@@ -698,6 +708,26 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
+		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index ce13cf20f625..d33b17ba51d2 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -444,6 +444,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\
+      (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
      pos.v += WORD_ROUND(ntohs(pos.p->length)))
@@ -454,6 +456,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\
+      (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
      err = (sctp_errhdr_t *)((void *)err + WORD_ROUND(ntohs(err->length))))
diff --git a/include/net/sock.h b/include/net/sock.h
index 14d3c0734007..3d5ff7436f41 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1425,6 +1425,16 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 	if (!sk_has_account(sk))
 		return;
 	sk->sk_forward_alloc += size;
+
+	/* Avoid a possible overflow.
+	 * TCP send queues can make this happen, if sk_mem_reclaim()
+	 * is not called and more than 2 GBytes are released at once.
+	 *
+	 * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
+	 * no need to hold that much forward allocation anyway.
+	 */
+	if (unlikely(sk->sk_forward_alloc >= 1 << 21))
+		__sk_mem_reclaim(sk, 1 << 20);
 }
 
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 1d22ce9f352e..31d0e5143848 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -88,7 +88,7 @@ struct switchdev_obj_ipv4_fib {
 	struct switchdev_obj obj;
 	u32 dst;
 	int dst_len;
-	struct fib_info fi;
+	struct fib_info *fi;
 	u8 tos;
 	u8 type;
 	u32 nlflags;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 414d822bc1db..e9d7a8ef9a6d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1156,6 +1156,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 }
 
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);
 
 #undef STATE_TRACE
 
@@ -1510,6 +1511,8 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli
 {
 	if (sk->sk_send_head == skb_unlinked)
 		sk->sk_send_head = NULL;
+	if (tcp_sk(sk)->highest_sack == skb_unlinked)
+		tcp_sk(sk)->highest_sack = NULL;
 }
 
 static inline void tcp_init_send_head(struct sock *sk)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d6f6e5006ee9..185fb037b332 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -948,10 +948,6 @@ struct xfrm_dst {
 	struct flow_cache_object flo;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	int num_pols, num_xfrms;
-#ifdef CONFIG_XFRM_SUB_POLICY
-	struct flowi *origin;
-	struct xfrm_selector *partner;
-#endif
 	u32 xfrm_genid;
 	u32 policy_genid;
 	u32 route_mtu_cached;
@@ -967,12 +963,6 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 	dst_release(xdst->route);
 	if (likely(xdst->u.dst.xfrm))
 		xfrm_state_put(xdst->u.dst.xfrm);
-#ifdef CONFIG_XFRM_SUB_POLICY
-	kfree(xdst->origin);
-	xdst->origin = NULL;
-	kfree(xdst->partner);
-	xdst->partner = NULL;
-#endif
 }
 #endif
 
diff --git a/include/rdma/ib.h b/include/rdma/ib.h
index cf8f9e700e48..a6b93706b0fc 100644
--- a/include/rdma/ib.h
+++ b/include/rdma/ib.h
@@ -34,6 +34,7 @@
 #define _RDMA_IB_H
 
 #include <linux/types.h>
+#include <linux/sched.h>
 
 struct ib_addr {
 	union {
@@ -86,4 +87,19 @@ struct sockaddr_ib {
 	__u64			sib_scope_id;
 };
 
+/*
+ * The IB interfaces that use write() as bi-directional ioctl() are
+ * fundamentally unsafe, since there are lots of ways to trigger "write()"
+ * calls from various contexts with elevated privileges. That includes the
+ * traditional suid executable error message writes, but also various kernel
+ * interfaces that can write to file descriptors.
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static inline bool ib_safe_file_access(struct file *filp)
+{
+	return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS);
+}
+
 #endif /* _RDMA_IB_H */
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 11528591d0d7..a78ff97eb249 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -197,10 +197,12 @@ static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 
 	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
 	if (dev) {
-		ip4 = (struct in_device *)dev->ip_ptr;
-		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
+		ip4 = in_dev_get(dev);
+		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) {
 			ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
 					       (struct in6_addr *)gid);
+			in_dev_put(ip4);
+		}
 		dev_put(dev);
 	}
 }
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 301969552d0a..b43e64d69734 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -138,12 +138,12 @@ struct ib_sa_path_rec {
 	union ib_gid sgid;
 	__be16       dlid;
 	__be16       slid;
-	int          raw_traffic;
+	u8           raw_traffic;
 	/* reserved */
 	__be32       flow_label;
 	u8           hop_limit;
 	u8           traffic_class;
-	int          reversible;
+	u8           reversible;
 	u8           numb_path;
 	__be16       pkey;
 	__be16       qos_class;
@@ -204,7 +204,7 @@ struct ib_sa_mcmember_rec {
 	u8           hop_limit;
 	u8           scope;
 	u8           join_state;
-	int          proxy_join;
+	u8           proxy_join;
 };
 
 /* Service Record Component Mask Sec 15.2.5.14 Ver 1.1	*/
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 4d1c46aac331..c7b1dc713cdd 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -196,6 +196,7 @@ struct iscsi_conn {
 	struct iscsi_task	*task;		/* xmit task in progress */
 
 	/* xmit */
+	spinlock_t		taskqueuelock;  /* protects the next three lists */
 	struct list_head	mgmtqueue;	/* mgmt (control) xmit queue */
 	struct list_head	cmdqueue;	/* data-path cmd queue */
 	struct list_head	requeue;	/* tasks needing another run */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index fe89d7cd67b9..293b9a7f53bc 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -239,6 +239,7 @@ scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...);
 enum scsi_target_state {
 	STARGET_CREATED = 1,
 	STARGET_RUNNING,
+	STARGET_REMOVE,
 	STARGET_DEL,
 };
 
@@ -306,6 +307,7 @@ extern void scsi_remove_device(struct scsi_device *);
 extern int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh);
 void scsi_attach_vpd(struct scsi_device *sdev);
 
+extern struct scsi_device *scsi_device_from_queue(struct request_queue *q);
 extern int scsi_device_get(struct scsi_device *);
 extern void scsi_device_put(struct scsi_device *);
 extern struct scsi_device *scsi_device_lookup(struct Scsi_Host *,
diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h
index dc10c52e0e91..393362bdb860 100644
--- a/include/soc/at91/at91sam9_ddrsdr.h
+++ b/include/soc/at91/at91sam9_ddrsdr.h
@@ -81,6 +81,7 @@
 #define			AT91_DDRSDRC_LPCB_POWER_DOWN		2
 #define			AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN	3
 #define		AT91_DDRSDRC_CLKFR	(1 << 2)	/* Clock Frozen */
+#define		AT91_DDRSDRC_LPDDR2_PWOFF	(1 << 3)	/* LPDDR Power Off */
 #define		AT91_DDRSDRC_PASR	(7 << 4)	/* Partial Array Self Refresh */
 #define		AT91_DDRSDRC_TCSR	(3 << 8)	/* Temperature Compensated Self Refresh */
 #define		AT91_DDRSDRC_DS		(3 << 10)	/* Drive Strength */
@@ -96,7 +97,9 @@
 #define			AT91_DDRSDRC_MD_SDR		0
 #define			AT91_DDRSDRC_MD_LOW_POWER_SDR	1
 #define			AT91_DDRSDRC_MD_LOW_POWER_DDR	3
+#define			AT91_DDRSDRC_MD_LPDDR3		5
 #define			AT91_DDRSDRC_MD_DDR2		6	/* [SAM9 Only] */
+#define			AT91_DDRSDRC_MD_LPDDR2		7
 #define		AT91_DDRSDRC_DBW	(1 << 4)		/* Data Bus Width */
 #define			AT91_DDRSDRC_DBW_32BITS		(0 <<  4)
 #define			AT91_DDRSDRC_DBW_16BITS		(1 <<  4)
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 373d3342002b..22f442ab85f9 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -64,6 +64,14 @@
 #define TA_DEFAULT_FABRIC_PROT_TYPE	0
 /* TPG status needs to be enabled to return sendtargets discovery endpoint info */
 #define TA_DEFAULT_TPG_ENABLED_SENDTARGETS 1
+/*
+ * Used to control the sending of keys with optional to respond state bit,
+ * as a workaround for non RFC compliant initiators,that do not propose,
+ * nor respond to specific keys required for login to complete.
+ *
+ * See iscsi_check_proposer_for_optional_reply() for more details.
+ */
+#define TA_DEFAULT_LOGIN_KEYS_WORKAROUND 1
 
 #define ISCSI_IOV_DATA_BUFFER		5
 
@@ -554,6 +562,7 @@ struct iscsi_conn {
 #define LOGIN_FLAGS_READ_ACTIVE		1
 #define LOGIN_FLAGS_CLOSED		2
 #define LOGIN_FLAGS_READY		4
+#define LOGIN_FLAGS_INITIAL_PDU		8
 	unsigned long		login_flags;
 	struct delayed_work	login_work;
 	struct delayed_work	login_cleanup_work;
@@ -765,6 +774,7 @@ struct iscsi_tpg_attrib {
 	u8			t10_pi;
 	u32			fabric_prot_type;
 	u32			tpg_enabled_sendtargets;
+	u32			login_keys_workaround;
 	struct iscsi_portal_group *tpg;
 };
 
@@ -774,6 +784,7 @@ struct iscsi_np {
 	int			np_sock_type;
 	enum np_thread_state_table np_thread_state;
 	bool                    enabled;
+	atomic_t		np_reset_count;
 	enum iscsi_timer_flags_table np_login_timer_flags;
 	u32			np_exports;
 	enum np_flags_table	np_flags;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 28ee5c2e6bcd..711322a8ee35 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -96,6 +96,6 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 bool target_sense_desc_format(struct se_device *dev);
 sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
-				       struct request_queue *q, int block_size);
+				       struct request_queue *q);
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 689f4d207122..1adf8739980c 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -139,6 +139,7 @@ enum se_cmd_flags_table {
 	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
 	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
 	SCF_ACK_KREF			= 0x00400000,
+	SCF_TASK_ATTR_SET		= 0x01000000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -179,6 +180,7 @@ enum tcm_sense_reason_table {
 	TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED	= R(0x15),
 	TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED	= R(0x16),
 	TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED	= R(0x17),
+	TCM_COPY_TARGET_DEVICE_NOT_REACHABLE	= R(0x18),
 #undef R
 };
 
@@ -542,6 +544,7 @@ struct se_node_acl {
 	/* Used to signal demo mode created ACL, disabled by default */
 	bool			dynamic_node_acl;
 	bool			acl_stop:1;
+	bool			dynamic_stop;
 	u32			queue_depth;
 	u32			acl_index;
 	enum target_prot_type	saved_prot_type;
@@ -711,6 +714,7 @@ struct se_lun {
 #define SE_LUN_LINK_MAGIC			0xffff7771
 	u32			lun_link_magic;
 	u32			lun_access;
+	bool			lun_shutdown;
 	u32			lun_index;
 
 	/* RELATIVE TARGET PORT IDENTIFER */
@@ -737,6 +741,7 @@ struct se_lun {
 	struct config_group	lun_group;
 	struct se_port_stat_grps port_stat_grps;
 	struct completion	lun_ref_comp;
+	struct completion	lun_shutdown_comp;
 	struct percpu_ref	lun_ref;
 	struct list_head	lun_dev_link;
 	struct hlist_node	link;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 7fb2557a760e..5f9b62c129fc 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -117,7 +117,7 @@ void	__transport_register_session(struct se_portal_group *,
 		struct se_node_acl *, struct se_session *, void *);
 void	transport_register_session(struct se_portal_group *,
 		struct se_node_acl *, struct se_session *, void *);
-void	target_get_session(struct se_session *);
+int	target_get_session(struct se_session *);
 void	target_put_session(struct se_session *);
 ssize_t	target_show_dynamic_sessions(struct se_portal_group *, char *);
 void	transport_free_session(struct se_session *);
@@ -163,16 +163,16 @@ int	core_tmr_alloc_req(struct se_cmd *, void *, u8, gfp_t);
 void	core_tmr_release_req(struct se_tmr_req *);
 int	transport_generic_handle_tmr(struct se_cmd *);
 void	transport_generic_request_failure(struct se_cmd *, sense_reason_t);
-void	__target_execute_cmd(struct se_cmd *);
 int	transport_lookup_tmr_lun(struct se_cmd *, u64);
 void	core_allocate_nexus_loss_ua(struct se_node_acl *acl);
 
 struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
 		unsigned char *);
+bool	target_tpg_has_node_acl(struct se_portal_group *tpg,
+		const char *);
 struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
 		unsigned char *);
-int	core_tpg_set_initiator_node_queue_depth(struct se_portal_group *,
-		unsigned char *, u32, int);
+int	core_tpg_set_initiator_node_queue_depth(struct se_node_acl *, u32);
 int	core_tpg_set_initiator_node_tag(struct se_portal_group *,
 		struct se_node_acl *, const char *);
 int	core_tpg_register(struct se_wwn *, struct se_portal_group *, int);
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 003dca933803..5664ca07c9c7 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -529,20 +529,27 @@ TRACE_EVENT(svc_xprt_do_enqueue,
 
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
-		__field_struct(struct sockaddr_storage, ss)
 		__field(int, pid)
 		__field(unsigned long, flags)
+		__dynamic_array(unsigned char, addr, xprt != NULL ?
+			xprt->xpt_remotelen : 0)
 	),
 
 	TP_fast_assign(
 		__entry->xprt = xprt;
-		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
 		__entry->pid = rqst? rqst->rq_task->pid : 0;
-		__entry->flags = xprt ? xprt->xpt_flags : 0;
+		if (xprt) {
+			memcpy(__get_dynamic_array(addr),
+				&xprt->xpt_remote,
+				xprt->xpt_remotelen);
+			__entry->flags = xprt->xpt_flags;
+		} else
+			__entry->flags = 0;
 	),
 
 	TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt,
-		(struct sockaddr *)&__entry->ss,
+		__get_dynamic_array_len(addr) != 0 ?
+			(struct sockaddr *)__get_dynamic_array(addr) : NULL,
 		__entry->pid, show_svc_xprt_flags(__entry->flags))
 );
 
@@ -553,18 +560,25 @@ TRACE_EVENT(svc_xprt_dequeue,
 
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
-		__field_struct(struct sockaddr_storage, ss)
 		__field(unsigned long, flags)
+		__dynamic_array(unsigned char, addr, xprt != NULL ?
+			xprt->xpt_remotelen : 0)
 	),
 
 	TP_fast_assign(
-		__entry->xprt = xprt,
-		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
-		__entry->flags = xprt ? xprt->xpt_flags : 0;
+		__entry->xprt = xprt;
+		if (xprt) {
+			memcpy(__get_dynamic_array(addr),
+					&xprt->xpt_remote,
+					xprt->xpt_remotelen);
+			__entry->flags = xprt->xpt_flags;
+		} else
+			__entry->flags = 0;
 	),
 
 	TP_printk("xprt=0x%p addr=%pIScp flags=%s", __entry->xprt,
-		(struct sockaddr *)&__entry->ss,
+		__get_dynamic_array_len(addr) != 0 ?
+			(struct sockaddr *)__get_dynamic_array(addr) : NULL,
 		show_svc_xprt_flags(__entry->flags))
 );
 
@@ -592,19 +606,26 @@ TRACE_EVENT(svc_handle_xprt,
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
 		__field(int, len)
-		__field_struct(struct sockaddr_storage, ss)
 		__field(unsigned long, flags)
+		__dynamic_array(unsigned char, addr, xprt != NULL ?
+			xprt->xpt_remotelen : 0)
 	),
 
 	TP_fast_assign(
 		__entry->xprt = xprt;
-		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
 		__entry->len = len;
-		__entry->flags = xprt ? xprt->xpt_flags : 0;
+		if (xprt) {
+			memcpy(__get_dynamic_array(addr),
+					&xprt->xpt_remote,
+					xprt->xpt_remotelen);
+			__entry->flags = xprt->xpt_flags;
+		} else
+			__entry->flags = 0;
 	),
 
 	TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt,
-		(struct sockaddr *)&__entry->ss,
+		__get_dynamic_array_len(addr) != 0 ?
+			(struct sockaddr *)__get_dynamic_array(addr) : NULL,
 		__entry->len, show_svc_xprt_flags(__entry->flags))
 );
 #endif /* _TRACE_SUNRPC_H */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 14e49c798135..b35533b94277 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -1,5 +1,6 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM raw_syscalls
+#undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE syscalls
 
 #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index 9692cda5f8fc..c48d93a28d1a 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -196,5 +196,6 @@ struct can_filter {
 };
 
 #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */
+#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */
 
 #endif /* !_UAPI_CAN_H */
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index e4c0a35d6417..e347b24ef9fb 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -313,6 +313,7 @@ enum hv_kvp_exchg_pool {
 #define HV_INVALIDARG			0x80070057
 #define HV_GUID_NOTFOUND		0x80041002
 #define HV_ERROR_ALREADY_EXISTS		0x80070050
+#define HV_ERROR_DISK_FULL		0x80070070
 
 #define ADDR_FAMILY_NONE	0x00
 #define ADDR_FAMILY_IPV4	0x01
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 9cf2394f0bcf..752f5dc040a5 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -19,14 +19,20 @@
 #ifndef _LINUX_IF_H
 #define _LINUX_IF_H
 
+#include <linux/libc-compat.h>          /* for compatibility with glibc */
 #include <linux/types.h>		/* for "__kernel_caddr_t" et al	*/
 #include <linux/socket.h>		/* for "struct sockaddr" et al	*/
 #include <linux/compiler.h>		/* for "__user" et al           */
 
+#if __UAPI_DEF_IF_IFNAMSIZ
 #define	IFNAMSIZ	16
+#endif /* __UAPI_DEF_IF_IFNAMSIZ */
 #define	IFALIASZ	256
 #include <linux/hdlc/ioctl.h>
 
+/* For glibc compatibility. An empty enum does not compile. */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \
+    __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0
 /**
  * enum net_device_flags - &struct net_device flags
  *
@@ -68,6 +74,8 @@
  * @IFF_ECHO: echo sent packets. Volatile.
  */
 enum net_device_flags {
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 	IFF_UP				= 1<<0,  /* sysfs */
 	IFF_BROADCAST			= 1<<1,  /* volatile */
 	IFF_DEBUG			= 1<<2,  /* sysfs */
@@ -84,11 +92,17 @@ enum net_device_flags {
 	IFF_PORTSEL			= 1<<13, /* sysfs */
 	IFF_AUTOMEDIA			= 1<<14, /* sysfs */
 	IFF_DYNAMIC			= 1<<15, /* sysfs */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 	IFF_LOWER_UP			= 1<<16, /* volatile */
 	IFF_DORMANT			= 1<<17, /* volatile */
 	IFF_ECHO			= 1<<18, /* volatile */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 };
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 #define IFF_UP				IFF_UP
 #define IFF_BROADCAST			IFF_BROADCAST
 #define IFF_DEBUG			IFF_DEBUG
@@ -105,9 +119,13 @@ enum net_device_flags {
 #define IFF_PORTSEL			IFF_PORTSEL
 #define IFF_AUTOMEDIA			IFF_AUTOMEDIA
 #define IFF_DYNAMIC			IFF_DYNAMIC
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 #define IFF_LOWER_UP			IFF_LOWER_UP
 #define IFF_DORMANT			IFF_DORMANT
 #define IFF_ECHO			IFF_ECHO
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 
 #define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
 		IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
@@ -166,6 +184,8 @@ enum {
  *	being very small might be worth keeping for clean configuration.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFMAP
 struct ifmap {
 	unsigned long mem_start;
 	unsigned long mem_end;
@@ -175,6 +195,7 @@ struct ifmap {
 	unsigned char port;
 	/* 3 bytes spare */
 };
+#endif /* __UAPI_DEF_IF_IFMAP */
 
 struct if_settings {
 	unsigned int type;	/* Type of physical device or protocol */
@@ -200,6 +221,8 @@ struct if_settings {
  * remainder may be interface specific.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFREQ
 struct ifreq {
 #define IFHWADDRLEN	6
 	union
@@ -223,6 +246,7 @@ struct ifreq {
 		struct	if_settings ifru_settings;
 	} ifr_ifru;
 };
+#endif /* __UAPI_DEF_IF_IFREQ */
 
 #define ifr_name	ifr_ifrn.ifrn_name	/* interface name 	*/
 #define ifr_hwaddr	ifr_ifru.ifru_hwaddr	/* MAC address 		*/
@@ -249,6 +273,8 @@ struct ifreq {
  * must know all networks accessible).
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFCONF
 struct ifconf  {
 	int	ifc_len;			/* size of buffer	*/
 	union {
@@ -256,6 +282,8 @@ struct ifconf  {
 		struct ifreq __user *ifcu_req;
 	} ifc_ifcu;
 };
+#endif /* __UAPI_DEF_IF_IFCONF */
+
 #define	ifc_buf	ifc_ifcu.ifcu_buf		/* buffer address	*/
 #define	ifc_req	ifc_ifcu.ifcu_req		/* array of structures	*/
 
diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index f6598d1c886e..316e838b7470 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -34,7 +34,7 @@
 #define RTF_PREF(pref)	((pref) << 27)
 #define RTF_PREF_MASK	0x18000000
 
-#define RTF_PCPU	0x40000000
+#define RTF_PCPU	0x40000000	/* read-only: can not be set by user */
 #define RTF_LOCAL	0x80000000
 
 
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 7d024ceb075d..e4f048ee7043 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -51,6 +51,40 @@
 /* We have included glibc headers... */
 #if defined(__GLIBC__)
 
+/* Coordinate with glibc net/if.h header. */
+#if defined(_NET_IF_H) && defined(__USE_MISC)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+
+#define __UAPI_DEF_IF_IFCONF 0
+#define __UAPI_DEF_IF_IFMAP 0
+#define __UAPI_DEF_IF_IFNAMSIZ 0
+#define __UAPI_DEF_IF_IFREQ 0
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 0
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+
+#else /* _NET_IF_H */
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
+#endif /* _NET_IF_H */
+
 /* Coordinate with glibc netinet/in.h header. */
 #if defined(_NETINET_IN_H)
 
@@ -117,6 +151,16 @@
  * that we need. */
 #else /* !defined(__GLIBC__) */
 
+/* Definitions for if.h */
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
 /* Definitions for in.h */
 #define __UAPI_DEF_IN_ADDR		1
 #define __UAPI_DEF_IN_IPPROTO		1
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index f095155d8749..0dba4e4ed2be 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -107,8 +107,10 @@ struct nlmsgerr {
 #define NETLINK_PKTINFO			3
 #define NETLINK_BROADCAST_ERROR		4
 #define NETLINK_NO_ENOBUFS		5
+#ifndef __KERNEL__
 #define NETLINK_RX_RING			6
 #define NETLINK_TX_RING			7
+#endif
 #define NETLINK_LISTEN_ALL_NSID		8
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
@@ -134,6 +136,7 @@ struct nl_mmap_hdr {
 	__u32		nm_gid;
 };
 
+#ifndef __KERNEL__
 enum nl_mmap_status {
 	NL_MMAP_STATUS_UNUSED,
 	NL_MMAP_STATUS_RESERVED,
@@ -145,6 +148,7 @@ enum nl_mmap_status {
 #define NL_MMAP_MSG_ALIGNMENT		NLMSG_ALIGNTO
 #define NL_MMAP_MSG_ALIGN(sz)		__ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
 #define NL_MMAP_HDRLEN			NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
 
 #define NET_MAJOR 36		/* Major 36 is reserved for networking 						*/
 
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index f2159d30d1f5..d79399394b46 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -48,6 +48,8 @@ enum {
 
 #define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
 #define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
+#ifndef __KERNEL__
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
+#endif
 
 #endif
diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f3dd6f..0c5d5dd61b6a 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 123a5af4e8bb..fa3b34365560 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -343,7 +343,7 @@ struct rtnexthop {
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
 
 /* Macros to handle hexthops */
 
diff --git a/include/uapi/linux/usb/ch11.h b/include/uapi/linux/usb/ch11.h
index 331499d597fa..9ce10d4a0245 100644
--- a/include/uapi/linux/usb/ch11.h
+++ b/include/uapi/linux/usb/ch11.h
@@ -22,6 +22,9 @@
  */
 #define USB_MAXCHILDREN		31
 
+/* See USB 3.1 spec Table 10-5 */
+#define USB_SS_MAXPORTS		15
+
 /*
  * Hub request types
  */
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 4338eb7b09b3..779a62aafafe 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -954,6 +954,7 @@ enum usb_device_speed {
 	USB_SPEED_HIGH,				/* usb 2.0 */
 	USB_SPEED_WIRELESS,			/* wireless (usb 2.5) */
 	USB_SPEED_SUPER,			/* usb 3.0 */
+	USB_SPEED_SUPER_PLUS,			/* usb 3.1 */
 };
 
 
diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h
index c039f1d68a09..086168e18ca8 100644
--- a/include/uapi/linux/v4l2-dv-timings.h
+++ b/include/uapi/linux/v4l2-dv-timings.h
@@ -183,7 +183,8 @@
 
 #define V4L2_DV_BT_CEA_3840X2160P24 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 1276, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
@@ -191,14 +192,16 @@
 
 #define V4L2_DV_BT_CEA_3840X2160P25 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \
 }
 
 #define V4L2_DV_BT_CEA_3840X2160P30 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
@@ -206,14 +209,16 @@
 
 #define V4L2_DV_BT_CEA_3840X2160P50 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		594000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \
 }
 
 #define V4L2_DV_BT_CEA_3840X2160P60 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		594000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
@@ -221,7 +226,8 @@
 
 #define V4L2_DV_BT_CEA_4096X2160P24 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 1020, 88, 296, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
@@ -229,14 +235,16 @@
 
 #define V4L2_DV_BT_CEA_4096X2160P25 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \
 }
 
 #define V4L2_DV_BT_CEA_4096X2160P30 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		297000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
@@ -244,14 +252,16 @@
 
 #define V4L2_DV_BT_CEA_4096X2160P50 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		594000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \
 }
 
 #define V4L2_DV_BT_CEA_4096X2160P60 { \
 	.type = V4L2_DV_BT_656_1120, \
-	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \
+	V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \
+		V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \
 		594000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \
 		V4L2_DV_BT_STD_CEA861, \
 		V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index a0e87d16b726..421d27413731 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -621,6 +621,9 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_JPGL	v4l2_fourcc('J', 'P', 'G', 'L') /* JPEG-Lite */
 #define V4L2_PIX_FMT_SE401      v4l2_fourcc('S', '4', '0', '1') /* se401 janggu compressed rgb */
 #define V4L2_PIX_FMT_S5C_UYVY_JPG v4l2_fourcc('S', '5', 'C', 'I') /* S5C73M3 interleaved UYVY/JPEG */
+#define V4L2_PIX_FMT_Y8I      v4l2_fourcc('Y', '8', 'I', ' ') /* Greyscale 8-bit L/R interleaved */
+#define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */
+#define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */
 
 /* SDR formats - used only for Software Defined Radio devices */
 #define V4L2_SDR_FMT_CU8          v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */
diff --git a/include/uapi/scsi/cxlflash_ioctl.h b/include/uapi/scsi/cxlflash_ioctl.h
index 831351b2e660..2302f3ce5f86 100644
--- a/include/uapi/scsi/cxlflash_ioctl.h
+++ b/include/uapi/scsi/cxlflash_ioctl.h
@@ -31,6 +31,16 @@ struct dk_cxlflash_hdr {
 };
 
 /*
+ * Return flag definitions available to all ioctls
+ *
+ * Similar to the input flags, these are grown from the bottom-up with the
+ * intention that ioctl-specific return flag definitions would grow from the
+ * top-down, allowing the two sets to co-exist. While not required/enforced
+ * at this time, this provides future flexibility.
+ */
+#define DK_CXLFLASH_ALL_PORTS_ACTIVE	0x0000000000000001ULL
+
+/*
  * Notes:
  * -----
  * The 'context_id' field of all ioctl structures contains the context
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index eeba75395f7d..c8529ce28a3f 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -16,6 +16,7 @@
 #include <linux/videodev2.h>
 #include <linux/bitmap.h>
 #include <linux/fb.h>
+#include <linux/of.h>
 #include <media/v4l2-mediabus.h>
 #include <video/videomode.h>
 
@@ -344,6 +345,7 @@ struct ipu_client_platformdata {
 	int dc;
 	int dp;
 	int dma[2];
+	struct device_node *of_node;
 };
 
 #endif /* __DRM_IPU_H__ */
diff --git a/include/xen/page.h b/include/xen/page.h
index 96294ac93755..9dc46cb8a0fd 100644
--- a/include/xen/page.h
+++ b/include/xen/page.h
@@ -15,9 +15,9 @@
  */
 
 #define xen_pfn_to_page(xen_pfn)	\
-	((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT)))
+	(pfn_to_page((unsigned long)(xen_pfn) >> (PAGE_SHIFT - XEN_PAGE_SHIFT)))
 #define page_to_xen_pfn(page)		\
-	(((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT)
+	((page_to_pfn(page)) << (PAGE_SHIFT - XEN_PAGE_SHIFT))
 
 #define XEN_PFN_PER_PAGE	(PAGE_SIZE / XEN_PAGE_SIZE)
 
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 161a1807e6ef..5e24eb0ab5dd 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1251,8 +1251,10 @@ retry:
 
 			timeo = MAX_SCHEDULE_TIMEOUT;
 			ret = netlink_attachskb(sock, nc, &timeo, NULL);
-			if (ret == 1)
+			if (ret == 1) {
+				sock = NULL;
 				goto retry;
+			}
 			if (ret) {
 				sock = NULL;
 				nc = NULL;
diff --git a/ipc/msg.c b/ipc/msg.c
index 1471db9a7e61..c6521c205cb4 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -680,7 +680,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
 
-		ipc_rcu_putref(msq, ipc_rcu_free);
+		ipc_rcu_putref(msq, msg_rcu_free);
 		/* raced with RMID? */
 		if (!ipc_valid_object(&msq->q_perm)) {
 			err = -EIDRM;
diff --git a/ipc/sem.c b/ipc/sem.c
index b471e5a3863d..9862c3d1c26d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -155,14 +155,21 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
 
 /*
  * Locking:
+ * a) global sem_lock() for read/write
  *	sem_undo.id_next,
  *	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.complex_mode
+ *	sem_array.pending{_alter,_const},
+ *	sem_array.sem_undo
  *
+ * b) global or semaphore sem_lock() for read/write:
  *	sem_array.sem_base[i].pending_{const,alter}:
- *		global or semaphore sem_lock() for read/write
+ *	sem_array.complex_mode (for read)
+ *
+ * c) special:
+ *	sem_undo_list.list_proc:
+ *	* undo_list->lock for write
+ *	* rcu for read
  */
 
 #define sc_semmsl	sem_ctls[0]
@@ -263,24 +270,25 @@ static void sem_rcu_free(struct rcu_head *head)
 #define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
 
 /*
- * Wait until all currently ongoing simple ops have completed.
+ * Enter the mode suitable for non-simple operations:
  * 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)
+static void complexmode_enter(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.
-		 */
+	if (sma->complex_mode)  {
+		/* We are already in complex_mode. Nothing to do */
 		return;
 	}
 
+	/* We need a full barrier after seting complex_mode:
+	 * The write to complex_mode must be visible
+	 * before we read the first sem->lock spinlock state.
+	 */
+	smp_store_mb(sma->complex_mode, true);
+
 	for (i = 0; i < sma->sem_nsems; i++) {
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
@@ -289,6 +297,28 @@ static void sem_wait_array(struct sem_array *sma)
 }
 
 /*
+ * Try to leave the mode that disallows simple operations:
+ * Caller must own sem_perm.lock.
+ */
+static void complexmode_tryleave(struct sem_array *sma)
+{
+	if (sma->complex_count)  {
+		/* Complex ops are sleeping.
+		 * We must stay in complex mode
+		 */
+		return;
+	}
+	/*
+	 * Immediately after setting complex_mode to false,
+	 * a simple op can start. Thus: all memory writes
+	 * performed by the current operation must be visible
+	 * before we set complex_mode to false.
+	 */
+	smp_store_release(&sma->complex_mode, false);
+}
+
+#define SEM_GLOBAL_LOCK	(-1)
+/*
  * 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
@@ -304,56 +334,42 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 		/* Complex operation - acquire a full lock */
 		ipc_lock_object(&sma->sem_perm);
 
-		/* And wait until all simple ops that are processed
-		 * right now have dropped their locks.
-		 */
-		sem_wait_array(sma);
-		return -1;
+		/* Prevent parallel simple ops */
+		complexmode_enter(sma);
+		return SEM_GLOBAL_LOCK;
 	}
 
 	/*
 	 * 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.
+	 * Optimized locking is possible if no complex operation
+	 * is either enqueued or processed right now.
+	 *
+	 * Both facts are tracked by complex_mode.
 	 */
 	sem = sma->sem_base + sops->sem_num;
 
-	if (sma->complex_count == 0) {
+	/*
+	 * Initial check for complex_mode. Just an optimization,
+	 * no locking, no memory barrier.
+	 */
+	if (!sma->complex_mode) {
 		/*
 		 * It appears that no complex operation is around.
 		 * Acquire the per-semaphore lock.
 		 */
 		spin_lock(&sem->lock);
 
-		/* Then check that the global lock is free */
-		if (!spin_is_locked(&sma->sem_perm.lock)) {
-			/*
-			 * We need a memory barrier with acquire semantics,
-			 * otherwise we can race with another thread that does:
-			 *	complex_count++;
-			 *	spin_unlock(sem_perm.lock);
-			 */
-			ipc_smp_acquire__after_spin_is_unlocked();
+		/*
+		 * See 51d7d5205d33
+		 * ("powerpc: Add smp_mb() to arch_spin_is_locked()"):
+		 * A full barrier is required: the write of sem->lock
+		 * must be visible before the read is executed
+		 */
+		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;
-			}
+		if (!smp_load_acquire(&sma->complex_mode)) {
+			/* fast path successful! */
+			return sops->sem_num;
 		}
 		spin_unlock(&sem->lock);
 	}
@@ -373,15 +389,16 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 		/* Not a false alarm, thus complete the sequence for a
 		 * full lock.
 		 */
-		sem_wait_array(sma);
-		return -1;
+		complexmode_enter(sma);
+		return SEM_GLOBAL_LOCK;
 	}
 }
 
 static inline void sem_unlock(struct sem_array *sma, int locknum)
 {
-	if (locknum == -1) {
+	if (locknum == SEM_GLOBAL_LOCK) {
 		unmerge_queues(sma);
+		complexmode_tryleave(sma);
 		ipc_unlock_object(&sma->sem_perm);
 	} else {
 		struct sem *sem = sma->sem_base + locknum;
@@ -442,7 +459,7 @@ 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, ipc_rcu_free);
+	ipc_rcu_putref(sma, sem_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -533,6 +550,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	}
 
 	sma->complex_count = 0;
+	sma->complex_mode = true; /* dropped by sem_unlock below */
 	INIT_LIST_HEAD(&sma->pending_alter);
 	INIT_LIST_HEAD(&sma->pending_const);
 	INIT_LIST_HEAD(&sma->list_id);
@@ -1385,7 +1403,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			rcu_read_unlock();
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				return -ENOMEM;
 			}
 
@@ -1419,20 +1437,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		if (nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
-			ipc_rcu_putref(sma, ipc_rcu_free);
+			ipc_rcu_putref(sma, sem_rcu_free);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1722,7 +1740,7 @@ 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) {
-		ipc_rcu_putref(sma, ipc_rcu_free);
+		ipc_rcu_putref(sma, sem_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -2186,10 +2204,10 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 	/*
 	 * 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.
+	 * In order to stay compatible with sem_lock(), we must
+	 * enter / leave complex_mode.
 	 */
-	sem_wait_array(sma);
+	complexmode_enter(sma);
 
 	sem_otime = get_semotime(sma);
 
@@ -2206,6 +2224,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 		   sem_otime,
 		   sma->sem_ctime);
 
+	complexmode_tryleave(sma);
+
 	return 0;
 }
 #endif
diff --git a/ipc/shm.c b/ipc/shm.c
index 3174634ca4e5..4982a4e7f009 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1083,8 +1083,8 @@ out_unlock1:
  * "raddr" thing points to kernel space, and there has to be a wrapper around
  * this.
  */
-long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
-	      unsigned long shmlba)
+long do_shmat(int shmid, char __user *shmaddr, int shmflg,
+	      ulong *raddr, unsigned long shmlba)
 {
 	struct shmid_kernel *shp;
 	unsigned long addr;
@@ -1105,8 +1105,13 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 		goto out;
 	else if ((addr = (ulong)shmaddr)) {
 		if (addr & (shmlba - 1)) {
-			if (shmflg & SHM_RND)
-				addr &= ~(shmlba - 1);	   /* round down */
+			/*
+			 * Round down to the nearest multiple of shmlba.
+			 * For sane do_mmap_pgoff() parameters, avoid
+			 * round downs that trigger nil-page and MAP_FIXED.
+			 */
+			if ((shmflg & SHM_RND) && addr >= shmlba)
+				addr &= ~(shmlba - 1);
 			else
 #ifndef __ARCH_FORCE_SHMLBA
 				if (addr & ~PAGE_MASK)
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 656c7e93ac0d..a162661c9d60 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/file.h>
 #include <linux/kernel.h>
 #include <linux/audit.h>
 #include <linux/kthread.h>
@@ -456,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 	list_del(&krule->rlist);
 
 	if (list_empty(&watch->rules)) {
+		/*
+		 * audit_remove_watch() drops our reference to 'parent' which
+		 * can get freed. Grab our own reference to be safe.
+		 */
+		audit_get_parent(parent);
 		audit_remove_watch(watch);
-
-		if (list_empty(&parent->watches)) {
-			audit_get_parent(parent);
+		if (list_empty(&parent->watches))
 			fsnotify_destroy_mark(&parent->mark, audit_watch_group);
-			audit_put_parent(parent);
-		}
+		audit_put_parent(parent);
 	}
 }
 
@@ -544,10 +547,11 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	unsigned long ino;
 	dev_t dev;
 
-	rcu_read_lock();
-	exe_file = rcu_dereference(tsk->mm->exe_file);
+	exe_file = get_task_exe_file(tsk);
+	if (!exe_file)
+		return 0;
 	ino = exe_file->f_inode->i_ino;
 	dev = exe_file->f_inode->i_sb->s_dev;
-	rcu_read_unlock();
+	fput(exe_file);
 	return audit_mark_compare(mark, ino, dev);
 }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b86cc04959de..48f45987dc6c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -73,6 +73,7 @@
 #include <linux/compat.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
+#include <linux/uaccess.h>
 #include <uapi/linux/limits.h>
 
 #include "audit.h"
@@ -82,7 +83,8 @@
 #define AUDITSC_SUCCESS 1
 #define AUDITSC_FAILURE 2
 
-/* no execve audit message should be longer than this (userspace limits) */
+/* no execve audit message should be longer than this (userspace limits),
+ * see the note near the top of audit_log_execve_info() about this value */
 #define MAX_EXECVE_AUDIT_LEN 7500
 
 /* max length to print of cmdline/proctitle value during audit */
@@ -988,184 +990,178 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid,
 	return rc;
 }
 
-/*
- * to_send and len_sent accounting are very loose estimates.  We aren't
- * really worried about a hard cap to MAX_EXECVE_AUDIT_LEN so much as being
- * within about 500 bytes (next page boundary)
- *
- * why snprintf?  an int is up to 12 digits long.  if we just assumed when
- * logging that a[%d]= was going to be 16 characters long we would be wasting
- * space in every audit message.  In one 7500 byte message we can log up to
- * about 1000 min size arguments.  That comes down to about 50% waste of space
- * if we didn't do the snprintf to find out how long arg_num_len was.
- */
-static int audit_log_single_execve_arg(struct audit_context *context,
-					struct audit_buffer **ab,
-					int arg_num,
-					size_t *len_sent,
-					const char __user *p,
-					char *buf)
+static void audit_log_execve_info(struct audit_context *context,
+				  struct audit_buffer **ab)
 {
-	char arg_num_len_buf[12];
-	const char __user *tmp_p = p;
-	/* how many digits are in arg_num? 5 is the length of ' a=""' */
-	size_t arg_num_len = snprintf(arg_num_len_buf, 12, "%d", arg_num) + 5;
-	size_t len, len_left, to_send;
-	size_t max_execve_audit_len = MAX_EXECVE_AUDIT_LEN;
-	unsigned int i, has_cntl = 0, too_long = 0;
-	int ret;
-
-	/* strnlen_user includes the null we don't want to send */
-	len_left = len = strnlen_user(p, MAX_ARG_STRLEN) - 1;
-
-	/*
-	 * We just created this mm, if we can't find the strings
-	 * we just copied into it something is _very_ wrong. Similar
-	 * for strings that are too long, we should not have created
-	 * any.
-	 */
-	if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
-		send_sig(SIGKILL, current, 0);
-		return -1;
+	long len_max;
+	long len_rem;
+	long len_full;
+	long len_buf;
+	long len_abuf;
+	long len_tmp;
+	bool require_data;
+	bool encode;
+	unsigned int iter;
+	unsigned int arg;
+	char *buf_head;
+	char *buf;
+	const char __user *p = (const char __user *)current->mm->arg_start;
+
+	/* NOTE: this buffer needs to be large enough to hold all the non-arg
+	 *       data we put in the audit record for this argument (see the
+	 *       code below) ... at this point in time 96 is plenty */
+	char abuf[96];
+
+	/* NOTE: we set MAX_EXECVE_AUDIT_LEN to a rather arbitrary limit, the
+	 *       current value of 7500 is not as important as the fact that it
+	 *       is less than 8k, a setting of 7500 gives us plenty of wiggle
+	 *       room if we go over a little bit in the logging below */
+	WARN_ON_ONCE(MAX_EXECVE_AUDIT_LEN > 7500);
+	len_max = MAX_EXECVE_AUDIT_LEN;
+
+	/* scratch buffer to hold the userspace args */
+	buf_head = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
+	if (!buf_head) {
+		audit_panic("out of memory for argv string");
+		return;
 	}
+	buf = buf_head;
 
-	/* walk the whole argument looking for non-ascii chars */
+	audit_log_format(*ab, "argc=%d", context->execve.argc);
+
+	len_rem = len_max;
+	len_buf = 0;
+	len_full = 0;
+	require_data = true;
+	encode = false;
+	iter = 0;
+	arg = 0;
 	do {
-		if (len_left > MAX_EXECVE_AUDIT_LEN)
-			to_send = MAX_EXECVE_AUDIT_LEN;
-		else
-			to_send = len_left;
-		ret = copy_from_user(buf, tmp_p, to_send);
-		/*
-		 * There is no reason for this copy to be short. We just
-		 * copied them here, and the mm hasn't been exposed to user-
-		 * space yet.
-		 */
-		if (ret) {
-			WARN_ON(1);
-			send_sig(SIGKILL, current, 0);
-			return -1;
-		}
-		buf[to_send] = '\0';
-		has_cntl = audit_string_contains_control(buf, to_send);
-		if (has_cntl) {
-			/*
-			 * hex messages get logged as 2 bytes, so we can only
-			 * send half as much in each message
-			 */
-			max_execve_audit_len = MAX_EXECVE_AUDIT_LEN / 2;
-			break;
-		}
-		len_left -= to_send;
-		tmp_p += to_send;
-	} while (len_left > 0);
-
-	len_left = len;
-
-	if (len > max_execve_audit_len)
-		too_long = 1;
-
-	/* rewalk the argument actually logging the message */
-	for (i = 0; len_left > 0; i++) {
-		int room_left;
-
-		if (len_left > max_execve_audit_len)
-			to_send = max_execve_audit_len;
-		else
-			to_send = len_left;
-
-		/* do we have space left to send this argument in this ab? */
-		room_left = MAX_EXECVE_AUDIT_LEN - arg_num_len - *len_sent;
-		if (has_cntl)
-			room_left -= (to_send * 2);
-		else
-			room_left -= to_send;
-		if (room_left < 0) {
-			*len_sent = 0;
-			audit_log_end(*ab);
-			*ab = audit_log_start(context, GFP_KERNEL, AUDIT_EXECVE);
-			if (!*ab)
-				return 0;
-		}
+		/* NOTE: we don't ever want to trust this value for anything
+		 *       serious, but the audit record format insists we
+		 *       provide an argument length for really long arguments,
+		 *       e.g. > MAX_EXECVE_AUDIT_LEN, so we have no choice but
+		 *       to use strncpy_from_user() to obtain this value for
+		 *       recording in the log, although we don't use it
+		 *       anywhere here to avoid a double-fetch problem */
+		if (len_full == 0)
+			len_full = strnlen_user(p, MAX_ARG_STRLEN) - 1;
+
+		/* read more data from userspace */
+		if (require_data) {
+			/* can we make more room in the buffer? */
+			if (buf != buf_head) {
+				memmove(buf_head, buf, len_buf);
+				buf = buf_head;
+			}
+
+			/* fetch as much as we can of the argument */
+			len_tmp = strncpy_from_user(&buf_head[len_buf], p,
+						    len_max - len_buf);
+			if (len_tmp == -EFAULT) {
+				/* unable to copy from userspace */
+				send_sig(SIGKILL, current, 0);
+				goto out;
+			} else if (len_tmp == (len_max - len_buf)) {
+				/* buffer is not large enough */
+				require_data = true;
+				/* NOTE: if we are going to span multiple
+				 *       buffers force the encoding so we stand
+				 *       a chance at a sane len_full value and
+				 *       consistent record encoding */
+				encode = true;
+				len_full = len_full * 2;
+				p += len_tmp;
+			} else {
+				require_data = false;
+				if (!encode)
+					encode = audit_string_contains_control(
+								buf, len_tmp);
+				/* try to use a trusted value for len_full */
+				if (len_full < len_max)
+					len_full = (encode ?
+						    len_tmp * 2 : len_tmp);
+				p += len_tmp + 1;
+			}
+			len_buf += len_tmp;
+			buf_head[len_buf] = '\0';
 
-		/*
-		 * first record needs to say how long the original string was
-		 * so we can be sure nothing was lost.
-		 */
-		if ((i == 0) && (too_long))
-			audit_log_format(*ab, " a%d_len=%zu", arg_num,
-					 has_cntl ? 2*len : len);
-
-		/*
-		 * normally arguments are small enough to fit and we already
-		 * filled buf above when we checked for control characters
-		 * so don't bother with another copy_from_user
-		 */
-		if (len >= max_execve_audit_len)
-			ret = copy_from_user(buf, p, to_send);
-		else
-			ret = 0;
-		if (ret) {
-			WARN_ON(1);
-			send_sig(SIGKILL, current, 0);
-			return -1;
+			/* length of the buffer in the audit record? */
+			len_abuf = (encode ? len_buf * 2 : len_buf + 2);
 		}
-		buf[to_send] = '\0';
-
-		/* actually log it */
-		audit_log_format(*ab, " a%d", arg_num);
-		if (too_long)
-			audit_log_format(*ab, "[%d]", i);
-		audit_log_format(*ab, "=");
-		if (has_cntl)
-			audit_log_n_hex(*ab, buf, to_send);
-		else
-			audit_log_string(*ab, buf);
-
-		p += to_send;
-		len_left -= to_send;
-		*len_sent += arg_num_len;
-		if (has_cntl)
-			*len_sent += to_send * 2;
-		else
-			*len_sent += to_send;
-	}
-	/* include the null we didn't log */
-	return len + 1;
-}
 
-static void audit_log_execve_info(struct audit_context *context,
-				  struct audit_buffer **ab)
-{
-	int i, len;
-	size_t len_sent = 0;
-	const char __user *p;
-	char *buf;
+		/* write as much as we can to the audit log */
+		if (len_buf > 0) {
+			/* NOTE: some magic numbers here - basically if we
+			 *       can't fit a reasonable amount of data into the
+			 *       existing audit buffer, flush it and start with
+			 *       a new buffer */
+			if ((sizeof(abuf) + 8) > len_rem) {
+				len_rem = len_max;
+				audit_log_end(*ab);
+				*ab = audit_log_start(context,
+						      GFP_KERNEL, AUDIT_EXECVE);
+				if (!*ab)
+					goto out;
+			}
 
-	p = (const char __user *)current->mm->arg_start;
+			/* create the non-arg portion of the arg record */
+			len_tmp = 0;
+			if (require_data || (iter > 0) ||
+			    ((len_abuf + sizeof(abuf)) > len_rem)) {
+				if (iter == 0) {
+					len_tmp += snprintf(&abuf[len_tmp],
+							sizeof(abuf) - len_tmp,
+							" a%d_len=%lu",
+							arg, len_full);
+				}
+				len_tmp += snprintf(&abuf[len_tmp],
+						    sizeof(abuf) - len_tmp,
+						    " a%d[%d]=", arg, iter++);
+			} else
+				len_tmp += snprintf(&abuf[len_tmp],
+						    sizeof(abuf) - len_tmp,
+						    " a%d=", arg);
+			WARN_ON(len_tmp >= sizeof(abuf));
+			abuf[sizeof(abuf) - 1] = '\0';
+
+			/* log the arg in the audit record */
+			audit_log_format(*ab, "%s", abuf);
+			len_rem -= len_tmp;
+			len_tmp = len_buf;
+			if (encode) {
+				if (len_abuf > len_rem)
+					len_tmp = len_rem / 2; /* encoding */
+				audit_log_n_hex(*ab, buf, len_tmp);
+				len_rem -= len_tmp * 2;
+				len_abuf -= len_tmp * 2;
+			} else {
+				if (len_abuf > len_rem)
+					len_tmp = len_rem - 2; /* quotes */
+				audit_log_n_string(*ab, buf, len_tmp);
+				len_rem -= len_tmp + 2;
+				/* don't subtract the "2" because we still need
+				 * to add quotes to the remaining string */
+				len_abuf -= len_tmp;
+			}
+			len_buf -= len_tmp;
+			buf += len_tmp;
+		}
 
-	audit_log_format(*ab, "argc=%d", context->execve.argc);
+		/* ready to move to the next argument? */
+		if ((len_buf == 0) && !require_data) {
+			arg++;
+			iter = 0;
+			len_full = 0;
+			require_data = true;
+			encode = false;
+		}
+	} while (arg < context->execve.argc);
 
-	/*
-	 * we need some kernel buffer to hold the userspace args.  Just
-	 * allocate one big one rather than allocating one of the right size
-	 * for every single argument inside audit_log_single_execve_arg()
-	 * should be <8k allocation so should be pretty safe.
-	 */
-	buf = kmalloc(MAX_EXECVE_AUDIT_LEN + 1, GFP_KERNEL);
-	if (!buf) {
-		audit_panic("out of memory for argv string");
-		return;
-	}
+	/* NOTE: the caller handles the final audit_log_end() call */
 
-	for (i = 0; i < context->execve.argc; i++) {
-		len = audit_log_single_execve_arg(context, ab, i,
-						  &len_sent, p, buf);
-		if (len <= 0)
-			break;
-		p += len;
-	}
-	kfree(buf);
+out:
+	kfree(buf_head);
 }
 
 static void show_special(struct audit_context *context, int *call_panic)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 4504ca66118d..50da680c479f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
 	if (!task)
 		return -EINVAL;
 
-	memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+	strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
 	return 0;
 }
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 5a8a797d50b7..cb85d228b1ac 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_inc(raw, true);
+		raw = bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -277,7 +277,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		goto out;
 
 	raw = bpf_any_get(inode->i_private, *type);
-	touch_atime(&path);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
 
 	path_put(&path);
 	return raw;
@@ -357,7 +358,7 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 static struct dentry *bpf_mount(struct file_system_type *type, int flags,
 				const char *dev_name, void *data)
 {
-	return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super);
+	return mount_nodev(type, flags, data, bpf_fill_super);
 }
 
 static struct file_system_type bpf_fs_type = {
@@ -365,7 +366,6 @@ static struct file_system_type bpf_fs_type = {
 	.name		= "bpf",
 	.mount		= bpf_mount,
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 MODULE_ALIAS_FS("bpf");
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3b39550d8485..4e32cc94edd9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -181,11 +181,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 {
-	atomic_inc(&map->refcnt);
+	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&map->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
 	if (uref)
 		atomic_inc(&map->usercnt);
+	return map;
 }
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -197,7 +204,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	bpf_map_inc(map, true);
+	map = bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -580,6 +587,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&prog->aux->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
+	return prog;
+}
+
 /* called by sockets/tracing/seccomp before attaching program to an event
  * pairs with bpf_prog_put()
  */
@@ -592,7 +608,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	if (IS_ERR(prog))
 		return prog;
 
-	atomic_inc(&prog->aux->refcnt);
+	prog = bpf_prog_inc(prog);
 	fdput(f);
 
 	return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2e7f7ab739e4..863e24f1e62e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -239,15 +239,6 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
-static const struct {
-	int map_type;
-	int func_id;
-} func_limit[] = {
-	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
-};
-
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -763,6 +754,11 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
 	if (err)
 		return err;
 
+	if (is_pointer_value(env, insn->src_reg)) {
+		verbose("R%d leaks addr into mem\n", insn->src_reg);
+		return -EACCES;
+	}
+
 	/* check whether atomic_add can read the memory */
 	err = check_mem_access(env, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_READ, -1);
@@ -898,24 +894,44 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 {
-	bool bool_map, bool_func;
-	int i;
-
 	if (!map)
 		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
-		bool_map = (map->map_type == func_limit[i].map_type);
-		bool_func = (func_id == func_limit[i].func_id);
-		/* only when map & func pair match it can continue.
-		 * don't allow any other map type to be passed into
-		 * the special func;
-		 */
-		if (bool_func && bool_map != bool_func)
-			return -EINVAL;
+	/* We need a two way check, first is from map perspective ... */
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_PROG_ARRAY:
+		if (func_id != BPF_FUNC_tail_call)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		if (func_id != BPF_FUNC_perf_event_read &&
+		    func_id != BPF_FUNC_perf_event_output)
+			goto error;
+		break;
+	default:
+		break;
+	}
+
+	/* ... and second from the function itself. */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_perf_event_read:
+	case BPF_FUNC_perf_event_output:
+		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+			goto error;
+		break;
+	default:
+		break;
 	}
 
 	return 0;
+error:
+	verbose("cannot pass map_type %d into func %d\n",
+		map->map_type, func_id);
+	return -EINVAL;
 }
 
 static int check_call(struct verifier_env *env, int func_id)
@@ -1348,6 +1364,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;
@@ -2003,7 +2020,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			if (IS_ERR(map)) {
 				verbose("fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
-				fdput(f);
 				return PTR_ERR(map);
 			}
 
@@ -2023,15 +2039,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return -E2BIG;
 			}
 
-			/* remember this map */
-			env->used_maps[env->used_map_cnt++] = map;
-
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			bpf_map_inc(map, false);
+			map = bpf_map_inc(map, false);
+			if (IS_ERR(map)) {
+				fdput(f);
+				return PTR_ERR(map);
+			}
+			env->used_maps[env->used_map_cnt++] = map;
+
 			fdput(f);
 next_insn:
 			insn++;
diff --git a/kernel/capability.c b/kernel/capability.c
index 45432b54d5c6..4984e1f552eb 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
 	return has_ns_capability_noaudit(t, &init_user_ns, cap);
 }
 
+static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit)
+{
+	int capable;
+
+	if (unlikely(!cap_valid(cap))) {
+		pr_crit("capable() called with invalid cap=%u\n", cap);
+		BUG();
+	}
+
+	capable = audit ? security_capable(current_cred(), ns, cap) :
+			  security_capable_noaudit(current_cred(), ns, cap);
+	if (capable == 0) {
+		current->flags |= PF_SUPERPRIV;
+		return true;
+	}
+	return false;
+}
+
 /**
  * ns_capable - Determine if the current task has a superior capability in effect
  * @ns:  The usernamespace we want the capability in
@@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
  */
 bool ns_capable(struct user_namespace *ns, int cap)
 {
-	if (unlikely(!cap_valid(cap))) {
-		pr_crit("capable() called with invalid cap=%u\n", cap);
-		BUG();
-	}
-
-	if (security_capable(current_cred(), ns, cap) == 0) {
-		current->flags |= PF_SUPERPRIV;
-		return true;
-	}
-	return false;
+	return ns_capable_common(ns, cap, true);
 }
 EXPORT_SYMBOL(ns_capable);
 
+/**
+ * ns_capable_noaudit - Determine if the current task has a superior capability
+ * (unaudited) in effect
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+	return ns_capable_common(ns, cap, false);
+}
+EXPORT_SYMBOL(ns_capable_noaudit);
 
 /**
  * capable - Determine if the current task has a superior capability in effect
@@ -431,6 +457,19 @@ bool file_ns_capable(const struct file *file, struct user_namespace *ns,
 EXPORT_SYMBOL(file_ns_capable);
 
 /**
+ * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode?
+ * @ns: The user namespace in question
+ * @inode: The inode in question
+ *
+ * Return true if the inode uid and gid are within the namespace.
+ */
+bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode)
+{
+	return kuid_has_mapping(ns, inode->i_uid) &&
+		kgid_has_mapping(ns, inode->i_gid);
+}
+
+/**
  * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
@@ -443,7 +482,26 @@ 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) &&
-		kgid_has_mapping(ns, inode->i_gid);
+	return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode);
 }
 EXPORT_SYMBOL(capable_wrt_inode_uidgid);
+
+/**
+ * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace
+ * @tsk: The task that may be ptraced
+ * @ns: The user namespace to search for CAP_SYS_PTRACE in
+ *
+ * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE
+ * in the specified user namespace.
+ */
+bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
+{
+	int ret = 0;  /* An absent tracer adds no restrictions */
+	const struct cred *cred;
+	rcu_read_lock();
+	cred = rcu_dereference(tsk->ptracer_cred);
+	if (cred)
+		ret = security_capable_noaudit(cred, ns, CAP_SYS_PTRACE);
+	rcu_read_unlock();
+	return (ret == 0);
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fb1ecfd2decd..4cb94b678e9f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -236,6 +236,9 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
  */
 static bool cgroup_ssid_enabled(int ssid)
 {
+	if (CGROUP_SUBSYS_COUNT == 0)
+		return false;
+
 	return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
 }
 
@@ -2498,6 +2501,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
 	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
+	/*
+	 * If ->dead, @src_set is associated with one or more dead cgroups
+	 * and doesn't contain any migratable tasks.  Ignore it early so
+	 * that the rest of migration path doesn't get confused by it.
+	 */
+	if (src_cset->dead)
+		return;
+
 	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
 	if (!list_empty(&src_cset->mg_preload_node))
@@ -2713,9 +2724,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 				    size_t nbytes, loff_t off, bool threadgroup)
 {
 	struct task_struct *tsk;
+	struct cgroup_subsys *ss;
 	struct cgroup *cgrp;
 	pid_t pid;
-	int ret;
+	int ssid, ret;
 
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return -EINVAL;
@@ -2740,11 +2752,12 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 		tsk = tsk->group_leader;
 
 	/*
-	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
-	 * trapped in a cpuset, or RT worker may be born in a cgroup
-	 * with no rt_runtime allocated.  Just say no.
+	 * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+	 * If userland migrates such a kthread to a non-root cgroup, it can
+	 * become trapped in a cpuset, or RT kthread may be born in a
+	 * cgroup with no rt_runtime allocated.  Just say no.
 	 */
-	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+	if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		goto out_unlock_rcu;
 	}
@@ -2763,8 +2776,10 @@ out_unlock_rcu:
 	rcu_read_unlock();
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	for_each_subsys(ss, ssid)
+		if (ss->post_attach)
+			ss->post_attach();
 	cgroup_kn_unlock(of->kn);
-	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
@@ -4681,14 +4696,15 @@ static void css_free_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css free path */
+		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
 
-		if (css->parent)
-			css_put(css->parent);
-
 		ss->css_free(css);
 		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
+
+		if (parent)
+			css_put(parent);
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
@@ -4781,6 +4797,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	memset(css, 0, sizeof(*css));
 	css->cgroup = cgrp;
 	css->ss = ss;
+	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
@@ -5131,6 +5148,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
 	struct cgroup_subsys_state *css;
+	struct cgrp_cset_link *link;
 	int ssid;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -5151,11 +5169,18 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 		return -EBUSY;
 
 	/*
-	 * Mark @cgrp dead.  This prevents further task migration and child
-	 * creation by disabling cgroup_lock_live_group().
+	 * Mark @cgrp and the associated csets dead.  The former prevents
+	 * further task migration and child creation by disabling
+	 * cgroup_lock_live_group().  The latter makes the csets ignored by
+	 * the migration path.
 	 */
 	cgrp->self.flags &= ~CSS_ONLINE;
 
+	spin_lock_bh(&css_set_lock);
+	list_for_each_entry(link, &cgrp->cset_links, cset_link)
+		link->cset->dead = true;
+	spin_unlock_bh(&css_set_lock);
+
 	/* initiate massacre of all css's */
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config
index c2de56ab0fce..7fa0c4ae6394 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -1,4 +1,12 @@
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
 CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
 CONFIG_SLOB=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 85ff5e26e23b..40d20bf5de28 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -223,12 +223,6 @@ static int cpu_notify(unsigned long val, void *v)
 	return __cpu_notify(val, v, -1, NULL);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void cpu_notify_nofail(unsigned long val, void *v)
-{
-	BUG_ON(cpu_notify(val, v));
-}
 EXPORT_SYMBOL(register_cpu_notifier);
 EXPORT_SYMBOL(__register_cpu_notifier);
 
@@ -246,6 +240,12 @@ void __unregister_cpu_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(__unregister_cpu_notifier);
 
+#ifdef CONFIG_HOTPLUG_CPU
+static void cpu_notify_nofail(unsigned long val, void *v)
+{
+	BUG_ON(cpu_notify(val, v));
+}
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 2ade632197d5..2924b6faa469 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -57,10 +57,10 @@
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+struct static_key cpusets_pre_enable_key __read_mostly = STATIC_KEY_INIT_FALSE;
 struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
 
 /* See "Frequency meter" comments, below. */
@@ -174,9 +174,9 @@ typedef enum {
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
 {
-	return test_bit(CS_ONLINE, &cs->flags);
+	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
 }
 
 static inline int is_cpu_exclusive(const struct cpuset *cs)
@@ -325,8 +325,7 @@ static struct file_system_type cpuset_fs_type = {
 /*
  * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.  The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
@@ -335,8 +334,20 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
 		cs = parent_cs(cs);
+		if (unlikely(!cs)) {
+			/*
+			 * The top cpuset doesn't have any online cpu as a
+			 * consequence of a race between cpuset_hotplug_work
+			 * and cpu hotplug notifier.  But we know the top
+			 * cpuset's effective_cpus is on its way to to be
+			 * identical to cpu_online_mask.
+			 */
+			cpumask_copy(pmask, cpu_online_mask);
+			return;
+		}
+	}
 	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
@@ -1015,7 +1026,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 	}
 }
 
-void cpuset_post_attach_flush(void)
+static void cpuset_post_attach(void)
 {
 	flush_workqueue(cpuset_migrate_mm_wq);
 }
@@ -1899,6 +1910,7 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
+		.private = FILE_MEMORY_PRESSURE,
 	},
 
 	{
@@ -2075,6 +2087,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&cpuset_mutex);
 }
 
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+void cpuset_fork(struct task_struct *task, void *priv)
+{
+	if (task_css_is_root(task, cpuset_cgrp_id))
+		return;
+
+	set_cpus_allowed_ptr(task, &current->cpus_allowed);
+	task->mems_allowed = current->mems_allowed;
+}
+
 struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc	= cpuset_css_alloc,
 	.css_online	= cpuset_css_online,
@@ -2083,7 +2109,9 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.can_attach	= cpuset_can_attach,
 	.cancel_attach	= cpuset_cancel_attach,
 	.attach		= cpuset_attach,
+	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
+	.fork		= cpuset_fork,
 	.legacy_cftypes	= files,
 	.early_init	= 1,
 };
diff --git a/kernel/cred.c b/kernel/cred.c
index 71179a09c1d6..ff8606f77d90 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -689,6 +689,8 @@ EXPORT_SYMBOL(set_security_override_from_ctx);
  */
 int set_create_files_as(struct cred *new, struct inode *inode)
 {
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EINVAL;
 	new->fsuid = inode->i_uid;
 	new->fsgid = inode->i_gid;
 	return security_kernel_create_files_as(new, inode);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0874e2edd275..79517e5549f1 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -598,11 +598,11 @@ return_normal:
 	/*
 	 * Wait for the other CPUs to be notified and be waiting for us:
 	 */
-	time_left = loops_per_jiffy * HZ;
+	time_left = MSEC_PER_SEC;
 	while (kgdb_do_roundup && --time_left &&
 	       (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) !=
 		   online_cpus)
-		cpu_relax();
+		udelay(1000);
 	if (!time_left)
 		pr_crit("Timed out waiting for secondary CPUs.\n");
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1087bbeb152b..3697063dd09a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -946,6 +946,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
+ *    cred_guard_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event_context::lock
@@ -1538,12 +1539,33 @@ static int __init perf_workqueue_init(void)
 
 core_initcall(perf_workqueue_init);
 
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+	struct perf_event *child;
+
+	if (!__pmu_filter_match(event))
+		return 0;
+
+	list_for_each_entry(child, &event->sibling_list, group_entry) {
+		if (!__pmu_filter_match(child))
+			return 0;
+	}
+
+	return 1;
+}
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
@@ -1580,14 +1602,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -3418,7 +3440,6 @@ static struct task_struct *
 find_lively_task_by_vpid(pid_t vpid)
 {
 	struct task_struct *task;
-	int err;
 
 	rcu_read_lock();
 	if (!vpid)
@@ -3432,16 +3453,7 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/* Reuse ptrace permission checks for now. */
-	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
-		goto errout;
-
 	return task;
-errout:
-	put_task_struct(task);
-	return ERR_PTR(err);
-
 }
 
 /*
@@ -6027,6 +6039,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	char *buf = NULL;
 	char *name;
 
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	if (vma->vm_flags & VM_MAYSHARE)
+		flags = MAP_SHARED;
+	else
+		flags = MAP_PRIVATE;
+
+	if (vma->vm_flags & VM_DENYWRITE)
+		flags |= MAP_DENYWRITE;
+	if (vma->vm_flags & VM_MAYEXEC)
+		flags |= MAP_EXECUTABLE;
+	if (vma->vm_flags & VM_LOCKED)
+		flags |= MAP_LOCKED;
+	if (vma->vm_flags & VM_HUGETLB)
+		flags |= MAP_HUGETLB;
+
 	if (file) {
 		struct inode *inode;
 		dev_t dev;
@@ -6053,27 +6086,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		maj = MAJOR(dev);
 		min = MINOR(dev);
 
-		if (vma->vm_flags & VM_READ)
-			prot |= PROT_READ;
-		if (vma->vm_flags & VM_WRITE)
-			prot |= PROT_WRITE;
-		if (vma->vm_flags & VM_EXEC)
-			prot |= PROT_EXEC;
-
-		if (vma->vm_flags & VM_MAYSHARE)
-			flags = MAP_SHARED;
-		else
-			flags = MAP_PRIVATE;
-
-		if (vma->vm_flags & VM_DENYWRITE)
-			flags |= MAP_DENYWRITE;
-		if (vma->vm_flags & VM_MAYEXEC)
-			flags |= MAP_EXECUTABLE;
-		if (vma->vm_flags & VM_LOCKED)
-			flags |= MAP_LOCKED;
-		if (vma->vm_flags & VM_HUGETLB)
-			flags |= MAP_HUGETLB;
-
 		goto got_name;
 	} else {
 		if (vma->vm_ops && vma->vm_ops->name) {
@@ -7110,7 +7122,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put(prog);
+		bpf_prog_put_rcu(prog);
 	}
 }
 
@@ -7979,6 +7991,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		}
 	}
 
+	/* symmetric to unaccount_event() in _free_event() */
+	account_event(event);
+
 	return event;
 
 err_per_task:
@@ -8235,6 +8250,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
 	return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+			     struct perf_event_context *ctx)
+{
+	struct perf_event_context *gctx;
+
+again:
+	rcu_read_lock();
+	gctx = READ_ONCE(group_leader->ctx);
+	if (!atomic_inc_not_zero(&gctx->refcount)) {
+		rcu_read_unlock();
+		goto again;
+	}
+	rcu_read_unlock();
+
+	mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+	if (group_leader->ctx != gctx) {
+		mutex_unlock(&ctx->mutex);
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
+		goto again;
+	}
+
+	return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -8325,6 +8371,24 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	get_online_cpus();
 
+	if (task) {
+		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		if (err)
+			goto err_cpus;
+
+		/*
+		 * Reuse ptrace permission checks for now.
+		 *
+		 * We must hold cred_guard_mutex across this and any potential
+		 * perf_install_in_context() call for this new event to
+		 * serialize against exec() altering our credentials (and the
+		 * perf_event_exit_task() that could imply).
+		 */
+		err = -EACCES;
+		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+			goto err_cred;
+	}
+
 	if (flags & PERF_FLAG_PID_CGROUP)
 		cgroup_fd = pid;
 
@@ -8332,7 +8396,7 @@ SYSCALL_DEFINE5(perf_event_open,
 				 NULL, NULL, cgroup_fd);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_cpus;
+		goto err_cred;
 	}
 
 	if (is_sampling_event(event)) {
@@ -8342,8 +8406,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	account_event(event);
-
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -8393,11 +8455,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
-	if (task) {
-		put_task_struct(task);
-		task = NULL;
-	}
-
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -8416,28 +8473,27 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 
 		/*
-		 * Do not allow to attach to a group in a different
-		 * task or CPU context:
+		 * Make sure we're both events for the same CPU;
+		 * grouping events for different CPUs is broken; since
+		 * you can never concurrently schedule them anyhow.
 		 */
-		if (move_group) {
-			/*
-			 * Make sure we're both on the same task, or both
-			 * per-cpu events.
-			 */
-			if (group_leader->ctx->task != ctx->task)
-				goto err_context;
+		if (group_leader->cpu != event->cpu)
+			goto err_context;
 
-			/*
-			 * Make sure we're both events for the same CPU;
-			 * grouping events for different CPUs is broken; since
-			 * you can never concurrently schedule them anyhow.
-			 */
-			if (group_leader->cpu != event->cpu)
-				goto err_context;
-		} else {
-			if (group_leader->ctx != ctx)
-				goto err_context;
-		}
+		/*
+		 * Make sure we're both on the same task, or both
+		 * per-CPU events.
+		 */
+		if (group_leader->ctx->task != ctx->task)
+			goto err_context;
+
+		/*
+		 * Do not allow to attach to a group in a different task
+		 * or CPU context. If we're moving SW events, we'll fix
+		 * this up later, so allow that.
+		 */
+		if (!move_group && group_leader->ctx != ctx)
+			goto err_context;
 
 		/*
 		 * Only a group leader can be exclusive or pinned
@@ -8460,8 +8516,26 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (move_group) {
-		gctx = group_leader->ctx;
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+		/*
+		 * Check if we raced against another sys_perf_event_open() call
+		 * moving the software group underneath us.
+		 */
+		if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			/*
+			 * If someone moved the group out from under us, check
+			 * if this new event wound up on the same ctx, if so
+			 * its the regular !move_group case, otherwise fail.
+			 */
+			if (gctx != ctx) {
+				err = -EINVAL;
+				goto err_locked;
+			} else {
+				perf_event_ctx_unlock(group_leader, gctx);
+				move_group = 0;
+			}
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -8485,6 +8559,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 
+	/*
+	 * This is the point on no return; we cannot fail hereafter. This is
+	 * where we start modifying current state.
+	 */
+
 	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
@@ -8551,9 +8630,14 @@ SYSCALL_DEFINE5(perf_event_open,
 	perf_unpin_context(ctx);
 
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 
+	if (task) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		put_task_struct(task);
+	}
+
 	put_online_cpus();
 
 	event->owner = current;
@@ -8574,7 +8658,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
 	if (move_group)
-		mutex_unlock(&gctx->mutex);
+		perf_event_ctx_unlock(group_leader, gctx);
 	mutex_unlock(&ctx->mutex);
 /* err_file: */
 	fput(event_file);
@@ -8582,7 +8666,15 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
+err_cred:
+	if (task)
+		mutex_unlock(&task->signal->cred_guard_mutex);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8626,8 +8718,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = EVENT_OWNER_KERNEL;
 
-	account_event(event);
-
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -8864,6 +8954,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 
 /*
  * When a child task exits, feed back event values to parent events.
+ *
+ * Can be called with cred_guard_mutex held when called from
+ * install_exec_creds().
  */
 void perf_event_exit_task(struct task_struct *child)
 {
@@ -9185,7 +9278,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	/*
@@ -9201,7 +9294,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
 		if (ret)
-			break;
+			goto out_unlock;
 	}
 
 	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -9229,6 +9322,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 	}
 
 	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
 	mutex_unlock(&parent_ctx->mutex);
 
 	perf_unpin_context(parent_ctx);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index adfdc0536117..014b69528194 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -347,6 +347,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 			 bool truncated)
 {
 	struct ring_buffer *rb = handle->rb;
+	bool wakeup = truncated;
 	unsigned long aux_head;
 	u64 flags = 0;
 
@@ -375,9 +376,16 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
 	aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
 
 	if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) {
-		perf_output_wakeup(handle);
+		wakeup = true;
 		local_add(rb->aux_watermark, &rb->aux_wakeup);
 	}
+
+	if (wakeup) {
+		if (truncated)
+			handle->event->pending_disable = 1;
+		perf_output_wakeup(handle);
+	}
+
 	handle->event = NULL;
 
 	local_set(&rb->aux_nest, 0);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 7dad84913abf..da0c09ff6112 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -171,8 +171,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr);
@@ -199,7 +201,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
diff --git a/kernel/exit.c b/kernel/exit.c
index 07110c6020a0..ffba5df4abd5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -918,17 +918,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 		task_pid_type(p, wo->wo_type) == wo->wo_pid;
 }
 
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int
+eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p)
 {
 	if (!eligible_pid(wo, p))
 		return 0;
-	/* Wait for all children (clone and not) if __WALL is set;
-	 * otherwise, wait for clone children *only* if __WCLONE is
-	 * set; otherwise, wait for non-clone children *only*.  (Note:
-	 * A "clone" child here is one that reports to its parent
-	 * using a signal other than SIGCHLD.) */
-	if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
-	    && !(wo->wo_flags & __WALL))
+
+	/*
+	 * Wait for all children (clone and not) if __WALL is set or
+	 * if it is traced by us.
+	 */
+	if (ptrace || (wo->wo_flags & __WALL))
+		return 1;
+
+	/*
+	 * Otherwise, wait for clone children *only* if __WCLONE is set;
+	 * otherwise, wait for non-clone children *only*.
+	 *
+	 * Note: a "clone" child here is one that reports to its parent
+	 * using a signal other than SIGCHLD, or a non-leader thread which
+	 * we can only see if it is traced by us.
+	 */
+	if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
 		return 0;
 
 	return 1;
@@ -1301,7 +1312,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	if (unlikely(exit_state == EXIT_DEAD))
 		return 0;
 
-	ret = eligible_child(wo, p);
+	ret = eligible_child(wo, ptrace, p);
 	if (!ret)
 		return ret;
 
diff --git a/kernel/extable.c b/kernel/extable.c
index e820ccee9846..4f06fc34313f 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr)
 	return 0;
 }
 
-int core_kernel_text(unsigned long addr)
+int notrace core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
 	    addr < (unsigned long)_etext)
diff --git a/kernel/fork.c b/kernel/fork.c
index 1155eac61687..68cfda1c1800 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -331,13 +331,14 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 }
 
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	int node = tsk_fork_get_node(orig);
 	int err;
 
+	if (node == NUMA_NO_NODE)
+		node = tsk_fork_get_node(orig);
 	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
@@ -367,7 +368,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	set_task_stack_end_magic(tsk);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
-	tsk->stack_canary = get_random_int();
+	tsk->stack_canary = get_random_long();
 #endif
 
 	/*
@@ -585,7 +586,8 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 #endif
 }
 
-static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
+static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
+	struct user_namespace *user_ns)
 {
 	mm->mmap = NULL;
 	mm->mm_rb = RB_ROOT;
@@ -625,6 +627,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	if (init_new_context(p, mm))
 		goto fail_nocontext;
 
+	mm->user_ns = get_user_ns(user_ns);
 	return mm;
 
 fail_nocontext:
@@ -670,7 +673,7 @@ struct mm_struct *mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	return mm_init(mm, current);
+	return mm_init(mm, current, current_user_ns());
 }
 
 /*
@@ -685,6 +688,7 @@ void __mmdrop(struct mm_struct *mm)
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
 	check_mm(mm);
+	put_user_ns(mm->user_ns);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -764,6 +768,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
 EXPORT_SYMBOL(get_mm_exe_file);
 
 /**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+	struct file *exe_file = NULL;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm) {
+		if (!(task->flags & PF_KTHREAD))
+			exe_file = get_mm_exe_file(mm);
+	}
+	task_unlock(task);
+	return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
+/**
  * get_task_mm - acquire a reference to the task's mm
  *
  * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
@@ -878,14 +905,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * If we're exiting normally, clear a user-space tid field if
-	 * requested.  We leave this alone when dying by signal, to leave
-	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
@@ -921,7 +946,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 
 	memcpy(mm, oldmm, sizeof(*mm));
 
-	if (!mm_init(mm, tsk))
+	if (!mm_init(mm, tsk, mm->user_ns))
 		goto fail_nomem;
 
 	err = dup_mmap(mm, oldmm);
@@ -1246,7 +1271,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
-					unsigned long tls)
+					unsigned long tls,
+					int node)
 {
 	int retval;
 	struct task_struct *p;
@@ -1299,7 +1325,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	retval = -ENOMEM;
-	p = dup_task_struct(current);
+	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
 
@@ -1369,7 +1395,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1521,6 +1546,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1564,11 +1590,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	*/
 	recalc_sigpending();
 	if (signal_pending(current)) {
-		spin_unlock(&current->sighand->siglock);
-		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
 		goto bad_fork_cancel_cgroup;
 	}
+	if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+		retval = -ENOMEM;
+		goto bad_fork_cancel_cgroup;
+	}
 
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1619,8 +1647,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	return p;
 
 bad_fork_cancel_cgroup:
+	spin_unlock(&current->sighand->siglock);
+	write_unlock_irq(&tasklist_lock);
 	cgroup_cancel_fork(p, cgrp_ss_priv);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_io:
@@ -1651,7 +1682,6 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
@@ -1675,7 +1705,8 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
 		init_idle(task, cpu);
@@ -1720,7 +1751,7 @@ long _do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, stack_size,
-			 child_tidptr, NULL, trace, tls);
+			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
diff --git a/kernel/futex.c b/kernel/futex.c
index 461c72b2dac2..3057dabf726f 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1244,10 +1244,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
-	else if (curval != uval)
-		ret = -EINVAL;
+	} else if (curval != uval) {
+		/*
+		 * If a unconditional UNLOCK_PI operation (user space did not
+		 * try the TID->0 transition) raced with a waiter setting the
+		 * FUTEX_WAITERS flag between get_user() and locking the hash
+		 * bucket lock, retry the operation.
+		 */
+		if ((FUTEX_TID_MASK & curval) == uval)
+			ret = -EAGAIN;
+		else
+			ret = -EINVAL;
+	}
 	if (ret) {
 		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -1474,8 +1484,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
 		hb_waiters_dec(hb1);
-		plist_add(&q->list, &hb2->chain);
 		hb_waiters_inc(hb2);
+		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
@@ -2538,6 +2548,15 @@ retry:
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		/*
+		 * A unconditional UNLOCK_PI op raced against a waiter
+		 * setting the FUTEX_WAITERS bit. Try again.
+		 */
+		if (ret == -EAGAIN) {
+			spin_unlock(&hb->lock);
+			put_futex_key(&key);
+			goto retry;
+		}
+		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
@@ -2671,7 +2690,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct rt_mutex *pi_mutex = NULL;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
@@ -2755,6 +2773,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+				rt_mutex_unlock(&q.pi_state->pi_mutex);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -2763,6 +2783,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
+		struct rt_mutex *pi_mutex;
+
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2786,18 +2808,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
+		/*
+		 * If fixup_pi_state_owner() faulted and was unable to handle
+		 * the fault, unlock the rt_mutex and return the fault to
+		 * userspace.
+		 */
+		if (ret && rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock the rt_mutex and return the fault to userspace.
-	 */
-	if (ret == -EFAULT) {
-		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
-	} else if (ret == -EINTR) {
+	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
 		 * futex_lock_pi() directly. We could restart this syscall, but
@@ -3180,4 +3203,4 @@ static int __init futex_init(void)
 
 	return 0;
 }
-__initcall(futex_init);
+core_initcall(futex_init);
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 7080ae1eb6c1..f850e906564b 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
 }
 EXPORT_SYMBOL(__gcov_merge_icall_topn);
 
+void __gcov_exit(void)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_exit);
+
 /**
  * gcov_enable_events - enable event reporting through gcov_event()
  *
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index e25e92fb44fa..46a18e72bce6 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#if (__GNUC__ >= 7)
+#define GCOV_COUNTERS			9
+#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
 #elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
 #define GCOV_COUNTERS			9
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 15206453b12a..e4453d9f788c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -810,8 +810,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
 	if (!desc)
 		return;
 
-	__irq_do_set_handler(desc, handle, 1, NULL);
 	desc->irq_common_data.handler_data = data;
+	__irq_do_set_handler(desc, handle, 1, NULL);
 
 	irq_put_desc_busunlock(desc, flags);
 }
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index abd286afbd27..a4775f3451b9 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -411,8 +411,29 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 }
 EXPORT_SYMBOL_GPL(irq_map_generic_chip);
 
+static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq)
+{
+	struct irq_data *data = irq_domain_get_irq_data(d, virq);
+	struct irq_domain_chip_generic *dgc = d->gc;
+	unsigned int hw_irq = data->hwirq;
+	struct irq_chip_generic *gc;
+	int irq_idx;
+
+	gc = irq_get_domain_generic_chip(d, hw_irq);
+	if (!gc)
+		return;
+
+	irq_idx = hw_irq % dgc->irqs_per_chip;
+
+	clear_bit(irq_idx, &gc->installed);
+	irq_domain_set_info(d, virq, hw_irq, &no_irq_chip, NULL, NULL, NULL,
+			    NULL);
+
+}
+
 struct irq_domain_ops irq_generic_chip_ops = {
 	.map	= irq_map_generic_chip,
+	.unmap  = irq_unmap_generic_chip,
 	.xlate	= irq_domain_xlate_onetwocell,
 };
 EXPORT_SYMBOL_GPL(irq_generic_chip_ops);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 6ead200370da..a079ed14f230 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1287,8 +1287,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			ret = __irq_set_trigger(desc,
 						new->flags & IRQF_TRIGGER_MASK);
 
-			if (ret)
+			if (ret) {
+				irq_release_resources(desc);
 				goto out_mask;
+			}
 		}
 
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 6b0c0b74a2a1..cd6009006510 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -268,7 +268,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 	struct msi_domain_ops *ops = info->ops;
 	msi_alloc_info_t arg;
 	struct msi_desc *desc;
-	int i, ret, virq = -1;
+	int i, ret, virq;
 
 	ret = ops->msi_check(domain, info, dev);
 	if (ret == 0)
@@ -278,12 +278,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	for_each_msi_entry(desc, dev) {
 		ops->set_desc(&arg, desc);
-		if (info->flags & MSI_FLAG_IDENTITY_MAP)
-			virq = (int)ops->get_hwirq(info, &arg);
-		else
-			virq = -1;
 
-		virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
+		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
 					       dev_to_node(dev), &arg, false);
 		if (virq < 0) {
 			ret = -ENOSPC;
@@ -302,11 +298,23 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 		ops->msi_finish(&arg, 0);
 
 	for_each_msi_entry(desc, dev) {
+		virq = desc->irq;
 		if (desc->nvec_used == 1)
 			dev_dbg(dev, "irq %d for MSI\n", virq);
 		else
 			dev_dbg(dev, "irq [%d-%d] for MSI\n",
 				virq, virq + desc->nvec_used - 1);
+		/*
+		 * This flag is set by the PCI layer as we need to activate
+		 * the MSI entries before the PCI layer enables MSI in the
+		 * card. Otherwise the card latches a random msi message.
+		 */
+		if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+			struct irq_data *irq_data;
+
+			irq_data = irq_domain_get_irq_data(domain, desc->irq);
+			irq_domain_activate_irq(irq_data);
+		}
 	}
 
 	return 0;
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4b4e..453ec4232852 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
 
 void static_key_slow_inc(struct static_key *key)
 {
+	int v, v1;
+
 	STATIC_KEY_CHECK_USE();
-	if (atomic_inc_not_zero(&key->enabled))
-		return;
+
+	/*
+	 * Careful if we get concurrent static_key_slow_inc() calls;
+	 * later calls must wait for the first one to _finish_ the
+	 * jump_label_update() process.  At the same time, however,
+	 * the jump_label_update() call below wants to see
+	 * static_key_enabled(&key) for jumps to be updated properly.
+	 *
+	 * So give a special meaning to negative key->enabled: it sends
+	 * static_key_slow_inc() down the slow path, and it is non-zero
+	 * so it counts as "enabled" in jump_label_update().  Note that
+	 * atomic_inc_unless_negative() checks >= 0, so roll our own.
+	 */
+	for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+		v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+		if (likely(v1 == v))
+			return;
+	}
 
 	jump_label_lock();
-	if (atomic_inc_return(&key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0) {
+		atomic_set(&key->enabled, -1);
 		jump_label_update(key);
+		atomic_set(&key->enabled, 1);
+	} else {
+		atomic_inc(&key->enabled);
+	}
 	jump_label_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	/*
+	 * The negative count check is valid even when a negative
+	 * key->enabled is in use by static_key_slow_inc(); a
+	 * __static_key_slow_dec() before the first static_key_slow_inc()
+	 * returns is unbalanced, because all other static_key_slow_inc()
+	 * instances block while the update is in progress.
+	 */
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
@@ -108,6 +138,13 @@ void static_key_slow_dec_deferred(struct static_key_deferred *key)
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
 
+void static_key_deferred_flush(struct static_key_deferred *key)
+{
+	STATIC_KEY_CHECK_USE();
+	flush_delayed_work(&key->work);
+}
+EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b70ada0028d2..6030efd4a188 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -934,7 +934,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min,
 	return 0;
 out:
 	vfree(pi->sechdrs);
+	pi->sechdrs = NULL;
+
 	vfree(pi->purgatory_buf);
+	pi->purgatory_buf = NULL;
 	return ret;
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d10ab6b9b5e0..695763516908 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -563,7 +563,7 @@ static void kprobe_optimizer(struct work_struct *work)
 }
 
 /* Wait for completing optimization and unoptimization */
-static void wait_for_kprobe_optimizer(void)
+void wait_for_kprobe_optimizer(void)
 {
 	mutex_lock(&kprobe_mutex);
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9ff173dca1ae..850b255649a2 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -18,6 +18,7 @@
 #include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
+#include <linux/cgroup.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -205,6 +206,7 @@ static int kthread(void *_create)
 	ret = -EINTR;
 
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+		cgroup_kthread_ready();
 		__kthread_parkme(&self);
 		ret = threadfn(data);
 	}
@@ -510,6 +512,7 @@ int kthreadd(void *unused)
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
+	cgroup_init_kthreadd();
 
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8ef1919d63b2..d580b7d6ee6d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -776,6 +776,8 @@ static void lock_torture_cleanup(void)
 	else
 		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: SUCCESS");
+	kfree(cxt.lwsa);
+	kfree(cxt.lrsa);
 	torture_cleanup_end();
 }
 
@@ -917,6 +919,8 @@ static int __init lock_torture_init(void)
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
 			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			kfree(writer_tasks);
+			writer_tasks = NULL;
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 5b9102a47ea5..c835270f0c2f 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	node->locked = 0;
 	node->next   = NULL;
 
-	prev = xchg_acquire(lock, node);
+	/*
+	 * We rely on the full barrier with global transitivity implied by the
+	 * below xchg() to order the initialization stores above against any
+	 * observation of @node. And to provide the ACQUIRE ordering associated
+	 * with a LOCK primitive.
+	 */
+	prev = xchg(lock, node);
 	if (likely(prev == NULL)) {
 		/*
 		 * Lock acquired, don't need to set node->locked to 1. Threads
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 0551c219c40e..89350f924c85 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
 	if (!hold_ctx)
 		return 0;
 
-	if (unlikely(ctx == hold_ctx))
-		return -EALREADY;
-
 	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
 	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	unsigned long flags;
 	int ret;
 
+	if (use_ww_ctx) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+			return -EALREADY;
+	}
+
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 87e9ce6a63c5..8173bc7fec92 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -255,6 +255,66 @@ static __always_inline void __pv_wait_head(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
+ *
+ *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
+ *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	u32 val;
+
+	for (;;) {
+		val = atomic_read(&lock->val);
+
+		if (!val) /* not locked, we're done */
+			goto done;
+
+		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+			break;
+
+		/* not locked, but pending, wait until we observe the lock */
+		cpu_relax();
+	}
+
+	/* any unlock is good */
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+done:
+	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8251e75dd9c0..b066724d7a5b 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
 
 static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 {
-	if (!rt_mutex_has_waiters(lock))
-		clear_rt_mutex_waiters(lock);
+	unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+	if (rt_mutex_has_waiters(lock))
+		return;
+
+	/*
+	 * The rbtree has no waiters enqueued, now make sure that the
+	 * lock->owner still has the waiters bit set, otherwise the
+	 * following can happen:
+	 *
+	 * CPU 0	CPU 1		CPU2
+	 * l->owner=T1
+	 *		rt_mutex_lock(l)
+	 *		lock(l->lock)
+	 *		l->owner = T1 | HAS_WAITERS;
+	 *		enqueue(T2)
+	 *		boost()
+	 *		  unlock(l->lock)
+	 *		block()
+	 *
+	 *				rt_mutex_lock(l)
+	 *				lock(l->lock)
+	 *				l->owner = T1 | HAS_WAITERS;
+	 *				enqueue(T3)
+	 *				boost()
+	 *				  unlock(l->lock)
+	 *				block()
+	 *		signal(->T2)	signal(->T3)
+	 *		lock(l->lock)
+	 *		dequeue(T2)
+	 *		deboost()
+	 *		  unlock(l->lock)
+	 *				lock(l->lock)
+	 *				dequeue(T3)
+	 *				 ==> wait list is empty
+	 *				deboost()
+	 *				 unlock(l->lock)
+	 *		lock(l->lock)
+	 *		fixup_rt_mutex_waiters()
+	 *		  if (wait_list_empty(l) {
+	 *		    l->owner = owner
+	 *		    owner = l->owner & ~HAS_WAITERS;
+	 *		      ==> l->owner = T1
+	 *		  }
+	 *				lock(l->lock)
+	 * rt_mutex_unlock(l)		fixup_rt_mutex_waiters()
+	 *				  if (wait_list_empty(l) {
+	 *				    owner = l->owner & ~HAS_WAITERS;
+	 * cmpxchg(l->owner, T1, NULL)
+	 *  ===> Success (l->owner = NULL)
+	 *
+	 *				    l->owner = owner
+	 *				      ==> l->owner = T1
+	 *				  }
+	 *
+	 * With the check for the waiter bit in place T3 on CPU2 will not
+	 * overwrite. All tasks fiddling with the waiters bit are
+	 * serialized by l->lock, so nothing else can modify the waiters
+	 * bit. If the bit is set then nothing can change l->owner either
+	 * so the simple RMW is safe. The cmpxchg() will simply fail if it
+	 * happens in the middle of the RMW because the waiters bit is
+	 * still set.
+	 */
+	owner = READ_ONCE(*p);
+	if (owner & RT_MUTEX_HAS_WAITERS)
+		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
 /*
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 4f5f83c7d2d3..e317e1cbb3eb 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -75,8 +75,9 @@ task_top_pi_waiter(struct task_struct *p)
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
-	return (struct task_struct *)
-		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
+	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
+
+	return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
 /*
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
index 536c727a56e9..9f9284f37f8d 100644
--- a/kernel/membarrier.c
+++ b/kernel/membarrier.c
@@ -16,6 +16,7 @@
 
 #include <linux/syscalls.h>
 #include <linux/membarrier.h>
+#include <linux/tick.h>
 
 /*
  * Bitmask made from a "or" of all commands within enum membarrier_cmd,
@@ -51,6 +52,9 @@
  */
 SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 {
+	/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+	if (tick_nohz_full_enabled())
+		return -ENOSYS;
 	if (unlikely(flags))
 		return -EINVAL;
 	switch (cmd) {
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 25ced161ebeb..f719c925cb54 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -159,7 +159,9 @@ static void devm_memremap_pages_release(struct device *dev, void *res)
 	struct page_map *page_map = res;
 
 	/* pages are dead and unused, undo the arch mapping */
+	mem_hotplug_begin();
 	arch_remove_memory(page_map->res.start, resource_size(&page_map->res));
+	mem_hotplug_done();
 }
 
 void *devm_memremap_pages(struct device *dev, struct resource *res)
@@ -189,7 +191,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res)
 	if (nid < 0)
 		nid = numa_mem_id();
 
+	mem_hotplug_begin();
 	error = arch_add_memory(nid, res->start, resource_size(res), true);
+	mem_hotplug_done();
 	if (error) {
 		devres_free(page_map);
 		return ERR_PTR(error);
diff --git a/kernel/module.c b/kernel/module.c
index 0e5c71195f18..b14a4f31221f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2606,13 +2606,18 @@ static inline void kmemleak_load_module(const struct module *mod,
 #endif
 
 #ifdef CONFIG_MODULE_SIG
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
 {
 	int err = -ENOKEY;
 	const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1;
 	const void *mod = info->hdr;
 
-	if (info->len > markerlen &&
+	/*
+	 * Require flags == 0, as a module with version information
+	 * removed is no longer the module that was signed
+	 */
+	if (flags == 0 &&
+	    info->len > markerlen &&
 	    memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) {
 		/* We truncate the module to discard the signature */
 		info->len -= markerlen;
@@ -2631,7 +2636,7 @@ static int module_sig_check(struct load_info *info)
 	return err;
 }
 #else /* !CONFIG_MODULE_SIG */
-static int module_sig_check(struct load_info *info)
+static int module_sig_check(struct load_info *info, int flags)
 {
 	return 0;
 }
@@ -3444,7 +3449,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	long err;
 	char *after_dashes;
 
-	err = module_sig_check(info);
+	err = module_sig_check(info, flags);
 	if (err)
 		goto free_copy;
 
diff --git a/kernel/padata.c b/kernel/padata.c
index b38bea9c466a..ecc7b3f452c7 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -189,19 +189,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
 
 	reorder = &next_queue->reorder;
 
+	spin_lock(&reorder->lock);
 	if (!list_empty(&reorder->list)) {
 		padata = list_entry(reorder->list.next,
 				    struct padata_priv, list);
 
-		spin_lock(&reorder->lock);
 		list_del_init(&padata->list);
 		atomic_dec(&pd->reorder_objects);
-		spin_unlock(&reorder->lock);
 
 		pd->processed++;
 
+		spin_unlock(&reorder->lock);
 		goto out;
 	}
+	spin_unlock(&reorder->lock);
 
 	if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
 		padata = ERR_PTR(-ENODATA);
@@ -356,7 +357,7 @@ static int padata_setup_cpumasks(struct parallel_data *pd,
 
 	cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
 	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
-		free_cpumask_var(pd->cpumask.cbcpu);
+		free_cpumask_var(pd->cpumask.pcpu);
 		return -ENOMEM;
 	}
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 41e2b54f36b5..1d07cf9af849 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -167,7 +167,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		pr_emerg("Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();
diff --git a/kernel/pid.c b/kernel/pid.c
index 78b3d9f80d44..b17263be9082 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -526,8 +526,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	if (!ns)
 		ns = task_active_pid_ns(current);
 	if (likely(pid_alive(task))) {
-		if (type != PIDTYPE_PID)
+		if (type != PIDTYPE_PID) {
+			if (type == __PIDTYPE_TGID)
+				type = PIDTYPE_PID;
 			task = task->group_leader;
+		}
 		nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
 	}
 	rcu_read_unlock();
@@ -536,12 +539,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 }
 EXPORT_SYMBOL(__task_pid_nr_ns);
 
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_tgid(tsk), ns);
-}
-EXPORT_SYMBOL(task_tgid_nr_ns);
-
 struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
 	return ns_of_pid(task_pid(tsk));
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a65ba137fd15..567ecc826bc8 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -255,7 +255,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 * if reparented.
 	 */
 	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 		if (pid_ns->nr_hashed == init_pids)
 			break;
 		schedule();
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b7342a24f559..3124cebaec31 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -299,12 +299,12 @@ static int create_image(int platform_mode)
 	save_processor_state();
 	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
 	error = swsusp_arch_suspend();
+	/* Restore control flow magically appears here */
+	restore_processor_state();
 	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
 	if (error)
 		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
 			error);
-	/* Restore control flow magically appears here */
-	restore_processor_state();
 	if (!in_suspend)
 		events_check_enabled = false;
 
@@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mode)
 	pm_message_t msg;
 	int error;
 
+	pm_suspend_clear_flags();
 	error = platform_begin(platform_mode);
 	if (error)
 		goto Close;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 3a970604308f..f155c62f1f2c 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -765,9 +765,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
  */
 static bool rtree_next_node(struct memory_bitmap *bm)
 {
-	bm->cur.node = list_entry(bm->cur.node->list.next,
-				  struct rtree_node, list);
-	if (&bm->cur.node->list != &bm->cur.zone->leaves) {
+	if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) {
+		bm->cur.node = list_entry(bm->cur.node->list.next,
+					  struct rtree_node, list);
 		bm->cur.node_pfn += BM_BITS_PER_BLOCK;
 		bm->cur.node_bit  = 0;
 		touch_softlockup_watchdog();
@@ -775,9 +775,9 @@ static bool rtree_next_node(struct memory_bitmap *bm)
 	}
 
 	/* No more nodes, goto next zone */
-	bm->cur.zone = list_entry(bm->cur.zone->list.next,
+	if (!list_is_last(&bm->cur.zone->list, &bm->zones)) {
+		bm->cur.zone = list_entry(bm->cur.zone->list.next,
 				  struct mem_zone_bm_rtree, list);
-	if (&bm->cur.zone->list != &bm->zones) {
 		bm->cur.node = list_entry(bm->cur.zone->leaves.next,
 					  struct rtree_node, list);
 		bm->cur.node_pfn = 0;
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 084452e34a12..bdff5ed57f10 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -203,8 +203,10 @@ static int __init test_suspend(void)
 
 	/* RTCs have initialized by now too ... can we use one? */
 	dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm);
-	if (dev)
+	if (dev) {
 		rtc = rtc_class_open(dev_name(dev));
+		put_device(dev);
+	}
 	if (!rtc) {
 		printk(warn_no_rtc);
 		return 0;
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index 276762f3a460..d5760c42f042 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -9,10 +9,10 @@
 
 char *_braille_console_setup(char **str, char **brl_options)
 {
-	if (!memcmp(*str, "brl,", 4)) {
+	if (!strncmp(*str, "brl,", 4)) {
 		*brl_options = "";
 		*str += 4;
-	} else if (!memcmp(str, "brl=", 4)) {
+	} else if (!strncmp(*str, "brl=", 4)) {
 		*brl_options = *str + 4;
 		*str = strchr(*brl_options, ',');
 		if (!*str)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c048e34b177f..0b5613554769 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1436,7 +1436,7 @@ static void call_console_drivers(int level,
 {
 	struct console *con;
 
-	trace_console(text, len);
+	trace_console_rcuidle(text, len);
 
 	if (level >= console_loglevel && !ignore_loglevel)
 		return;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 3189e51db7e8..5e2cd1030702 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -28,17 +28,26 @@
 #include <linux/compat.h>
 
 
+void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
+		   const struct cred *ptracer_cred)
+{
+	BUG_ON(!list_empty(&child->ptrace_entry));
+	list_add(&child->ptrace_entry, &new_parent->ptraced);
+	child->parent = new_parent;
+	child->ptracer_cred = get_cred(ptracer_cred);
+}
+
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
  *
  * Must be called with the tasklist lock write-held.
  */
-void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
+static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 {
-	BUG_ON(!list_empty(&child->ptrace_entry));
-	list_add(&child->ptrace_entry, &new_parent->ptraced);
-	child->parent = new_parent;
+	rcu_read_lock();
+	__ptrace_link(child, new_parent, __task_cred(new_parent));
+	rcu_read_unlock();
 }
 
 /**
@@ -71,11 +80,15 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  */
 void __ptrace_unlink(struct task_struct *child)
 {
+	const struct cred *old_cred;
 	BUG_ON(!child->ptrace);
 
 	child->ptrace = 0;
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
+	old_cred = child->ptracer_cred;
+	child->ptracer_cred = NULL;
+	put_cred(old_cred);
 
 	spin_lock(&child->sighand->siglock);
 
@@ -144,11 +157,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task)
 
 	WARN_ON(!task->ptrace || task->parent != current);
 
+	/*
+	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+	 * Recheck state under the lock to close this race.
+	 */
 	spin_lock_irq(&task->sighand->siglock);
-	if (__fatal_signal_pending(task))
-		wake_up_state(task, __TASK_TRACED);
-	else
-		task->state = TASK_TRACED;
+	if (task->state == __TASK_TRACED) {
+		if (__fatal_signal_pending(task))
+			wake_up_state(task, __TASK_TRACED);
+		else
+			task->state = TASK_TRACED;
+	}
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
@@ -219,7 +238,7 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
-	int dumpable = 0;
+	struct mm_struct *mm;
 	kuid_t caller_uid;
 	kgid_t caller_gid;
 
@@ -270,16 +289,11 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return -EPERM;
 ok:
 	rcu_read_unlock();
-	smp_rmb();
-	if (task->mm)
-		dumpable = get_dumpable(task->mm);
-	rcu_read_lock();
-	if (dumpable != SUID_DUMP_USER &&
-	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
-		rcu_read_unlock();
-		return -EPERM;
-	}
-	rcu_read_unlock();
+	mm = task->mm;
+	if (mm &&
+	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
+	     !ptrace_has_cap(mm->user_ns, mode)))
+	    return -EPERM;
 
 	return security_ptrace_access_check(task, mode);
 }
@@ -343,13 +357,9 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	if (seize)
 		flags |= PT_SEIZED;
-	rcu_read_lock();
-	if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
-		flags |= PT_PTRACE_CAP;
-	rcu_read_unlock();
 	task->ptrace = flags;
 
-	__ptrace_link(task, current);
+	ptrace_link(task, current);
 
 	/* SEIZE doesn't trap tracee on attach */
 	if (!seize)
@@ -416,7 +426,7 @@ static int ptrace_traceme(void)
 		 */
 		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
 			current->ptrace = PT_PTRACED;
-			__ptrace_link(current, current->real_parent);
+			ptrace_link(current, current->real_parent);
 		}
 	}
 	write_unlock_irq(&tasklist_lock);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 630c19772630..32cbe72bf545 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2275,6 +2275,7 @@ static int rcu_nocb_kthread(void *arg)
 				cl++;
 			c++;
 			local_bh_enable();
+			cond_resched_rcu_qs();
 			list = next;
 		}
 		trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
diff --git a/kernel/resource.c b/kernel/resource.c
index 249b1eb1e6e1..a4a94e700fb9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -105,16 +105,25 @@ static int r_show(struct seq_file *m, void *v)
 {
 	struct resource *root = m->private;
 	struct resource *r = v, *p;
+	unsigned long long start, end;
 	int width = root->end < 0x10000 ? 4 : 8;
 	int depth;
 
 	for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
 		if (p->parent == root)
 			break;
+
+	if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) {
+		start = r->start;
+		end = r->end;
+	} else {
+		start = end = 0;
+	}
+
 	seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
 			depth * 2, "",
-			width, (unsigned long long) r->start,
-			width, (unsigned long long) r->end,
+			width, start,
+			width, end,
 			r->name ? r->name : "<BAD>");
 	return 0;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eb70592f03f6..dece705b7f8c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -627,7 +627,10 @@ int get_nohz_timer_target(void)
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
+			if (cpu == i)
+				continue;
+
+			if (!idle_cpu(i) && is_housekeeping_cpu(i)) {
 				cpu = i;
 				goto unlock;
 			}
@@ -1942,6 +1945,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
+	/*
+	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
+	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
+	 * in smp_cond_load_acquire() below.
+	 *
+	 * sched_ttwu_pending()                 try_to_wake_up()
+	 *   [S] p->on_rq = 1;                  [L] P->state
+	 *       UNLOCK rq->lock  -----.
+	 *                              \
+	 *				 +---   RMB
+	 * schedule()                   /
+	 *       LOCK rq->lock    -----'
+	 *       UNLOCK rq->lock
+	 *
+	 * [task p]
+	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *
+	 * Pairs with the UNLOCK+LOCK on rq->lock from the
+	 * last wakeup of our task and the schedule that got our task
+	 * current.
+	 */
+	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
 		goto stat;
 
@@ -3008,7 +3033,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
 static inline void schedule_debug(struct task_struct *prev)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
-	BUG_ON(task_stack_end_corrupted(prev));
+	if (task_stack_end_corrupted(prev))
+		panic("corrupted stack end detected inside scheduler\n");
 #endif
 
 	if (unlikely(in_atomic_preempt_off())) {
@@ -4950,14 +4976,16 @@ void show_state_filter(unsigned long state_filter)
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
+		 * Also, reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI.
 		 */
 		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
 	}
 
-	touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
 	sysrq_sched_debug_show();
 #endif
@@ -6094,6 +6122,9 @@ enum s_alloc {
  * Build an iteration mask that can exclude certain CPUs from the upwards
  * domain traversal.
  *
+ * Only CPUs that can arrive at this group should be considered to continue
+ * balancing.
+ *
  * Asymmetric node setups can result in situations where the domain tree is of
  * unequal depth, make sure to skip domains that already cover the entire
  * range.
@@ -6105,18 +6136,31 @@ enum s_alloc {
  */
 static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	const struct cpumask *sg_span = sched_group_cpus(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
+			continue;
+
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
 			continue;
 
 		cpumask_set_cpu(i, sched_group_mask(sg));
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg)));
 }
 
 /*
@@ -7692,7 +7736,7 @@ void set_curr_task(int cpu, struct task_struct *p)
 /* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
-static void free_sched_group(struct task_group *tg)
+static void sched_free_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
@@ -7718,7 +7762,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	return tg;
 
 err:
-	free_sched_group(tg);
+	sched_free_group(tg);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -7738,17 +7782,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 }
 
 /* rcu callback to free various structures associated with a task group */
-static void free_sched_group_rcu(struct rcu_head *rhp)
+static void sched_free_group_rcu(struct rcu_head *rhp)
 {
 	/* now it should be safe to free those cfs_rqs */
-	free_sched_group(container_of(rhp, struct task_group, rcu));
+	sched_free_group(container_of(rhp, struct task_group, rcu));
 }
 
-/* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
 {
 	/* wait for possible concurrent references to cfs_rqs complete */
-	call_rcu(&tg->rcu, free_sched_group_rcu);
+	call_rcu(&tg->rcu, sched_free_group_rcu);
 }
 
 void sched_offline_group(struct task_group *tg)
@@ -8212,6 +8255,7 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	return &tg->css;
 }
 
+/* Expose task group only after completing cgroup initialization */
 static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
@@ -8222,18 +8266,21 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
-static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
-	sched_destroy_group(tg);
+	sched_offline_group(tg);
 }
 
-static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
-	sched_offline_group(tg);
+	/*
+	 * Relies on the RCU grace period between css_released() and this.
+	 */
+	sched_free_group(tg);
 }
 
 static void cpu_cgroup_fork(struct task_struct *task, void *private)
@@ -8593,9 +8640,9 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
-	.css_free	= cpu_cgroup_css_free,
 	.css_online	= cpu_cgroup_css_online,
-	.css_offline	= cpu_cgroup_css_offline,
+	.css_released	= cpu_cgroup_css_released,
+	.css_free	= cpu_cgroup_css_free,
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 05de80b48586..a1aecbedf5b1 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -259,21 +259,21 @@ static __always_inline bool steal_account_process_tick(void)
 #ifdef CONFIG_PARAVIRT
 	if (static_key_false(&paravirt_steal_enabled)) {
 		u64 steal;
-		cputime_t steal_ct;
+		unsigned long steal_jiffies;
 
 		steal = paravirt_steal_clock(smp_processor_id());
 		steal -= this_rq()->prev_steal_time;
 
 		/*
-		 * cputime_t may be less precise than nsecs (eg: if it's
-		 * based on jiffies). Lets cast the result to cputime
+		 * steal is in nsecs but our caller is expecting steal
+		 * time in jiffies. Lets cast the result to jiffies
 		 * granularity and account the rest on the next rounds.
 		 */
-		steal_ct = nsecs_to_cputime(steal);
-		this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
+		steal_jiffies = nsecs_to_jiffies(steal);
+		this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
 
-		account_steal_time(steal_ct);
-		return steal_ct;
+		account_steal_time(jiffies_to_cputime(steal_jiffies));
+		return steal_jiffies;
 	}
 #endif
 	return false;
@@ -600,19 +600,25 @@ static void cputime_adjust(struct task_cputime *curr,
 	stime = curr->stime;
 	utime = curr->utime;
 
-	if (utime == 0) {
-		stime = rtime;
+	/*
+	 * If either stime or both stime and utime are 0, assume all runtime is
+	 * userspace. Once a task gets some ticks, the monotonicy code at
+	 * 'update' will ensure things converge to the observed ratio.
+	 */
+	if (stime == 0) {
+		utime = rtime;
 		goto update;
 	}
 
-	if (stime == 0) {
-		utime = rtime;
+	if (utime == 0) {
+		stime = rtime;
 		goto update;
 	}
 
 	stime = scale_stime((__force u64)stime, (__force u64)rtime,
 			    (__force u64)(stime + utime));
 
+update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
@@ -635,7 +641,6 @@ static void cputime_adjust(struct task_cputime *curr,
 		stime = rtime - utime;
 	}
 
-update:
 	prev->stime = stime;
 	prev->utime = utime;
 out:
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b0a15e285f9..e984f059e5fc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1771,12 +1771,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
 			queue_push_tasks(rq);
-#else
+#endif
 		if (dl_task(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
-#endif
 	}
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cfdc0e61066c..812069b66f47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -687,8 +687,6 @@ void init_entity_runnable_average(struct sched_entity *se)
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -1193,8 +1191,6 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
-	if (p)
-		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1262,20 +1258,30 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
+	bool assigned = false;
 
 	rcu_read_lock();
 
 	raw_spin_lock_irq(&dst_rq->lock);
 	cur = dst_rq->curr;
 	/*
-	 * No need to move the exiting task, and this ensures that ->curr
-	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
-	 * is safe under RCU read lock.
-	 * Note that rcu_read_lock() itself can't protect from the final
-	 * put_task_struct() after the last schedule().
+	 * No need to move the exiting task or idle task.
 	 */
 	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	else {
+		/*
+		 * The task_struct must be protected here to protect the
+		 * p->numa_faults access in the task_weight since the
+		 * numa_faults could already be freed in the following path:
+		 * finish_task_switch()
+		 *     --> put_task_struct()
+		 *         --> __put_task_struct()
+		 *             --> task_numa_free()
+		 */
+		get_task_struct(cur);
+	}
+
 	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
@@ -1359,6 +1365,7 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
+			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1384,9 +1391,16 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
+	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
+	/*
+	 * The dst_rq->curr isn't assigned. The protection for task_struct is
+	 * finished.
+	 */
+	if (cur && !assigned)
+		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
@@ -2682,6 +2696,23 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	typeof(*ptr) val = (_val);				\
+	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
+	res = var - val;					\
+	if (res > var)						\
+		res = 0;					\
+	WRITE_ONCE(*ptr, res);					\
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
@@ -2690,15 +2721,15 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-		sa->load_avg = max_t(long, sa->load_avg - r, 0);
-		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->load_avg, r);
+		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-		sa->util_avg = max_t(long, sa->util_avg - r, 0);
-		sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+		sub_positive(&sa->util_avg, r);
+		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 	}
 
 	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2764,10 +2795,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
 
-	cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-	cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-	cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-	cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 }
 
 /* Add the load generated by se into cfs_rq's load average */
@@ -3887,6 +3918,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4202,15 +4253,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
 			/*
 			 * Bias pick_next to pick a task from this cfs_rq, as
 			 * p is sleeping when it is within its sched_slice.
 			 */
-			if (task_sleep && parent_entity(se))
-				set_next_buddy(parent_entity(se));
-
-			/* avoid re-evaluating load for this entity */
-			se = parent_entity(se);
+			if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+				set_next_buddy(se);
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
@@ -4577,19 +4627,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		return wl;
 
 	for_each_sched_entity(se) {
-		long w, W;
+		struct cfs_rq *cfs_rq = se->my_q;
+		long W, w = cfs_rq_load_avg(cfs_rq);
 
-		tg = se->my_q->tg;
+		tg = cfs_rq->tg;
 
 		/*
 		 * W = @wg + \Sum rw_j
 		 */
-		W = wg + calc_tg_weight(tg, se->my_q);
+		W = wg + atomic_long_read(&tg->load_avg);
+
+		/* Ensure \Sum rw_j >= rw_i */
+		W -= cfs_rq->tg_load_avg_contrib;
+		W += w;
 
 		/*
 		 * w = rw_i + @wl
 		 */
-		w = cfs_rq_load_avg(se->my_q) + wl;
+		w += wl;
 
 		/*
 		 * wl = S * s'_i; see (2)
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index ef7159012cf3..f8e8d68ed3fd 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -99,10 +99,13 @@ long calc_load_fold_active(struct rq *this_rq)
 static unsigned long
 calc_load(unsigned long load, unsigned long exp, unsigned long active)
 {
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	load += 1UL << (FSHIFT - 1);
-	return load >> FSHIFT;
+	unsigned long newload;
+
+	newload = load * exp + active * (FIXED_1 - exp);
+	if (active >= load)
+		newload += FIXED_1-1;
+
+	return newload / FIXED_1;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -198,8 +201,9 @@ void calc_load_exit_idle(void)
 	struct rq *this_rq = this_rq();
 
 	/*
-	 * If we're still before the sample window, we're done.
+	 * If we're still before the pending sample window, we're done.
 	 */
+	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update))
 		return;
 
@@ -208,7 +212,6 @@ void calc_load_exit_idle(void)
 	 * accounted through the nohz accounting, so skip the entire deal and
 	 * sync up for the next window.
 	 */
-	this_rq->calc_load_update = calc_load_update;
 	if (time_before(jiffies, this_rq->calc_load_update + 10))
 		this_rq->calc_load_update += LOAD_FREQ;
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86abe0ea1..78ae5c1d9412 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2136,10 +2136,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
 			queue_push_tasks(rq);
-#else
+#endif /* CONFIG_SMP */
 		if (p->prio < rq->curr->prio)
 			resched_curr(rq);
-#endif /* CONFIG_SMP */
 	}
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b242775bf670..55d92a1ca070 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -417,7 +417,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/signal.c b/kernel/signal.c
index f3f1f7a972fd..5d50ea899b6d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task)
 	 * fresh group stop.  Read comment in do_signal_stop() for details.
 	 */
 	if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
-		sig->flags = SIGNAL_STOP_STOPPED;
+		signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED);
 		return true;
 	}
 	return false;
@@ -503,7 +503,8 @@ int unhandled_signal(struct task_struct *tsk, int sig)
 	return !tsk->ptrace;
 }
 
-static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+static void collect_signal(int sig, struct sigpending *list, siginfo_t *info,
+			   bool *resched_timer)
 {
 	struct sigqueue *q, *first = NULL;
 
@@ -525,6 +526,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
 still_pending:
 		list_del_init(&first->list);
 		copy_siginfo(info, &first->info);
+
+		*resched_timer =
+			(first->flags & SIGQUEUE_PREALLOC) &&
+			(info->si_code == SI_TIMER) &&
+			(info->si_sys_private);
+
 		__sigqueue_free(first);
 	} else {
 		/*
@@ -541,12 +548,12 @@ still_pending:
 }
 
 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
-			siginfo_t *info)
+			siginfo_t *info, bool *resched_timer)
 {
 	int sig = next_signal(pending, mask);
 
 	if (sig)
-		collect_signal(sig, pending, info);
+		collect_signal(sig, pending, info, resched_timer);
 	return sig;
 }
 
@@ -558,15 +565,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
  */
 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 {
+	bool resched_timer = false;
 	int signr;
 
 	/* We only dequeue private signals from ourselves, we don't let
 	 * signalfd steal them
 	 */
-	signr = __dequeue_signal(&tsk->pending, mask, info);
+	signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
 	if (!signr) {
 		signr = __dequeue_signal(&tsk->signal->shared_pending,
-					 mask, info);
+					 mask, info, &resched_timer);
 		/*
 		 * itimer signal ?
 		 *
@@ -611,7 +619,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 		 */
 		current->jobctl |= JOBCTL_STOP_DEQUEUED;
 	}
-	if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
+	if (resched_timer) {
 		/*
 		 * Release the siglock to ensure proper locking order
 		 * of timer locks outside of siglocks.  Note, we leave
@@ -837,7 +845,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
 			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
 			 * notify its parent. See get_signal_to_deliver().
 			 */
-			signal->flags = why | SIGNAL_STOP_CONTINUED;
+			signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
 			signal->group_stop_count = 0;
 			signal->group_exit_code = 0;
 		}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index dc6858d6639e..002ec084124b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -65,6 +65,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/kexec.h>
 #include <linux/bpf.h>
+#include <linux/mount.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -173,7 +174,7 @@ extern int no_unaligned_warning;
 #define SYSCTL_WRITES_WARN	 0
 #define SYSCTL_WRITES_STRICT	 1
 
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
 
 static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -1735,6 +1736,28 @@ static struct ctl_table fs_table[] = {
 		.proc_handler	= &pipe_proc_fn,
 		.extra1		= &pipe_min_size,
 	},
+	{
+		.procname	= "pipe-user-pages-hard",
+		.data		= &pipe_user_pages_hard,
+		.maxlen		= sizeof(pipe_user_pages_hard),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "pipe-user-pages-soft",
+		.data		= &pipe_user_pages_soft,
+		.maxlen		= sizeof(pipe_user_pages_soft),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "mount-max",
+		.data		= &sysctl_mount_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+	},
 	{ }
 };
 
@@ -2037,6 +2060,24 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 	return 0;
 }
 
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+				 int *valp,
+				 int write, void *data)
+{
+	if (write) {
+		if (*negp)
+			return -EINVAL;
+		if (*lvalp > UINT_MAX)
+			return -EINVAL;
+		*valp = *lvalp;
+	} else {
+		unsigned int val = *valp;
+		*negp = false;
+		*lvalp = (unsigned long)val;
+	}
+	return 0;
+}
+
 static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
@@ -2164,8 +2205,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
 int proc_dointvec(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,buffer,lenp,ppos,
-		    	    NULL,NULL);
+	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
+				do_proc_douintvec_conv, NULL);
 }
 
 /*
@@ -2366,6 +2426,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 				break;
 			if (neg)
 				continue;
+			val = convmul * val / convdiv;
 			if ((min && val < *min) || (max && val > *max))
 				continue;
 			*i = val;
@@ -2778,6 +2839,12 @@ int proc_dointvec(struct ctl_table *table, int write,
 	return -ENOSYS;
 }
 
+int proc_douintvec(struct ctl_table *table, int write,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
 int proc_dointvec_minmax(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -2823,6 +2890,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  * exception granted :-)
  */
 EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
 EXPORT_SYMBOL(proc_dointvec_jiffies);
 EXPORT_SYMBOL(proc_dointvec_minmax);
 EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 7e7746a42a62..10a1d7dc9313 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1321,7 +1321,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	}
 
 	mnt = task_active_pid_ns(current)->proc_mnt;
-	file = file_open_root(mnt->mnt_root, mnt, pathname, flags);
+	file = file_open_root(mnt->mnt_root, mnt, pathname, flags, 0);
 	result = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_putname;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 7fbba635a549..6fcc367ad531 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -339,7 +339,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
-	start = ktime_add(start, base->gettime());
+	start = ktime_add_safe(start, base->gettime());
 	alarm_start(alarm, start);
 }
 EXPORT_SYMBOL_GPL(alarm_start_relative);
@@ -425,7 +425,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 		overrun++;
 	}
 
-	alarm->node.expires = ktime_add(alarm->node.expires, interval);
+	alarm->node.expires = ktime_add_safe(alarm->node.expires, interval);
 	return overrun;
 }
 EXPORT_SYMBOL_GPL(alarm_forward);
@@ -611,13 +611,22 @@ 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);
+
+	/*
+	 * Rate limit to the tick as a hot fix to prevent DOS. Will be
+	 * mopped up later.
+	 */
+	if (timr->it.alarm.interval.tv64 &&
+			ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC)
+		timr->it.alarm.interval = ktime_set(0, TICK_NSEC);
+
 	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);
+		exp = ktime_add_safe(now, exp);
 	}
 
 	alarm_start(&timr->it.alarm.alarmtimer, exp);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1347882d131e..b98810d2f3b4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		/* cs is a watchdog. */
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+	struct clocksource *cs, *old_wd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	/* save current watchdog */
+	old_wd = watchdog;
+	if (fallback)
+		watchdog = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* cs is a clocksource to be watched. */
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+			continue;
+
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_wd)
+			continue;
+
 		/* Pick the best watchdog. */
-		if (!watchdog || cs->rating > watchdog->rating) {
+		if (!watchdog || cs->rating > watchdog->rating)
 			watchdog = cs;
-			/* Reset watchdog cycles */
-			clocksource_reset_watchdog();
-		}
 	}
+	/* If we failed to find a fallback restore the old one. */
+	if (!watchdog)
+		watchdog = old_wd;
+
+	/* If we changed the watchdog we need to reset cycles. */
+	if (watchdog != old_wd)
+		clocksource_reset_watchdog();
+
 	/* Check if the watchdog timer needs to be started. */
 	clocksource_start_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
-	/*
-	 * I really can't convince myself to support this on hardware
-	 * designed by lobotomized monkeys.
-	 */
-	if (clocksource_is_watchdog(cs))
-		return -EBUSY;
+	if (clocksource_is_watchdog(cs)) {
+		/* Select and try to install a replacement watchdog. */
+		clocksource_select_watchdog(true);
+		if (clocksource_is_watchdog(cs))
+			return -EBUSY;
+	}
 
 	if (cs == curr_clocksource) {
 		/* Select and try to install a replacement clock source */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index fa909f9fd559..17f7bcff1e02 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,6 +94,9 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	/* Make sure we catch unsupported clockids */
+	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
+
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
@@ -102,7 +105,9 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
-	return hrtimer_clock_to_base_table[clock_id];
+	int base = hrtimer_clock_to_base_table[clock_id];
+	BUG_ON(base == HRTIMER_MAX_CLOCK_BASES);
+	return base;
 }
 
 /*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 149cc8086aea..ab861771e37f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -674,8 +674,24 @@ int ntp_validate_timex(struct timex *txc)
 			return -EINVAL;
 	}
 
-	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
-		return -EPERM;
+	if (txc->modes & ADJ_SETOFFSET) {
+		/* In order to inject time, you gotta be super-user! */
+		if (!capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		if (txc->modes & ADJ_NANO) {
+			struct timespec ts;
+
+			ts.tv_sec = txc->time.tv_sec;
+			ts.tv_nsec = txc->time.tv_usec;
+			if (!timespec_inject_offset_valid(&ts))
+				return -EINVAL;
+
+		} else {
+			if (!timeval_inject_offset_valid(&txc->time))
+				return -EINVAL;
+		}
+	}
 
 	/*
 	 * Check for potential multiplication overflows that can
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index f5e86d282d52..80016b329d94 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -808,6 +808,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			timer->it.cpu.expires = 0;
 			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
 					   &itp->it_value);
+			return;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
 			unlock_task_sighand(p, &flags);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f6aae7977824..d2a20e83ebae 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -871,6 +871,9 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
 	int cpu = smp_processor_id();
 
+	if (!bc)
+		return;
+
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
 		int was_periodic = clockevent_state_periodic(bc);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 99188ee5d9d0..6e4866834d26 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -116,6 +116,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
+/*
+ * tk_clock_read - atomic clocksource read() helper
+ *
+ * This helper is necessary to use in the read paths because, while the
+ * seqlock ensures we don't return a bad value while structures are updated,
+ * it doesn't protect from potential crashes. There is the possibility that
+ * the tkr's clocksource may change between the read reference, and the
+ * clock reference passed to the read function.  This can cause crashes if
+ * the wrong clocksource is passed to the wrong read function.
+ * This isn't necessary to use when holding the timekeeper_lock or doing
+ * a read of the fast-timekeeper tkrs (which is protected by its own locking
+ * and update logic).
+ */
+static inline u64 tk_clock_read(struct tk_read_base *tkr)
+{
+	struct clocksource *clock = READ_ONCE(tkr->clock);
+
+	return clock->read(clock);
+}
+
 #ifdef CONFIG_DEBUG_TIMEKEEPING
 #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
 
@@ -173,7 +193,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	 */
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		now = tkr->read(tkr->clock);
+		now = tk_clock_read(tkr);
 		last = tkr->cycle_last;
 		mask = tkr->mask;
 		max = tkr->clock->max_cycles;
@@ -207,7 +227,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	cycle_t cycle_now, delta;
 
 	/* read clocksource */
-	cycle_now = tkr->read(tkr->clock);
+	cycle_now = tk_clock_read(tkr);
 
 	/* calculate the delta since the last update_wall_time */
 	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
@@ -235,12 +255,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 
 	old_clock = tk->tkr_mono.clock;
 	tk->tkr_mono.clock = clock;
-	tk->tkr_mono.read = clock->read;
 	tk->tkr_mono.mask = clock->mask;
-	tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+	tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);
 
 	tk->tkr_raw.clock = clock;
-	tk->tkr_raw.read = clock->read;
 	tk->tkr_raw.mask = clock->mask;
 	tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
 
@@ -298,17 +316,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+					  cycle_t delta)
+{
+	u64 nsec;
+
+	nsec = delta * tkr->mult + tkr->xtime_nsec;
+	nsec >>= tkr->shift;
+
+	/* If arch requires, add in get_arch_timeoffset() */
+	return nsec + arch_gettimeoffset();
+}
+
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
 	cycle_t delta;
-	s64 nsec;
 
 	delta = timekeeping_get_delta(tkr);
+	return timekeeping_delta_to_ns(tkr, delta);
+}
 
-	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
+static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
+					    cycle_t cycles)
+{
+	cycle_t delta;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
+	return timekeeping_delta_to_ns(tkr, delta);
 }
 
 /**
@@ -383,7 +418,13 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+		now = ktime_to_ns(tkr->base);
+
+		now += timekeeping_delta_to_ns(tkr,
+				clocksource_delta(
+					tk_clock_read(tkr),
+					tkr->cycle_last,
+					tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;
@@ -409,6 +450,10 @@ static cycle_t dummy_clock_read(struct clocksource *cs)
 	return cycles_at_suspend;
 }
 
+static struct clocksource dummy_clock = {
+	.read = dummy_clock_read,
+};
+
 /**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
  * @tk: Timekeeper to snapshot.
@@ -425,13 +470,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk)
 	struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
-	cycles_at_suspend = tkr->read(tkr->clock);
-	tkr_dummy.read = dummy_clock_read;
+	cycles_at_suspend = tk_clock_read(tkr);
+	tkr_dummy.clock = &dummy_clock;
 	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
 
 	tkr = &tk->tkr_raw;
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
-	tkr_dummy.read = dummy_clock_read;
+	tkr_dummy.clock = &dummy_clock;
 	update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
 }
 
@@ -595,11 +640,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
  */
 static void timekeeping_forward_now(struct timekeeper *tk)
 {
-	struct clocksource *clock = tk->tkr_mono.clock;
 	cycle_t cycle_now, delta;
 	s64 nsec;
 
-	cycle_now = tk->tkr_mono.read(clock);
+	cycle_now = tk_clock_read(&tk->tkr_mono);
 	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 	tk->tkr_mono.cycle_last = cycle_now;
 	tk->tkr_raw.cycle_last  = cycle_now;
@@ -958,7 +1002,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	struct timespec64 ts64, tmp;
 	int ret = 0;
 
-	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_inject_offset_valid(ts))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*ts);
@@ -1382,7 +1426,7 @@ void timekeeping_resume(void)
 	 * The less preferred source will only be tried if there is no better
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
-	cycle_now = tk->tkr_mono.read(clock);
+	cycle_now = tk_clock_read(&tk->tkr_mono);
 	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
 		cycle_now > tk->tkr_mono.cycle_last) {
 		u64 num, max = ULLONG_MAX;
@@ -1777,7 +1821,7 @@ void update_wall_time(void)
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
 #else
-	offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 #endif
 
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd65236712..107310a6f36f 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
 
 #include "timekeeping_internal.h"
 
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
 {
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
 
 void tk_debug_account_sleep_time(struct timespec64 *t)
 {
-	sleep_time_bin[fls(t->tv_sec)]++;
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
 }
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 9b1044e936a6..05ea5167e6bb 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -1,4 +1,8 @@
 
+# We are fully aware of the dangers of __builtin_return_address()
+FRAME_CFLAGS := $(call cc-disable-warning,frame-address)
+KBUILD_CFLAGS += $(FRAME_CFLAGS)
+
 # Do not instrument the tracer itself:
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3f743b147247..eba904bae48c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3535,7 +3535,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
 	int exclude_mod = 0;
 	int found = 0;
 	int ret;
-	int clear_filter;
+	int clear_filter = 0;
 
 	if (func) {
 		func_g.type = filter_parse_regex(func, len, &func_g.search,
@@ -3677,23 +3677,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
 	ftrace_probe_registered = 1;
 }
 
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
 {
 	int i;
 
 	if (!ftrace_probe_registered)
-		return;
+		return false;
 
 	for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
 		struct hlist_head *hhd = &ftrace_func_hash[i];
 		if (hhd->first)
-			return;
+			return false;
 	}
 
 	/* no more funcs left */
 	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
+	return true;
 }
 
 
@@ -3820,6 +3821,7 @@ static void
 __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				  void *data, int flags)
 {
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
@@ -3831,6 +3833,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
 	int i, ret;
+	bool disabled;
 
 	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		func_g.search = NULL;
@@ -3849,6 +3852,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
+	old_hash_ops.filter_hash = old_hash;
+	/* Probes only have filters */
+	old_hash_ops.notrace_hash = NULL;
+
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash)
 		/* Hmm, should report this somehow */
@@ -3886,12 +3893,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		}
 	}
 	mutex_lock(&ftrace_lock);
-	__disable_ftrace_function_probe();
+	disabled = __disable_ftrace_function_probe();
 	/*
 	 * Remove after the disable is called. Otherwise, if the last
 	 * probe is removed, a null hash means *all enabled*.
 	 */
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+	/* still need to update the function call sites */
+	if (ftrace_enabled && !disabled)
+		ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+				       &old_hash_ops);
 	synchronize_sched();
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c6045a27ba3..1275175b0946 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -437,7 +437,7 @@ struct ring_buffer_per_cpu {
 	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
-	unsigned int			nr_pages;
+	unsigned long			nr_pages;
 	unsigned int			current_context;
 	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
@@ -458,7 +458,7 @@ struct ring_buffer_per_cpu {
 	u64				write_stamp;
 	u64				read_stamp;
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
-	int				nr_pages_to_update;
+	long				nr_pages_to_update;
 	struct list_head		new_pages; /* new pages to add */
 	struct work_struct		update_pages_work;
 	struct completion		update_done;
@@ -1137,10 +1137,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	return 0;
 }
 
-static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu)
+static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
 {
-	int i;
 	struct buffer_page *bpage, *tmp;
+	long i;
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
@@ -1177,7 +1177,7 @@ free_pages:
 }
 
 static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
-			     unsigned nr_pages)
+			     unsigned long nr_pages)
 {
 	LIST_HEAD(pages);
 
@@ -1202,7 +1202,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 }
 
 static struct ring_buffer_per_cpu *
-rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, long nr_pages, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
@@ -1302,8 +1302,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 					struct lock_class_key *key)
 {
 	struct ring_buffer *buffer;
+	long nr_pages;
 	int bsize;
-	int cpu, nr_pages;
+	int cpu;
 
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1429,12 +1430,12 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
 }
 
 static int
-rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 {
 	struct list_head *tail_page, *to_remove, *next_page;
 	struct buffer_page *to_remove_page, *tmp_iter_page;
 	struct buffer_page *last_page, *first_page;
-	unsigned int nr_removed;
+	unsigned long nr_removed;
 	unsigned long head_bit;
 	int page_entries;
 
@@ -1651,7 +1652,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			int cpu_id)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned nr_pages;
+	unsigned long nr_pages;
 	int cpu, err = 0;
 
 	/*
@@ -1665,14 +1666,13 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return size;
 
-	size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
-	size *= BUF_PAGE_SIZE;
+	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
 	/* we need a minimum of two pages */
-	if (size < BUF_PAGE_SIZE * 2)
-		size = BUF_PAGE_SIZE * 2;
+	if (nr_pages < 2)
+		nr_pages = 2;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	size = nr_pages * BUF_PAGE_SIZE;
 
 	/*
 	 * Don't succeed if resizing is disabled, as a reader might be
@@ -3440,11 +3440,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *reader;
+	struct buffer_page *head_page;
+	struct buffer_page *commit_page;
+	unsigned commit;
 
 	cpu_buffer = iter->cpu_buffer;
 
-	return iter->head_page == cpu_buffer->commit_page &&
-		iter->head == rb_commit_index(cpu_buffer);
+	/* Remember, trace recording is off when iterator is in use */
+	reader = cpu_buffer->reader_page;
+	head_page = cpu_buffer->head_page;
+	commit_page = cpu_buffer->commit_page;
+	commit = rb_page_commit(commit_page);
+
+	return ((iter->head_page == commit_page && iter->head == commit) ||
+		(iter->head_page == reader && commit_page == head_page &&
+		 head_page->read == commit &&
+		 iter->head == rb_page_commit(cpu_buffer->reader_page)));
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
 
@@ -4645,8 +4657,9 @@ static int rb_cpu_notify(struct notifier_block *self,
 	struct ring_buffer *buffer =
 		container_of(self, struct ring_buffer, cpu_notify);
 	long cpu = (long)hcpu;
-	int cpu_i, nr_pages_same;
-	unsigned int nr_pages;
+	long nr_pages_same;
+	int cpu_i;
+	unsigned long nr_pages;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
@@ -4874,9 +4887,9 @@ static __init int test_ringbuffer(void)
 		rb_data[cpu].cnt = cpu;
 		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
 						 "rbtester/%d", cpu);
-		if (WARN_ON(!rb_threads[cpu])) {
+		if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
 			pr_cont("FAILED\n");
-			ret = -1;
+			ret = PTR_ERR(rb_threads[cpu]);
 			goto out_free;
 		}
 
@@ -4886,9 +4899,9 @@ static __init int test_ringbuffer(void)
 
 	/* Now create the rb hammer! */
 	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
-	if (WARN_ON(!rb_hammer)) {
+	if (WARN_ON(IS_ERR(rb_hammer))) {
 		pr_cont("FAILED\n");
-		ret = -1;
+		ret = PTR_ERR(rb_hammer);
 		goto out_free;
 	}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d9293402ee68..d59ebd9d21df 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1660,7 +1660,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 		TRACE_FLAG_IRQS_NOSUPPORT |
 #endif
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
-		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+		((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
 		(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
 }
@@ -4727,19 +4727,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	struct trace_iterator *iter = filp->private_data;
 	ssize_t sret;
 
-	/* return any leftover data */
-	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (sret != -EBUSY)
-		return sret;
-
-	trace_seq_init(&iter->seq);
-
 	/*
 	 * Avoid more than one consumer on a single file descriptor
 	 * This is just a matter of traces coherency, the ring buffer itself
 	 * is protected.
 	 */
 	mutex_lock(&iter->mutex);
+
+	/* return any leftover data */
+	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+	if (sret != -EBUSY)
+		goto out;
+
+	trace_seq_init(&iter->seq);
+
 	if (iter->trace->read) {
 		sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
 		if (sret)
@@ -4949,7 +4950,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
 	spd.nr_pages = i;
 
-	ret = splice_to_pipe(pipe, &spd);
+	if (i)
+		ret = splice_to_pipe(pipe, &spd);
+	else
+		ret = 0;
 out:
 	splice_shrink_spd(&spd);
 	return ret;
@@ -5763,9 +5767,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
 	if (*ppos & (PAGE_SIZE - 1))
 		return -EINVAL;
 
@@ -5775,6 +5776,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
  again:
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
@@ -5832,19 +5836,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	/* did we read anything? */
 	if (!spd.nr_pages) {
 		if (ret)
-			return ret;
+			goto out;
 
+		ret = -EAGAIN;
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
-			return -EAGAIN;
+			goto out;
 
 		ret = wait_on_pipe(iter, true);
 		if (ret)
-			return ret;
+			goto out;
 
 		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
+out:
 	splice_shrink_spd(&spd);
 
 	return ret;
@@ -6054,11 +6060,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
 		return ret;
 
  out_reg:
-	ret = register_ftrace_function_probe(glob, ops, count);
+	ret = alloc_snapshot(&global_trace);
+	if (ret < 0)
+		goto out;
 
-	if (ret >= 0)
-		alloc_snapshot(&global_trace);
+	ret = register_ftrace_function_probe(glob, ops, count);
 
+ out:
 	return ret < 0 ? ret : 0;
 }
 
@@ -6729,6 +6737,7 @@ static int instance_rmdir(const char *name)
 	}
 	kfree(tr->topts);
 
+	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d202d991edae..996f0fd34312 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2107,8 +2107,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	trace_create_file("filter", 0644, file->dir, file,
 			  &ftrace_event_filter_fops);
 
-	trace_create_file("trigger", 0644, file->dir, file,
-			  &event_trigger_fops);
+	/*
+	 * Only event directories that can be enabled should have
+	 * triggers.
+	 */
+	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
+		trace_create_file("trigger", 0644, file->dir, file,
+				  &event_trigger_fops);
 
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 6816302542b2..f0e5408499b6 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1979,6 +1979,10 @@ static int create_filter(struct trace_event_call *call,
 		if (err && set_str)
 			append_filter_err(ps, filter);
 	}
+	if (err && !set_str) {
+		free_event_filter(filter);
+		filter = NULL;
+	}
 	create_filter_finish(ps);
 
 	*filterp = filter;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a663cbb84107..7fd6f5a26143 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -780,6 +780,10 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
+		/* If a graph tracer ignored set_graph_notrace */
+		if (call->depth < -1)
+			call->depth += FTRACE_NOTRACE_DEPTH;
+
 		/*
 		 * Comments display at + 1 to depth. Since
 		 * this is a leaf function, keep the comments
@@ -788,7 +792,8 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		cpu_data->depth = call->depth - 1;
 
 		/* No need to keep this function around for this depth */
-		if (call->depth < FTRACE_RETFUNC_DEPTH)
+		if (call->depth < FTRACE_RETFUNC_DEPTH &&
+		    !WARN_ON_ONCE(call->depth < 0))
 			cpu_data->enter_funcs[call->depth] = 0;
 	}
 
@@ -818,11 +823,16 @@ print_graph_entry_nested(struct trace_iterator *iter,
 		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
 
+		/* If a graph tracer ignored set_graph_notrace */
+		if (call->depth < -1)
+			call->depth += FTRACE_NOTRACE_DEPTH;
+
 		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 		cpu_data->depth = call->depth;
 
 		/* Save this function pointer to see if the exit matches */
-		if (call->depth < FTRACE_RETFUNC_DEPTH)
+		if (call->depth < FTRACE_RETFUNC_DEPTH &&
+		    !WARN_ON_ONCE(call->depth < 0))
 			cpu_data->enter_funcs[call->depth] = call->func;
 	}
 
@@ -1052,7 +1062,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		 */
 		cpu_data->depth = trace->depth - 1;
 
-		if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+		if (trace->depth < FTRACE_RETFUNC_DEPTH &&
+		    !WARN_ON_ONCE(trace->depth < 0)) {
 			if (cpu_data->enter_funcs[trace->depth] != trace->func)
 				func_match = 0;
 			cpu_data->enter_funcs[trace->depth] = 0;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index e4e56589ec1d..be3222b7d72e 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr,
 		return 0;
 
 	local_save_flags(*flags);
-	/* slight chance to get a false positive on tracing_cpu */
-	if (!irqs_disabled_flags(*flags))
+	/*
+	 * Slight chance to get a false positive on tracing_cpu,
+	 * although I'm starting to think there isn't a chance.
+	 * Leave this for now just to be paranoid.
+	 */
+	if (!irqs_disabled_flags(*flags) && !preempt_count())
 		return 0;
 
 	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9956440d0e6..e9092a0247bf 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -659,30 +659,25 @@ static int create_trace_kprobe(int argc, char **argv)
 		pr_info("Probe point is not specified.\n");
 		return -EINVAL;
 	}
-	if (isdigit(argv[1][0])) {
-		if (is_return) {
-			pr_info("Return probe point must be a symbol.\n");
-			return -EINVAL;
-		}
-		/* an address specified */
-		ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
-		if (ret) {
-			pr_info("Failed to parse address.\n");
-			return ret;
-		}
-	} else {
+
+	/* try to parse an address. if that fails, try to read the
+	 * input as a symbol. */
+	if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
 		/* a symbol specified */
 		symbol = argv[1];
 		/* TODO: support .init module functions */
 		ret = traceprobe_split_symbol_offset(symbol, &offset);
 		if (ret) {
-			pr_info("Failed to parse symbol.\n");
+			pr_info("Failed to parse either an address or a symbol.\n");
 			return ret;
 		}
 		if (offset && is_return) {
 			pr_info("Return probe must be used without offset.\n");
 			return -EINVAL;
 		}
+	} else if (is_return) {
+		pr_info("Return probe point must be a symbol.\n");
+		return -EINVAL;
 	}
 	argc -= 2; argv += 2;
 
@@ -1471,6 +1466,11 @@ static __init int kprobe_trace_self_tests_init(void)
 
 end:
 	release_all_trace_kprobes();
+	/*
+	 * Wait for the optimizer work to finish. Otherwise it might fiddle
+	 * with probes in already freed __init text.
+	 */
+	wait_for_kprobe_optimizer();
 	if (warn)
 		pr_cont("NG: Some tests are failed. Please check them.\n");
 	else
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 060df67dbdd1..ad1d6164e946 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
 {
 	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
 	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
 		if (!strcmp(pos->fmt, fmt))
 			return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
 		if (tb_fmt) {
-			*iter = tb_fmt->fmt;
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
 			continue;
 		}
 
@@ -296,6 +301,9 @@ static int t_show(struct seq_file *m, void *v)
 	const char *str = *fmt;
 	int i;
 
+	if (!*fmt)
+		return 0;
+
 	seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
 
 	/*
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 18f34cf75f74..c1e0b5f429b6 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -328,7 +328,6 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	 */
 	if (is_hardlockup()) {
 		int this_cpu = smp_processor_id();
-		struct pt_regs *regs = get_irq_regs();
 
 		/* only print hardlockups once */
 		if (__this_cpu_read(hard_watchdog_warn) == true)
@@ -907,6 +906,9 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 		 * both lockup detectors are disabled if proc_watchdog_update()
 		 * returns an error.
 		 */
+		if (old == new)
+			goto out;
+
 		err = proc_watchdog_update();
 	}
 out:
@@ -951,7 +953,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write,
 int proc_watchdog_thresh(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old;
+	int err, old, new;
 
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
@@ -971,6 +973,10 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
 	/*
 	 * Update the sample period. Restore on failure.
 	 */
+	new = ACCESS_ONCE(watchdog_thresh);
+	if (old == new)
+		goto out;
+
 	set_sample_period();
 	err = proc_watchdog_update();
 	if (err) {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 450c21fd0e6e..23231237f2e2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -649,6 +649,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	 */
 	smp_wmb();
 	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+	/*
+	 * The following mb guarantees that previous clear of a PENDING bit
+	 * will not be reordered with any speculative LOADS or STORES from
+	 * work->current_func, which is executed afterwards.  This possible
+	 * reordering can lead to a missed execution on attempt to qeueue
+	 * the same @work.  E.g. consider this case:
+	 *
+	 *   CPU#0                         CPU#1
+	 *   ----------------------------  --------------------------------
+	 *
+	 * 1  STORE event_indicated
+	 * 2  queue_work_on() {
+	 * 3    test_and_set_bit(PENDING)
+	 * 4 }                             set_..._and_clear_pending() {
+	 * 5                                 set_work_data() # clear bit
+	 * 6                                 smp_mb()
+	 * 7                               work->current_func() {
+	 * 8				      LOAD event_indicated
+	 *				   }
+	 *
+	 * Without an explicit full barrier speculative LOAD on line 8 can
+	 * be executed before CPU#0 does STORE on line 1.  If that happens,
+	 * CPU#0 observes the PENDING bit is still set and new execution of
+	 * a @work is not queued in a hope, that CPU#1 will eventually
+	 * finish the queued @work.  Meanwhile CPU#1 does not see
+	 * event_indicated is set, because speculative LOAD was executed
+	 * before actual STORE.
+	 */
+	smp_mb();
 }
 
 static void clear_work_data(struct work_struct *work)
@@ -3618,8 +3647,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 		return -EINVAL;
 
 	/* creating multiple pwqs breaks ordering guarantee */
-	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
-		return -EINVAL;
+	if (!list_empty(&wq->pwqs)) {
+		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+			return -EINVAL;
+
+		wq->flags &= ~__WQ_ORDERED;
+	}
 
 	ctx = apply_wqattrs_prepare(wq, attrs);
 
@@ -3805,6 +3838,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
 
+	/*
+	 * Unbound && max_active == 1 used to imply ordered, which is no
+	 * longer the case on NUMA machines due to per-node pools.  While
+	 * alloc_ordered_workqueue() is the right way to create an ordered
+	 * workqueue, keep the previous behavior to avoid subtle breakages
+	 * on NUMA.
+	 */
+	if ((flags & WQ_UNBOUND) && max_active == 1)
+		flags |= __WQ_ORDERED;
+
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
@@ -3993,13 +4036,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 	struct pool_workqueue *pwq;
 
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
+	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
 
 	for_each_pwq(pwq, wq)
@@ -4428,6 +4472,17 @@ static void rebind_workers(struct worker_pool *pool)
 						  pool->attrs->cpumask) < 0);
 
 	spin_lock_irq(&pool->lock);
+
+	/*
+	 * XXX: CPU hotplug notifiers are weird and can call DOWN_FAILED
+	 * w/o preceding DOWN_PREPARE.  Work around it.  CPU hotplug is
+	 * being reworked and this can go away in time.
+	 */
+	if (!(pool->flags & POOL_DISASSOCIATED)) {
+		spin_unlock_irq(&pool->lock);
+		return;
+	}
+
 	pool->flags &= ~POOL_DISASSOCIATED;
 
 	for_each_pool_worker(worker, pool) {
@@ -5114,7 +5169,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	 * attributes breaks ordering guarantee.  Disallow exposing ordered
 	 * workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8c15b29d5adc..b53b375e14bd 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -145,7 +145,7 @@ config DEBUG_INFO_REDUCED
 
 config DEBUG_INFO_SPLIT
 	bool "Produce split debuginfo in .dwo files"
-	depends on DEBUG_INFO
+	depends on DEBUG_INFO && !FRV
 	help
 	  Generate debug info into separate .dwo files. This significantly
 	  reduces the build directory size for builds with DEBUG_INFO,
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 2b3f46c049d4..554522934c44 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -74,7 +74,7 @@ next_tag:
 
 	/* Extract a tag from the data */
 	tag = data[dp++];
-	if (tag == 0) {
+	if (tag == ASN1_EOC) {
 		/* It appears to be an EOC. */
 		if (data[dp++] != 0)
 			goto invalid_eoc;
@@ -96,10 +96,8 @@ next_tag:
 
 	/* Extract the length */
 	len = data[dp++];
-	if (len <= 0x7f) {
-		dp += len;
-		goto next_tag;
-	}
+	if (len <= 0x7f)
+		goto check_length;
 
 	if (unlikely(len == ASN1_INDEFINITE_LENGTH)) {
 		/* Indefinite length */
@@ -110,14 +108,18 @@ next_tag:
 	}
 
 	n = len - 0x80;
-	if (unlikely(n > sizeof(size_t) - 1))
+	if (unlikely(n > sizeof(len) - 1))
 		goto length_too_long;
 	if (unlikely(n > datalen - dp))
 		goto data_overrun_error;
-	for (len = 0; n > 0; n--) {
+	len = 0;
+	for (; n > 0; n--) {
 		len <<= 8;
 		len |= data[dp++];
 	}
+check_length:
+	if (len > datalen - dp)
+		goto data_overrun_error;
 	dp += len;
 	goto next_tag;
 
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 03dd576e6773..59fd7c0b119c 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -524,7 +524,9 @@ static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit,
 			free_slot = i;
 			continue;
 		}
-		if (ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) {
+		if (assoc_array_ptr_is_leaf(ptr) &&
+		    ops->compare_object(assoc_array_ptr_to_leaf(ptr),
+					index_key)) {
 			pr_devel("replace in slot %d\n", i);
 			edit->leaf_p = &node->slots[i];
 			edit->dead_leaf = node->slots[i];
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 8f13cf73c2ec..79069d7938ea 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -22,14 +22,14 @@
  *	the values[M, M+1, ..., N] into the ints array in get_options.
  */
 
-static int get_range(char **str, int *pint)
+static int get_range(char **str, int *pint, int n)
 {
 	int x, inc_counter, upper_range;
 
 	(*str)++;
 	upper_range = simple_strtol((*str), NULL, 0);
 	inc_counter = upper_range - *pint;
-	for (x = *pint; x < upper_range; x++)
+	for (x = *pint; n && x < upper_range; x++, n--)
 		*pint++ = x;
 	return inc_counter;
 }
@@ -96,7 +96,7 @@ char *get_options(const char *str, int nints, int *ints)
 			break;
 		if (res == 3) {
 			int range_nums;
-			range_nums = get_range((char **)&str, ints + i);
+			range_nums = get_range((char **)&str, ints + i, nints - i);
 			if (range_nums < 0)
 				break;
 			/*
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 4a1515f4b452..51a76af25c66 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -657,9 +657,9 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	spin_lock_irqsave(&free_entries_lock, flags);
 
 	if (list_empty(&free_entries)) {
-		pr_err("DMA-API: debugging out of memory - disabling\n");
 		global_disable = true;
 		spin_unlock_irqrestore(&free_entries_lock, flags);
+		pr_err("DMA-API: debugging out of memory - disabling\n");
 		return NULL;
 	}
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 116a166b096f..27aa9c629d13 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -273,7 +273,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 	struct gen_pool_chunk *chunk;
 	unsigned long addr = 0;
 	int order = pool->min_alloc_order;
-	int nbits, start_bit = 0, end_bit, remain;
+	int nbits, start_bit, end_bit, remain;
 
 #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 	BUG_ON(in_nmi());
@@ -288,6 +288,7 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 		if (size > atomic_read(&chunk->avail))
 			continue;
 
+		start_bit = 0;
 		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 75232ad0a5e7..daca582a8ed0 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -298,33 +298,13 @@ done:
 }
 
 /*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
-	if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		bytes = min(bytes, i->iov->iov_len - i->iov_offset);
-		return fault_in_pages_readable(buf, bytes);
-	}
-	return 0;
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
-/*
  * Fault in one or more iovecs of the given iov_iter, to a maximum length of
  * bytes.  For each iovec, fault in each page that constitutes the iovec.
  *
  * Return 0 on success, or non-zero if the memory could not be accessed (i.e.
  * because it is an invalid address).
  */
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes)
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 {
 	size_t skip = i->iov_offset;
 	const struct iovec *iov;
@@ -341,7 +321,7 @@ int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable);
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
 
 void iov_iter_init(struct iov_iter *i, int direction,
 			const struct iovec *iov, unsigned long nr_segs,
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 94be244e8441..d8a5cf66c316 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -321,6 +321,70 @@ int kstrtos8(const char *s, unsigned int base, s8 *res)
 }
 EXPORT_SYMBOL(kstrtos8);
 
+/**
+ * kstrtobool - convert common user inputs into boolean values
+ * @s: input string
+ * @res: result
+ *
+ * This routine returns 0 iff the first character is one of 'Yy1Nn0', or
+ * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL.  Value
+ * pointed to by res is updated upon finding a match.
+ */
+int kstrtobool(const char *s, bool *res)
+{
+	if (!s)
+		return -EINVAL;
+
+	switch (s[0]) {
+	case 'y':
+	case 'Y':
+	case '1':
+		*res = true;
+		return 0;
+	case 'n':
+	case 'N':
+	case '0':
+		*res = false;
+		return 0;
+	case 'o':
+	case 'O':
+		switch (s[1]) {
+		case 'n':
+		case 'N':
+			*res = true;
+			return 0;
+		case 'f':
+		case 'F':
+			*res = false;
+			return 0;
+		default:
+			break;
+		}
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(kstrtobool);
+
+/*
+ * Since "base" would be a nonsense argument, this open-codes the
+ * _from_user helper instead of using the helper macro below.
+ */
+int kstrtobool_from_user(const char __user *s, size_t count, bool *res)
+{
+	/* Longest string needed to differentiate, newline, terminator */
+	char buf[4];
+
+	count = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, s, count))
+		return -EFAULT;
+	buf[count] = '\0';
+	return kstrtobool(buf, res);
+}
+EXPORT_SYMBOL(kstrtobool_from_user);
+
 #define kstrto_from_user(f, g, type)					\
 int f(const char __user *s, size_t count, unsigned int base, type *res)	\
 {									\
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index abcecdc2d0f2..0710a62ad2f6 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -11,8 +11,7 @@
 /*
  * Detects 64 bits mode
  */
-#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \
-	|| defined(__ppc64__) || defined(__LP64__))
+#if defined(CONFIG_64BIT)
 #define LZ4_ARCH64 1
 #else
 #define LZ4_ARCH64 0
@@ -35,6 +34,10 @@ typedef struct _U64_S { u64 v; } U64_S;
 
 #define PUT4(s, d) (A32(d) = A32(s))
 #define PUT8(s, d) (A64(d) = A64(s))
+
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p)	\
+	(d = s - A16(p))
+
 #define LZ4_WRITE_LITTLEENDIAN_16(p, v)	\
 	do {	\
 		A16(p) = v; \
@@ -51,10 +54,13 @@ typedef struct _U64_S { u64 v; } U64_S;
 #define PUT8(s, d) \
 	put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
 
-#define LZ4_WRITE_LITTLEENDIAN_16(p, v)	\
-	do {	\
-		put_unaligned(v, (u16 *)(p)); \
-		p += 2; \
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p)	\
+	(d = s - get_unaligned_le16(p))
+
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v)			\
+	do {						\
+		put_unaligned_le16(v, (u16 *)(p));	\
+		p += 2;					\
 	} while (0)
 #endif
 
@@ -140,9 +146,6 @@ typedef struct _U64_S { u64 v; } U64_S;
 
 #endif
 
-#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
-	(d = s - get_unaligned_le16(p))
-
 #define LZ4_WILDCOPY(s, d, e)		\
 	do {				\
 		LZ4_COPYPACKET(s, d);	\
diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c
index 5464c8744ea9..e24388a863a7 100644
--- a/lib/mpi/mpi-pow.c
+++ b/lib/mpi/mpi-pow.c
@@ -64,8 +64,13 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod)
 	if (!esize) {
 		/* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0
 		 * depending on if MOD equals 1.  */
-		rp[0] = 1;
 		res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1;
+		if (res->nlimbs) {
+			if (mpi_resize(res, 1) < 0)
+				goto enomem;
+			rp = res->d;
+			rp[0] = 1;
+		}
 		res->sign = 0;
 		goto leave;
 	}
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 3db76b8c1115..e37dbf53e226 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -128,6 +128,23 @@ leave:
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
+static int count_lzeros(MPI a)
+{
+	mpi_limb_t alimb;
+	int i, lzeros = 0;
+
+	for (i = a->nlimbs - 1; i >= 0; i--) {
+		alimb = a->d[i];
+		if (alimb == 0) {
+			lzeros += sizeof(mpi_limb_t);
+		} else {
+			lzeros += count_leading_zeros(alimb) / 8;
+			break;
+		}
+	}
+	return lzeros;
+}
+
 /**
  * mpi_read_buffer() - read MPI to a bufer provided by user (msb first)
  *
@@ -146,7 +163,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	uint8_t *p;
 	mpi_limb_t alimb;
 	unsigned int n = mpi_get_size(a);
-	int i, lzeros = 0;
+	int i, lzeros;
 
 	if (buf_len < n || !buf || !nbytes)
 		return -EINVAL;
@@ -154,14 +171,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	if (sign)
 		*sign = a->sign;
 
-	p = (void *)&a->d[a->nlimbs] - 1;
-
-	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
-		if (!*p)
-			lzeros++;
-		else
-			break;
-	}
+	lzeros = count_lzeros(a);
 
 	p = buf;
 	*nbytes = n - lzeros;
@@ -343,7 +353,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 	u8 *p, *p2;
 	mpi_limb_t alimb, alimb2;
 	unsigned int n = mpi_get_size(a);
-	int i, x, y = 0, lzeros = 0, buf_len;
+	int i, x, y = 0, lzeros, buf_len;
 
 	if (!nbytes || *nbytes < n)
 		return -EINVAL;
@@ -351,20 +361,15 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 	if (sign)
 		*sign = a->sign;
 
-	p = (void *)&a->d[a->nlimbs] - 1;
-
-	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
-		if (!*p)
-			lzeros++;
-		else
-			break;
-	}
+	lzeros = count_lzeros(a);
 
 	*nbytes = n - lzeros;
 	buf_len = sgl->length;
 	p2 = sg_virt(sgl);
 
-	for (i = a->nlimbs - 1; i >= 0; i--) {
+	for (i = a->nlimbs - 1 - lzeros / BYTES_PER_MPI_LIMB,
+			lzeros %= BYTES_PER_MPI_LIMB;
+		i >= 0; i--) {
 		alimb = a->d[i];
 		p = (u8 *)&alimb2;
 #if BYTES_PER_MPI_LIMB == 4
@@ -385,17 +390,12 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 #error please implement for this limb size.
 #endif
 		if (lzeros > 0) {
-			if (lzeros >= sizeof(alimb)) {
-				p -= sizeof(alimb);
-				continue;
-			} else {
-				mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
-				mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
-							+ lzeros;
-				*limb1 = *limb2;
-				p -= lzeros;
-				y = lzeros;
-			}
+			mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
+			mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
+				+ lzeros;
+			*limb1 = *limb2;
+			p -= lzeros;
+			y = lzeros;
 			lzeros -= sizeof(alimb);
 		}
 
diff --git a/lib/string.c b/lib/string.c
index 0323c0d5629a..1a90db9bc6e1 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -630,35 +630,6 @@ bool sysfs_streq(const char *s1, const char *s2)
 }
 EXPORT_SYMBOL(sysfs_streq);
 
-/**
- * strtobool - convert common user inputs into boolean values
- * @s: input string
- * @res: result
- *
- * This routine returns 0 iff the first character is one of 'Yy1Nn0'.
- * Otherwise it will return -EINVAL.  Value pointed to by res is
- * updated upon finding a match.
- */
-int strtobool(const char *s, bool *res)
-{
-	switch (s[0]) {
-	case 'y':
-	case 'Y':
-	case '1':
-		*res = true;
-		break;
-	case 'n':
-	case 'N':
-	case '0':
-		*res = false;
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(strtobool);
-
 #ifndef __HAVE_ARCH_MEMSET
 /**
  * memset - Fill a region of memory with the given value
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 76f29ecba8f4..771234d050c7 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -452,11 +452,11 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
 
 	/*
-	 * For mappings greater than a page, we limit the stride (and
-	 * hence alignment) to a page size.
+	 * For mappings greater than or equal to a page, we limit the stride
+	 * (and hence alignment) to a page size.
 	 */
 	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size > PAGE_SIZE)
+	if (size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index 98866a770770..25b5cbfb7615 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -327,36 +327,67 @@ out:
 }
 
 #define string_get_size_maxbuf 16
-#define test_string_get_size_one(size, blk_size, units, exp_result)            \
+#define test_string_get_size_one(size, blk_size, exp_result10, exp_result2)    \
 	do {                                                                   \
-		BUILD_BUG_ON(sizeof(exp_result) >= string_get_size_maxbuf);    \
-		__test_string_get_size((size), (blk_size), (units),            \
-				       (exp_result));                          \
+		BUILD_BUG_ON(sizeof(exp_result10) >= string_get_size_maxbuf);  \
+		BUILD_BUG_ON(sizeof(exp_result2) >= string_get_size_maxbuf);   \
+		__test_string_get_size((size), (blk_size), (exp_result10),     \
+				       (exp_result2));                         \
 	} while (0)
 
 
-static __init void __test_string_get_size(const u64 size, const u64 blk_size,
-					  const enum string_size_units units,
-					  const char *exp_result)
+static __init void test_string_get_size_check(const char *units,
+					      const char *exp,
+					      char *res,
+					      const u64 size,
+					      const u64 blk_size)
 {
-	char buf[string_get_size_maxbuf];
-
-	string_get_size(size, blk_size, units, buf, sizeof(buf));
-	if (!memcmp(buf, exp_result, strlen(exp_result) + 1))
+	if (!memcmp(res, exp, strlen(exp) + 1))
 		return;
 
-	buf[sizeof(buf) - 1] = '\0';
-	pr_warn("Test 'test_string_get_size_one' failed!\n");
-	pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n",
+	res[string_get_size_maxbuf - 1] = '\0';
+
+	pr_warn("Test 'test_string_get_size' failed!\n");
+	pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %s)\n",
 		size, blk_size, units);
-	pr_warn("expected: '%s', got '%s'\n", exp_result, buf);
+	pr_warn("expected: '%s', got '%s'\n", exp, res);
+}
+
+static __init void __test_string_get_size(const u64 size, const u64 blk_size,
+					  const char *exp_result10,
+					  const char *exp_result2)
+{
+	char buf10[string_get_size_maxbuf];
+	char buf2[string_get_size_maxbuf];
+
+	string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10));
+	string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2));
+
+	test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10,
+				   size, blk_size);
+
+	test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2,
+				   size, blk_size);
 }
 
 static __init void test_string_get_size(void)
 {
-	test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB");
-	test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB");
-	test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B");
+	/* small values */
+	test_string_get_size_one(0, 512, "0 B", "0 B");
+	test_string_get_size_one(1, 512, "512 B", "512 B");
+	test_string_get_size_one(1100, 1, "1.10 kB", "1.07 KiB");
+
+	/* normal values */
+	test_string_get_size_one(16384, 512, "8.39 MB", "8.00 MiB");
+	test_string_get_size_one(500118192, 512, "256 GB", "238 GiB");
+	test_string_get_size_one(8192, 4096, "33.6 MB", "32.0 MiB");
+
+	/* weird block sizes */
+	test_string_get_size_one(3000, 1900, "5.70 MB", "5.44 MiB");
+
+	/* huge values */
+	test_string_get_size_one(U64_MAX, 4096, "75.6 ZB", "64.0 ZiB");
+	test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB");
 }
 
 static int __init test_string_helpers_init(void)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 10cd1860e5b0..7e26aea3e404 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4315,6 +4315,51 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		/* Mainly testing JIT + imm64 here. */
+		"JMP_JGE_X: ldimm64 test 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 2),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xeeeeeeeeU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 0),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffffU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 4),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
 	/* BPF_JMP | BPF_JNE | BPF_X */
 	{
 		"JMP_JNE_X: if (3 != 2) return 1",
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 0ecef3e4690e..5e6db6b1e3bd 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -58,7 +58,9 @@ static int __init test_user_copy_init(void)
 	usermem = (char __user *)user_addr;
 	bad_usermem = (char *)user_addr;
 
-	/* Legitimate usage: none of these should fail. */
+	/*
+	 * Legitimate usage: none of these copies should fail.
+	 */
 	ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE),
 		    "legitimate copy_from_user failed");
 	ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE),
@@ -68,19 +70,33 @@ static int __init test_user_copy_init(void)
 	ret |= test(put_user(value, (unsigned long __user *)usermem),
 		    "legitimate put_user failed");
 
-	/* Invalid usage: none of these should succeed. */
+	/*
+	 * Invalid usage: none of these copies should succeed.
+	 */
+
+	/* Reject kernel-to-kernel copies through copy_from_user(). */
 	ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE),
 				    PAGE_SIZE),
 		    "illegal all-kernel copy_from_user passed");
+
+#if 0
+	/*
+	 * When running with SMAP/PAN/etc, this will Oops the kernel
+	 * due to the zeroing of userspace memory on failure. This needs
+	 * to be tested in LKDTM instead, since this test module does not
+	 * expect to explode.
+	 */
 	ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem,
 				    PAGE_SIZE),
 		    "illegal reversed copy_from_user passed");
+#endif
 	ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE,
 				  PAGE_SIZE),
 		    "illegal all-kernel copy_to_user passed");
 	ret |= test(!copy_to_user((char __user *)kmem, bad_usermem,
 				  PAGE_SIZE),
 		    "illegal reversed copy_to_user passed");
+
 	ret |= test(!get_user(value, (unsigned long __user *)kmem),
 		    "illegal get_user passed");
 	ret |= test(!put_user(value, (unsigned long __user *)kmem),
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index cbe6f0b96f29..a988d4ef39da 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -757,15 +757,20 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	if (!bdi->wb_congested)
 		return -ENOMEM;
 
+	atomic_set(&bdi->wb_congested->refcnt, 1);
+
 	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (err) {
-		kfree(bdi->wb_congested);
+		wb_congested_put(bdi->wb_congested);
 		return err;
 	}
 	return 0;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+{
+	wb_congested_put(bdi->wb_congested);
+}
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
@@ -825,6 +830,20 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
 }
 EXPORT_SYMBOL(bdi_register_dev);
 
+int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
+{
+	int rc;
+
+	rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt),
+			MINOR(owner->devt));
+	if (rc)
+		return rc;
+	bdi->owner = owner;
+	get_device(owner);
+	return 0;
+}
+EXPORT_SYMBOL(bdi_register_owner);
+
 /*
  * Remove bdi from bdi_list, and ensure that it is no longer visible
  */
@@ -849,6 +868,11 @@ void bdi_unregister(struct backing_dev_info *bdi)
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
 	}
+
+	if (bdi->owner) {
+		put_device(bdi->owner);
+		bdi->owner = NULL;
+	}
 }
 
 void bdi_exit(struct backing_dev_info *bdi)
diff --git a/mm/cma.c b/mm/cma.c
index ea506eb18cd6..bd0e1412475e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -183,7 +183,8 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 		return -EINVAL;
 
 	/* ensure minimal alignment required by mm core */
-	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	alignment = PAGE_SIZE <<
+			max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
 
 	/* alignment should be aligned with order_per_bit */
 	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
@@ -266,8 +267,8 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	 * migratetype page by page allocator's buddy algorithm. In the case,
 	 * you couldn't get a contiguous memory, which is not what we want.
 	 */
-	alignment = max(alignment,
-		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
+	alignment = max(alignment,  (phys_addr_t)PAGE_SIZE <<
+			  max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
 	base = ALIGN(base, alignment);
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);
diff --git a/mm/compaction.c b/mm/compaction.c
index de3e1e71cd9f..dba02dec7195 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -475,25 +475,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
+		if (!isolated)
+			break;
+
 		total_isolated += isolated;
+		cc->nr_freepages += isolated;
 		for (i = 0; i < isolated; i++) {
 			list_add(&page->lru, freelist);
 			page++;
 		}
-
-		/* If a page was split, advance to the end of it */
-		if (isolated) {
-			cc->nr_freepages += isolated;
-			if (!strict &&
-				cc->nr_migratepages <= cc->nr_freepages) {
-				blockpfn += isolated;
-				break;
-			}
-
-			blockpfn += isolated - 1;
-			cursor += isolated - 1;
-			continue;
+		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
+			blockpfn += isolated;
+			break;
 		}
+		/* Advance to the end of split page */
+		blockpfn += isolated - 1;
+		cursor += isolated - 1;
+		continue;
 
 isolate_fail:
 		if (strict)
@@ -503,6 +501,9 @@ isolate_fail:
 
 	}
 
+	if (locked)
+		spin_unlock_irqrestore(&cc->zone->lock, flags);
+
 	/*
 	 * There is a tiny chance that we have read bogus compound_order(),
 	 * so be careful to not go outside of the pageblock.
@@ -524,9 +525,6 @@ isolate_fail:
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	if (locked)
-		spin_unlock_irqrestore(&cc->zone->lock, flags);
-
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
@@ -880,16 +878,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
 							ISOLATE_UNEVICTABLE);
 
-		/*
-		 * In case of fatal failure, release everything that might
-		 * have been isolated in the previous iteration, and signal
-		 * the failure back to caller.
-		 */
-		if (!pfn) {
-			putback_movable_pages(&cc->migratepages);
-			cc->nr_migratepages = 0;
+		if (!pfn)
 			break;
-		}
 
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
 			break;
@@ -974,7 +964,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_end_pfn = block_start_pfn,
 				block_start_pfn -= pageblock_nr_pages,
 				isolate_start_pfn = block_start_pfn) {
-
 		/*
 		 * This can iterate a massively long zone without finding any
 		 * suitable migration targets, so periodically check if we need
@@ -998,32 +987,30 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Found a block suitable for isolating free pages from. */
-		isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, false);
+		isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
+					freelist, false);
 
 		/*
-		 * If we isolated enough freepages, or aborted due to async
-		 * compaction being contended, terminate the loop.
-		 * Remember where the free scanner should restart next time,
-		 * which is where isolate_freepages_block() left off.
-		 * But if it scanned the whole pageblock, isolate_start_pfn
-		 * now points at block_end_pfn, which is the start of the next
-		 * pageblock.
-		 * In that case we will however want to restart at the start
-		 * of the previous pageblock.
+		 * If we isolated enough freepages, or aborted due to lock
+		 * contention, terminate.
 		 */
 		if ((cc->nr_freepages >= cc->nr_migratepages)
 							|| cc->contended) {
-			if (isolate_start_pfn >= block_end_pfn)
+			if (isolate_start_pfn >= block_end_pfn) {
+				/*
+				 * Restart at previous pageblock if more
+				 * freepages can be isolated next time.
+				 */
 				isolate_start_pfn =
 					block_start_pfn - pageblock_nr_pages;
+			}
 			break;
-		} else {
+		} else if (isolate_start_pfn < block_end_pfn) {
 			/*
-			 * isolate_freepages_block() should not terminate
-			 * prematurely unless contended, or isolated enough
+			 * If isolation failed early, do not continue
+			 * needlessly.
 			 */
-			VM_BUG_ON(isolate_start_pfn < block_end_pfn);
+			break;
 		}
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 1bb007624b53..69f75c77c098 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -109,6 +109,48 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page, void **shadowp)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	error = __radix_tree_create(&mapping->page_tree, page->index,
+				    &node, &slot);
+	if (error)
+		return error;
+	if (*slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		if (shadowp)
+			*shadowp = p;
+		mapping->nrshadows--;
+		if (node)
+			workingset_node_shadows_dec(node);
+	}
+	radix_tree_replace_slot(slot, page);
+	mapping->nrpages++;
+	if (node) {
+		workingset_node_pages_inc(node);
+		/*
+		 * Don't track node that contains actual pages.
+		 *
+		 * Avoid acquiring the list_lru lock if already
+		 * untracked.  The list_empty() test is safe as
+		 * node->private_list is protected by
+		 * mapping->tree_lock.
+		 */
+		if (!list_empty(&node->private_list))
+			list_lru_del(&workingset_shadow_nodes,
+				     &node->private_list);
+	}
+	return 0;
+}
+
 static void page_cache_tree_delete(struct address_space *mapping,
 				   struct page *page, void *shadow)
 {
@@ -122,6 +164,14 @@ static void page_cache_tree_delete(struct address_space *mapping,
 
 	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
 
+	if (!node) {
+		/*
+		 * We need a node to properly account shadow
+		 * entries. Don't plant any without. XXX
+		 */
+		shadow = NULL;
+	}
+
 	if (shadow) {
 		mapping->nrshadows++;
 		/*
@@ -538,9 +588,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		memcg = mem_cgroup_begin_page_stat(old);
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		__delete_from_page_cache(old, NULL, memcg);
-		error = radix_tree_insert(&mapping->page_tree, offset, new);
+		error = page_cache_tree_insert(mapping, new, NULL);
 		BUG_ON(error);
-		mapping->nrpages++;
 
 		/*
 		 * hugetlb pages do not participate in page cache accounting.
@@ -562,48 +611,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
-static int page_cache_tree_insert(struct address_space *mapping,
-				  struct page *page, void **shadowp)
-{
-	struct radix_tree_node *node;
-	void **slot;
-	int error;
-
-	error = __radix_tree_create(&mapping->page_tree, page->index,
-				    &node, &slot);
-	if (error)
-		return error;
-	if (*slot) {
-		void *p;
-
-		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
-		if (!radix_tree_exceptional_entry(p))
-			return -EEXIST;
-		if (shadowp)
-			*shadowp = p;
-		mapping->nrshadows--;
-		if (node)
-			workingset_node_shadows_dec(node);
-	}
-	radix_tree_replace_slot(slot, page);
-	mapping->nrpages++;
-	if (node) {
-		workingset_node_pages_inc(node);
-		/*
-		 * Don't track node that contains actual pages.
-		 *
-		 * Avoid acquiring the list_lru lock if already
-		 * untracked.  The list_empty() test is safe as
-		 * node->private_list is protected by
-		 * mapping->tree_lock.
-		 */
-		if (!list_empty(&node->private_list))
-			list_lru_del(&workingset_shadow_nodes,
-				     &node->private_list);
-	}
-	return 0;
-}
-
 static int __add_to_page_cache_locked(struct page *page,
 				      struct address_space *mapping,
 				      pgoff_t offset, gfp_t gfp_mask,
@@ -858,9 +865,12 @@ void page_endio(struct page *page, int rw, int err)
 		unlock_page(page);
 	} else { /* rw == WRITE */
 		if (err) {
+			struct address_space *mapping;
+
 			SetPageError(page);
-			if (page->mapping)
-				mapping_set_error(page->mapping, err);
+			mapping = page_mapping(page);
+			if (mapping)
+				mapping_set_error(mapping, err);
 		}
 		end_page_writeback(page);
 	}
@@ -1552,6 +1562,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
 
 		cond_resched();
 find_page:
+		if (fatal_signal_pending(current)) {
+			error = -EINTR;
+			goto out;
+		}
+
 		page = find_get_page(mapping, index);
 		if (!page) {
 			page_cache_sync_readahead(mapping,
diff --git a/mm/gup.c b/mm/gup.c
index deafa2c91b36..b599526db9f7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -58,6 +58,16 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
 	return -EEXIST;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
+{
+	return pte_write(pte) ||
+		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
+}
+
 static struct page *follow_page_pte(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd, unsigned int flags)
 {
@@ -92,7 +102,7 @@ retry:
 	}
 	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
-	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
+	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
 		pte_unmap_unlock(ptep, ptl);
 		return NULL;
 	}
@@ -302,11 +312,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	/* mlock all present pages, but do not fault in new pages */
 	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
 		return -ENOENT;
-	/* For mm_populate(), just skip the stack guard page. */
-	if ((*flags & FOLL_POPULATE) &&
-			(stack_guard_page_start(vma, address) ||
-			 stack_guard_page_end(vma, address + PAGE_SIZE)))
-		return -ENOENT;
 	if (*flags & FOLL_WRITE)
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (nonblocking)
@@ -352,7 +357,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	 * reCOWed by userspace write).
 	 */
 	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
-		*flags &= ~FOLL_WRITE;
+	        *flags |= FOLL_COW;
 	return 0;
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 62fe06bb7d04..6c6f5ccfcda1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1269,6 +1269,16 @@ out_unlock:
 	return ret;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 				   unsigned long addr,
 				   pmd_t *pmd,
@@ -1279,7 +1289,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
-	if (flags & FOLL_WRITE && !pmd_write(*pmd))
+	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
 		goto out;
 
 	/* Avoid dumping huge zero page */
@@ -1353,8 +1363,11 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	if (unlikely(pmd_trans_migrating(*pmdp))) {
 		page = pmd_page(*pmdp);
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		goto out;
 	}
 
@@ -1386,8 +1399,11 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
+		if (!get_page_unless_zero(page))
+			goto out_unlock;
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
+		put_page(page);
 		page_nid = -1;
 		goto out;
 	}
@@ -2134,10 +2150,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 		 * page fault if needed.
 		 */
 		return 0;
-	if (vma->vm_ops)
+	if (vma->vm_ops || (vm_flags & VM_NO_THP))
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2498,8 +2513,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
-	return true;
+	return !(vma->vm_flags & VM_NO_THP);
 }
 
 static void collapse_huge_page(struct mm_struct *mm,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ef6963b577fd..7294301d8495 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1416,12 +1416,13 @@ static void dissolve_free_huge_page(struct page *page)
 {
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
-		struct hstate *h = page_hstate(page);
-		int nid = page_to_nid(page);
-		list_del(&page->lru);
+		struct page *head = compound_head(page);
+		struct hstate *h = page_hstate(head);
+		int nid = page_to_nid(head);
+		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
-		update_and_free_page(h, page);
+		update_and_free_page(h, head);
 	}
 	spin_unlock(&hugetlb_lock);
 }
@@ -1429,7 +1430,8 @@ static void dissolve_free_huge_page(struct page *page)
 /*
  * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
  * make specified memory blocks removable from the system.
- * Note that start_pfn should aligned with (minimum) hugepage size.
+ * Note that this will dissolve a free gigantic hugepage completely, if any
+ * part of it lies within the given range.
  */
 void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -1438,7 +1440,6 @@ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	if (!hugepages_supported())
 		return;
 
-	VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order));
 	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order)
 		dissolve_free_huge_page(pfn_to_page(pfn));
 }
@@ -1722,23 +1723,32 @@ free:
 }
 
 /*
- * When releasing a hugetlb pool reservation, any surplus pages that were
- * allocated to satisfy the reservation must be explicitly freed if they were
- * never used.
- * Called with hugetlb_lock held.
+ * This routine has two main purposes:
+ * 1) Decrement the reservation count (resv_huge_pages) by the value passed
+ *    in unused_resv_pages.  This corresponds to the prior adjustments made
+ *    to the associated reservation map.
+ * 2) Free any unused surplus pages that may have been allocated to satisfy
+ *    the reservation.  As many as unused_resv_pages may be freed.
+ *
+ * Called with hugetlb_lock held.  However, the lock could be dropped (and
+ * reacquired) during calls to cond_resched_lock.  Whenever dropping the lock,
+ * we must make sure nobody else can claim pages we are in the process of
+ * freeing.  Do this by ensuring resv_huge_page always is greater than the
+ * number of huge pages we plan to free when dropping the lock.
  */
 static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
 
-	/* Uncommit the reservation */
-	h->resv_huge_pages -= unused_resv_pages;
-
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
-		return;
+		goto out;
 
+	/*
+	 * Part (or even all) of the reservation could have been backed
+	 * by pre-allocated pages. Only free surplus pages.
+	 */
 	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
 	/*
@@ -1748,12 +1758,22 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * when the nodes with surplus pages have no free pages.
 	 * free_pool_huge_page() will balance the the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
+	 *
+	 * Note that we decrement resv_huge_pages as we free the pages.  If
+	 * we drop the lock, resv_huge_pages will still be sufficiently large
+	 * to cover subsequent pages we may free.
 	 */
 	while (nr_pages--) {
+		h->resv_huge_pages--;
+		unused_resv_pages--;
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
-			break;
+			goto out;
 		cond_resched_lock(&hugetlb_lock);
 	}
+
+out:
+	/* Fully uncommit the reservation */
+	h->resv_huge_pages -= unused_resv_pages;
 }
 
 
@@ -2170,6 +2190,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 		 * and reducing the surplus.
 		 */
 		spin_unlock(&hugetlb_lock);
+
+		/* yield cpu to avoid soft lockup */
+		cond_resched();
+
 		if (hstate_is_gigantic(h))
 			ret = alloc_fresh_gigantic_page(h, nodes_allowed);
 		else
@@ -4209,7 +4233,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		if (saddr) {
 			spte = huge_pte_offset(svma->vm_mm, saddr);
 			if (spte) {
-				mm_inc_nr_pmds(mm);
 				get_page(virt_to_page(spte));
 				break;
 			}
@@ -4224,9 +4247,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (pud_none(*pud)) {
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
+		mm_inc_nr_pmds(mm);
 	} else {
 		put_page(virt_to_page(spte));
-		mm_inc_nr_pmds(mm);
 	}
 	spin_unlock(ptl);
 out:
@@ -4339,6 +4362,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
+	pte_t pte;
 retry:
 	ptl = pmd_lockptr(mm, pmd);
 	spin_lock(ptl);
@@ -4348,12 +4372,13 @@ retry:
 	 */
 	if (!pmd_huge(*pmd))
 		goto out;
-	if (pmd_present(*pmd)) {
+	pte = huge_ptep_get((pte_t *)pmd);
+	if (pte_present(pte)) {
 		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
 		if (flags & FOLL_GET)
 			get_page(page);
 	} else {
-		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
 			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
 			goto retry;
diff --git a/mm/init-mm.c b/mm/init-mm.c
index a56a851908d2..975e49f00f34 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -6,6 +6,7 @@
 #include <linux/cpumask.h>
 
 #include <linux/atomic.h>
+#include <linux/user_namespace.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 
@@ -21,5 +22,6 @@ struct mm_struct init_mm = {
 	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+	.user_ns	= &init_user_ns,
 	INIT_MM_CONTEXT(init_mm)
 };
diff --git a/mm/internal.h b/mm/internal.h
index 38e24b89e4c4..f63f4393d633 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -22,7 +22,8 @@
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
+			__GFP_ATOMIC)
 
 /* The GFP flags allowed during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))
@@ -452,6 +453,7 @@ struct tlbflush_unmap_batch;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 void try_to_unmap_flush(void);
 void try_to_unmap_flush_dirty(void);
+void flush_tlb_batched_pending(struct mm_struct *mm);
 #else
 static inline void try_to_unmap_flush(void)
 {
@@ -459,6 +461,8 @@ static inline void try_to_unmap_flush(void)
 static inline void try_to_unmap_flush_dirty(void)
 {
 }
-
+static inline void flush_tlb_batched_pending(struct mm_struct *mm)
+{
+}
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 4f6c62e5c21e..37ff0ab6a8ff 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -52,6 +52,9 @@ struct kasan_global {
 #if KASAN_ABI_VERSION >= 4
 	struct kasan_source_location *location;
 #endif
+#if KASAN_ABI_VERSION >= 5
+	char *odr_indicator;
+#endif
 };
 
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 12f222d0224b..b4e31f78ae69 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/printk.h>
@@ -251,6 +252,8 @@ void kasan_report(unsigned long addr, size_t size,
 	if (likely(!kasan_report_enabled()))
 		return;
 
+	disable_trace_on_warning();
+
 	info.access_addr = (void *)addr;
 	info.access_size = size;
 	info.is_write = is_write;
diff --git a/mm/ksm.c b/mm/ksm.c
index b5cd647daa52..2f028e6d0831 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -283,7 +283,8 @@ static inline struct rmap_item *alloc_rmap_item(void)
 {
 	struct rmap_item *rmap_item;
 
-	rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
+	rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL |
+						__GFP_NORETRY | __GFP_NOWARN);
 	if (rmap_item)
 		ksm_rmap_items++;
 	return rmap_item;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index afc71ea9a381..786176b1a0ee 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -117,6 +117,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
 		l = list_lru_from_kmem(nlru, item);
 		list_add_tail(item, &l->list);
 		l->nr_items++;
+		nlru->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -136,6 +137,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 		l = list_lru_from_kmem(nlru, item);
 		list_del_init(item);
 		l->nr_items--;
+		nlru->nr_items--;
 		spin_unlock(&nlru->lock);
 		return true;
 	}
@@ -183,15 +185,10 @@ EXPORT_SYMBOL_GPL(list_lru_count_one);
 
 unsigned long list_lru_count_node(struct list_lru *lru, int nid)
 {
-	long count = 0;
-	int memcg_idx;
+	struct list_lru_node *nlru;
 
-	count += __list_lru_count_one(lru, nid, -1);
-	if (list_lru_memcg_aware(lru)) {
-		for_each_memcg_cache_index(memcg_idx)
-			count += __list_lru_count_one(lru, nid, memcg_idx);
-	}
-	return count;
+	nlru = &lru->node[nid];
+	return nlru->nr_items;
 }
 EXPORT_SYMBOL_GPL(list_lru_count_node);
 
@@ -226,6 +223,7 @@ restart:
 			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
 			isolated++;
+			nlru->nr_items--;
 			/*
 			 * If the lru lock has been dropped, our list
 			 * traversal is now invalid and so we have to
@@ -554,6 +552,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 	err = memcg_init_list_lru(lru, memcg_aware);
 	if (err) {
 		kfree(lru->node);
+		/* Do this so a list_lru_destroy() doesn't crash: */
+		lru->node = NULL;
 		goto out;
 	}
 
diff --git a/mm/memblock.c b/mm/memblock.c
index d300f1329814..f8fab45bfdb7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1634,6 +1634,30 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name
 	}
 }
 
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+	struct memblock_type *type = &memblock.reserved;
+	unsigned long size = 0;
+	int idx;
+
+	for (idx = 0; idx < type->cnt; idx++) {
+		struct memblock_region *rgn = &type->regions[idx];
+		phys_addr_t start, end;
+
+		if (rgn->base + rgn->size < start_addr)
+			continue;
+		if (rgn->base > end_addr)
+			continue;
+
+		start = rgn->base;
+		end = start + rgn->size;
+		size += end - start;
+	}
+
+	return size;
+}
+
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ee6acd279953..e25b93a4267d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -196,6 +196,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 /* "mc" and its members are protected by cgroup_mutex */
 static struct move_charge_struct {
 	spinlock_t	  lock; /* for from, to */
+	struct mm_struct  *mm;
 	struct mem_cgroup *from;
 	struct mem_cgroup *to;
 	unsigned long flags;
@@ -271,21 +272,7 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 
 static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 {
-	return memcg->css.id;
-}
-
-/*
- * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock().  The caller is responsible for calling
- * css_tryget_online() if the mem_cgroup is used for charging. (dropping
- * refcnt from swap can be called against removed memcg.)
- */
-static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
-{
-	struct cgroup_subsys_state *css;
-
-	css = css_from_id(id, &memory_cgrp_subsys);
-	return mem_cgroup_from_css(css);
+	return memcg->id.id;
 }
 
 /* Writing them here to avoid exposing memcg's inner layout */
@@ -1332,7 +1319,7 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	return limit;
 }
 
-static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order)
 {
 	struct oom_control oc = {
@@ -1410,6 +1397,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	}
 unlock:
 	mutex_unlock(&oom_lock);
+	return chosen;
 }
 
 #if MAX_NUMNODES > 1
@@ -2067,6 +2055,15 @@ retry:
 		     current->flags & PF_EXITING))
 		goto force;
 
+	/*
+	 * Prevent unbounded recursion when reclaim operations need to
+	 * allocate memory. This might exceed the limits temporarily,
+	 * but we prefer facilitating memory reclaim and getting back
+	 * under the limit over triggering OOM kills in these cases.
+	 */
+	if (unlikely(current->flags & PF_MEMALLOC))
+		goto force;
+
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
 
@@ -3659,6 +3656,7 @@ static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
 	 * ordering is imposed by list_lru_node->lock taken by
 	 * memcg_drain_all_list_lrus().
 	 */
+	rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
 	css_for_each_descendant_pre(css, &memcg->css) {
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -3666,6 +3664,8 @@ static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
 		if (!memcg->use_hierarchy)
 			break;
 	}
+	rcu_read_unlock();
+
 	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
 
 	memcg_free_cache_id(kmemcg_id);
@@ -4119,6 +4119,70 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	{ },	/* terminate */
 };
 
+/*
+ * Private memory cgroup IDR
+ *
+ * Swap-out records and page cache shadow entries need to store memcg
+ * references in constrained space, so we maintain an ID space that is
+ * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
+ * memory-controlled cgroups to 64k.
+ *
+ * However, there usually are many references to the oflline CSS after
+ * the cgroup has been destroyed, such as page cache or reclaimable
+ * slab objects, that don't need to hang on to the ID. We want to keep
+ * those dead CSS from occupying IDs, or we might quickly exhaust the
+ * relatively small ID space and prevent the creation of new cgroups
+ * even when there are much fewer than 64k cgroups - possibly none.
+ *
+ * Maintain a private 16-bit ID space for memcg, and allow the ID to
+ * be freed and recycled when it's no longer needed, which is usually
+ * when the CSS is offlined.
+ *
+ * The only exception to that are records of swapped out tmpfs/shmem
+ * pages that need to be attributed to live ancestors on swapin. But
+ * those references are manageable from userspace.
+ */
+
+static DEFINE_IDR(mem_cgroup_idr);
+
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
+{
+	atomic_add(n, &memcg->id.ref);
+}
+
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
+{
+	if (atomic_sub_and_test(n, &memcg->id.ref)) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+
+		/* Memcg ID pins CSS */
+		css_put(&memcg->css);
+	}
+}
+
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+	mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+	mem_cgroup_id_put_many(memcg, 1);
+}
+
+/**
+ * mem_cgroup_from_id - look up a memcg from a memcg id
+ * @id: the memcg id to look up
+ *
+ * Caller must hold rcu_read_lock().
+ */
+struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return idr_find(&mem_cgroup_idr, id);
+}
+
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
@@ -4173,6 +4237,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
 		goto out_free_stat;
 
+	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
+				 1, MEM_CGROUP_ID_MAX,
+				 GFP_KERNEL);
+	if (memcg->id.id < 0)
+		goto out_free_stat;
+
 	return memcg;
 
 out_free_stat:
@@ -4258,9 +4328,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
 #endif
+	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return &memcg->css;
 
 free_out:
+	idr_remove(&mem_cgroup_idr, memcg->id.id);
 	__mem_cgroup_free(memcg);
 	return ERR_PTR(error);
 }
@@ -4272,8 +4344,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
 	int ret;
 
-	if (css->id > MEM_CGROUP_ID_MAX)
-		return -ENOSPC;
+	/* Online state pins memcg ID, memcg ID pins CSS */
+	mem_cgroup_id_get(mem_cgroup_from_css(css));
+	css_get(css);
 
 	if (!parent)
 		return 0;
@@ -4347,6 +4420,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	memcg_deactivate_kmem(memcg);
 
 	wb_memcg_offline(memcg);
+
+	mem_cgroup_id_put(memcg);
 }
 
 static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
@@ -4403,9 +4478,9 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		return ret;
 	}
 
-	/* Try charges one by one with reclaim */
+	/* Try charges one by one with reclaim, but do not retry */
 	while (count--) {
-		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+		ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -4780,6 +4855,8 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.from))
 			page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
 
+		mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
 		/*
 		 * we charged both to->memory and to->memsw, so we
 		 * should uncharge to->memory.
@@ -4787,9 +4864,9 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.to))
 			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-		css_put_many(&mc.from->css, mc.moved_swap);
+		mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+		css_put_many(&mc.to->css, mc.moved_swap);
 
-		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
 	memcg_oom_recover(from);
@@ -4799,6 +4876,8 @@ static void __mem_cgroup_clear_mc(void)
 
 static void mem_cgroup_clear_mc(void)
 {
+	struct mm_struct *mm = mc.mm;
+
 	/*
 	 * we must clear moving_task before waking up waiters at the end of
 	 * task migration.
@@ -4808,7 +4887,10 @@ static void mem_cgroup_clear_mc(void)
 	spin_lock(&mc.lock);
 	mc.from = NULL;
 	mc.to = NULL;
+	mc.mm = NULL;
 	spin_unlock(&mc.lock);
+
+	mmput(mm);
 }
 
 static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -4865,6 +4947,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 		VM_BUG_ON(mc.moved_swap);
 
 		spin_lock(&mc.lock);
+		mc.mm = mm;
 		mc.from = from;
 		mc.to = memcg;
 		mc.flags = move_flags;
@@ -4874,8 +4957,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 		ret = mem_cgroup_precharge_mc(mm);
 		if (ret)
 			mem_cgroup_clear_mc();
+	} else {
+		mmput(mm);
 	}
-	mmput(mm);
 	return ret;
 }
 
@@ -4984,11 +5068,11 @@ put:			/* get_mctgt_type() gets the page */
 	return ret;
 }
 
-static void mem_cgroup_move_charge(struct mm_struct *mm)
+static void mem_cgroup_move_charge(void)
 {
 	struct mm_walk mem_cgroup_move_charge_walk = {
 		.pmd_entry = mem_cgroup_move_charge_pte_range,
-		.mm = mm,
+		.mm = mc.mm,
 	};
 
 	lru_add_drain_all();
@@ -5000,7 +5084,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
 	atomic_inc(&mc.from->moving_account);
 	synchronize_rcu();
 retry:
-	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+	if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) {
 		/*
 		 * Someone who are holding the mmap_sem might be waiting in
 		 * waitq. So we cancel all extra charges, wake up all waiters,
@@ -5017,23 +5101,16 @@ retry:
 	 * additional charge, the page walk just aborts.
 	 */
 	walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk);
-	up_read(&mm->mmap_sem);
+	up_read(&mc.mm->mmap_sem);
 	atomic_dec(&mc.from->moving_account);
 }
 
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
 {
-	struct cgroup_subsys_state *css;
-	struct task_struct *p = cgroup_taskset_first(tset, &css);
-	struct mm_struct *mm = get_task_mm(p);
-
-	if (mm) {
-		if (mc.to)
-			mem_cgroup_move_charge(mm);
-		mmput(mm);
-	}
-	if (mc.to)
+	if (mc.to) {
+		mem_cgroup_move_charge();
 		mem_cgroup_clear_mc();
+	}
 }
 #else	/* !CONFIG_MMU */
 static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -5043,7 +5120,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
 {
 }
 #endif
@@ -5121,6 +5198,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 				 char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long nr_pages;
 	unsigned long high;
 	int err;
 
@@ -5131,6 +5209,11 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 
 	memcg->high = high;
 
+	nr_pages = page_counter_read(&memcg->memory);
+	if (nr_pages > high)
+		try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
+					     GFP_KERNEL, true);
+
 	memcg_wb_domain_size_changed(memcg);
 	return nbytes;
 }
@@ -5152,6 +5235,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned int nr_reclaims = MEM_CGROUP_RECLAIM_RETRIES;
+	bool drained = false;
 	unsigned long max;
 	int err;
 
@@ -5160,9 +5245,36 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	if (err)
 		return err;
 
-	err = mem_cgroup_resize_limit(memcg, max);
-	if (err)
-		return err;
+	xchg(&memcg->memory.limit, max);
+
+	for (;;) {
+		unsigned long nr_pages = page_counter_read(&memcg->memory);
+
+		if (nr_pages <= max)
+			break;
+
+		if (signal_pending(current)) {
+			err = -EINTR;
+			break;
+		}
+
+		if (!drained) {
+			drain_all_stock(memcg);
+			drained = true;
+			continue;
+		}
+
+		if (nr_reclaims) {
+			if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
+							  GFP_KERNEL, true))
+				nr_reclaims--;
+			continue;
+		}
+
+		mem_cgroup_events(memcg, MEMCG_OOM, 1);
+		if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0))
+			break;
+	}
 
 	memcg_wb_domain_size_changed(memcg);
 	return nbytes;
@@ -5222,7 +5334,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_reset = mem_cgroup_css_reset,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
-	.attach = mem_cgroup_move_task,
+	.post_attach = mem_cgroup_move_task,
 	.bind = mem_cgroup_bind,
 	.dfl_cftypes = memory_files,
 	.legacy_cftypes = mem_cgroup_legacy_files,
@@ -5621,6 +5733,24 @@ static int __init mem_cgroup_init(void)
 subsys_initcall(mem_cgroup_init);
 
 #ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+	while (!atomic_inc_not_zero(&memcg->id.ref)) {
+		/*
+		 * The root cgroup cannot be destroyed, so it's refcount must
+		 * always be >= 1.
+		 */
+		if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+			VM_BUG_ON(1);
+			break;
+		}
+		memcg = parent_mem_cgroup(memcg);
+		if (!memcg)
+			memcg = root_mem_cgroup;
+	}
+	return memcg;
+}
+
 /**
  * mem_cgroup_swapout - transfer a memsw charge to swap
  * @page: page whose memsw charge to transfer
@@ -5630,7 +5760,7 @@ subsys_initcall(mem_cgroup_init);
  */
 void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg, *swap_memcg;
 	unsigned short oldid;
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5645,15 +5775,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return;
 
-	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+	/*
+	 * In case the memcg owning these pages has been offlined and doesn't
+	 * have an ID allocated to it anymore, charge the closest online
+	 * ancestor for the swap instead and transfer the memory+swap charge.
+	 */
+	swap_memcg = mem_cgroup_id_get_online(memcg);
+	oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
 	VM_BUG_ON_PAGE(oldid, page);
-	mem_cgroup_swap_statistics(memcg, true);
+	mem_cgroup_swap_statistics(swap_memcg, true);
 
 	page->mem_cgroup = NULL;
 
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, 1);
 
+	if (memcg != swap_memcg) {
+		if (!mem_cgroup_is_root(swap_memcg))
+			page_counter_charge(&swap_memcg->memsw, 1);
+		page_counter_uncharge(&memcg->memsw, 1);
+	}
+
 	/*
 	 * Interrupts should be disabled here because the caller holds the
 	 * mapping->tree_lock lock which is taken with interrupts-off. It is
@@ -5663,6 +5805,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON(!irqs_disabled());
 	mem_cgroup_charge_statistics(memcg, page, -1);
 	memcg_check_events(memcg, page);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put(&memcg->css);
 }
 
 /**
@@ -5686,7 +5831,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 		if (!mem_cgroup_is_root(memcg))
 			page_counter_uncharge(&memcg->memsw, 1);
 		mem_cgroup_swap_statistics(memcg, false);
-		css_put(&memcg->css);
+		mem_cgroup_id_put(memcg);
 	}
 	rcu_read_unlock();
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 750b7893ee3a..091fe9b06663 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1208,7 +1208,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
 	 * correctly, we save a copy of the page flags at this time.
 	 */
-	page_flags = p->flags;
+	if (PageHuge(p))
+		page_flags = hpage->flags;
+	else
+		page_flags = p->flags;
 
 	/*
 	 * unpoison always clear PG_hwpoison inside page lock
@@ -1619,12 +1622,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
-		/*
-		 * We know that soft_offline_huge_page() tries to migrate
-		 * only one hugepage pointed to by hpage, so we need not
-		 * run through the pagelist here.
-		 */
-		putback_active_hugepage(hpage);
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
 		if (ret > 0)
 			ret = -EIO;
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index b80bf4746b67..9ac55172aa7b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -797,6 +797,46 @@ out:
 	return pfn_to_page(pfn);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd)
+{
+	unsigned long pfn = pmd_pfn(pmd);
+
+	/*
+	 * There is no pmd_special() but there may be special pmds, e.g.
+	 * in a direct-access (dax) mapping, so let's just replicate the
+	 * !HAVE_PTE_SPECIAL case from vm_normal_page() here.
+	 */
+	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
+		if (vma->vm_flags & VM_MIXEDMAP) {
+			if (!pfn_valid(pfn))
+				return NULL;
+			goto out;
+		} else {
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
+			if (pfn == vma->vm_pgoff + off)
+				return NULL;
+			if (!is_cow_mapping(vma->vm_flags))
+				return NULL;
+		}
+	}
+
+	if (is_zero_pfn(pfn))
+		return NULL;
+	if (unlikely(pfn > highest_memmap_pfn))
+		return NULL;
+
+	/*
+	 * NOTE! We still have PageReserved() pages in the page tables.
+	 * eg. VDSO mappings can cause them to exist.
+	 */
+out:
+	return pfn_to_page(pfn);
+}
+#endif
+
 /*
  * copy one vm_area from one task to the other. Assumes the page tables
  * already present in the new task to be cleared in the whole range
@@ -1087,6 +1127,7 @@ again:
 	init_rss_vec(rss);
 	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	pte = start_pte;
+	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
@@ -2622,40 +2663,6 @@ out_release:
 }
 
 /*
- * This is like a special single-page "expand_{down|up}wards()",
- * except we must first make sure that 'address{-|+}PAGE_SIZE'
- * doesn't hit another vma.
- */
-static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
-{
-	address &= PAGE_MASK;
-	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-		struct vm_area_struct *prev = vma->vm_prev;
-
-		/*
-		 * Is there a mapping abutting this one below?
-		 *
-		 * That's only ok if it's the same stack mapping
-		 * that has gotten split..
-		 */
-		if (prev && prev->vm_end == address)
-			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
-
-		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;
-
-		/* As VM_GROWSDOWN but s/below/above/ */
-		if (next && next->vm_start == address + PAGE_SIZE)
-			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
-
-		return expand_upwards(vma, address + PAGE_SIZE);
-	}
-	return 0;
-}
-
-/*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
@@ -2675,10 +2682,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
-	/* Check if we need to add a guard page to the stack */
-	if (check_stack_guard_page(vma, address) < 0)
-		return VM_FAULT_SIGSEGV;
-
 	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a042a9d537bb..a18923e4359d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1371,17 +1371,20 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) is belongs to the same zone.
+ * Confirm all pages in a range [start, end) belong to the same zone.
+ * When true, return its valid [start, end).
  */
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+			 unsigned long *valid_start, unsigned long *valid_end)
 {
 	unsigned long pfn, sec_end_pfn;
+	unsigned long start, end;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
-	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
+	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
 	     pfn < end_pfn;
-	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+	     pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
 		/* Make sure the memory section is present first */
 		if (!present_section_nr(pfn_to_section_nr(pfn)))
 			continue;
@@ -1397,10 +1400,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
 				return 0;
+			if (!zone)
+				start = pfn + i;
 			zone = page_zone(page);
+			end = pfn + MAX_ORDER_NR_PAGES;
 		}
 	}
-	return 1;
+
+	if (zone) {
+		*valid_start = start;
+		*valid_end = end;
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /*
@@ -1718,6 +1731,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	long offlined_pages;
 	int ret, drain, retry_max, node;
 	unsigned long flags;
+	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
 
@@ -1728,10 +1742,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		return -EINVAL;
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
 		return -EINVAL;
 
-	zone = page_zone(pfn_to_page(start_pfn));
+	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 87a177917cb2..c947014d128a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -894,11 +894,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 		*policy |= (pol->flags & MPOL_MODE_FLAGS);
 	}
 
-	if (vma) {
-		up_read(&current->mm->mmap_sem);
-		vma = NULL;
-	}
-
 	err = 0;
 	if (nmask) {
 		if (mpol_store_user_nodemask(pol)) {
@@ -1492,7 +1487,6 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 		       compat_ulong_t, maxnode)
 {
-	long err = 0;
 	unsigned long __user *nm = NULL;
 	unsigned long nr_bits, alloc_size;
 	DECLARE_BITMAP(bm, MAX_NUMNODES);
@@ -1501,14 +1495,13 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
 
 	if (nmask) {
-		err = compat_get_bitmap(bm, nmask, nr_bits);
+		if (compat_get_bitmap(bm, nmask, nr_bits))
+			return -EFAULT;
 		nm = compat_alloc_user_space(alloc_size);
-		err |= copy_to_user(nm, bm, alloc_size);
+		if (copy_to_user(nm, bm, alloc_size))
+			return -EFAULT;
 	}
 
-	if (err)
-		return -EFAULT;
-
 	return sys_set_mempolicy(mode, nm, nr_bits+1);
 }
 
@@ -1516,7 +1509,6 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 		       compat_ulong_t, mode, compat_ulong_t __user *, nmask,
 		       compat_ulong_t, maxnode, compat_ulong_t, flags)
 {
-	long err = 0;
 	unsigned long __user *nm = NULL;
 	unsigned long nr_bits, alloc_size;
 	nodemask_t bm;
@@ -1525,14 +1517,13 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
 
 	if (nmask) {
-		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+		if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+			return -EFAULT;
 		nm = compat_alloc_user_space(alloc_size);
-		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+		if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+			return -EFAULT;
 	}
 
-	if (err)
-		return -EFAULT;
-
 	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
 }
 
@@ -2006,8 +1997,8 @@ retry_cpuset:
 
 	nmask = policy_nodemask(gfp, pol);
 	zl = policy_zonelist(gfp, pol, node);
-	mpol_cond_put(pol);
 	page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+	mpol_cond_put(pol);
 out:
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
diff --git a/mm/mempool.c b/mm/mempool.c
index 004d42b1dfaf..7924f4f58a6d 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -135,8 +135,8 @@ static void *remove_element(mempool_t *pool)
 	void *element = pool->elements[--pool->curr_nr];
 
 	BUG_ON(pool->curr_nr < 0);
-	check_element(pool, element);
 	kasan_unpoison_element(pool, element);
+	check_element(pool, element);
 	return element;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 6d17e0ab42d4..afedcfab60e2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -38,6 +38,7 @@
 #include <linux/balloon_compaction.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
+#include <linux/ptrace.h>
 
 #include <asm/tlbflush.h>
 
@@ -429,6 +430,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 
 	return MIGRATEPAGE_SUCCESS;
 }
+EXPORT_SYMBOL(migrate_page_move_mapping);
 
 /*
  * The expected number of remaining references is the same as that
@@ -579,6 +581,7 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	if (PageWriteback(newpage))
 		end_page_writeback(newpage);
 }
+EXPORT_SYMBOL(migrate_page_copy);
 
 /************************************************************
  *                    Migration functions
@@ -963,7 +966,13 @@ out:
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		/* Soft-offlined page shouldn't go through lru cache list */
-		if (reason == MR_MEMORY_FAILURE) {
+		if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) {
+			/*
+			 * With this release, we free successfully migrated
+			 * page and set PG_HWPoison on just freed page
+			 * intentionally. Although it's rather weird, it's how
+			 * HWPoison flag works at the moment.
+			 */
 			put_page(page);
 			if (!test_set_page_hwpoison(page))
 				num_poisoned_pages_inc();
@@ -1475,7 +1484,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 		const int __user *, nodes,
 		int __user *, status, int, flags)
 {
-	const struct cred *cred = current_cred(), *tcred;
 	struct task_struct *task;
 	struct mm_struct *mm;
 	int err;
@@ -1499,14 +1507,9 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 
 	/*
 	 * Check if this process has the right to modify the specified
-	 * process. The right exists if the process has administrative
-	 * capabilities, superuser privileges or the same
-	 * userid as the target process.
+	 * process. Use the regular "ptrace_may_access()" checks.
 	 */
-	tcred = __task_cred(task);
-	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
-	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
-	    !capable(CAP_SYS_NICE)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
 		rcu_read_unlock();
 		err = -EPERM;
 		goto out;
diff --git a/mm/mlock.c b/mm/mlock.c
index d6006b146fea..9d2e773f3a95 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -277,7 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
@@ -297,6 +297,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 				continue;
 			else
 				__munlock_isolation_failed(page);
+		} else {
+			delta_munlocked++;
 		}
 
 		/*
@@ -308,7 +310,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(&zone->lru_lock);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 455772a05e54..eaa460ddcaf9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -288,6 +288,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	unsigned long retval;
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *next;
 	unsigned long min_brk;
 	bool populate;
 
@@ -332,7 +333,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	}
 
 	/* Check against existing mmap mappings. */
-	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
+	next = find_vma(mm, oldbrk);
+	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
 		goto out;
 
 	/* Ok, looks good - let it rip. */
@@ -355,10 +357,22 @@ out:
 
 static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 {
-	unsigned long max, subtree_gap;
-	max = vma->vm_start;
-	if (vma->vm_prev)
-		max -= vma->vm_prev->vm_end;
+	unsigned long max, prev_end, subtree_gap;
+
+	/*
+	 * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
+	 * allow two stack_guard_gaps between them here, and when choosing
+	 * an unmapped area; whereas when expanding we only require one.
+	 * That's a little inconsistent, but keeps the code here simpler.
+	 */
+	max = vm_start_gap(vma);
+	if (vma->vm_prev) {
+		prev_end = vm_end_gap(vma->vm_prev);
+		if (max > prev_end)
+			max -= prev_end;
+		else
+			max = 0;
+	}
 	if (vma->vm_rb.rb_left) {
 		subtree_gap = rb_entry(vma->vm_rb.rb_left,
 				struct vm_area_struct, vm_rb)->rb_subtree_gap;
@@ -451,7 +465,7 @@ static void validate_mm(struct mm_struct *mm)
 			anon_vma_unlock_read(anon_vma);
 		}
 
-		highest_address = vma->vm_end;
+		highest_address = vm_end_gap(vma);
 		vma = vma->vm_next;
 		i++;
 	}
@@ -620,7 +634,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_next)
 		vma_gap_update(vma->vm_next);
 	else
-		mm->highest_vm_end = vma->vm_end;
+		mm->highest_vm_end = vm_end_gap(vma);
 
 	/*
 	 * vma->vm_prev wasn't known when we followed the rbtree to find the
@@ -866,7 +880,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 			vma_gap_update(vma);
 		if (end_changed) {
 			if (!next)
-				mm->highest_vm_end = end;
+				mm->highest_vm_end = vm_end_gap(vma);
 			else if (!adjust_next)
 				vma_gap_update(next);
 		}
@@ -909,7 +923,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 		else if (next)
 			vma_gap_update(next);
 		else
-			mm->highest_vm_end = end;
+			VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
 	}
 	if (insert && file)
 		uprobe_mmap(insert);
@@ -1741,7 +1755,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 
 	while (true) {
 		/* Visit left subtree if it looks promising */
-		gap_end = vma->vm_start;
+		gap_end = vm_start_gap(vma);
 		if (gap_end >= low_limit && vma->vm_rb.rb_left) {
 			struct vm_area_struct *left =
 				rb_entry(vma->vm_rb.rb_left,
@@ -1752,12 +1766,13 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 			}
 		}
 
-		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
 check_current:
 		/* Check if current node has a suitable gap */
 		if (gap_start > high_limit)
 			return -ENOMEM;
-		if (gap_end >= low_limit && gap_end - gap_start >= length)
+		if (gap_end >= low_limit &&
+		    gap_end > gap_start && gap_end - gap_start >= length)
 			goto found;
 
 		/* Visit right subtree if it looks promising */
@@ -1779,8 +1794,8 @@ check_current:
 			vma = rb_entry(rb_parent(prev),
 				       struct vm_area_struct, vm_rb);
 			if (prev == vma->vm_rb.rb_left) {
-				gap_start = vma->vm_prev->vm_end;
-				gap_end = vma->vm_start;
+				gap_start = vm_end_gap(vma->vm_prev);
+				gap_end = vm_start_gap(vma);
 				goto check_current;
 			}
 		}
@@ -1844,7 +1859,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
 	while (true) {
 		/* Visit right subtree if it looks promising */
-		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0;
 		if (gap_start <= high_limit && vma->vm_rb.rb_right) {
 			struct vm_area_struct *right =
 				rb_entry(vma->vm_rb.rb_right,
@@ -1857,10 +1872,11 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 
 check_current:
 		/* Check if current node has a suitable gap */
-		gap_end = vma->vm_start;
+		gap_end = vm_start_gap(vma);
 		if (gap_end < low_limit)
 			return -ENOMEM;
-		if (gap_start <= high_limit && gap_end - gap_start >= length)
+		if (gap_start <= high_limit &&
+		    gap_end > gap_start && gap_end - gap_start >= length)
 			goto found;
 
 		/* Visit left subtree if it looks promising */
@@ -1883,7 +1899,7 @@ check_current:
 				       struct vm_area_struct, vm_rb);
 			if (prev == vma->vm_rb.rb_right) {
 				gap_start = vma->vm_prev ?
-					vma->vm_prev->vm_end : 0;
+					vm_end_gap(vma->vm_prev) : 0;
 				goto check_current;
 			}
 		}
@@ -1921,7 +1937,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct vm_unmapped_area_info info;
 
 	if (len > TASK_SIZE - mmap_min_addr)
@@ -1932,9 +1948,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 
@@ -1957,7 +1974,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
 			  const unsigned long flags)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
@@ -1972,9 +1989,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* requesting a specific address */
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)) &&
+				(!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 
@@ -2099,21 +2117,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
  * update accounting. This is shared with both the
  * grow-up and grow-down cases.
  */
-static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma,
+			     unsigned long size, unsigned long grow)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start, actual_size;
+	unsigned long new_start;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	actual_size = size;
-	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
-		actual_size -= PAGE_SIZE;
-	if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
@@ -2151,16 +2167,32 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *next;
+	unsigned long gap_addr;
 	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
-	/* Guard against wrapping around to address 0. */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else
+	/* Guard against exceeding limits of the address space. */
+	address &= PAGE_MASK;
+	if (address >= (TASK_SIZE & PAGE_MASK))
 		return -ENOMEM;
+	address += PAGE_SIZE;
+
+	/* Enforce stack_guard_gap */
+	gap_addr = address + stack_guard_gap;
+
+	/* Guard against overflow */
+	if (gap_addr < address || gap_addr > TASK_SIZE)
+		gap_addr = TASK_SIZE;
+
+	next = vma->vm_next;
+	if (next && next->vm_start < gap_addr) {
+		if (!(next->vm_flags & VM_GROWSUP))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
 
 	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
@@ -2206,7 +2238,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				if (vma->vm_next)
 					vma_gap_update(vma->vm_next);
 				else
-					mm->highest_vm_end = address;
+					mm->highest_vm_end = vm_end_gap(vma);
 				spin_unlock(&mm->page_table_lock);
 
 				perf_event_mmap(vma);
@@ -2227,6 +2259,8 @@ int expand_downwards(struct vm_area_struct *vma,
 				   unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *prev;
+	unsigned long gap_addr;
 	int error;
 
 	address &= PAGE_MASK;
@@ -2234,6 +2268,17 @@ int expand_downwards(struct vm_area_struct *vma,
 	if (error)
 		return error;
 
+	/* Enforce stack_guard_gap */
+	gap_addr = address - stack_guard_gap;
+	if (gap_addr > address)
+		return -ENOMEM;
+	prev = vma->vm_prev;
+	if (prev && prev->vm_end > gap_addr) {
+		if (!(prev->vm_flags & VM_GROWSDOWN))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
 	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
@@ -2289,28 +2334,25 @@ int expand_downwards(struct vm_area_struct *vma,
 	return error;
 }
 
-/*
- * Note how expand_stack() refuses to expand the stack all the way to
- * abut the next virtual mapping, *unless* that mapping itself is also
- * a stack mapping. We want to leave room for a guard page, after all
- * (the guard page itself is not added here, that is done by the
- * actual page faulting logic)
- *
- * This matches the behavior of the guard page logic (see mm/memory.c:
- * check_stack_guard_page()), which only allows the guard page to be
- * removed under these circumstances.
- */
+/* enforced gap between the expanding stack and other mappings. */
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+static int __init cmdline_parse_stack_guard_gap(char *p)
+{
+	unsigned long val;
+	char *endptr;
+
+	val = simple_strtoul(p, &endptr, 10);
+	if (!*endptr)
+		stack_guard_gap = val << PAGE_SHIFT;
+
+	return 0;
+}
+__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
+
 #ifdef CONFIG_STACK_GROWSUP
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
-	struct vm_area_struct *next;
-
-	address &= PAGE_MASK;
-	next = vma->vm_next;
-	if (next && next->vm_start == address + PAGE_SIZE) {
-		if (!(next->vm_flags & VM_GROWSUP))
-			return -ENOMEM;
-	}
 	return expand_upwards(vma, address);
 }
 
@@ -2332,14 +2374,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 #else
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
-	struct vm_area_struct *prev;
-
-	address &= PAGE_MASK;
-	prev = vma->vm_prev;
-	if (prev && prev->vm_end == address) {
-		if (!(prev->vm_flags & VM_GROWSDOWN))
-			return -ENOMEM;
-	}
 	return expand_downwards(vma, address);
 }
 
@@ -2437,7 +2471,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 		vma->vm_prev = prev;
 		vma_gap_update(vma);
 	} else
-		mm->highest_vm_end = prev ? prev->vm_end : 0;
+		mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
 	tail_vma->vm_next = NULL;
 
 	/* Kill the cache */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ef5be8eaab00..c0b4b2a49462 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -72,6 +72,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	if (!pte)
 		return 0;
 
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;
diff --git a/mm/mremap.c b/mm/mremap.c
index c25bc6268e46..fe7b7f65f4f4 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -135,6 +135,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	new_ptl = pte_lockptr(mm, new_pmd);
 	if (new_ptl != old_ptl)
 		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 
 	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d15d88c8efa1..fd51ebfc423f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -359,8 +359,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
 	unsigned long bytes = vm_dirty_bytes;
 	unsigned long bg_bytes = dirty_background_bytes;
-	unsigned long ratio = vm_dirty_ratio;
-	unsigned long bg_ratio = dirty_background_ratio;
+	/* convert ratios to per-PAGE_SIZE for higher precision */
+	unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
+	unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
 	unsigned long thresh;
 	unsigned long bg_thresh;
 	struct task_struct *tsk;
@@ -372,26 +373,28 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		/*
 		 * The byte settings can't be applied directly to memcg
 		 * domains.  Convert them to ratios by scaling against
-		 * globally available memory.
+		 * globally available memory.  As the ratios are in
+		 * per-PAGE_SIZE, they can be obtained by dividing bytes by
+		 * number of pages.
 		 */
 		if (bytes)
-			ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 /
-				    global_avail, 100UL);
+			ratio = min(DIV_ROUND_UP(bytes, global_avail),
+				    PAGE_SIZE);
 		if (bg_bytes)
-			bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 /
-				       global_avail, 100UL);
+			bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
+				       PAGE_SIZE);
 		bytes = bg_bytes = 0;
 	}
 
 	if (bytes)
 		thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
 	else
-		thresh = (ratio * available_memory) / 100;
+		thresh = (ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_bytes)
 		bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
 	else
-		bg_thresh = (bg_ratio * available_memory) / 100;
+		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	if (bg_thresh >= thresh)
 		bg_thresh = thresh / 2;
@@ -1899,7 +1902,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	if (gdtc->dirty > gdtc->bg_thresh)
 		return true;
 
-	if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc))
+	if (wb_stat(wb, WB_RECLAIMABLE) >
+	    wb_calc_thresh(gdtc->wb, gdtc->bg_thresh))
 		return true;
 
 	if (mdtc) {
@@ -1913,7 +1917,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		if (mdtc->dirty > mdtc->bg_thresh)
 			return true;
 
-		if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc))
+		if (wb_stat(wb, WB_RECLAIMABLE) >
+		    wb_calc_thresh(mdtc->wb, mdtc->bg_thresh))
 			return true;
 	}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d666df5ef95..53286b2f5b1c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -269,13 +269,35 @@ int page_group_by_mobility_disabled __read_mostly;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
+	unsigned long max_initialise;
+	unsigned long reserved_lowmem;
+
+	/*
+	 * Initialise at least 2G of a node but also take into account that
+	 * two large system hashes that can take up 1GB for 0.25TB/node.
+	 */
+	max_initialise = max(2UL << (30 - PAGE_SHIFT),
+		(pgdat->node_spanned_pages >> 8));
+
+	/*
+	 * Compensate the all the memblock reservations (e.g. crash kernel)
+	 * from the initial estimation to make sure we will initialize enough
+	 * memory to boot.
+	 */
+	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+			pgdat->node_start_pfn + max_initialise);
+	max_initialise += reserved_lowmem;
+
+	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
-	if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
+	int nid = early_pfn_to_nid(pfn);
+
+	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
 		return true;
 
 	return false;
@@ -300,10 +322,9 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 	/* Always populate low zones for address-contrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-
 	/* Initialise at least 2G of the highest zone */
 	(*nr_initialised)++;
-	if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
+	if ((*nr_initialised > pgdat->static_init_size) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -662,34 +683,28 @@ static inline void __free_one_page(struct page *page,
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
-	unsigned int max_order = MAX_ORDER;
+	unsigned int max_order;
+
+	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
 
 	VM_BUG_ON(migratetype == -1);
-	if (is_migrate_isolate(migratetype)) {
-		/*
-		 * We restrict max order of merging to prevent merge
-		 * between freepages on isolate pageblock and normal
-		 * pageblock. Without this, pageblock isolation
-		 * could cause incorrect freepage accounting.
-		 */
-		max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
-	} else {
+	if (likely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
-	}
 
-	page_idx = pfn & ((1 << max_order) - 1);
+	page_idx = pfn & ((1 << MAX_ORDER) - 1);
 
 	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
+continue_merging:
 	while (order < max_order - 1) {
 		buddy_idx = __find_buddy_index(page_idx, order);
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
-			break;
+			goto done_merging;
 		/*
 		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
 		 * merge with it and move up one order.
@@ -706,6 +721,32 @@ static inline void __free_one_page(struct page *page,
 		page_idx = combined_idx;
 		order++;
 	}
+	if (max_order < MAX_ORDER) {
+		/* If we are here, it means order is >= pageblock_order.
+		 * We want to prevent merge between freepages on isolate
+		 * pageblock and normal pageblock. Without this, pageblock
+		 * isolation could cause incorrect freepage or CMA accounting.
+		 *
+		 * We don't want to hit this code for the more frequent
+		 * low-order merging.
+		 */
+		if (unlikely(has_isolate_pageblock(zone))) {
+			int buddy_mt;
+
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+			buddy_mt = get_pageblock_migratetype(buddy);
+
+			if (migratetype != buddy_mt
+					&& (is_migrate_isolate(migratetype) ||
+						is_migrate_isolate(buddy_mt)))
+				goto done_merging;
+		}
+		max_order++;
+		goto continue_merging;
+	}
+
+done_merging:
 	set_page_order(page, order);
 
 	/*
@@ -931,7 +972,7 @@ static inline void init_reserved_page(unsigned long pfn)
  * marks the pages PageReserved. The remaining valid pages are later
  * sent to the buddy page allocator.
  */
-void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
+void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long end_pfn = PFN_UP(end);
@@ -1037,7 +1078,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
 	if (nid < 0)
-		nid = 0;
+		nid = first_online_node;
 	spin_unlock(&early_pfn_lock);
 
 	return nid;
@@ -1486,14 +1527,14 @@ int move_freepages(struct zone *zone,
 #endif
 
 	for (page = start_page; page <= end_page;) {
-		/* Make sure we are not inadvertently changing nodes */
-		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
 		if (!pfn_valid_within(page_to_pfn(page))) {
 			page++;
 			continue;
 		}
 
+		/* Make sure we are not inadvertently changing nodes */
+		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+
 		if (!PageBuddy(page)) {
 			page++;
 			continue;
@@ -2445,7 +2486,7 @@ static bool zone_local(struct zone *local_zone, struct zone *zone)
 
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
-	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
+	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
 				RECLAIM_DISTANCE;
 }
 #else	/* CONFIG_NUMA */
@@ -5321,7 +5362,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
 
-	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -5340,6 +5380,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
+	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 
@@ -5674,15 +5715,18 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 				sizeof(arch_zone_lowest_possible_pfn));
 	memset(arch_zone_highest_possible_pfn, 0,
 				sizeof(arch_zone_highest_possible_pfn));
-	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
-	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
-	for (i = 1; i < MAX_NR_ZONES; i++) {
+
+	start_pfn = find_min_pfn_with_active_regions();
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
-		arch_zone_lowest_possible_pfn[i] =
-			arch_zone_highest_possible_pfn[i-1];
-		arch_zone_highest_possible_pfn[i] =
-			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
+
+		end_pfn = max(max_zone_pfn[i], start_pfn);
+		arch_zone_lowest_possible_pfn[i] = start_pfn;
+		arch_zone_highest_possible_pfn[i] = end_pfn;
+
+		start_pfn = end_pfn;
 	}
 	arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
 	arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;
@@ -5803,8 +5847,8 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	}
 
 	if (pages && s)
-		pr_info("Freeing %s memory: %ldK (%p - %p)\n",
-			s, pages << (PAGE_SHIFT - 10), start, end);
+		pr_info("Freeing %s memory: %ldK\n",
+			s, pages << (PAGE_SHIFT - 10));
 
 	return pages;
 }
@@ -6173,7 +6217,7 @@ int __meminit init_per_zone_wmark_min(void)
 	setup_per_zone_inactive_ratio();
 	return 0;
 }
-module_init(init_per_zone_wmark_min)
+core_initcall(init_per_zone_wmark_min)
 
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
@@ -6760,7 +6804,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/* Make sure the range is really isolated. */
 	if (test_pages_isolated(outer_start, end, false)) {
-		pr_info("%s: [%lx, %lx) PFNs busy\n",
+		pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
 			__func__, outer_start, end);
 		ret = -EBUSY;
 		goto done;
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 4568fd58f70a..00c96462cc36 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -283,11 +283,11 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private,
 	 * now as a simple work-around, we use the next node for destination.
 	 */
 	if (PageHuge(page)) {
-		nodemask_t src = nodemask_of_node(page_to_nid(page));
-		nodemask_t dst;
-		nodes_complement(dst, src);
+		int node = next_online_node(page_to_nid(page));
+		if (node == MAX_NUMNODES)
+			node = first_online_node;
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
-					    next_node(page_to_nid(page), dst));
+					    node);
 	}
 
 	if (PageHighMem(page))
diff --git a/mm/percpu.c b/mm/percpu.c
index 8a943b97a053..ef6353f0adbd 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -110,7 +110,7 @@ struct pcpu_chunk {
 	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
-	struct work_struct	map_extend_work;/* async ->map[] extension */
+	struct list_head	map_extend_list;/* on pcpu_map_extend_chunks */
 
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
@@ -160,10 +160,13 @@ static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
 static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
-static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
+static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map ext */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
 
+/* chunks which need their map areas extended, protected by pcpu_lock */
+static LIST_HEAD(pcpu_map_extend_chunks);
+
 /*
  * The number of empty populated pages, protected by pcpu_lock.  The
  * reserved chunk doesn't contribute to the count.
@@ -397,13 +400,19 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
 {
 	int margin, new_alloc;
 
+	lockdep_assert_held(&pcpu_lock);
+
 	if (is_atomic) {
 		margin = 3;
 
 		if (chunk->map_alloc <
-		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
-		    pcpu_async_enabled)
-			schedule_work(&chunk->map_extend_work);
+		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) {
+			if (list_empty(&chunk->map_extend_list)) {
+				list_add_tail(&chunk->map_extend_list,
+					      &pcpu_map_extend_chunks);
+				pcpu_schedule_balance_work();
+			}
+		}
 	} else {
 		margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
 	}
@@ -437,6 +446,8 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
+	lockdep_assert_held(&pcpu_alloc_mutex);
+
 	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
@@ -469,20 +480,6 @@ out_unlock:
 	return 0;
 }
 
-static void pcpu_map_extend_workfn(struct work_struct *work)
-{
-	struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk,
-						map_extend_work);
-	int new_alloc;
-
-	spin_lock_irq(&pcpu_lock);
-	new_alloc = pcpu_need_to_extend(chunk, false);
-	spin_unlock_irq(&pcpu_lock);
-
-	if (new_alloc)
-		pcpu_extend_area_map(chunk, new_alloc);
-}
-
 /**
  * pcpu_fit_in_area - try to fit the requested allocation in a candidate area
  * @chunk: chunk the candidate area belongs to
@@ -742,7 +739,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
-	INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&chunk->map_extend_list);
 	chunk->free_size = pcpu_unit_size;
 	chunk->contig_hint = pcpu_unit_size;
 
@@ -897,6 +894,9 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
+	if (!is_atomic)
+		mutex_lock(&pcpu_alloc_mutex);
+
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
@@ -969,12 +969,9 @@ restart:
 	if (is_atomic)
 		goto fail;
 
-	mutex_lock(&pcpu_alloc_mutex);
-
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
 		chunk = pcpu_create_chunk();
 		if (!chunk) {
-			mutex_unlock(&pcpu_alloc_mutex);
 			err = "failed to allocate new chunk";
 			goto fail;
 		}
@@ -985,7 +982,6 @@ restart:
 		spin_lock_irqsave(&pcpu_lock, flags);
 	}
 
-	mutex_unlock(&pcpu_alloc_mutex);
 	goto restart;
 
 area_found:
@@ -995,8 +991,6 @@ area_found:
 	if (!is_atomic) {
 		int page_start, page_end, rs, re;
 
-		mutex_lock(&pcpu_alloc_mutex);
-
 		page_start = PFN_DOWN(off);
 		page_end = PFN_UP(off + size);
 
@@ -1007,7 +1001,6 @@ area_found:
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
-				mutex_unlock(&pcpu_alloc_mutex);
 				pcpu_free_area(chunk, off, &occ_pages);
 				err = "failed to populate";
 				goto fail_unlock;
@@ -1019,8 +1012,11 @@ area_found:
 		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	if (chunk != pcpu_reserved_chunk)
+	if (chunk != pcpu_reserved_chunk) {
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_nr_empty_pop_pages -= occ_pages;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
 
 	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
 		pcpu_schedule_balance_work();
@@ -1047,6 +1043,8 @@ fail:
 		/* see the flag handling in pcpu_blance_workfn() */
 		pcpu_atomic_alloc_failed = true;
 		pcpu_schedule_balance_work();
+	} else {
+		mutex_unlock(&pcpu_alloc_mutex);
 	}
 	return NULL;
 }
@@ -1131,6 +1129,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
 			continue;
 
+		list_del_init(&chunk->map_extend_list);
 		list_move(&chunk->list, &to_free);
 	}
 
@@ -1148,6 +1147,25 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		pcpu_destroy_chunk(chunk);
 	}
 
+	/* service chunks which requested async area map extension */
+	do {
+		int new_alloc = 0;
+
+		spin_lock_irq(&pcpu_lock);
+
+		chunk = list_first_entry_or_null(&pcpu_map_extend_chunks,
+					struct pcpu_chunk, map_extend_list);
+		if (chunk) {
+			list_del_init(&chunk->map_extend_list);
+			new_alloc = pcpu_need_to_extend(chunk, false);
+		}
+
+		spin_unlock_irq(&pcpu_lock);
+
+		if (new_alloc)
+			pcpu_extend_area_map(chunk, new_alloc);
+	} while (chunk);
+
 	/*
 	 * Ensure there are certain number of free populated pages for
 	 * atomic allocs.  Fill up from the most packed so that atomic
@@ -1646,7 +1664,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 */
 	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
-	INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
+	INIT_LIST_HEAD(&schunk->map_extend_list);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
 	schunk->map_alloc = ARRAY_SIZE(smap);
@@ -1675,7 +1693,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	if (dyn_size) {
 		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
-		INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
+		INIT_LIST_HEAD(&dchunk->map_extend_list);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
 		dchunk->map_alloc = ARRAY_SIZE(dmap);
diff --git a/mm/rmap.c b/mm/rmap.c
index b577fbb98d4b..ede183c32f45 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -649,6 +649,13 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
 	tlb_ubc->flush_required = true;
 
 	/*
+	 * Ensure compiler does not re-order the setting of tlb_flush_batched
+	 * before the PTE is cleared.
+	 */
+	barrier();
+	mm->tlb_flush_batched = true;
+
+	/*
 	 * If the PTE was dirty then it's best to assume it's writable. The
 	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
 	 * before the page is queued for IO.
@@ -675,6 +682,35 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
 
 	return should_defer;
 }
+
+/*
+ * Reclaim unmaps pages under the PTL but do not flush the TLB prior to
+ * releasing the PTL if TLB flushes are batched. It's possible for a parallel
+ * operation such as mprotect or munmap to race between reclaim unmapping
+ * the page and flushing the page. If this race occurs, it potentially allows
+ * access to data via a stale TLB entry. Tracking all mm's that have TLB
+ * batching in flight would be expensive during reclaim so instead track
+ * whether TLB batching occurred in the past and if so then do a flush here
+ * if required. This will cost one additional flush per reclaim cycle paid
+ * by the first operation at risk such as mprotect and mumap.
+ *
+ * This must be called under the PTL so that an access to tlb_flush_batched
+ * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
+ * via the PTL.
+ */
+void flush_tlb_batched_pending(struct mm_struct *mm)
+{
+	if (mm->tlb_flush_batched) {
+		flush_tlb_mm(mm);
+
+		/*
+		 * Do not allow the compiler to re-order the clearing of
+		 * tlb_flush_batched before the tlb is flushed.
+		 */
+		barrier();
+		mm->tlb_flush_batched = false;
+	}
+}
 #else
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
 		struct page *page, bool writable)
diff --git a/mm/shmem.c b/mm/shmem.c
index ea5a70cfc1d8..1b11ccc0a3b7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2153,9 +2153,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 									NULL);
 		if (error) {
 			/* Remove the !PageUptodate pages we added */
-			shmem_undo_range(inode,
-				(loff_t)start << PAGE_CACHE_SHIFT,
-				(loff_t)index << PAGE_CACHE_SHIFT, true);
+			if (index > start) {
+				shmem_undo_range(inode,
+				 (loff_t)start << PAGE_CACHE_SHIFT,
+				 ((loff_t)index << PAGE_CACHE_SHIFT) - 1, true);
+			}
 			goto undone;
 		}
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3c6a86b4ec25..bec2fce9fafc 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -521,8 +521,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 
 	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
-	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
-			       css->id, memcg_name_buf);
+	cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
+			       css->serial_nr, memcg_name_buf);
 	if (!cache_name)
 		goto out_unlock;
 
diff --git a/mm/slub.c b/mm/slub.c
index 46997517406e..4cf3a9c768b1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2819,6 +2819,7 @@ struct detached_freelist {
 	void *tail;
 	void *freelist;
 	int cnt;
+	struct kmem_cache *s;
 };
 
 /*
@@ -2833,8 +2834,9 @@ struct detached_freelist {
  * synchronization primitive.  Look ahead in the array is limited due
  * to performance reasons.
  */
-static int build_detached_freelist(struct kmem_cache *s, size_t size,
-				   void **p, struct detached_freelist *df)
+static inline
+int build_detached_freelist(struct kmem_cache *s, size_t size,
+			    void **p, struct detached_freelist *df)
 {
 	size_t first_skipped_index = 0;
 	int lookahead = 3;
@@ -2850,8 +2852,11 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	if (!object)
 		return 0;
 
+	/* Support for memcg, compiler can optimize this out */
+	df->s = cache_from_obj(s, object);
+
 	/* Start new detached freelist */
-	set_freepointer(s, object, NULL);
+	set_freepointer(df->s, object, NULL);
 	df->page = virt_to_head_page(object);
 	df->tail = object;
 	df->freelist = object;
@@ -2866,7 +2871,7 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 		/* df->page is always set at this point */
 		if (df->page == virt_to_head_page(object)) {
 			/* Opportunity build freelist */
-			set_freepointer(s, object, df->freelist);
+			set_freepointer(df->s, object, df->freelist);
 			df->freelist = object;
 			df->cnt++;
 			p[size] = NULL; /* mark object processed */
@@ -2885,25 +2890,20 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	return first_skipped_index;
 }
 
-
 /* Note that interrupts must be enabled when calling this function. */
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
 	if (WARN_ON(!size))
 		return;
 
 	do {
 		struct detached_freelist df;
-		struct kmem_cache *s;
-
-		/* Support for memcg */
-		s = cache_from_obj(orig_s, p[size - 1]);
 
 		size = build_detached_freelist(s, size, p, &df);
 		if (unlikely(!df.page))
 			continue;
 
-		slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
@@ -5261,6 +5261,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		char mbuf[64];
 		char *buf;
 		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+		ssize_t len;
 
 		if (!attr || !attr->store || !attr->show)
 			continue;
@@ -5285,8 +5286,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(root_cache, buf);
-		attr->store(s, buf, strlen(buf));
+		len = attr->show(root_cache, buf);
+		if (len > 0)
+			attr->store(s, buf, len);
 	}
 
 	if (buffer)
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index b5f7f24b8dd1..09f733b0424a 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -48,6 +48,9 @@ static int swap_cgroup_prepare(int type)
 		if (!page)
 			goto not_enough_page;
 		ctrl->map[idx] = page;
+
+		if (!(idx % SWAP_CLUSTER_MAX))
+			cond_resched();
 	}
 	return 0;
 not_enough_page:
@@ -202,6 +205,8 @@ void swap_cgroup_swapoff(int type)
 			struct page *page = map[i];
 			if (page)
 				__free_page(page);
+			if (!(i % SWAP_CLUSTER_MAX))
+				cond_resched();
 		}
 		vfree(map);
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 58877312cf6b..c1a0f3dea8b5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2225,6 +2225,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 		swab32s(&swap_header->info.version);
 		swab32s(&swap_header->info.last_page);
 		swab32s(&swap_header->info.nr_badpages);
+		if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+			return 0;
 		for (i = 0; i < swap_header->info.nr_badpages; i++)
 			swab32s(&swap_header->info.badpages[i]);
 	}
diff --git a/mm/truncate.c b/mm/truncate.c
index 76e35ad97102..f4c8270f7b84 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -732,7 +732,7 @@ EXPORT_SYMBOL(truncate_setsize);
  */
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
 {
-	int bsize = 1 << inode->i_blkbits;
+	int bsize = i_blocksize(inode);
 	loff_t rounded_from;
 	struct page *page;
 	pgoff_t index;
diff --git a/mm/util.c b/mm/util.c
index 9af1c12b310c..d5259b62f8d7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -199,36 +199,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-static int vm_is_stack_for_task(struct task_struct *t,
-				struct vm_area_struct *vma)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
 {
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
-/*
- * Check if the vma is being used as a stack.
- * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the task_struct of the task
- * that the vma is stack for. Must be called under rcu_read_lock().
- */
-struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group)
-{
-	if (vm_is_stack_for_task(task, vma))
-		return task;
-
-	if (in_group) {
-		struct task_struct *t;
-
-		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma))
-				return t;
-		}
-	}
-
-	return NULL;
-}
-
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index c5afd573d7da..3fb15c25af87 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -112,9 +112,16 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 						    unsigned long reclaimed)
 {
 	unsigned long scale = scanned + reclaimed;
-	unsigned long pressure;
+	unsigned long pressure = 0;
 
 	/*
+	 * reclaimed can be greater than scanned in cases
+	 * like THP, where the scanned is 1 and reclaimed
+	 * could be 512
+	 */
+	if (reclaimed >= scanned)
+		goto out;
+	/*
 	 * We calculate the ratio (in percents) of how many pages were
 	 * scanned vs. reclaimed in a given time frame (window). Note that
 	 * time is in VM reclaimer's "ticks", i.e. number of pages
@@ -124,6 +131,7 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
 	pressure = scale - (reclaimed * scale / scanned);
 	pressure = pressure * 100 / scale;
 
+out:
 	pr_debug("%s: %3lu  (s: %lu  r: %lu)\n", __func__, pressure,
 		 scanned, reclaimed);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2aec4241b42a..440c2df9be82 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -277,6 +277,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
+	long scanned = 0, next_deferred;
 
 	freeable = shrinker->count_objects(shrinker, shrinkctl);
 	if (freeable == 0)
@@ -298,7 +299,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
 		total_scan = freeable;
-	}
+		next_deferred = nr;
+	} else
+		next_deferred = total_scan;
 
 	/*
 	 * We need to avoid excessive windup on filesystem shrinkers
@@ -355,17 +358,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 
 		count_vm_events(SLABS_SCANNED, nr_to_scan);
 		total_scan -= nr_to_scan;
+		scanned += nr_to_scan;
 
 		cond_resched();
 	}
 
+	if (next_deferred >= scanned)
+		next_deferred -= scanned;
+	else
+		next_deferred = 0;
 	/*
 	 * move the unused scan count back into the shrinker in a
 	 * manner that handles concurrent updates. If we exhausted the
 	 * scan, there is no need to do an update.
 	 */
-	if (total_scan > 0)
-		new_nr = atomic_long_add_return(total_scan,
+	if (next_deferred > 0)
+		new_nr = atomic_long_add_return(next_deferred,
 						&shrinker->nr_deferred[nid]);
 	else
 		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
@@ -2159,23 +2167,6 @@ out:
 	}
 }
 
-#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-static void init_tlb_ubc(void)
-{
-	/*
-	 * This deliberately does not clear the cpumask as it's expensive
-	 * and unnecessary. If there happens to be data in there then the
-	 * first SWAP_CLUSTER_MAX pages will send an unnecessary IPI and
-	 * then will be cleared.
-	 */
-	current->tlb_ubc.flush_required = false;
-}
-#else
-static inline void init_tlb_ubc(void)
-{
-}
-#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
-
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
@@ -2210,8 +2201,6 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness,
 	scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
 			 sc->priority == DEF_PRIORITY);
 
-	init_tlb_ubc();
-
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
@@ -2534,13 +2523,13 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					requested_highidx, sc->nodemask) {
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		enum zone_type classzone_idx;
 
 		if (!populated_zone(zone))
 			continue;
 
-		classzone_idx = requested_highidx;
+		classzone_idx = gfp_zone(sc->gfp_mask);
 		while (!populated_zone(zone->zone_pgdat->node_zones +
 							classzone_idx))
 			classzone_idx--;
@@ -2929,7 +2918,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.may_writepage,
 					    sc.gfp_mask);
 
+	current->flags |= PF_MEMALLOC;
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+	current->flags &= ~PF_MEMALLOC;
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
diff --git a/mm/workingset.c b/mm/workingset.c
index aa017133744b..df66f426fdcf 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -341,21 +341,19 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * no pages, so we expect to be able to remove them all and
 	 * delete and free the empty node afterwards.
 	 */
-
-	BUG_ON(!node->count);
-	BUG_ON(node->count & RADIX_TREE_COUNT_MASK);
+	BUG_ON(!workingset_node_shadows(node));
+	BUG_ON(workingset_node_pages(node));
 
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
 			BUG_ON(!radix_tree_exceptional_entry(node->slots[i]));
 			node->slots[i] = NULL;
-			BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT));
-			node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+			workingset_node_shadows_dec(node);
 			BUG_ON(!mapping->nrshadows);
 			mapping->nrshadows--;
 		}
 	}
-	BUG_ON(node->count);
+	BUG_ON(workingset_node_shadows(node));
 	inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
 	if (!__radix_tree_delete_node(&mapping->page_tree, node))
 		BUG();
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index fc083996e40a..c1ea19478119 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1732,10 +1732,13 @@ static struct page *isolate_source_page(struct size_class *class)
 static unsigned long zs_can_compact(struct size_class *class)
 {
 	unsigned long obj_wasted;
+	unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
+	unsigned long obj_used = zs_stat_get(class, OBJ_USED);
 
-	obj_wasted = zs_stat_get(class, OBJ_ALLOCATED) -
-		zs_stat_get(class, OBJ_USED);
+	if (obj_allocated <= obj_used)
+		return 0;
 
+	obj_wasted = obj_allocated - obj_used;
 	obj_wasted /= get_maxobj_per_zspage(class->size,
 			class->pages_per_zspage);
 
diff --git a/mm/zswap.c b/mm/zswap.c
index bf14508afd64..45476f429789 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry;
 
 /* Enable/disable zswap (disabled by default) */
 static bool zswap_enabled;
-module_param_named(enabled, zswap_enabled, bool, 0644);
+static int zswap_enabled_param_set(const char *,
+				   const struct kernel_param *);
+static struct kernel_param_ops zswap_enabled_param_ops = {
+	.set =		zswap_enabled_param_set,
+	.get =		param_get_bool,
+};
+module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
 
 /* Crypto compressor to use */
 #define ZSWAP_COMPRESSOR_DEFAULT "lzo"
@@ -170,10 +176,15 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
 static LIST_HEAD(zswap_pools);
 /* protects zswap_pools list modification */
 static DEFINE_SPINLOCK(zswap_pools_lock);
+/* pool counter to provide unique names to zpool */
+static atomic_t zswap_pools_count = ATOMIC_INIT(0);
 
 /* used by param callback function */
 static bool zswap_init_started;
 
+/* fatal error during init */
+static bool zswap_init_failed;
+
 /*********************************
 * helpers and fwd declarations
 **********************************/
@@ -565,6 +576,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
 static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 {
 	struct zswap_pool *pool;
+	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
@@ -573,7 +585,10 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		return NULL;
 	}
 
-	pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops);
+	/* unique name for each pool specifically required by zsmalloc */
+	snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count));
+
+	pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops);
 	if (!pool->zpool) {
 		pr_err("%s zpool not available\n", type);
 		goto error;
@@ -696,6 +711,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	char *s = strstrip((char *)val);
 	int ret;
 
+	if (zswap_init_failed) {
+		pr_err("can't set param, initialization failed\n");
+		return -ENODEV;
+	}
+
 	/* no change required */
 	if (!strcmp(s, *(char **)kp->arg))
 		return 0;
@@ -775,6 +795,17 @@ static int zswap_zpool_param_set(const char *val,
 	return __zswap_param_set(val, kp, NULL, zswap_compressor);
 }
 
+static int zswap_enabled_param_set(const char *val,
+				   const struct kernel_param *kp)
+{
+	if (zswap_init_failed) {
+		pr_err("can't enable, initialization failed\n");
+		return -ENODEV;
+	}
+
+	return param_set_bool(val, kp);
+}
+
 /*********************************
 * writeback code
 **********************************/
@@ -1261,6 +1292,9 @@ pool_fail:
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:
+	/* if built-in, we aren't unloaded on failure; don't allow use */
+	zswap_init_failed = true;
+	zswap_enabled = false;
 	return -ENOMEM;
 }
 /* must be late so crypto has time to come up */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index d2cd9de4b724..5e4199d5a388 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -278,7 +278,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	free_netdev(new_dev);
+	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+		free_netdev(new_dev);
 	return err;
 }
 
@@ -291,6 +292,10 @@ static void vlan_sync_address(struct net_device *dev,
 	if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr))
 		return;
 
+	/* vlan continues to inherit address of lower device */
+	if (vlan_dev_inherit_address(vlandev, dev))
+		goto out;
+
 	/* vlan address was different from the old address and is equal to
 	 * the new address */
 	if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
@@ -303,6 +308,7 @@ static void vlan_sync_address(struct net_device *dev,
 	    !ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
 		dev_uc_add(dev, vlandev->dev_addr);
 
+out:
 	ether_addr_copy(vlan->real_dev_addr, dev->dev_addr);
 }
 
@@ -659,7 +665,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*vhdr));
 	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 9d010a09ab98..cc1557978066 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -109,6 +109,8 @@ int vlan_check_real_dev(struct net_device *real_dev,
 void vlan_setup(struct net_device *dev);
 int register_vlan_dev(struct net_device *dev);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+bool vlan_dev_inherit_address(struct net_device *dev,
+			      struct net_device *real_dev);
 
 static inline u32 vlan_get_ingress_priority(struct net_device *dev,
 					    u16 vlan_tci)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index fded86508117..ca4dc9031073 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -244,6 +244,17 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
 	strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
 }
 
+bool vlan_dev_inherit_address(struct net_device *dev,
+			      struct net_device *real_dev)
+{
+	if (dev->addr_assign_type != NET_ADDR_STOLEN)
+		return false;
+
+	ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+	call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	return true;
+}
+
 static int vlan_dev_open(struct net_device *dev)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
@@ -254,7 +265,8 @@ static int vlan_dev_open(struct net_device *dev)
 	    !(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
 		return -ENETDOWN;
 
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) {
+	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) &&
+	    !vlan_dev_inherit_address(dev, real_dev)) {
 		err = dev_uc_add(real_dev, dev->dev_addr);
 		if (err < 0)
 			goto out;
@@ -558,8 +570,10 @@ static int vlan_dev_init(struct net_device *dev)
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
 
-	if (is_zero_ether_addr(dev->dev_addr))
-		eth_hw_addr_inherit(dev, real_dev);
+	if (is_zero_ether_addr(dev->dev_addr)) {
+		ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
+		dev->addr_assign_type = NET_ADDR_STOLEN;
+	}
 	if (is_zero_ether_addr(dev->broadcast))
 		memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
 
diff --git a/net/9p/client.c b/net/9p/client.c
index ea79ee9a7348..f5feac4ff4ec 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -2101,6 +2101,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 		trace_9p_protocol_dump(clnt, req->rc);
 		goto free_and_error;
 	}
+	if (rsize < count) {
+		pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize);
+		count = rsize;
+	}
 
 	p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fbd0acf80b13..2fdebabbfacd 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock)
 			release_sock(sk);
 			ax25_disconnect(ax25, 0);
 			lock_sock(sk);
-			ax25_destroy_socket(ax25);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_destroy_socket(ax25);
 			break;
 
 		case AX25_STATE_3:
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 951cd57bb07d..5237dff6941d 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 	switch (ax25->state) {
 
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index b563a3f5f2a8..2fa3be965101 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 004467c9e6e1..2c0d6ef66f9d 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 
 	switch (ax25->state) {
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 3b78e8473a01..983f0b5e14f1 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	ax25_stop_heartbeat(ax25);
+	if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
+		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
 	ax25_stop_t3timer(ax25);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index a49c705fb86b..5f19133c5530 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -553,6 +553,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
  * be sent to
  * @bat_priv: the bat priv with all the soft interface information
  * @ip_dst: ipv4 to look up in the DHT
+ * @vid: VLAN identifier
  *
  * An originator O is selected if and only if its DHT_ID value is one of three
  * closest values (from the LEFT, with wrap around if needed) then the hash
@@ -561,7 +562,8 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
  * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM.
  */
 static struct batadv_dat_candidate *
-batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
+batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst,
+			     unsigned short vid)
 {
 	int select;
 	batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key;
@@ -577,7 +579,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
 		return NULL;
 
 	dat.ip = ip_dst;
-	dat.vid = 0;
+	dat.vid = vid;
 	ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat,
 						    BATADV_DAT_ADDR_MAX);
 
@@ -597,6 +599,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: payload to send
  * @ip: the DHT key
+ * @vid: VLAN identifier
  * @packet_subtype: unicast4addr packet subtype to use
  *
  * This function copies the skb with pskb_copy() and is sent as unicast packet
@@ -607,7 +610,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
  */
 static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
 				 struct sk_buff *skb, __be32 ip,
-				 int packet_subtype)
+				 unsigned short vid, int packet_subtype)
 {
 	int i;
 	bool ret = false;
@@ -616,7 +619,7 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
 	struct sk_buff *tmp_skb;
 	struct batadv_dat_candidate *cand;
 
-	cand = batadv_dat_select_candidates(bat_priv, ip);
+	cand = batadv_dat_select_candidates(bat_priv, ip, vid);
 	if (!cand)
 		goto out;
 
@@ -1004,7 +1007,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		ret = true;
 	} else {
 		/* Send the request to the DHT */
-		ret = batadv_dat_send_data(bat_priv, skb, ip_dst,
+		ret = batadv_dat_send_data(bat_priv, skb, ip_dst, vid,
 					   BATADV_P_DAT_DHT_GET);
 	}
 out:
@@ -1132,8 +1135,8 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
 	/* Send the ARP reply to the candidates for both the IP addresses that
 	 * the node obtained from the ARP reply
 	 */
-	batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT);
-	batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT);
+	batadv_dat_send_data(bat_priv, skb, ip_src, vid, BATADV_P_DAT_DHT_PUT);
+	batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT);
 }
 
 /**
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 17851d3aaf22..6282f021ddfb 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -197,18 +197,12 @@ static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node)
 {
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
-	struct batadv_algo_ops *bao;
-
-	bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
 		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
 
-	if (bao->bat_neigh_free)
-		bao->bat_neigh_free(neigh_node);
-
 	batadv_hardif_free_ref(neigh_node->if_incoming);
 
 	kfree_rcu(neigh_node, rcu);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 3207667e69de..d8a2f33e60e5 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -104,6 +104,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
 		neigh_node = NULL;
 
 	spin_lock_bh(&orig_node->neigh_list_lock);
+	/* curr_router used earlier may not be the current orig_ifinfo->router
+	 * anymore because it was dereferenced outside of the neigh_list_lock
+	 * protected region. After the new best neighbor has replace the current
+	 * best neighbor the reference counter needs to decrease. Consequently,
+	 * the code needs to ensure the curr_router variable contains a pointer
+	 * to the replaced best neighbor.
+	 */
+	curr_router = rcu_dereference_protected(orig_ifinfo->router, true);
+
 	rcu_assign_pointer(orig_ifinfo->router, neigh_node);
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 	batadv_orig_ifinfo_free_ref(orig_ifinfo);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index f664324805eb..0e0c3b8ed927 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -630,6 +630,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 
 		if (pending) {
 			hlist_del(&forw_packet->list);
+			if (!forw_packet->own)
+				atomic_inc(&bat_priv->bcast_queue_left);
+
 			batadv_forw_packet_free(forw_packet);
 		}
 	}
@@ -657,6 +660,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 
 		if (pending) {
 			hlist_del(&forw_packet->list);
+			if (!forw_packet->own)
+				atomic_inc(&bat_priv->batman_queue_left);
+
 			batadv_forw_packet_free(forw_packet);
 		}
 	}
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index ac4d08de5df4..720f1a5b81ac 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -407,11 +407,17 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	 */
 	nf_reset(skb);
 
+	if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
+		goto dropped;
+
 	vid = batadv_get_vid(skb, 0);
 	ethhdr = eth_hdr(skb);
 
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_8021Q:
+		if (!pskb_may_pull(skb, VLAN_ETH_HLEN))
+			goto dropped;
+
 		vhdr = (struct vlan_ethhdr *)skb->data;
 
 		if (vhdr->h_vlan_encapsulated_proto != ethertype)
@@ -423,8 +429,6 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	}
 
 	/* skb->dev & skb->pkt_type are set here */
-	if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
-		goto dropped;
 	skb->protocol = eth_type_trans(skb, soft_iface);
 
 	/* should not be necessary anymore as we use skb_pull_rcsum()
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 83b0ca27a45e..f2079acb555d 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -2764,7 +2764,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv,
 							     &tvlv_tt_data,
 							     &tt_change,
 							     &tt_len);
-		if (!tt_len)
+		if (!tt_len || !tvlv_len)
 			goto unlock;
 
 		/* Copy the last orig_node's OGM buffer */
@@ -2782,7 +2782,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv,
 							     &tvlv_tt_data,
 							     &tt_change,
 							     &tt_len);
-		if (!tt_len)
+		if (!tt_len || !tvlv_len)
 			goto out;
 
 		/* fill the rest of the tvlv with the real TT entries */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index d260efd70499..cbd347c2e4a5 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1136,8 +1136,6 @@ struct batadv_forw_packet {
  * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better
  *  than neigh2 for their respective outgoing interface from the metric
  *  prospective
- * @bat_neigh_free: free the resources allocated by the routing algorithm for a
- *  neigh_node object
  * @bat_orig_print: print the originator table (optional)
  * @bat_orig_free: free the resources allocated by the routing algorithm for an
  *  orig_node object
@@ -1165,7 +1163,6 @@ struct batadv_algo_ops {
 		 struct batadv_hard_iface *if_outgoing1,
 		 struct batadv_neigh_node *neigh2,
 		 struct batadv_hard_iface *if_outgoing2);
-	void (*bat_neigh_free)(struct batadv_neigh_node *neigh);
 	/* orig_node handling API */
 	void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq,
 			       struct batadv_hard_iface *hard_iface);
diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c
index 1641367e54ca..69f56073b337 100644
--- a/net/bluetooth/bnep/core.c
+++ b/net/bluetooth/bnep/core.c
@@ -484,16 +484,16 @@ static int bnep_session(void *arg)
 	struct net_device *dev = s->dev;
 	struct sock *sk = s->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	BT_DBG("");
 
 	set_user_nice(current, -15);
 
-	init_waitqueue_entry(&wait, current);
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 
 		if (atomic_read(&s->terminate))
 			break;
@@ -515,9 +515,8 @@ static int bnep_session(void *arg)
 				break;
 		netif_wake_queue(dev);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	/* Cleanup session */
@@ -663,7 +662,7 @@ int bnep_del_connection(struct bnep_conndel_req *req)
 	s = __bnep_get_session(req->dst);
 	if (s) {
 		atomic_inc(&s->terminate);
-		wake_up_process(s->task);
+		wake_up_interruptible(sk_sleep(s->sock->sk));
 	} else
 		err = -ENOENT;
 
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index 298ed37010e6..3a39fd523e40 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -281,16 +281,16 @@ static int cmtp_session(void *arg)
 	struct cmtp_session *session = arg;
 	struct sock *sk = session->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	BT_DBG("session %p", session);
 
 	set_user_nice(current, -15);
 
-	init_waitqueue_entry(&wait, current);
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 
 		if (atomic_read(&session->terminate))
 			break;
@@ -307,9 +307,8 @@ static int cmtp_session(void *arg)
 
 		cmtp_process_transmit(session);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	down_write(&cmtp_session_sem);
@@ -394,7 +393,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock)
 		err = cmtp_attach_device(session);
 		if (err < 0) {
 			atomic_inc(&session->terminate);
-			wake_up_process(session->task);
+			wake_up_interruptible(sk_sleep(session->sock->sk));
 			up_write(&cmtp_session_sem);
 			return err;
 		}
@@ -432,7 +431,11 @@ int cmtp_del_connection(struct cmtp_conndel_req *req)
 
 		/* Stop session thread */
 		atomic_inc(&session->terminate);
-		wake_up_process(session->task);
+
+		/* Ensure session->terminate is updated */
+		smp_mb__after_atomic();
+
+		wake_up_interruptible(sk_sleep(session->sock->sk));
 	} else
 		err = -ENOENT;
 
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index b1eb8c09a660..c842f40c1173 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1164,7 +1164,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE))
+	if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_NOSIGNAL|MSG_ERRQUEUE|
+			       MSG_CMSG_COMPAT))
 		return -EINVAL;
 
 	if (len < 4 || len > HCI_MAX_FRAME_SIZE)
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 0bec4588c3c8..1fc076420d1e 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -36,6 +36,7 @@
 #define VERSION "1.2"
 
 static DECLARE_RWSEM(hidp_session_sem);
+static DECLARE_WAIT_QUEUE_HEAD(hidp_session_wq);
 static LIST_HEAD(hidp_session_list);
 
 static unsigned char hidp_keycode[256] = {
@@ -1068,12 +1069,12 @@ static int hidp_session_start_sync(struct hidp_session *session)
  * Wake up session thread and notify it to stop. This is asynchronous and
  * returns immediately. Call this whenever a runtime error occurs and you want
  * the session to stop.
- * Note: wake_up_process() performs any necessary memory-barriers for us.
+ * Note: wake_up_interruptible() performs any necessary memory-barriers for us.
  */
 static void hidp_session_terminate(struct hidp_session *session)
 {
 	atomic_inc(&session->terminate);
-	wake_up_process(session->task);
+	wake_up_interruptible(&hidp_session_wq);
 }
 
 /*
@@ -1180,7 +1181,9 @@ static void hidp_session_run(struct hidp_session *session)
 	struct sock *ctrl_sk = session->ctrl_sock->sk;
 	struct sock *intr_sk = session->intr_sock->sk;
 	struct sk_buff *skb;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&hidp_session_wq, &wait);
 	for (;;) {
 		/*
 		 * This thread can be woken up two ways:
@@ -1188,12 +1191,10 @@ static void hidp_session_run(struct hidp_session *session)
 		 *    session->terminate flag and wakes this thread up.
 		 *  - Via modifying the socket state of ctrl/intr_sock. This
 		 *    thread is woken up by ->sk_state_changed().
-		 *
-		 * Note: set_current_state() performs any necessary
-		 * memory-barriers for us.
 		 */
-		set_current_state(TASK_INTERRUPTIBLE);
 
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 		if (atomic_read(&session->terminate))
 			break;
 
@@ -1227,11 +1228,22 @@ static void hidp_session_run(struct hidp_session *session)
 		hidp_process_transmit(session, &session->ctrl_transmit,
 				      session->ctrl_sock);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
+	remove_wait_queue(&hidp_session_wq, &wait);
 
 	atomic_inc(&session->terminate);
-	set_current_state(TASK_RUNNING);
+
+	/* Ensure session->terminate is updated */
+	smp_mb__after_atomic();
+}
+
+static int hidp_session_wake_function(wait_queue_t *wait,
+				      unsigned int mode,
+				      int sync, void *key)
+{
+	wake_up_interruptible(&hidp_session_wq);
+	return false;
 }
 
 /*
@@ -1244,7 +1256,8 @@ static void hidp_session_run(struct hidp_session *session)
 static int hidp_session_thread(void *arg)
 {
 	struct hidp_session *session = arg;
-	wait_queue_t ctrl_wait, intr_wait;
+	DEFINE_WAIT_FUNC(ctrl_wait, hidp_session_wake_function);
+	DEFINE_WAIT_FUNC(intr_wait, hidp_session_wake_function);
 
 	BT_DBG("session %p", session);
 
@@ -1254,8 +1267,6 @@ static int hidp_session_thread(void *arg)
 	set_user_nice(current, -15);
 	hidp_set_timer(session);
 
-	init_waitqueue_entry(&ctrl_wait, current);
-	init_waitqueue_entry(&intr_wait, current);
 	add_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait);
 	add_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait);
 	/* This memory barrier is paired with wq_has_sleeper(). See
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 66e8b6ee19a5..357bcd34cf1f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -57,7 +57,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				       u8 code, u8 ident, u16 dlen, void *data);
 static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len,
 			   void *data);
-static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data);
+static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data, size_t data_size);
 static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err);
 
 static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
@@ -1462,7 +1462,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 
 			set_bit(CONF_REQ_SENT, &chan->conf_state);
 			l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-				       l2cap_build_conf_req(chan, buf), buf);
+				       l2cap_build_conf_req(chan, buf, sizeof(buf)), buf);
 			chan->num_conf_req++;
 		}
 
@@ -2966,12 +2966,15 @@ static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen,
 	return len;
 }
 
-static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val)
+static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val, size_t size)
 {
 	struct l2cap_conf_opt *opt = *ptr;
 
 	BT_DBG("type 0x%2.2x len %u val 0x%lx", type, len, val);
 
+	if (size < L2CAP_CONF_OPT_SIZE + len)
+		return;
+
 	opt->type = type;
 	opt->len  = len;
 
@@ -2996,7 +2999,7 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val)
 	*ptr += L2CAP_CONF_OPT_SIZE + len;
 }
 
-static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan)
+static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan, size_t size)
 {
 	struct l2cap_conf_efs efs;
 
@@ -3024,7 +3027,7 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan)
 	}
 
 	l2cap_add_conf_opt(ptr, L2CAP_CONF_EFS, sizeof(efs),
-			   (unsigned long) &efs);
+			   (unsigned long) &efs, size);
 }
 
 static void l2cap_ack_timeout(struct work_struct *work)
@@ -3170,11 +3173,12 @@ static inline void l2cap_txwin_setup(struct l2cap_chan *chan)
 	chan->ack_win = chan->tx_win;
 }
 
-static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data)
+static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data, size_t data_size)
 {
 	struct l2cap_conf_req *req = data;
 	struct l2cap_conf_rfc rfc = { .mode = chan->mode };
 	void *ptr = req->data;
+	void *endptr = data + data_size;
 	u16 size;
 
 	BT_DBG("chan %p", chan);
@@ -3199,7 +3203,7 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data)
 
 done:
 	if (chan->imtu != L2CAP_DEFAULT_MTU)
-		l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu);
+		l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, endptr - ptr);
 
 	switch (chan->mode) {
 	case L2CAP_MODE_BASIC:
@@ -3218,7 +3222,7 @@ done:
 		rfc.max_pdu_size    = 0;
 
 		l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc),
-				   (unsigned long) &rfc);
+				   (unsigned long) &rfc, endptr - ptr);
 		break;
 
 	case L2CAP_MODE_ERTM:
@@ -3238,21 +3242,21 @@ done:
 				       L2CAP_DEFAULT_TX_WINDOW);
 
 		l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc),
-				   (unsigned long) &rfc);
+				   (unsigned long) &rfc, endptr - ptr);
 
 		if (test_bit(FLAG_EFS_ENABLE, &chan->flags))
-			l2cap_add_opt_efs(&ptr, chan);
+			l2cap_add_opt_efs(&ptr, chan, endptr - ptr);
 
 		if (test_bit(FLAG_EXT_CTRL, &chan->flags))
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2,
-					   chan->tx_win);
+					   chan->tx_win, endptr - ptr);
 
 		if (chan->conn->feat_mask & L2CAP_FEAT_FCS)
 			if (chan->fcs == L2CAP_FCS_NONE ||
 			    test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) {
 				chan->fcs = L2CAP_FCS_NONE;
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1,
-						   chan->fcs);
+						   chan->fcs, endptr - ptr);
 			}
 		break;
 
@@ -3270,17 +3274,17 @@ done:
 		rfc.max_pdu_size = cpu_to_le16(size);
 
 		l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc),
-				   (unsigned long) &rfc);
+				   (unsigned long) &rfc, endptr - ptr);
 
 		if (test_bit(FLAG_EFS_ENABLE, &chan->flags))
-			l2cap_add_opt_efs(&ptr, chan);
+			l2cap_add_opt_efs(&ptr, chan, endptr - ptr);
 
 		if (chan->conn->feat_mask & L2CAP_FEAT_FCS)
 			if (chan->fcs == L2CAP_FCS_NONE ||
 			    test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) {
 				chan->fcs = L2CAP_FCS_NONE;
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1,
-						   chan->fcs);
+						   chan->fcs, endptr - ptr);
 			}
 		break;
 	}
@@ -3291,10 +3295,11 @@ done:
 	return ptr - data;
 }
 
-static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
+static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data_size)
 {
 	struct l2cap_conf_rsp *rsp = data;
 	void *ptr = rsp->data;
+	void *endptr = data + data_size;
 	void *req = chan->conf_req;
 	int len = chan->conf_len;
 	int type, hint, olen;
@@ -3396,7 +3401,7 @@ done:
 			return -ECONNREFUSED;
 
 		l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc),
-				   (unsigned long) &rfc);
+				   (unsigned long) &rfc, endptr - ptr);
 	}
 
 	if (result == L2CAP_CONF_SUCCESS) {
@@ -3409,7 +3414,7 @@ done:
 			chan->omtu = mtu;
 			set_bit(CONF_MTU_DONE, &chan->conf_state);
 		}
-		l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->omtu);
+		l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->omtu, endptr - ptr);
 
 		if (remote_efs) {
 			if (chan->local_stype != L2CAP_SERV_NOTRAFIC &&
@@ -3423,7 +3428,7 @@ done:
 
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS,
 						   sizeof(efs),
-						   (unsigned long) &efs);
+						   (unsigned long) &efs, endptr - ptr);
 			} else {
 				/* Send PENDING Conf Rsp */
 				result = L2CAP_CONF_PENDING;
@@ -3456,7 +3461,7 @@ done:
 			set_bit(CONF_MODE_DONE, &chan->conf_state);
 
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC,
-					   sizeof(rfc), (unsigned long) &rfc);
+					   sizeof(rfc), (unsigned long) &rfc, endptr - ptr);
 
 			if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) {
 				chan->remote_id = efs.id;
@@ -3470,7 +3475,7 @@ done:
 					le32_to_cpu(efs.sdu_itime);
 				l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS,
 						   sizeof(efs),
-						   (unsigned long) &efs);
+						   (unsigned long) &efs, endptr - ptr);
 			}
 			break;
 
@@ -3484,7 +3489,7 @@ done:
 			set_bit(CONF_MODE_DONE, &chan->conf_state);
 
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc),
-					   (unsigned long) &rfc);
+					   (unsigned long) &rfc, endptr - ptr);
 
 			break;
 
@@ -3506,10 +3511,11 @@ done:
 }
 
 static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
-				void *data, u16 *result)
+				void *data, size_t size, u16 *result)
 {
 	struct l2cap_conf_req *req = data;
 	void *ptr = req->data;
+	void *endptr = data + size;
 	int type, olen;
 	unsigned long val;
 	struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC };
@@ -3527,13 +3533,13 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
 				chan->imtu = L2CAP_DEFAULT_MIN_MTU;
 			} else
 				chan->imtu = val;
-			l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu);
+			l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, endptr - ptr);
 			break;
 
 		case L2CAP_CONF_FLUSH_TO:
 			chan->flush_to = val;
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO,
-					   2, chan->flush_to);
+					   2, chan->flush_to, endptr - ptr);
 			break;
 
 		case L2CAP_CONF_RFC:
@@ -3547,13 +3553,13 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
 			chan->fcs = 0;
 
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC,
-					   sizeof(rfc), (unsigned long) &rfc);
+					   sizeof(rfc), (unsigned long) &rfc, endptr - ptr);
 			break;
 
 		case L2CAP_CONF_EWS:
 			chan->ack_win = min_t(u16, val, chan->ack_win);
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2,
-					   chan->tx_win);
+					   chan->tx_win, endptr - ptr);
 			break;
 
 		case L2CAP_CONF_EFS:
@@ -3566,7 +3572,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
 				return -ECONNREFUSED;
 
 			l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs),
-					   (unsigned long) &efs);
+					   (unsigned long) &efs, endptr - ptr);
 			break;
 
 		case L2CAP_CONF_FCS:
@@ -3671,7 +3677,7 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan)
 		return;
 
 	l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-		       l2cap_build_conf_req(chan, buf), buf);
+		       l2cap_build_conf_req(chan, buf, sizeof(buf)), buf);
 	chan->num_conf_req++;
 }
 
@@ -3879,7 +3885,7 @@ sendresp:
 		u8 buf[128];
 		set_bit(CONF_REQ_SENT, &chan->conf_state);
 		l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-			       l2cap_build_conf_req(chan, buf), buf);
+			       l2cap_build_conf_req(chan, buf, sizeof(buf)), buf);
 		chan->num_conf_req++;
 	}
 
@@ -3957,7 +3963,7 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn,
 			break;
 
 		l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-			       l2cap_build_conf_req(chan, req), req);
+			       l2cap_build_conf_req(chan, req, sizeof(req)), req);
 		chan->num_conf_req++;
 		break;
 
@@ -4069,7 +4075,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 	}
 
 	/* Complete config. */
-	len = l2cap_parse_conf_req(chan, rsp);
+	len = l2cap_parse_conf_req(chan, rsp, sizeof(rsp));
 	if (len < 0) {
 		l2cap_send_disconn_req(chan, ECONNRESET);
 		goto unlock;
@@ -4103,7 +4109,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 	if (!test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) {
 		u8 buf[64];
 		l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ,
-			       l2cap_build_conf_req(chan, buf), buf);
+			       l2cap_build_conf_req(chan, buf, sizeof(buf)), buf);
 		chan->num_conf_req++;
 	}
 
@@ -4163,7 +4169,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
 			char buf[64];
 
 			len = l2cap_parse_conf_rsp(chan, rsp->data, len,
-						   buf, &result);
+						   buf, sizeof(buf), &result);
 			if (len < 0) {
 				l2cap_send_disconn_req(chan, ECONNRESET);
 				goto done;
@@ -4193,7 +4199,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
 			/* throw out any old stored conf requests */
 			result = L2CAP_CONF_SUCCESS;
 			len = l2cap_parse_conf_rsp(chan, rsp->data, len,
-						   req, &result);
+						   req, sizeof(req), &result);
 			if (len < 0) {
 				l2cap_send_disconn_req(chan, ECONNRESET);
 				goto done;
@@ -4770,7 +4776,7 @@ static void l2cap_do_create(struct l2cap_chan *chan, int result,
 			set_bit(CONF_REQ_SENT, &chan->conf_state);
 			l2cap_send_cmd(chan->conn, l2cap_get_ident(chan->conn),
 				       L2CAP_CONF_REQ,
-				       l2cap_build_conf_req(chan, buf), buf);
+				       l2cap_build_conf_req(chan, buf, sizeof(buf)), buf);
 			chan->num_conf_req++;
 		}
 	}
@@ -7442,7 +7448,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 				set_bit(CONF_REQ_SENT, &chan->conf_state);
 				l2cap_send_cmd(conn, l2cap_get_ident(conn),
 					       L2CAP_CONF_REQ,
-					       l2cap_build_conf_req(chan, buf),
+					       l2cap_build_conf_req(chan, buf, sizeof(buf)),
 					       buf);
 				chan->num_conf_req++;
 			}
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1bb551527044..d9bbbded49ef 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -927,7 +927,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (get_user(opt, (u32 __user *) optval)) {
+		if (get_user(opt, (u16 __user *) optval)) {
 			err = -EFAULT;
 			break;
 		}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7f22119276f3..b1b0a1c0bd8d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7155,6 +7155,10 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				       status);
 
+	if (data_len != sizeof(*cp) + cp->adv_data_len + cp->scan_rsp_len)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				       MGMT_STATUS_INVALID_PARAMS);
+
 	flags = __le32_to_cpu(cp->flags);
 	timeout = __le16_to_cpu(cp->timeout);
 	duration = __le16_to_cpu(cp->duration);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 4b175df35184..906f88550cd8 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -23,6 +23,7 @@
 #include <linux/debugfs.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
+#include <crypto/algapi.h>
 #include <crypto/b128ops.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -524,7 +525,7 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
 	if (err)
 		return false;
 
-	return !memcmp(bdaddr->b, hash, 3);
+	return !crypto_memneq(bdaddr->b, hash, 3);
 }
 
 int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa)
@@ -577,7 +578,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16])
 			/* This is unlikely, but we need to check that
 			 * we didn't accidentially generate a debug key.
 			 */
-			if (memcmp(smp->local_sk, debug_sk, 32))
+			if (crypto_memneq(smp->local_sk, debug_sk, 32))
 				break;
 		}
 		smp->debug_key = false;
@@ -991,7 +992,7 @@ static u8 smp_random(struct smp_chan *smp)
 	if (ret)
 		return SMP_UNSPECIFIED;
 
-	if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) {
+	if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) {
 		BT_ERR("Pairing failed (confirmation values mismatch)");
 		return SMP_CONFIRM_FAILED;
 	}
@@ -1491,7 +1492,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
 			   smp->rrnd, r, cfm))
 			return SMP_UNSPECIFIED;
 
-		if (memcmp(smp->pcnf, cfm, 16))
+		if (crypto_memneq(smp->pcnf, cfm, 16))
 			return SMP_CONFIRM_FAILED;
 
 		smp->passkey_round++;
@@ -1875,7 +1876,7 @@ static u8 sc_send_public_key(struct smp_chan *smp)
 			/* This is unlikely, but we need to check that
 			 * we didn't accidentially generate a debug key.
 			 */
-			if (memcmp(smp->local_sk, debug_sk, 32))
+			if (crypto_memneq(smp->local_sk, debug_sk, 32))
 				break;
 		}
 	}
@@ -2140,7 +2141,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 		if (err)
 			return SMP_UNSPECIFIED;
 
-		if (memcmp(smp->pcnf, cfm, 16))
+		if (crypto_memneq(smp->pcnf, cfm, 16))
 			return SMP_CONFIRM_FAILED;
 	} else {
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
@@ -2621,7 +2622,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 		if (err)
 			return SMP_UNSPECIFIED;
 
-		if (memcmp(cfm.confirm_val, smp->pcnf, 16))
+		if (crypto_memneq(cfm.confirm_val, smp->pcnf, 16))
 			return SMP_CONFIRM_FAILED;
 	}
 
@@ -2654,7 +2655,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	else
 		hcon->pending_sec_level = BT_SECURITY_FIPS;
 
-	if (!memcmp(debug_pk, smp->remote_pk, 64))
+	if (!crypto_memneq(debug_pk, smp->remote_pk, 64))
 		set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags);
 
 	if (smp->method == DSP_PASSKEY) {
@@ -2753,7 +2754,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (err)
 		return SMP_UNSPECIFIED;
 
-	if (memcmp(check->e, e, 16))
+	if (crypto_memneq(check->e, e, 16))
 		return SMP_DHKEY_CHECK_FAILED;
 
 	if (!hcon->out) {
@@ -3463,7 +3464,7 @@ static int __init test_ah(struct crypto_blkcipher *tfm_aes)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 3))
+	if (crypto_memneq(res, exp, 3))
 		return -EINVAL;
 
 	return 0;
@@ -3493,7 +3494,7 @@ static int __init test_c1(struct crypto_blkcipher *tfm_aes)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 16))
+	if (crypto_memneq(res, exp, 16))
 		return -EINVAL;
 
 	return 0;
@@ -3518,7 +3519,7 @@ static int __init test_s1(struct crypto_blkcipher *tfm_aes)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 16))
+	if (crypto_memneq(res, exp, 16))
 		return -EINVAL;
 
 	return 0;
@@ -3550,7 +3551,7 @@ static int __init test_f4(struct crypto_hash *tfm_cmac)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 16))
+	if (crypto_memneq(res, exp, 16))
 		return -EINVAL;
 
 	return 0;
@@ -3584,10 +3585,10 @@ static int __init test_f5(struct crypto_hash *tfm_cmac)
 	if (err)
 		return err;
 
-	if (memcmp(mackey, exp_mackey, 16))
+	if (crypto_memneq(mackey, exp_mackey, 16))
 		return -EINVAL;
 
-	if (memcmp(ltk, exp_ltk, 16))
+	if (crypto_memneq(ltk, exp_ltk, 16))
 		return -EINVAL;
 
 	return 0;
@@ -3620,7 +3621,7 @@ static int __init test_f6(struct crypto_hash *tfm_cmac)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 16))
+	if (crypto_memneq(res, exp, 16))
 		return -EINVAL;
 
 	return 0;
@@ -3674,7 +3675,7 @@ static int __init test_h6(struct crypto_hash *tfm_cmac)
 	if (err)
 		return err;
 
-	if (memcmp(res, exp, 16))
+	if (crypto_memneq(res, exp, 16))
 		return -EINVAL;
 
 	return 0;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index a642bb829d09..09442e0f7f67 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -278,6 +278,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index f7fba74108a9..e24754a0e052 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook);
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 263b4de4de57..60a3dbfca8a1 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -21,18 +21,19 @@
 #include <asm/uaccess.h>
 #include "br_private.h"
 
-/* called with RTNL */
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
 {
 	struct net_device *dev;
 	int i = 0;
 
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (i >= num)
 			break;
 		if (dev->priv_flags & IFF_EBRIDGE)
 			indices[i++] = dev->ifindex;
 	}
+	rcu_read_unlock();
 
 	return i;
 }
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 03661d97463c..d80c15d028fe 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -464,8 +464,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			       &ip6h->saddr)) {
 		kfree_skb(skb);
+		br->has_ipv6_addr = 0;
 		return NULL;
 	}
+
+	br->has_ipv6_addr = 1;
 	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
 
 	hopopt = (u8 *)(ip6h + 1);
@@ -948,13 +951,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query)
 		mod_timer(&query->timer, jiffies);
 }
 
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void __br_multicast_enable_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 
-	spin_lock(&br->multicast_lock);
 	if (br->multicast_disabled || !netif_running(br->dev))
-		goto out;
+		return;
 
 	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -962,8 +964,14 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 #endif
 	if (port->multicast_router == 2 && hlist_unhashed(&port->rlist))
 		br_multicast_add_router(br, port);
+}
 
-out:
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+	struct net_bridge *br = port->br;
+
+	spin_lock(&br->multicast_lock);
+	__br_multicast_enable_port(port);
 	spin_unlock(&br->multicast_lock);
 }
 
@@ -1110,7 +1118,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		} else {
 			err = br_ip6_multicast_add_group(br, port,
 							 &grec->grec_mca, vid);
-			if (!err)
+			if (err)
 				break;
 		}
 	}
@@ -1270,6 +1278,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	__be32 group;
 	int err = 0;
 
@@ -1280,14 +1289,14 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 
 	group = ih->group;
 
-	if (skb->len == sizeof(*ih)) {
+	if (skb->len == offset + sizeof(*ih)) {
 		max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);
 
 		if (!max_delay) {
 			max_delay = 10 * HZ;
 			group = 0;
 		}
-	} else if (skb->len >= sizeof(*ih3)) {
+	} else if (skb->len >= offset + sizeof(*ih3)) {
 		ih3 = igmpv3_query_hdr(skb);
 		if (ih3->nsrcs)
 			goto out;
@@ -1348,6 +1357,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	const struct in6_addr *group = NULL;
 	bool is_general_query;
 	int err = 0;
@@ -1357,8 +1367,8 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
-	if (skb->len == sizeof(*mld)) {
-		if (!pskb_may_pull(skb, sizeof(*mld))) {
+	if (skb->len == offset + sizeof(*mld)) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld))) {
 			err = -EINVAL;
 			goto out;
 		}
@@ -1367,7 +1377,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		if (max_delay)
 			group = &mld->mld_mca;
 	} else {
-		if (!pskb_may_pull(skb, sizeof(*mld2q))) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) {
 			err = -EINVAL;
 			goto out;
 		}
@@ -1734,6 +1744,7 @@ void br_multicast_init(struct net_bridge *br)
 	br->ip6_other_query.delay_time = 0;
 	br->ip6_querier.port = NULL;
 #endif
+	br->has_ipv6_addr = 1;
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
@@ -1899,8 +1910,9 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
-	int err = 0;
 	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_port *port;
+	int err = 0;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (br->multicast_disabled == !val)
@@ -1928,10 +1940,9 @@ rollback:
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_own_query);
-#if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_own_query);
-#endif
+	br_multicast_open(br);
+	list_for_each_entry(port, &br->port_list, list)
+		__br_multicast_enable_port(port);
 
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 7ddbe7ec81d6..97fc19f001bf 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -516,21 +516,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -901,12 +886,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
 		.hook = br_nf_forward_ip,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_FORWARD,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 40197ff8918a..ff8bb41d713f 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -768,23 +768,16 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 			return -EPROTONOSUPPORT;
 		}
 	}
-#endif
 
-	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 (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+		__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
 
-	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);
+		if (defpvid >= VLAN_VID_MASK)
+			return -EINVAL;
 	}
+#endif
 
-	return register_netdevice(dev);
+	return 0;
 }
 
 static int br_port_slave_changelink(struct net_device *brdev,
@@ -1068,6 +1061,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	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);
+	int err;
+
+	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);
+	}
+
+	err = br_changelink(dev, tb, data);
+	if (err)
+		return err;
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_size(const struct net_device *brdev)
 {
 	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 216018c76018..1001a1b7df9b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -301,6 +301,7 @@ struct net_bridge
 	u8				multicast_disabled:1;
 	u8				multicast_querier:1;
 	u8				multicast_query_use_ifaddr:1;
+	u8				has_ipv6_addr:1;
 
 	u32				hash_elasticity;
 	u32				hash_max;
@@ -574,10 +575,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_other_query *querier)
+				struct bridge_mcast_other_query *querier,
+				const bool is_ipv6)
 {
+	bool own_querier_enabled;
+
+	if (br->multicast_querier) {
+		if (is_ipv6 && !br->has_ipv6_addr)
+			own_querier_enabled = false;
+		else
+			own_querier_enabled = true;
+	} else {
+		own_querier_enabled = false;
+	}
+
 	return time_is_before_jiffies(querier->delay_time) &&
-	       (br->multicast_querier || timer_pending(&querier->timer));
+	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
@@ -585,10 +598,12 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip4_other_query, false);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip6_other_query, true);
 #endif
 	default:
 		return false;
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 5f3f64553179..eff69cb270d2 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -567,6 +567,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
 
 }
 
+/* Set time interval that dynamic forwarding entries live
+ * For pure software bridge, allow values outside the 802.1
+ * standard specification for special cases:
+ *  0 - entry never ages (all permanant)
+ *  1 - entry disappears (no persistance)
+ *
+ * Offloaded switch entries maybe more restrictive
+ */
 int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 {
 	struct switchdev_attr attr = {
@@ -577,11 +585,8 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 	unsigned long t = clock_t_to_jiffies(ageing_time);
 	int err;
 
-	if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME)
-		return -ERANGE;
-
 	err = switchdev_port_attr_set(br->dev, &attr);
-	if (err)
+	if (err && err != -EOPNOTSUPP)
 		return err;
 
 	br->ageing_time = t;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 8a7ada8bb947..bcb4559e735d 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -166,6 +166,8 @@ 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 */
+		if (br->dev->flags & IFF_UP)
+			mod_timer(&br->hello_timer, jiffies + br->hello_time);
 		br_port_state_selection(br);
 	}
 
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 5f0f5af0ec35..7dbe6a5c31eb 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -40,7 +40,7 @@ static void br_hello_timer_expired(unsigned long arg)
 	if (br->dev->flags & IFF_UP) {
 		br_config_bpdu_generation(br);
 
-		if (br->stp_enabled != BR_USER_STP)
+		if (br->stp_enabled == BR_KERNEL_STP)
 			mod_timer(&br->hello_timer,
 				  round_jiffies(jiffies + br->hello_time));
 	}
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index f6c3b2137eea..71b6ab240dea 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx)
 {
 	struct sk_buff *skb;
 
-	if (likely(in_interrupt()))
-		skb = alloc_skb(len + pfx, GFP_ATOMIC);
-	else
-		skb = alloc_skb(len + pfx, GFP_KERNEL);
-
+	skb = alloc_skb(len + pfx, GFP_ATOMIC);
 	if (unlikely(skb == NULL))
 		return NULL;
 
@@ -286,7 +282,7 @@ int cfpkt_setlen(struct cfpkt *pkt, u16 len)
 		else
 			skb_trim(skb, len);
 
-			return cfpkt_getlen(pkt);
+		return cfpkt_getlen(pkt);
 	}
 
 	/* Need to expand SKB */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 166d436196c1..928f58064098 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  * @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  */
 int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident)
+		    char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		r->func    = func;
 		r->data    = data;
 		r->ident   = ident;
+		r->sk      = sk;
 
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
@@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register);
 static void can_rx_delete_receiver(struct rcu_head *rp)
 {
 	struct receiver *r = container_of(rp, struct receiver, rcu);
+	struct sock *sk = r->sk;
 
 	kmem_cache_free(rcv_cache, r);
+	if (sk)
+		sock_put(sk);
 }
 
 /**
@@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	spin_unlock(&can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (r)
+	if (r) {
+		if (r->sk)
+			sock_hold(r->sk);
 		call_rcu(&r->rcu, can_rx_delete_receiver);
+	}
 }
 EXPORT_SYMBOL(can_rx_unregister);
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9fc45a..b86f5129e838 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -50,13 +50,14 @@
 
 struct receiver {
 	struct hlist_node list;
-	struct rcu_head rcu;
 	canid_t can_id;
 	canid_t mask;
 	unsigned long matches;
 	void (*func)(struct sk_buff *, void *);
 	void *data;
 	char *ident;
+	struct sock *sk;
+	struct rcu_head rcu;
 };
 
 #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 6863310d6973..4ccfd356baed 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -710,14 +710,23 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, canid_t can_id,
 
 static void bcm_remove_op(struct bcm_op *op)
 {
-	hrtimer_cancel(&op->timer);
-	hrtimer_cancel(&op->thrtimer);
-
-	if (op->tsklet.func)
-		tasklet_kill(&op->tsklet);
+	if (op->tsklet.func) {
+		while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) ||
+		       test_bit(TASKLET_STATE_RUN, &op->tsklet.state) ||
+		       hrtimer_active(&op->timer)) {
+			hrtimer_cancel(&op->timer);
+			tasklet_kill(&op->tsklet);
+		}
+	}
 
-	if (op->thrtsklet.func)
-		tasklet_kill(&op->thrtsklet);
+	if (op->thrtsklet.func) {
+		while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) ||
+		       test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) ||
+		       hrtimer_active(&op->thrtimer)) {
+			hrtimer_cancel(&op->thrtimer);
+			tasklet_kill(&op->thrtsklet);
+		}
+	}
 
 	if ((op->frames) && (op->frames != &op->sframe))
 		kfree(op->frames);
@@ -1170,7 +1179,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				err = can_rx_register(dev, op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
-						      "bcm");
+						      "bcm", sk);
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
@@ -1179,7 +1188,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		} else
 			err = can_rx_register(NULL, op->can_id,
 					      REGMASK(op->can_id),
-					      bcm_rx_handler, op, "bcm");
+					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
 			list_del(&op->list);
@@ -1500,24 +1509,31 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
 	struct sock *sk = sock->sk;
 	struct bcm_sock *bo = bcm_sk(sk);
+	int ret = 0;
 
 	if (len < sizeof(*addr))
 		return -EINVAL;
 
-	if (bo->bound)
-		return -EISCONN;
+	lock_sock(sk);
+
+	if (bo->bound) {
+		ret = -EISCONN;
+		goto fail;
+	}
 
 	/* bind a device to this socket */
 	if (addr->can_ifindex) {
 		struct net_device *dev;
 
 		dev = dev_get_by_index(&init_net, addr->can_ifindex);
-		if (!dev)
-			return -ENODEV;
-
+		if (!dev) {
+			ret = -ENODEV;
+			goto fail;
+		}
 		if (dev->type != ARPHRD_CAN) {
 			dev_put(dev);
-			return -ENODEV;
+			ret = -ENODEV;
+			goto fail;
 		}
 
 		bo->ifindex = dev->ifindex;
@@ -1528,17 +1544,24 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
 		bo->ifindex = 0;
 	}
 
-	bo->bound = 1;
-
 	if (proc_dir) {
 		/* unique socket address as filename */
 		sprintf(bo->procname, "%lu", sock_i_ino(sk));
 		bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
 						     proc_dir,
 						     &bcm_proc_fops, sk);
+		if (!bo->bcm_proc_read) {
+			ret = -ENOMEM;
+			goto fail;
+		}
 	}
 
-	return 0;
+	bo->bound = 1;
+
+fail:
+	release_sock(sk);
+
+	return ret;
 }
 
 static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/can/gw.c b/net/can/gw.c
index 455168718c2e..77c8af4047ef 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj)
 {
 	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
-			       gwj, "gw");
+			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)
diff --git a/net/can/raw.c b/net/can/raw.c
index 2e67b1423cd3..e9403a26a1d5 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	for (i = 0; i < count; i++) {
 		err = can_rx_register(dev, filter[i].can_id,
 				      filter[i].can_mask,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
@@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
 
 	if (err_mask)
 		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
@@ -499,6 +499,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen % sizeof(struct can_filter) != 0)
 			return -EINVAL;
 
+		if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter))
+			return -EINVAL;
+
 		count = optlen / sizeof(struct can_filter);
 
 		if (count > 1) {
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 63ae5dd24fc5..a6b2f2138c9d 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -7,6 +7,7 @@
 #include <linux/kthread.h>
 #include <linux/net.h>
 #include <linux/nsproxy.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
@@ -478,11 +479,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 {
 	struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
 	struct socket *sock;
+	unsigned int noio_flag;
 	int ret;
 
 	BUG_ON(con->sock);
+
+	/* sock_create_kern() allocates with GFP_KERNEL */
+	noio_flag = memalloc_noio_save();
 	ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
+	memalloc_noio_restore(noio_flag);
 	if (ret)
 		return ret;
 	sock->sk->sk_allocation = GFP_NOFS;
@@ -2042,6 +2048,19 @@ static int process_connect(struct ceph_connection *con)
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
 
+	if (con->auth_reply_buf) {
+		/*
+		 * Any connection that defines ->get_authorizer()
+		 * should also define ->verify_authorizer_reply().
+		 * See get_connect_authorizer().
+		 */
+		ret = con->ops->verify_authorizer_reply(con, 0);
+		if (ret < 0) {
+			con->error_msg = "bad authorize reply";
+			return ret;
+		}
+	}
+
 	switch (con->in_reply.tag) {
 	case CEPH_MSGR_TAG_FEATURES:
 		pr_err("%s%lld %s feature set mismatch,"
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 7d8f581d9f1f..bc95e48d5cfb 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1192,6 +1192,114 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
 }
 
 /*
+ * Encoding order is (new_up_client, new_state, new_weight).  Need to
+ * apply in the (new_weight, new_state, new_up_client) order, because
+ * an incremental map may look like e.g.
+ *
+ *     new_up_client: { osd=6, addr=... } # set osd_state and addr
+ *     new_state: { osd=6, xorstate=EXISTS } # clear osd_state
+ */
+static int decode_new_up_state_weight(void **p, void *end,
+				      struct ceph_osdmap *map)
+{
+	void *new_up_client;
+	void *new_state;
+	void *new_weight_end;
+	u32 len;
+
+	new_up_client = *p;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	len *= sizeof(u32) + sizeof(struct ceph_entity_addr);
+	ceph_decode_need(p, end, len, e_inval);
+	*p += len;
+
+	new_state = *p;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	len *= sizeof(u32) + sizeof(u8);
+	ceph_decode_need(p, end, len, e_inval);
+	*p += len;
+
+	/* new_weight */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	while (len--) {
+		s32 osd;
+		u32 w;
+
+		ceph_decode_need(p, end, 2*sizeof(u32), e_inval);
+		osd = ceph_decode_32(p);
+		w = ceph_decode_32(p);
+		BUG_ON(osd >= map->max_osd);
+		pr_info("osd%d weight 0x%x %s\n", osd, w,
+		     w == CEPH_OSD_IN ? "(in)" :
+		     (w == CEPH_OSD_OUT ? "(out)" : ""));
+		map->osd_weight[osd] = w;
+
+		/*
+		 * If we are marking in, set the EXISTS, and clear the
+		 * AUTOOUT and NEW bits.
+		 */
+		if (w) {
+			map->osd_state[osd] |= CEPH_OSD_EXISTS;
+			map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT |
+						 CEPH_OSD_NEW);
+		}
+	}
+	new_weight_end = *p;
+
+	/* new_state (up/down) */
+	*p = new_state;
+	len = ceph_decode_32(p);
+	while (len--) {
+		s32 osd;
+		u8 xorstate;
+		int ret;
+
+		osd = ceph_decode_32(p);
+		xorstate = ceph_decode_8(p);
+		if (xorstate == 0)
+			xorstate = CEPH_OSD_UP;
+		BUG_ON(osd >= map->max_osd);
+		if ((map->osd_state[osd] & CEPH_OSD_UP) &&
+		    (xorstate & CEPH_OSD_UP))
+			pr_info("osd%d down\n", osd);
+		if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
+		    (xorstate & CEPH_OSD_EXISTS)) {
+			pr_info("osd%d does not exist\n", osd);
+			ret = set_primary_affinity(map, osd,
+						   CEPH_OSD_DEFAULT_PRIMARY_AFFINITY);
+			if (ret)
+				return ret;
+			memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr));
+			map->osd_state[osd] = 0;
+		} else {
+			map->osd_state[osd] ^= xorstate;
+		}
+	}
+
+	/* new_up_client */
+	*p = new_up_client;
+	len = ceph_decode_32(p);
+	while (len--) {
+		s32 osd;
+		struct ceph_entity_addr addr;
+
+		osd = ceph_decode_32(p);
+		ceph_decode_copy(p, &addr, sizeof(addr));
+		ceph_decode_addr(&addr);
+		BUG_ON(osd >= map->max_osd);
+		pr_info("osd%d up\n", osd);
+		map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
+		map->osd_addr[osd] = addr;
+	}
+
+	*p = new_weight_end;
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+/*
  * decode and apply an incremental map update.
  */
 struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
@@ -1290,49 +1398,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
-	/* new_up */
-	ceph_decode_32_safe(p, end, len, e_inval);
-	while (len--) {
-		u32 osd;
-		struct ceph_entity_addr addr;
-		ceph_decode_32_safe(p, end, osd, e_inval);
-		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval);
-		ceph_decode_addr(&addr);
-		pr_info("osd%d up\n", osd);
-		BUG_ON(osd >= map->max_osd);
-		map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS;
-		map->osd_addr[osd] = addr;
-	}
-
-	/* new_state */
-	ceph_decode_32_safe(p, end, len, e_inval);
-	while (len--) {
-		u32 osd;
-		u8 xorstate;
-		ceph_decode_32_safe(p, end, osd, e_inval);
-		xorstate = **(u8 **)p;
-		(*p)++;  /* clean flag */
-		if (xorstate == 0)
-			xorstate = CEPH_OSD_UP;
-		if (xorstate & CEPH_OSD_UP)
-			pr_info("osd%d down\n", osd);
-		if (osd < map->max_osd)
-			map->osd_state[osd] ^= xorstate;
-	}
-
-	/* new_weight */
-	ceph_decode_32_safe(p, end, len, e_inval);
-	while (len--) {
-		u32 osd, off;
-		ceph_decode_need(p, end, sizeof(u32)*2, e_inval);
-		osd = ceph_decode_32(p);
-		off = ceph_decode_32(p);
-		pr_info("osd%d weight 0x%x %s\n", osd, off,
-		     off == CEPH_OSD_IN ? "(in)" :
-		     (off == CEPH_OSD_OUT ? "(out)" : ""));
-		if (osd < map->max_osd)
-			map->osd_weight[osd] = off;
-	}
+	/* new_up_client, new_state, new_weight */
+	err = decode_new_up_state_weight(p, end, map);
+	if (err)
+		goto bad;
 
 	/* new_pg_temp */
 	err = decode_new_pg_temp(p, end, map);
diff --git a/net/core/dev.c b/net/core/dev.c
index 9efbdb3ff78a..24d243084aab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -182,7 +182,7 @@ EXPORT_SYMBOL(dev_base_lock);
 /* protects napi_hash addition/deletion and napi_gen_id */
 static DEFINE_SPINLOCK(napi_hash_lock);
 
-static unsigned int napi_gen_id;
+static unsigned int napi_gen_id = NR_CPUS;
 static DEFINE_HASHTABLE(napi_hash, 8);
 
 static seqcount_t devnet_rename_seq;
@@ -1246,8 +1246,9 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 	if (!new_ifalias)
 		return -ENOMEM;
 	dev->ifalias = new_ifalias;
+	memcpy(dev->ifalias, alias, len);
+	dev->ifalias[len] = 0;
 
-	strlcpy(dev->ifalias, alias, len+1);
 	return len;
 }
 
@@ -1676,37 +1677,59 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
 
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
 static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
+static void netstamp_clear(struct work_struct *work)
+{
+	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
+
+	wanted = atomic_add_return(deferred, &netstamp_wanted);
+	if (wanted > 0)
+		static_key_enable(&netstamp_needed);
+	else
+		static_key_disable(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
 
 void net_enable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
 
-	if (deferred) {
-		while (--deferred)
-			static_key_slow_dec(&netstamp_needed);
-		return;
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 0)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+			return;
 	}
-#endif
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_inc(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	if (in_interrupt()) {
-		atomic_inc(&netstamp_needed_deferred);
-		return;
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 1)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+			return;
 	}
-#endif
+	atomic_dec(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_dec(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
@@ -2462,7 +2485,7 @@ int skb_checksum_help(struct sk_buff *skb)
 			goto out;
 	}
 
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
 out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
 out:
@@ -2527,9 +2550,10 @@ EXPORT_SYMBOL(skb_mac_gso_segment);
 static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
-		return skb->ip_summed != CHECKSUM_PARTIAL;
-	else
-		return skb->ip_summed == CHECKSUM_NONE;
+		return skb->ip_summed != CHECKSUM_PARTIAL &&
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
+
+	return skb->ip_summed == CHECKSUM_NONE;
 }
 
 /**
@@ -2548,11 +2572,12 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path)
 {
+	struct sk_buff *segs;
+
 	if (unlikely(skb_needs_check(skb, tx_path))) {
 		int err;
 
-		skb_warn_bad_offload(skb);
-
+		/* We're going to init ->check field in TCP or UDP header */
 		err = skb_cow_head(skb, 0);
 		if (err < 0)
 			return ERR_PTR(err);
@@ -2567,7 +2592,12 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	skb_reset_mac_len(skb);
 
-	return skb_mac_gso_segment(skb, features);
+	segs = skb_mac_gso_segment(skb, features);
+
+	if (unlikely(skb_needs_check(skb, tx_path)))
+		skb_warn_bad_offload(skb);
+
+	return segs;
 }
 EXPORT_SYMBOL(__skb_gso_segment);
 
@@ -2650,9 +2680,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, type)) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(skb->dev, skb)) {
-		features &= ~NETIF_F_SG;
 	}
+	if (illegal_highdma(skb->dev, skb))
+		features &= ~NETIF_F_SG;
 
 	return features;
 }
@@ -2836,6 +2866,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 	}
 	return head;
 }
+EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
@@ -3026,7 +3057,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 	int queue_index = 0;
 
 #ifdef CONFIG_XPS
-	if (skb->sender_cpu == 0)
+	u32 sender_cpu = skb->sender_cpu - 1;
+
+	if (sender_cpu >= (u32)NR_CPUS)
 		skb->sender_cpu = raw_smp_processor_id() + 1;
 #endif
 
@@ -3722,6 +3755,22 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 }
 
 /**
+ *	netdev_is_rx_handler_busy - check if receive handler is registered
+ *	@dev: device to check
+ *
+ *	Check if a receive handler is already registered for a given device.
+ *	Return true if there one.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
+/**
  *	netdev_rx_handler_register - register receive handler
  *	@dev: device to register a handler for
  *	@rx_handler: receive handler to register
@@ -4170,7 +4219,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
+						    skb_frag_size(frag0),
+						    skb->end - skb->tail);
 	}
 }
 
@@ -4223,7 +4274,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->same_flow = 0;
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
-		NAPI_GRO_CB(skb)->udp_mark = 0;
+		NAPI_GRO_CB(skb)->encap_mark = 0;
+		NAPI_GRO_CB(skb)->recursion_counter = 0;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
@@ -4330,6 +4382,12 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
+static void napi_skb_free_stolen_head(struct sk_buff *skb)
+{
+	skb_dst_drop(skb);
+	kmem_cache_free(skbuff_head_cache, skb);
+}
+
 static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
 	switch (ret) {
@@ -4343,12 +4401,10 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 		break;
 
 	case GRO_MERGED_FREE:
-		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
-			skb_dst_drop(skb);
-			kmem_cache_free(skbuff_head_cache, skb);
-		} else {
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+			napi_skb_free_stolen_head(skb);
+		else
 			__kfree_skb(skb);
-		}
 		break;
 
 	case GRO_HELD:
@@ -4414,10 +4470,16 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
 		break;
 
 	case GRO_DROP:
-	case GRO_MERGED_FREE:
 		napi_reuse_skb(napi, skb);
 		break;
 
+	case GRO_MERGED_FREE:
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+			napi_skb_free_stolen_head(skb);
+		else
+			napi_reuse_skb(napi, skb);
+		break;
+
 	case GRO_MERGED:
 		break;
 	}
@@ -4684,25 +4746,22 @@ EXPORT_SYMBOL_GPL(napi_by_id);
 
 void napi_hash_add(struct napi_struct *napi)
 {
-	if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+	if (test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
+		return;
 
-		spin_lock(&napi_hash_lock);
+	spin_lock(&napi_hash_lock);
 
-		/* 0 is not a valid id, we also skip an id that is taken
-		 * we expect both events to be extremely rare
-		 */
-		napi->napi_id = 0;
-		while (!napi->napi_id) {
-			napi->napi_id = ++napi_gen_id;
-			if (napi_by_id(napi->napi_id))
-				napi->napi_id = 0;
-		}
+	/* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+	do {
+		if (unlikely(++napi_gen_id < NR_CPUS + 1))
+			napi_gen_id = NR_CPUS + 1;
+	} while (napi_by_id(napi_gen_id));
+	napi->napi_id = napi_gen_id;
 
-		hlist_add_head_rcu(&napi->napi_hash_node,
-			&napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+	hlist_add_head_rcu(&napi->napi_hash_node,
+			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
 
-		spin_unlock(&napi_hash_lock);
-	}
+	spin_unlock(&napi_hash_lock);
 }
 EXPORT_SYMBOL_GPL(napi_hash_add);
 
@@ -5188,6 +5247,7 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
 
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
+					u16 ref_nr,
 					struct list_head *dev_list,
 					void *private, bool master)
 {
@@ -5197,7 +5257,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj = __netdev_find_adj(adj_dev, dev_list);
 
 	if (adj) {
-		adj->ref_nr++;
+		adj->ref_nr += ref_nr;
 		return 0;
 	}
 
@@ -5207,7 +5267,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 
 	adj->dev = adj_dev;
 	adj->master = master;
-	adj->ref_nr = 1;
+	adj->ref_nr = ref_nr;
 	adj->private = private;
 	dev_hold(adj_dev);
 
@@ -5246,6 +5306,7 @@ free_adj:
 
 static void __netdev_adjacent_dev_remove(struct net_device *dev,
 					 struct net_device *adj_dev,
+					 u16 ref_nr,
 					 struct list_head *dev_list)
 {
 	struct netdev_adjacent *adj;
@@ -5258,10 +5319,10 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 		BUG();
 	}
 
-	if (adj->ref_nr > 1) {
-		pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
-			 adj->ref_nr-1);
-		adj->ref_nr--;
+	if (adj->ref_nr > ref_nr) {
+		pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name,
+			 ref_nr, adj->ref_nr-ref_nr);
+		adj->ref_nr -= ref_nr;
 		return;
 	}
 
@@ -5280,21 +5341,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 
 static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 					    struct net_device *upper_dev,
+					    u16 ref_nr,
 					    struct list_head *up_list,
 					    struct list_head *down_list,
 					    void *private, bool master)
 {
 	int ret;
 
-	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
-					   master);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+					   private, master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
-					   false);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+					   private, false);
 	if (ret) {
-		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+		__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
 		return ret;
 	}
 
@@ -5302,9 +5364,10 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 }
 
 static int __netdev_adjacent_dev_link(struct net_device *dev,
-				      struct net_device *upper_dev)
+				      struct net_device *upper_dev,
+				      u16 ref_nr)
 {
-	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
 						&dev->all_adj_list.upper,
 						&upper_dev->all_adj_list.lower,
 						NULL, false);
@@ -5312,17 +5375,19 @@ static int __netdev_adjacent_dev_link(struct net_device *dev,
 
 static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
 					       struct net_device *upper_dev,
+					       u16 ref_nr,
 					       struct list_head *up_list,
 					       struct list_head *down_list)
 {
-	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
-	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
+	__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+	__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
 }
 
 static void __netdev_adjacent_dev_unlink(struct net_device *dev,
-					 struct net_device *upper_dev)
+					 struct net_device *upper_dev,
+					 u16 ref_nr)
 {
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
 					   &dev->all_adj_list.upper,
 					   &upper_dev->all_adj_list.lower);
 }
@@ -5331,17 +5396,17 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 						struct net_device *upper_dev,
 						void *private, bool master)
 {
-	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+	int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
 
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
 					       &dev->adj_list.upper,
 					       &upper_dev->adj_list.lower,
 					       private, master);
 	if (ret) {
-		__netdev_adjacent_dev_unlink(dev, upper_dev);
+		__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
 		return ret;
 	}
 
@@ -5351,8 +5416,8 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 						   struct net_device *upper_dev)
 {
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
 					   &dev->adj_list.upper,
 					   &upper_dev->adj_list.lower);
 }
@@ -5404,7 +5469,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			pr_debug("Interlinking %s with %s, non-neighbour\n",
 				 i->dev->name, j->dev->name);
-			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
+			ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
 			if (ret)
 				goto rollback_mesh;
 		}
@@ -5414,7 +5479,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		pr_debug("linking %s's upper device %s with %s\n",
 			 upper_dev->name, i->dev->name, dev->name);
-		ret = __netdev_adjacent_dev_link(dev, i->dev);
+		ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
 		if (ret)
 			goto rollback_upper_mesh;
 	}
@@ -5423,7 +5488,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		pr_debug("linking %s's lower device %s with %s\n", dev->name,
 			 i->dev->name, upper_dev->name);
-		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
+		ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
 		if (ret)
 			goto rollback_lower_mesh;
 	}
@@ -5437,7 +5502,7 @@ rollback_lower_mesh:
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 	}
 
 	i = NULL;
@@ -5447,7 +5512,7 @@ rollback_upper_mesh:
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 	}
 
 	i = j = NULL;
@@ -5459,7 +5524,7 @@ rollback_mesh:
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			if (i == to_i && j == to_j)
 				break;
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 		}
 		if (i == to_i)
 			break;
@@ -5543,16 +5608,16 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 
 	/* remove also the devices itself from lower/upper device
 	 * list
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
 				      &changeupper_info.info);
@@ -7004,8 +7069,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 	} else {
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
-	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
-	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
+	storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index b94b1d293506..151e047ce072 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
 
 	error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex);
 	if (error)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 252e155c837b..a2270188b864 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -80,6 +80,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	struct nlattr *nla;
 	struct sk_buff *skb;
 	unsigned long flags;
+	void *msg_header;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
@@ -87,21 +88,41 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 
 	skb = genlmsg_new(al, GFP_KERNEL);
 
-	if (skb) {
-		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
-				0, NET_DM_CMD_ALERT);
-		nla = nla_reserve(skb, NLA_UNSPEC,
-				  sizeof(struct net_dm_alert_msg));
-		msg = nla_data(nla);
-		memset(msg, 0, al);
-	} else {
-		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	if (!skb)
+		goto err;
+
+	msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				 0, NET_DM_CMD_ALERT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
+	}
+	nla = nla_reserve(skb, NLA_UNSPEC,
+			  sizeof(struct net_dm_alert_msg));
+	if (!nla) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
 	}
+	msg = nla_data(nla);
+	memset(msg, 0, al);
+	goto out;
 
+err:
+	mod_timer(&data->send_timer, jiffies + HZ / 10);
+out:
 	spin_lock_irqsave(&data->lock, flags);
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
 
+	if (skb) {
+		struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
+		struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
+
+		genlmsg_end(skb, genlmsg_data(gnlh));
+	}
+
 	return skb;
 }
 
diff --git a/net/core/dst.c b/net/core/dst.c
index a1656e3b8d72..e72d706f8d0c 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -315,25 +315,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -342,7 +347,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
@@ -457,6 +462,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event,
 		spin_lock_bh(&dst_garbage.lock);
 		dst = dst_garbage.list;
 		dst_garbage.list = NULL;
+		/* The code in dst_ifdown places a hold on the loopback device.
+		 * If the gc entry processing is set to expire after a lengthy
+		 * interval, this hold can cause netdev_wait_allrefs() to hang
+		 * out and wait for a long time -- until the the loopback
+		 * interface is released.  If we're really unlucky, it'll emit
+		 * pr_emerg messages to console too.  Reset the interval here,
+		 * so dst cleanups occur in a more timely fashion.
+		 */
+		if (dst_garbage.timer_inc > DST_GC_INC) {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+			mod_delayed_work(system_wq, &dst_gc_work,
+					 dst_garbage.timer_expires);
+		}
 		spin_unlock_bh(&dst_garbage.lock);
 
 		if (last)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 29edf74846fc..b6bca625b0d2 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -886,9 +886,12 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 	if (regs.len > reglen)
 		regs.len = reglen;
 
-	regbuf = vzalloc(reglen);
-	if (reglen && !regbuf)
-		return -ENOMEM;
+	regbuf = NULL;
+	if (reglen) {
+		regbuf = vzalloc(reglen);
+		if (!regbuf)
+			return -ENOMEM;
+	}
 
 	ops->get_regs(dev, &regs, regbuf);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 37157c4c1a78..e94355452166 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -52,9 +52,10 @@
 #include <net/dst.h>
 
 /**
- *	sk_filter - run a packet through a socket filter
+ *	sk_filter_trim_cap - run a packet through a socket filter
  *	@sk: sock associated with &sk_buff
  *	@skb: buffer to filter
+ *	@cap: limit on how short the eBPF program may trim the packet
  *
  * Run the eBPF program and then cut skb->data to correct size returned by
  * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
@@ -63,7 +64,7 @@
  * be accepted or -EPERM if the packet should be tossed.
  *
  */
-int sk_filter(struct sock *sk, struct sk_buff *skb)
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 {
 	int err;
 	struct sk_filter *filter;
@@ -84,14 +85,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
 		unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
-
-		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
+		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
 	}
 	rcu_read_unlock();
 
 	return err;
 }
-EXPORT_SYMBOL(sk_filter);
+EXPORT_SYMBOL(sk_filter_trim_cap);
 
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
@@ -1139,7 +1139,8 @@ void bpf_prog_destroy(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_destroy);
 
-static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk,
+			    bool locked)
 {
 	struct sk_filter *fp, *old_fp;
 
@@ -1155,10 +1156,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 	}
 
-	old_fp = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	old_fp = rcu_dereference_protected(sk->sk_filter, locked);
 	rcu_assign_pointer(sk->sk_filter, fp);
-
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
 
@@ -1175,7 +1174,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
  * occurs or there is insufficient memory for the filter a negative
  * errno code is returned. On success the return is zero.
  */
-int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked)
 {
 	unsigned int fsize = bpf_classic_proglen(fprog);
 	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
@@ -1213,7 +1213,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, locked);
 	if (err < 0) {
 		__bpf_prog_release(prog);
 		return err;
@@ -1221,7 +1221,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sk_attach_filter);
+EXPORT_SYMBOL_GPL(__sk_attach_filter);
+
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+{
+	return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk));
+}
 
 int sk_attach_bpf(u32 ufd, struct sock *sk)
 {
@@ -1240,7 +1245,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 		return -EINVAL;
 	}
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk));
 	if (err < 0) {
 		bpf_prog_put(prog);
 		return err;
@@ -1270,9 +1275,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 	 */
 	if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
 		return -EFAULT;
-
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + len)))
+	if (unlikely(skb_try_make_writable(skb, offset + len)))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, len, buf);
@@ -1316,8 +1319,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
 
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + sizeof(sum))))
+	if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1362,9 +1364,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 
 	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
-
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + sizeof(sum))))
+	if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1549,6 +1549,13 @@ bool bpf_helper_changes_skb_data(void *func)
 		return true;
 	if (func == bpf_skb_vlan_pop)
 		return true;
+	if (func == bpf_skb_store_bytes)
+		return true;
+	if (func == bpf_l3_csum_replace)
+		return true;
+	if (func == bpf_l4_csum_replace)
+		return true;
+
 	return false;
 }
 
@@ -1913,7 +1920,7 @@ static int __init register_sk_filter_ops(void)
 }
 late_initcall(register_sk_filter_ops);
 
-int sk_detach_filter(struct sock *sk)
+int __sk_detach_filter(struct sock *sk, bool locked)
 {
 	int ret = -ENOENT;
 	struct sk_filter *filter;
@@ -1921,8 +1928,7 @@ int sk_detach_filter(struct sock *sk)
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
 
-	filter = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	filter = rcu_dereference_protected(sk->sk_filter, locked);
 	if (filter) {
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 		sk_filter_uncharge(sk, filter);
@@ -1931,7 +1937,12 @@ int sk_detach_filter(struct sock *sk)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sk_detach_filter);
+EXPORT_SYMBOL_GPL(__sk_detach_filter);
+
+int sk_detach_filter(struct sock *sk)
+{
+	return __sk_detach_filter(sk, sock_owned_by_user(sk));
+}
 
 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 12e700332010..ee9082792530 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -131,7 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_keyid *key_keyid;
 	u8 ip_proto = 0;
-	bool ret = false;
+	bool ret;
 
 	if (!data) {
 		data = skb->data;
@@ -492,12 +492,17 @@ ip_proto_again:
 out_good:
 	ret = true;
 
-out_bad:
+	key_control->thoff = (u16)nhoff;
+out:
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
-	key_control->thoff = (u16)nhoff;
 
 	return ret;
+
+out_bad:
+	ret = false;
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
@@ -662,6 +667,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
+static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	__flow_hash_secret_init();
+
+	memset(&keys, 0, sizeof(keys));
+	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
+			   NULL, 0, 0, 0,
+			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	return __flow_hash_from_keys(&keys, hashrnd);
+}
+EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
+
 /**
  * __skb_get_hash: calculate a flow hash
  * @skb: sk_buff to calculate flow hash from
@@ -874,6 +896,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	},
 };
 
+static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
 static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -895,10 +940,13 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_dissector,
 				flow_keys_dissector_keys,
 				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_dissector_symmetric,
+				flow_keys_dissector_symmetric_keys,
+				ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
 	skb_flow_dissector_init(&flow_keys_buf_dissector,
 				flow_keys_buf_dissector_keys,
 				ARRAY_SIZE(flow_keys_buf_dissector_keys));
 	return 0;
 }
 
-late_initcall_sync(init_default_flow_dissectors);
+core_initcall(init_default_flow_dissectors);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f18ae91b652e..ae92131c4f89 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -859,7 +859,8 @@ static void neigh_probe(struct neighbour *neigh)
 	if (skb)
 		skb = skb_clone(skb, GFP_ATOMIC);
 	write_unlock(&neigh->lock);
-	neigh->ops->solicit(neigh, skb);
+	if (neigh->ops->solicit)
+		neigh->ops->solicit(neigh, skb);
 	atomic_inc(&neigh->probes);
 	kfree_skb(skb);
 }
@@ -2467,13 +2468,17 @@ int neigh_xmit(int index, struct net_device *dev,
 		tbl = neigh_tables[index];
 		if (!tbl)
 			goto out;
+		rcu_read_lock_bh();
 		neigh = __neigh_lookup_noref(tbl, addr, dev);
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-		if (IS_ERR(neigh))
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
 			goto out_kfree_skb;
+		}
 		err = neigh->output(neigh, skb);
+		rcu_read_unlock_bh();
 	}
 	else if (index == NEIGH_LINK_TABLE) {
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2c2eb1b629b1..2e9a1c2818c7 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -217,6 +217,8 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	bool alloc;
 	int id;
 
+	if (atomic_read(&net->count) == 0)
+		return NETNSA_NSID_NOT_ASSIGNED;
 	spin_lock_irqsave(&net->nsid_lock, flags);
 	alloc = atomic_read(&peer->count) == 0 ? false : true;
 	id = __peernet2id_alloc(net, peer, &alloc);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 94acfc89ad97..440aa9f6e0a8 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work)
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
 		struct netdev_queue *txq;
+		unsigned int q_index;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
 			kfree_skb(skb);
 			continue;
 		}
 
-		txq = skb_get_tx_queue(dev, skb);
-
 		local_irq_save(flags);
+		/* check if skb->queue_mapping is still valid */
+		q_index = skb_get_queue_mapping(skb);
+		if (unlikely(q_index >= dev->real_num_tx_queues)) {
+			q_index = q_index % dev->real_num_tx_queues;
+			skb_set_queue_mapping(skb, q_index);
+		}
+		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4da4d51a2ccf..b6327601f979 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -215,8 +215,8 @@
 #define M_NETIF_RECEIVE 	1	/* Inject packets into stack */
 
 /* If lock -- protects updating of if_list */
-#define   if_lock(t)           spin_lock(&(t->if_lock));
-#define   if_unlock(t)           spin_unlock(&(t->if_lock));
+#define   if_lock(t)           mutex_lock(&(t->if_lock));
+#define   if_unlock(t)           mutex_unlock(&(t->if_lock));
 
 /* Used to help with determining the pkts on receive */
 #define PKTGEN_MAGIC 0xbe9be955
@@ -422,7 +422,7 @@ struct pktgen_net {
 };
 
 struct pktgen_thread {
-	spinlock_t if_lock;		/* for list of devices */
+	struct mutex if_lock;		/* for list of devices */
 	struct list_head if_list;	/* All device here */
 	struct list_head th_list;
 	struct task_struct *tsk;
@@ -2002,11 +2002,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 {
 	struct pktgen_thread *t;
 
+	mutex_lock(&pktgen_thread_lock);
+
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
 		struct pktgen_dev *pkt_dev;
 
-		rcu_read_lock();
-		list_for_each_entry_rcu(pkt_dev, &t->if_list, list) {
+		if_lock(t);
+		list_for_each_entry(pkt_dev, &t->if_list, list) {
 			if (pkt_dev->odev != dev)
 				continue;
 
@@ -2021,8 +2023,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 				       dev->name);
 			break;
 		}
-		rcu_read_unlock();
+		if_unlock(t);
 	}
+	mutex_unlock(&pktgen_thread_lock);
 }
 
 static int pktgen_device_event(struct notifier_block *unused,
@@ -2278,7 +2281,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 
 static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
 {
-	pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev);
+	pkt_dev->pkt_overhead = 0;
 	pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32);
 	pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev);
 	pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
@@ -2769,13 +2772,13 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
 }
 
 static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
-					struct pktgen_dev *pkt_dev,
-					unsigned int extralen)
+					struct pktgen_dev *pkt_dev)
 {
+	unsigned int extralen = LL_RESERVED_SPACE(dev);
 	struct sk_buff *skb = NULL;
-	unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen +
-			    pkt_dev->pkt_overhead;
+	unsigned int size;
 
+	size = pkt_dev->cur_pkt_size + 64 + extralen + pkt_dev->pkt_overhead;
 	if (pkt_dev->flags & F_NODE) {
 		int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id();
 
@@ -2788,8 +2791,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
 
+	/* the caller pre-fetches from skb->data and reserves for the mac hdr */
 	if (likely(skb))
-		skb_reserve(skb, LL_RESERVED_SPACE(dev));
+		skb_reserve(skb, extralen - 16);
 
 	return skb;
 }
@@ -2822,16 +2826,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	datalen = (odev->hard_header_len + 16) & ~0xf;
-
-	skb = pktgen_alloc_skb(odev, pkt_dev, datalen);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
 	}
 
 	prefetchw(skb->data);
-	skb_reserve(skb, datalen);
+	skb_reserve(skb, 16);
 
 	/*  Reserve for ethernet and IP header  */
 	eth = (__u8 *) skb_push(skb, 14);
@@ -2951,7 +2953,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	skb = pktgen_alloc_skb(odev, pkt_dev, 16);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
@@ -3727,7 +3729,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 		return -ENOMEM;
 	}
 
-	spin_lock_init(&t->if_lock);
+	mutex_init(&t->if_lock);
 	t->cpu = cpu;
 
 	INIT_LIST_HEAD(&t->if_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 34ba7a08876d..5b3d611d8b5f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -897,6 +897,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
+	       + nla_total_size(4) /* IFLA_GROUP */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -905,6 +906,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1017,7 +1019,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
 		return err;
 	}
 
-	if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name))
+	if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name))
 		return -EMSGSIZE;
 
 	return 0;
@@ -1088,6 +1090,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	struct ifla_vf_mac vf_mac;
 	struct ifla_vf_info ivi;
 
+	memset(&ivi, 0, sizeof(ivi));
+
 	/* Not all SR-IOV capable drivers support the
 	 * spoofcheck and "RSS query enable" query.  Preset to
 	 * -1 so the user space tool can detect that the driver
@@ -1096,7 +1100,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	ivi.spoofchk = -1;
 	ivi.rss_query_en = -1;
 	ivi.trusted = -1;
-	memset(ivi.mac, 0, sizeof(ivi.mac));
 	/* The default value for VF link state is "auto"
 	 * IFLA_VF_LINK_STATE_AUTO which equals zero
 	 */
@@ -1174,14 +1177,16 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 
 static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 {
-	struct rtnl_link_ifmap map = {
-		.mem_start   = dev->mem_start,
-		.mem_end     = dev->mem_end,
-		.base_addr   = dev->base_addr,
-		.irq         = dev->irq,
-		.dma         = dev->dma,
-		.port        = dev->if_port,
-	};
+	struct rtnl_link_ifmap map;
+
+	memset(&map, 0, sizeof(map));
+	map.mem_start   = dev->mem_start;
+	map.mem_end     = dev->mem_end;
+	map.base_addr   = dev->base_addr;
+	map.irq         = dev->irq;
+	map.dma         = dev->dma;
+	map.port        = dev->if_port;
+
 	if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
 		return -EMSGSIZE;
 
@@ -1367,6 +1372,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PHYS_SWITCH_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
+	[IFLA_GROUP]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1455,13 +1461,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       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;
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
@@ -1469,10 +1475,12 @@ cont:
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
@@ -1734,7 +1742,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct sockaddr *sa;
 		int len;
 
-		len = sizeof(sa_family_t) + dev->addr_len;
+		len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
+						  sizeof(*sa));
 		sa = kmalloc(len, GFP_KERNEL);
 		if (!sa) {
 			err = -ENOMEM;
@@ -2597,7 +2606,10 @@ nla_put_failure:
 
 static inline size_t rtnl_fdb_nlmsg_size(void)
 {
-	return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
+	return NLMSG_ALIGN(sizeof(struct ndmsg)) +
+	       nla_total_size(ETH_ALEN) +	/* NDA_LLADDR */
+	       nla_total_size(sizeof(u16)) +	/* NDA_VLAN */
+	       0;
 }
 
 static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
@@ -3121,8 +3133,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 				err = br_dev->netdev_ops->ndo_bridge_getlink(
 						skb, portid, seq, dev,
 						filter_mask, NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
@@ -3133,16 +3149,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 							      seq, dev,
 							      filter_mask,
 							      NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
 	}
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 	cb->args[0] = idx;
 
-	return skb->len;
+	return err;
 }
 
 static inline size_t bridge_nlmsg_size(void)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5bf88f58bee7..73dfd7729bc9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3678,13 +3678,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
@@ -3735,7 +3736,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
@@ -3745,14 +3746,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
@@ -4084,9 +4086,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
 	if (!pskb_may_pull(skb_chk, offset))
 		goto err;
 
-	__skb_pull(skb_chk, offset);
+	skb_pull_rcsum(skb_chk, offset);
 	ret = skb_chkf(skb_chk);
-	__skb_push(skb_chk, offset);
+	skb_push_rcsum(skb_chk, offset);
 
 	if (ret)
 		goto err;
@@ -4409,15 +4411,16 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		__skb_push(skb, offset);
 		err = __vlan_insert_tag(skb, skb->vlan_proto,
 					skb_vlan_tag_get(skb));
-		if (err)
+		if (err) {
+			__skb_pull(skb, offset);
 			return err;
+		}
+
 		skb->protocol = skb->vlan_proto;
 		skb->mac_len += VLAN_HLEN;
-		__skb_pull(skb, offset);
 
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+		__skb_pull(skb, offset);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 0d91f7dca751..bd2fad27891e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -745,7 +745,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		val = min_t(u32, val, sysctl_wmem_max);
 set_sndbuf:
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-		sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
+		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
 		/* Wake up sending tasks if we upped the value. */
 		sk->sk_write_space(sk);
 		break;
@@ -781,7 +781,7 @@ set_rcvbuf:
 		 * returning the value we actually used in getsockopt
 		 * is the most desirable behavior.
 		 */
-		sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
+		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -1459,6 +1459,11 @@ void sk_destruct(struct sock *sk)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -1552,6 +1557,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
@@ -1562,6 +1573,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		}
 
 		newsk->sk_err	   = 0;
+		newsk->sk_err_soft = 0;
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
@@ -1678,17 +1690,17 @@ EXPORT_SYMBOL(skb_set_owner_w);
 
 void skb_orphan_partial(struct sk_buff *skb)
 {
-	/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
-	 * so we do not completely orphan skb, but transfert all
-	 * accounted bytes but one, to avoid unexpected reorders.
-	 */
 	if (skb->destructor == sock_wfree
 #ifdef CONFIG_INET
 	    || skb->destructor == tcp_wfree
 #endif
 		) {
-		atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
-		skb->truesize = 1;
+		struct sock *sk = skb->sk;
+
+		if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+			atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+			skb->destructor = sock_efree;
+		}
 	} else {
 		skb_orphan(skb);
 	}
@@ -2690,11 +2702,6 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198e730c..5e3a7302f774 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 1704948e6a12..f227f002c73d 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk)
 	 * singleton values (which always leads to failure).
 	 * These settings can still (later) be overridden via sockopts.
 	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
-	    ccid_get_builtin_ccids(&rx.val, &rx.len))
+	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
 		return -ENOBUFS;
+	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
+		kfree(tx.val);
+		return -ENOBUFS;
+	}
 
 	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
 	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 3bd14e885396..dbe2573f6ba1 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
 								    skb) < 0)
 				return 1;
-			goto discard;
+			consume_skb(skb);
+			return 0;
 		}
 		if (dh->dccph_type == DCCP_PKT_RESET)
 			goto discard;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 902d606324a0..e217f17997a4 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -204,8 +204,6 @@ void dccp_req_err(struct sock *sk, u64 seq)
 	 * ICMPs are not backlogged, hence we cannot get an established
 	 * socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else {
@@ -237,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const u8 offset = iph->ihl << 2;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -247,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
 				       iph->daddr, dh->dccph_dport,
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
@@ -634,6 +635,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
@@ -698,6 +700,7 @@ int dccp_invalid_packet(struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh;
 	unsigned int cscov;
+	u8 dccph_doff;
 
 	if (skb->pkt_type != PACKET_HOST)
 		return 1;
@@ -719,18 +722,19 @@ int dccp_invalid_packet(struct sk_buff *skb)
 	/*
 	 * If P.Data Offset is too small for packet type, drop packet and return
 	 */
-	if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
-		DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff);
+	dccph_doff = dh->dccph_doff;
+	if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
+		DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff);
 		return 1;
 	}
 	/*
 	 * If P.Data Offset is too too large for packet, drop packet and return
 	 */
-	if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) {
-		DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff);
+	if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
+		DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
 		return 1;
 	}
-
+	dh = dccp_hdr(skb);
 	/*
 	 * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
 	 * has short sequence numbers), drop packet and return
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index b8608b71a66d..09a9ab65f4e1 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
 	struct sock *sk;
@@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
-				   ICMP6_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet6_lookup_established(net, &dccp_hashinfo,
 					&hdr->daddr, dh->dccph_dport,
@@ -121,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
@@ -373,6 +376,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
@@ -419,6 +423,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
+		newnp->ipv6_mc_list = NULL;
+		newnp->ipv6_ac_list = NULL;
+		newnp->ipv6_fl_list = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 
@@ -483,6 +490,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 	/* Clone RX bits */
 	newnp->rxopt.all = np->rxopt.all;
 
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 	newnp->pktoptions = NULL;
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
@@ -947,6 +957,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
+	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 1994f8af646b..68eed344b471 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			return NULL;
 		}
@@ -145,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
@@ -159,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -185,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
-
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -249,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 41e65804ddf5..b68168fcc06a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -24,6 +24,7 @@
 #include <net/checksum.h>
 
 #include <net/inet_sock.h>
+#include <net/inet_common.h>
 #include <net/sock.h>
 #include <net/xfrm.h>
 
@@ -170,6 +171,15 @@ const char *dccp_packet_name(const int type)
 
 EXPORT_SYMBOL_GPL(dccp_packet_name);
 
+static void dccp_sk_destruct(struct sock *sk)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+	dp->dccps_hc_tx_ccid = NULL;
+	inet_sock_destruct(sk);
+}
+
 int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
@@ -179,6 +189,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
 	sk->sk_state		= DCCP_CLOSED;
 	sk->sk_write_space	= dccp_write_space;
+	sk->sk_destruct		= dccp_sk_destruct;
 	icsk->icsk_sync_mss	= dccp_sync_mss;
 	dp->dccps_mss_cache	= 536;
 	dp->dccps_rate_last	= jiffies;
@@ -201,10 +212,7 @@ void dccp_destroy_sock(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	/*
-	 * DCCP doesn't use sk_write_queue, just sk_send_head
-	 * for retransmissions
-	 */
+	__skb_queue_purge(&sk->sk_write_queue);
 	if (sk->sk_send_head != NULL) {
 		kfree_skb(sk->sk_send_head);
 		sk->sk_send_head = NULL;
@@ -222,8 +230,7 @@ void dccp_destroy_sock(struct sock *sk)
 		dp->dccps_hc_rx_ackvec = NULL;
 	}
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+	dp->dccps_hc_rx_ccid = NULL;
 
 	/* clean up feature negotiation state */
 	dccp_feat_list_purge(&dp->dccps_featneg);
@@ -1009,6 +1016,10 @@ void dccp_close(struct sock *sk, long timeout)
 		__kfree_skb(skb);
 	}
 
+	/* If socket has been already reset kill it. */
+	if (sk->sk_state == DCCP_CLOSED)
+		goto adjudge_to_death;
+
 	if (data_was_unread) {
 		/* Unread data was tossed, send an appropriate Reset Code */
 		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 607a14f20d88..403593bd2b83 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_route *rt)
 	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
 }
 
-static inline void dnrt_drop(struct dn_route *rt)
-{
-	dst_release(&rt->dst);
-	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
 static void dn_dst_check_expire(unsigned long dummy)
 {
 	int i;
@@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops)
 			}
 			*rtp = rt->dst.dn_next;
 			rt->dst.dn_next = NULL;
-			dnrt_drop(rt);
+			dnrt_free(rt);
 			break;
 		}
 		spin_unlock_bh(&dn_rt_hash_table[i].lock);
@@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
 			dst_use(&rth->dst, now);
 			spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 
-			dnrt_drop(rt);
+			dst_free(&rt->dst);
 			*rp = rth;
 			return 0;
 		}
@@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long dummy)
 		for(; rt; rt = next) {
 			next = rcu_dereference_raw(rt->dst.dn_next);
 			RCU_INIT_POINTER(rt->dst.dn_next, NULL);
-			dst_free((struct dst_entry *)rt);
+			dnrt_free(rt);
 		}
 
 nothing_to_declare:
@@ -1034,10 +1028,13 @@ source_ok:
 	if (!fld.daddr) {
 		fld.daddr = fld.saddr;
 
-		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
+		err = -EINVAL;
 		dev_out = init_net.loopback_dev;
+		if (!dev_out->dn_ptr)
+			goto out;
+		err = -EADDRNOTAVAIL;
 		dev_hold(dev_out);
 		if (!fld.daddr) {
 			fld.daddr =
@@ -1110,6 +1107,8 @@ source_ok:
 		if (dev_out == NULL)
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
+		if (!dn_db)
+			goto e_inval;
 		/* Possible improvement - check all devices for local addr */
 		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
@@ -1151,6 +1150,8 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
+		if (!dev_out->dn_ptr)
+			goto e_inval;
 		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
@@ -1180,7 +1181,7 @@ make_route:
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
+	rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;
 
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 85f2fdc360c2..29246bc9a7b4 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -102,7 +102,9 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 
-	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
+	if (skb->len < sizeof(*nlh) ||
+	    nlh->nlmsg_len < sizeof(*nlh) ||
+	    skb->len < nlh->nlmsg_len)
 		return;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 7bc787b095c8..554c2a961ad5 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1006,10 +1006,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
 	/* Use already configured phy mode */
 	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
 		p->phy_interface = p->phy->interface;
-	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-			   p->phy_interface);
-
-	return 0;
+	return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+				  p->phy_interface);
 }
 
 static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
@@ -1101,6 +1099,8 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	netif_device_detach(slave_dev);
+
 	if (p->phy) {
 		phy_stop(p->phy);
 		p->old_pause = -1;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9e63f252a89e..52dcd414c2af 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -353,6 +353,7 @@ void ether_setup(struct net_device *dev)
 	dev->header_ops		= &eth_header_ops;
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->addr_len		= ETH_ALEN;
 	dev->tx_queue_len	= 1000;	/* Ethernet wants good queues */
@@ -436,7 +437,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*eh));
 	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5c5db6636704..967a47ff78a4 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1014,7 +1014,7 @@ static struct inet_protosw inetsw_array[] =
 		.type =       SOCK_DGRAM,
 		.protocol =   IPPROTO_ICMP,
 		.prot =       &ping_prot,
-		.ops =        &inet_dgram_ops,
+		.ops =        &inet_sockraw_ops,
 		.flags =      INET_PROTOSW_REUSE,
        },
 
@@ -1372,7 +1372,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -1383,6 +1383,19 @@ out:
 	return pp;
 }
 
+static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	if (NAPI_GRO_CB(skb)->encap_mark) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	return inet_gro_receive(head, skb);
+}
+
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	if (sk->sk_family == AF_INET)
@@ -1425,6 +1438,13 @@ out_unlock:
 	return err;
 }
 
+static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP;
+	return inet_gro_complete(skb, nhoff);
+}
+
 int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 			 unsigned short type, unsigned char protocol,
 			 struct net *net)
@@ -1652,8 +1672,8 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 static const struct net_offload ipip_offload = {
 	.callbacks = {
 		.gso_segment	= inet_gso_segment,
-		.gro_receive	= inet_gro_receive,
-		.gro_complete	= inet_gro_complete,
+		.gro_receive	= ipip_gro_receive,
+		.gro_complete	= ipip_gro_complete,
 	},
 };
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 59b3e0e8fd51..711b4dfa17c3 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1250,7 +1250,7 @@ void __init arp_init(void)
 /*
  *	ax25 -> ASCII conversion
  */
-static char *ax2asc2(ax25_address *a, char *buf)
+static void ax2asc2(ax25_address *a, char *buf)
 {
 	char c, *s;
 	int n;
@@ -1272,10 +1272,10 @@ static char *ax2asc2(ax25_address *a, char *buf)
 	*s++ = n + '0';
 	*s++ = '\0';
 
-	if (*buf == '\0' || *buf == '-')
-		return "*";
-
-	return buf;
+	if (*buf == '\0' || *buf == '-') {
+		buf[0] = '*';
+		buf[1] = '\0';
+	}
 }
 #endif /* CONFIG_AX25 */
 
@@ -1309,7 +1309,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 	}
 #endif
 	sprintf(tbuf, "%pI4", n->primary_key);
-	seq_printf(seq, "%-16s 0x%-10x0x%-10x%s     *        %s\n",
+	seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s     *        %s\n",
 		   tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
 	read_unlock(&n->lock);
 }
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index bdb2a07ec363..6cc3e1d602fb 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1657,6 +1657,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 				goto validate_return_locked;
 			}
 
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto validate_return_locked;
+		}
 		tag_len = tag[1];
 		if (tag_len > (opt_len - opt_iter)) {
 			err_offset = opt_iter + 1;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f6303b17546b..0212591b0077 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 477937465a20..20fb25e3027b 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
 	void *tmp;
 };
 
+struct esp_output_extra {
+	__be32 seqhi;
+	u32 esphoff;
+};
+
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
  *
  * TODO: Use spare space in skb for this where possible.
  */
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
 {
 	unsigned int len;
 
-	len = seqhilen;
+	len = extralen;
 
 	len += crypto_aead_ivsize(aead);
 
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 	return kmalloc(len, GFP_ATOMIC);
 }
 
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
 {
-	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
 }
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
 {
 	return crypto_aead_ivsize(aead) ?
-	       PTR_ALIGN((u8 *)tmp + seqhilen,
-			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+	       PTR_ALIGN((u8 *)tmp + extralen,
+			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
 }
 
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 {
 	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
 	void *tmp = ESP_SKB_CB(skb)->tmp;
-	__be32 *seqhi = esp_tmp_seqhi(tmp);
+	__be32 *seqhi = esp_tmp_extra(tmp);
 
 	esph->seq_no = esph->spi;
 	esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 
 static void esp_output_restore_header(struct sk_buff *skb)
 {
-	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+				sizeof(__be32));
 }
 
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
+	struct esp_output_extra *extra;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int seqhilen;
-	__be32 *seqhi;
+	int extralen;
 	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	seqhilen = 0;
+	extralen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
 		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	seqhi = esp_tmp_seqhi(tmp);
+	seqhi = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
@@ -464,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		esph = (void *)skb_push(skb, 4);
 		*seqhi = esph->spi;
 		esph->spi = esph->seq_no;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
 		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
 	}
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 473447593060..0cb240c749bf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -85,7 +85,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (tb)
 		return tb;
 
-	if (id == RT_TABLE_LOCAL)
+	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
 		alias = fib_new_table(net, RT_TABLE_MAIN);
 
 	tb = fib_trie_table(id, alias);
@@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	struct in_device *in_dev;
 	struct fib_result res;
 	struct rtable *rt;
-	struct flowi4 fl4;
 	struct net *net;
 	int scope;
 
@@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
-		fl4.flowi4_oif = 0;
-		fl4.flowi4_iif = LOOPBACK_IFINDEX;
-		fl4.daddr = ip_hdr(skb)->saddr;
-		fl4.saddr = 0;
-		fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
-		fl4.flowi4_scope = scope;
-		fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
-		fl4.flowi4_tun_key.tun_id = 0;
+		struct flowi4 fl4 = {
+			.flowi4_iif = LOOPBACK_IFINDEX,
+			.daddr = ip_hdr(skb)->saddr,
+			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_scope = scope,
+			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
 	} else {
@@ -759,7 +757,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int e = 0, s_e;
 	struct fib_table *tb;
 	struct hlist_head *head;
-	int dumped = 0;
+	int dumped = 0, err;
 
 	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
@@ -779,20 +777,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			if (dumped)
 				memset(&cb->args[2], 0, sizeof(cb->args) -
 						 2 * sizeof(cb->args[0]));
-			if (fib_table_dump(tb, skb, cb) < 0)
-				goto out;
+			err = fib_table_dump(tb, skb, cb);
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 			dumped = 1;
 next:
 			e++;
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 
 	cb->args[1] = e;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 /* Prepare and feed intra-kernel routing request.
@@ -906,7 +911,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
@@ -922,6 +931,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -997,6 +1009,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
@@ -1074,7 +1087,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
@@ -1305,13 +1319,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e8ff10..313e3c11a15a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -204,6 +204,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
+	struct dst_metrics *m;
 
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
@@ -214,8 +215,9 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	if (fi->fib_metrics != (u32 *) dst_default_metrics)
-		kfree(fi->fib_metrics);
+	m = fi->fib_metrics;
+	if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
+		kfree(m);
 	kfree(fi);
 }
 
@@ -479,6 +481,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
 
+		if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			return -EINVAL;
+
 		nexthop_nh->nh_flags =
 			(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
 		nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
@@ -975,13 +980,15 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			val = 65535 - 40;
 		if (type == RTAX_MTU && val > 65535 - 15)
 			val = 65535 - 15;
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			return -EINVAL;
-		fi->fib_metrics[type - 1] = val;
+		fi->fib_metrics->metrics[type - 1] = val;
 	}
 
 	if (ecn_ca)
-		fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+		fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
 
 	return 0;
 }
@@ -1001,6 +1008,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
 		goto err_inval;
 
+	if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		goto err_inval;
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (cfg->fc_mp) {
 		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
@@ -1034,14 +1044,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		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;
-
+		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
+		atomic_set(&fi->fib_metrics->refcnt, 1);
+	} else {
+		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
+	}
+	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
@@ -1243,7 +1256,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (fi->fib_priority &&
 	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
 		goto nla_put_failure;
-	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
+	if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0)
 		goto nla_put_failure;
 
 	if (fi->fib_prefsrc &&
@@ -1269,8 +1282,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
 			goto nla_put_failure;
 #endif
-		if (fi->fib_nh->nh_lwtstate)
-			lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
+		if (fi->fib_nh->nh_lwtstate &&
+		    lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
+			goto nla_put_failure;
 	}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (fi->fib_nhs > 1) {
@@ -1306,8 +1320,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
 				goto nla_put_failure;
 #endif
-			if (nh->nh_lwtstate)
-				lwtunnel_fill_encap(skb, nh->nh_lwtstate);
+			if (nh->nh_lwtstate &&
+			    lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
+				goto nla_put_failure;
+
 			/* length of rtnetlink header + attributes */
 			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
 		} endfor_nexthops(fi);
@@ -1580,8 +1596,13 @@ void fib_select_multipath(struct fib_result *res, int hash)
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, int mp_hash)
 {
+	bool oif_check;
+
+	oif_check = (fl4->flowi4_oif == 0 ||
+		     fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF);
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
+	if (res->fi->fib_nhs > 1 && oif_check) {
 		if (mp_hash < 0)
 			mp_hash = get_hash_from_flowi4(fl4) >> 1;
 
@@ -1591,7 +1612,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 #endif
 	if (!res->prefixlen &&
 	    res->table->tb_num_default > 1 &&
-	    res->type == RTN_UNICAST && !fl4->flowi4_oif)
+	    res->type == RTN_UNICAST && oif_check)
 		fib_select_default(fl4, res);
 
 	if (!fl4->saddr)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 744e5936c10d..5c598f99a500 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1906,6 +1906,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 
 	/* rcu_read_lock is hold by caller */
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		int err;
+
 		if (i < s_i) {
 			i++;
 			continue;
@@ -1916,17 +1918,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 			continue;
 		}
 
-		if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq,
-				  RTM_NEWROUTE,
-				  tb->tb_id,
-				  fa->fa_type,
-				  xkey,
-				  KEYLENGTH - fa->fa_slen,
-				  fa->fa_tos,
-				  fa->fa_info, NLM_F_MULTI) < 0) {
+		err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
+				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+				    tb->tb_id, fa->fa_type,
+				    xkey, KEYLENGTH - fa->fa_slen,
+				    fa->fa_tos, fa->fa_info, NLM_F_MULTI);
+		if (err < 0) {
 			cb->args[4] = i;
-			return -1;
+			return err;
 		}
 		i++;
 	}
@@ -1948,10 +1947,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	t_key key = cb->args[3];
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+		int err;
+
+		err = fn_trie_dump_leaf(l, tb, skb, cb);
+		if (err < 0) {
 			cb->args[3] = key;
 			cb->args[2] = count;
-			return -1;
+			return err;
 		}
 
 		++count;
@@ -2453,29 +2455,22 @@ struct fib_route_iter {
 static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 					    loff_t pos)
 {
-	struct fib_table *tb = iter->main_tb;
 	struct key_vector *l, **tp = &iter->tnode;
-	struct trie *t;
 	t_key key;
 
-	/* use cache location of next-to-find key */
+	/* use cached location of previously found key */
 	if (iter->pos > 0 && pos >= iter->pos) {
-		pos -= iter->pos;
 		key = iter->key;
 	} else {
-		t = (struct trie *)tb->tb_data;
-		iter->tnode = t->kv;
-		iter->pos = 0;
+		iter->pos = 1;
 		key = 0;
 	}
 
-	while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+	pos -= iter->pos;
+
+	while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
 		key = l->key + 1;
 		iter->pos++;
-
-		if (--pos <= 0)
-			break;
-
 		l = NULL;
 
 		/* handle unlikely case of a key wrap */
@@ -2484,7 +2479,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	}
 
 	if (l)
-		iter->key = key;	/* remember it */
+		iter->key = l->key;	/* remember it */
 	else
 		iter->pos = 0;		/* forget it */
 
@@ -2505,14 +2500,14 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 		return NULL;
 
 	iter->main_tb = tb;
+	t = (struct trie *)tb->tb_data;
+	iter->tnode = t->kv;
 
 	if (*pos != 0)
 		return fib_route_get_idx(iter, *pos);
 
-	t = (struct trie *)tb->tb_data;
-	iter->tnode = t->kv;
 	iter->pos = 0;
-	iter->key = 0;
+	iter->key = KEY_MAX;
 
 	return SEQ_START_TOKEN;
 }
@@ -2521,7 +2516,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
 	struct key_vector *l = NULL;
-	t_key key = iter->key;
+	t_key key = iter->key + 1;
 
 	++*pos;
 
@@ -2530,7 +2525,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		l = leaf_walk_rcu(&iter->tnode, key);
 
 	if (l) {
-		iter->key = l->key + 1;
+		iter->key = l->key;
 		iter->pos++;
 	} else {
 		iter->pos = 0;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index bd903fe0f750..08d8ee124538 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -48,7 +48,7 @@ static inline struct fou *fou_from_sock(struct sock *sk)
 	return sk->sk_user_data;
 }
 
-static void fou_recv_pull(struct sk_buff *skb, size_t len)
+static int fou_recv_pull(struct sk_buff *skb, size_t len)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
@@ -59,6 +59,7 @@ static void fou_recv_pull(struct sk_buff *skb, size_t len)
 	__skb_pull(skb, len);
 	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 	skb_reset_transport_header(skb);
+	return iptunnel_pull_offloads(skb);
 }
 
 static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
@@ -68,9 +69,14 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!fou)
 		return 1;
 
-	fou_recv_pull(skb, sizeof(struct udphdr));
+	if (fou_recv_pull(skb, sizeof(struct udphdr)))
+		goto drop;
 
 	return -fou->protocol;
+
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
@@ -170,6 +176,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
+	if (iptunnel_pull_offloads(skb))
+		goto drop;
+
 	return -guehdr->proto_ctype;
 
 drop:
@@ -192,7 +201,7 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -351,7 +360,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 5a8ee3282550..79ae0d7becbf 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -128,6 +128,11 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	struct packet_offload *ptype;
 	__be16 type;
 
+	if (NAPI_GRO_CB(skb)->encap_mark)
+		goto out;
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*greh);
 	greh = skb_gro_header_fast(skb, off);
@@ -214,7 +219,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
 	skb_gro_postpull_rcsum(skb, greh, grehlen);
 
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 05e4cba14162..3809d523d012 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -225,9 +225,14 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
 	int tv = prandom_u32() % in_dev->mr_maxdelay;
+	unsigned long exp = jiffies + tv + 2;
+
+	if (in_dev->mr_gq_running &&
+	    time_after_eq(exp, (in_dev->mr_gq_timer).expires))
+		return;
 
 	in_dev->mr_gq_running = 1;
-	if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2))
+	if (!mod_timer(&in_dev->mr_gq_timer, exp))
 		in_dev_hold(in_dev);
 }
 
@@ -356,9 +361,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
@@ -1098,6 +1102,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
 	if (!pmc)
 		return;
+	spin_lock_init(&pmc->lock);
 	spin_lock_bh(&im->lock);
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
@@ -2022,21 +2027,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 
 static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
-	struct ip_sf_list *psf, *nextpsf;
+	struct ip_sf_list *psf, *nextpsf, *tomb, *sources;
 
-	for (psf = pmc->tomb; psf; psf = nextpsf) {
+	spin_lock_bh(&pmc->lock);
+	tomb = pmc->tomb;
+	pmc->tomb = NULL;
+	sources = pmc->sources;
+	pmc->sources = NULL;
+	pmc->sfmode = MCAST_EXCLUDE;
+	pmc->sfcount[MCAST_INCLUDE] = 0;
+	pmc->sfcount[MCAST_EXCLUDE] = 1;
+	spin_unlock_bh(&pmc->lock);
+
+	for (psf = tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->tomb = NULL;
-	for (psf = pmc->sources; psf; psf = nextpsf) {
+	for (psf = sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->sources = NULL;
-	pmc->sfmode = MCAST_EXCLUDE;
-	pmc->sfcount[MCAST_INCLUDE] = 0;
-	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
 /* Join a multicast group
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 64148914803a..45fa2aaa3d3f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -669,6 +669,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
 		newsk->sk_write_space = sk_stream_write_space;
 
+		inet_sk(newsk)->mc_list = NULL;
+
 		newsk->sk_mark = inet_rsk(req)->ir_mark;
 		atomic64_set(&newsk->sk_cookie,
 			     atomic64_read(&inet_rsk(req)->ir_cookie));
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 614521437e30..3e4184088082 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -180,6 +180,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags)
 	return flags;
 }
 
+/* Fills in tpi and returns header length to be pulled. */
 static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			    bool *csum_err)
 {
@@ -239,7 +240,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 				return -EINVAL;
 		}
 	}
-	return iptunnel_pull_header(skb, hdr_len, tpi->proto);
+	return hdr_len;
 }
 
 static void ipgre_err(struct sk_buff *skb, u32 info,
@@ -342,7 +343,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
 
-	if (parse_gre_header(skb, &tpi, &csum_err)) {
+	if (parse_gre_header(skb, &tpi, &csum_err) < 0) {
 		if (!csum_err)		/* ignore csum errors. */
 			return;
 	}
@@ -420,6 +421,7 @@ static int gre_rcv(struct sk_buff *skb)
 {
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
+	int hdr_len;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
@@ -429,7 +431,10 @@ static int gre_rcv(struct sk_buff *skb)
 	}
 #endif
 
-	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+	hdr_len = parse_gre_header(skb, &tpi, &csum_err);
+	if (hdr_len < 0)
+		goto drop;
+	if (iptunnel_pull_header(skb, hdr_len, tpi.proto) < 0)
 		goto drop;
 
 	if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
@@ -1242,6 +1247,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 49f02856304d..09c73dd541c5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -102,6 +102,9 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	iph->tot_len = htons(skb->len);
 	ip_send_check(iph);
+
+	skb->protocol = htons(ETH_P_IP);
+
 	return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);
@@ -919,10 +922,12 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    (((length + (skb ? skb->len : fragheaderlen)) > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -1237,13 +1242,17 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	if (!skb)
 		return -EINVAL;
 
-	cork->length += size;
 	if ((size + skb->len > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) == 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
+		if (skb->ip_summed != CHECKSUM_PARTIAL)
+			return -EOPNOTSUPP;
+
 		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 	}
+	cork->length += size;
 
 	while (size > 0) {
 		if (skb_is_gso(skb)) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a50124260f5a..f300d1cbfa91 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -98,15 +98,17 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 }
 
 static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
-				  int offset)
+				  int tlen, int offset)
 {
 	__wsum csum = skb->csum;
 
 	if (skb->ip_summed != CHECKSUM_COMPLETE)
 		return;
 
-	if (offset != 0)
-		csum = csum_sub(csum, csum_partial(skb->data, offset, 0));
+	if (offset != 0) {
+		int tend_off = skb_transport_offset(skb) + tlen;
+		csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0));
+	}
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
@@ -152,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 }
 
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
-			 int offset)
+			 int tlen, int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
@@ -215,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 	}
 
 	if (flags & IP_CMSG_CHECKSUM)
-		ip_cmsg_recv_checksum(msg, skb, offset);
+		ip_cmsg_recv_checksum(msg, skb, tlen, offset);
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
@@ -1190,7 +1192,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	/* We need to keep the dst for __ip_options_echo()
+	 * We could restrict the test to opt.ts_needtime || opt.srr,
+	 * but the following is good enough as IP options are not often used.
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen))
+		skb_dst_force(skb);
+	else
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cbb51f3fac06..3310ac75e3f3 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -663,6 +663,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -760,7 +762,6 @@ 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;
@@ -947,17 +948,31 @@ done:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6cb9009c3d96..dbda0565781c 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -116,7 +116,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
 	skb->pkt_type = PACKET_HOST;
-	return 0;
+
+	return iptunnel_pull_offloads(skb);
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 4d8f0b698777..65036891e080 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -540,6 +540,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.get_link_net	= ip_tunnel_get_link_net,
 };
 
+static bool is_vti_tunnel(const struct net_device *dev)
+{
+	return dev->netdev_ops == &vti_netdev_ops;
+}
+
+static int vti_device_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	if (!is_vti_tunnel(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_DOWN:
+		if (!net_eq(tunnel->net, dev_net(dev)))
+			xfrm_garbage_collect(tunnel->net);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block vti_notifier_block __read_mostly = {
+	.notifier_call = vti_device_event,
+};
+
 static int __init vti_init(void)
 {
 	const char *msg;
@@ -547,6 +574,8 @@ static int __init vti_init(void)
 
 	pr_info("IPv4 over IPsec tunneling driver\n");
 
+	register_netdevice_notifier(&vti_notifier_block);
+
 	msg = "tunnel device";
 	err = register_pernet_device(&vti_net_ops);
 	if (err < 0)
@@ -579,6 +608,7 @@ xfrm_proto_ah_failed:
 xfrm_proto_esp_failed:
 	unregister_pernet_device(&vti_net_ops);
 pernet_dev_failed:
+	unregister_netdevice_notifier(&vti_notifier_block);
 	pr_err("vti init: failed to register %s\n", msg);
 	return err;
 }
@@ -590,6 +620,7 @@ static void __exit vti_fini(void)
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
 	unregister_pernet_device(&vti_net_ops);
+	unregister_netdevice_notifier(&vti_notifier_block);
 }
 
 module_init(vti_init);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c3a38353f5dc..8e77786549c6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -882,8 +882,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 
-	if (c)
+	if (c) {
+		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+	}
 	return c;
 }
 
@@ -2190,7 +2192,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 int ipmr_get_route(struct net *net, struct sk_buff *skb,
 		   __be32 saddr, __be32 daddr,
-		   struct rtmsg *rtm, int nowait)
+		   struct rtmsg *rtm, int nowait, u32 portid)
 {
 	struct mfc_cache *cache;
 	struct mr_table *mrt;
@@ -2235,6 +2237,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			return -ENOMEM;
 		}
 
+		NETLINK_CB(skb2).portid = portid;
 		skb_push(skb2, sizeof(struct iphdr));
 		skb_reset_network_header(skb2);
 		iph = ip_hdr(skb2);
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 11dccba474b7..6e3e0e8b1ce3 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -359,11 +359,24 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 }
 
 /* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
 {
 	static const struct arpt_arp uncond;
 
-	return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct arpt_entry) &&
+	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
+}
+
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct arpt_entry *target)
+{
+	struct arpt_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -402,11 +415,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct arpt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->arp)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -439,6 +451,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct arpt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -458,9 +472,15 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct arpt_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct arpt_entry *)
 					(entry0 + newpos);
@@ -474,25 +494,6 @@ next:
 	return 1;
 }
 
-static inline int check_entry(const struct arpt_entry *e, const char *name)
-{
-	const struct xt_entry_target *t;
-
-	if (!arp_checkentry(&e->arp)) {
-		duprintf("arp_tables: arp check failed %p %s.\n", e, name);
-		return -EINVAL;
-	}
-
-	if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
-		return -EINVAL;
-
-	t = arpt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
-}
-
 static inline int check_target(struct arpt_entry *e, const char *name)
 {
 	struct xt_entry_target *t = arpt_get_target(e);
@@ -522,10 +523,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
 	struct xt_target *target;
 	int ret;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	e->counters.pcnt = xt_percpu_counter_alloc();
 	if (IS_ERR_VALUE(e->counters.pcnt))
 		return -ENOMEM;
@@ -557,7 +554,7 @@ static bool check_underflow(const struct arpt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->arp))
+	if (!unconditional(e))
 		return false;
 	t = arpt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -576,9 +573,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 					     unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -590,6 +589,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 		return -EINVAL;
 	}
 
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -598,9 +605,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
@@ -691,10 +698,8 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		}
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
-		duprintf("Looping hook\n");
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
 		return -ELOOP;
-	}
 
 	/* Finally, each sanity check must pass */
 	i = 0;
@@ -1125,55 +1130,17 @@ static int do_add_counters(struct net *net, const void __user *user,
 	unsigned int i;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	struct arpt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
 
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
-
-	t = xt_find_table_lock(net, NFPROTO_ARP, name);
+	t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1181,7 +1148,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
@@ -1208,6 +1175,18 @@ static int do_add_counters(struct net *net, const void __user *user,
 }
 
 #ifdef CONFIG_COMPAT
+struct compat_arpt_replace {
+	char				name[XT_TABLE_MAXNAMELEN];
+	u32				valid_hooks;
+	u32				num_entries;
+	u32				size;
+	u32				hook_entry[NF_ARP_NUMHOOKS];
+	u32				underflow[NF_ARP_NUMHOOKS];
+	u32				num_counters;
+	compat_uptr_t			counters;
+	struct compat_arpt_entry	entries[0];
+};
+
 static inline void compat_release_entry(struct compat_arpt_entry *e)
 {
 	struct xt_entry_target *t;
@@ -1216,24 +1195,22 @@ static inline void compat_release_entry(struct compat_arpt_entry *e)
 	module_put(t->u.kernel.target->me);
 }
 
-static inline int
+static int
 check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned char *limit)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
@@ -1245,8 +1222,11 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct arpt_entry *)e, name);
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset,
+					    e->next_offset);
 	if (ret)
 		return ret;
 
@@ -1270,17 +1250,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	if (ret)
 		goto release_target;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 release_target:
@@ -1289,18 +1258,17 @@ out:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	struct arpt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct arpt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct arpt_entry));
@@ -1321,148 +1289,82 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
 }
 
-static int translate_compat_table(const char *name,
-				  unsigned int valid_hooks,
-				  struct xt_table_info **pinfo,
+static int translate_compat_table(struct xt_table_info **pinfo,
 				  void **pentry0,
-				  unsigned int total_size,
-				  unsigned int number,
-				  unsigned int *hook_entries,
-				  unsigned int *underflows)
+				  const struct compat_arpt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_arpt_entry *iter0;
-	struct arpt_entry *iter1;
+	struct arpt_replace repl;
 	unsigned int size;
 	int ret = 0;
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
-
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
-	xt_compat_init_offsets(NFPROTO_ARP, number);
+	xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = info->hook_entry[i];
 		newinfo->underflow[i] = info->underflow[i];
 	}
 	entry1 = newinfo->entries;
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone */
+
 	xt_compat_flush_offsets(NFPROTO_ARP);
 	xt_compat_unlock(NFPROTO_ARP);
-	if (ret)
-		goto free_newinfo;
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		iter1->counters.pcnt = xt_percpu_counter_alloc();
-		if (IS_ERR_VALUE(iter1->counters.pcnt)) {
-			ret = -ENOMEM;
-			break;
-		}
-
-		ret = check_target(iter1, name);
-		if (ret != 0) {
-			xt_percpu_counter_free(iter1->counters.pcnt);
-			break;
-		}
-		++i;
-		if (strcmp(arpt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
+
 	*pinfo = newinfo;
 	*pentry0 = entry1;
 	xt_free_table_info(info);
@@ -1470,31 +1372,18 @@ static int translate_compat_table(const char *name,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(NFPROTO_ARP);
+	xt_compat_unlock(NFPROTO_ARP);
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(NFPROTO_ARP);
-	xt_compat_unlock(NFPROTO_ARP);
-	goto out;
 }
 
-struct compat_arpt_replace {
-	char				name[XT_TABLE_MAXNAMELEN];
-	u32				valid_hooks;
-	u32				num_entries;
-	u32				size;
-	u32				hook_entry[NF_ARP_NUMHOOKS];
-	u32				underflow[NF_ARP_NUMHOOKS];
-	u32				num_counters;
-	compat_uptr_t			counters;
-	struct compat_arpt_entry	entries[0];
-};
-
 static int compat_do_replace(struct net *net, void __user *user,
 			     unsigned int len)
 {
@@ -1527,10 +1416,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index b99affad6ba1..a399c5419622 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
 {
 	static const struct ipt_ip uncond;
 
-	return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ipt_entry) &&
+	       memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
 #undef FWINV
 }
 
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ipt_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		   t->verdict < 0 &&
-		   unconditional(&s->ip)) {
+		   t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -443,6 +443,18 @@ ipt_do_table(struct sk_buff *skb,
 #endif
 }
 
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct ipt_entry *target)
+{
+	struct ipt_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
+}
+
 /* Figures out from what hook each rule can be called: returns 0 if
    there are loops.  Puts hook bitmask in comefrom. */
 static int
@@ -476,11 +488,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ipt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->ip)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -521,6 +532,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct ipt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -539,9 +552,15 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct ipt_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct ipt_entry *)
 					(entry0 + newpos);
@@ -569,27 +588,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ipt_entry *e, const char *name)
-{
-	const struct xt_entry_target *t;
-
-	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip check failed %p %s.\n", e, name);
-		return -EINVAL;
-	}
-
-	if (e->target_offset + sizeof(struct xt_entry_target) >
-	    e->next_offset)
-		return -EINVAL;
-
-	t = ipt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int
 check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
 {
 	const struct ipt_ip *ip = par->entryinfo;
@@ -666,10 +664,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	e->counters.pcnt = xt_percpu_counter_alloc();
 	if (IS_ERR_VALUE(e->counters.pcnt))
 		return -ENOMEM;
@@ -721,7 +715,7 @@ static bool check_underflow(const struct ipt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ip))
+	if (!unconditional(e))
 		return false;
 	t = ipt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -741,9 +735,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -755,6 +751,14 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 		return -EINVAL;
 	}
 
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -763,9 +767,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
@@ -1309,55 +1313,17 @@ do_add_counters(struct net *net, const void __user *user,
 	unsigned int i;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	struct ipt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
-
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
 
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
-
-	t = xt_find_table_lock(net, AF_INET, name);
+	t = xt_find_table_lock(net, AF_INET, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1365,7 +1331,7 @@ do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
@@ -1444,7 +1410,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
 
 static int
 compat_find_calc_match(struct xt_entry_match *m,
-		       const char *name,
 		       const struct ipt_ip *ip,
 		       int *size)
 {
@@ -1479,21 +1444,19 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned char *limit)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
 	unsigned int j;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
@@ -1505,8 +1468,11 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ipt_entry *)e, name);
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	ret = xt_compat_check_entry_offsets(e, e->elems,
+					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
@@ -1514,7 +1480,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	entry_offset = (void *)e - (void *)base;
 	j = 0;
 	xt_ematch_foreach(ematch, e) {
-		ret = compat_find_calc_match(ematch, name, &e->ip, &off);
+		ret = compat_find_calc_match(ematch, &e->ip, &off);
 		if (ret != 0)
 			goto release_matches;
 		++j;
@@ -1537,17 +1503,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	if (ret)
 		goto out;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 out:
@@ -1561,19 +1516,18 @@ release_matches:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	struct ipt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 	struct xt_entry_match *ematch;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct ipt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct ipt_entry));
@@ -1582,201 +1536,105 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	*dstptr += sizeof(struct ipt_entry);
 	*size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry);
 
-	xt_ematch_foreach(ematch, e) {
-		ret = xt_compat_match_from_user(ematch, dstptr, size);
-		if (ret != 0)
-			return ret;
-	}
+	xt_ematch_foreach(ematch, e)
+		xt_compat_match_from_user(ematch, dstptr, size);
+
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ipt_get_target(e);
 	target = t->u.kernel.target;
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
+
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if ((unsigned char *)de - base < newinfo->hook_entry[h])
 			newinfo->hook_entry[h] -= origsize - *size;
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
-}
-
-static int
-compat_check_entry(struct ipt_entry *e, struct net *net, const char *name)
-{
-	struct xt_entry_match *ematch;
-	struct xt_mtchk_param mtpar;
-	unsigned int j;
-	int ret = 0;
-
-	e->counters.pcnt = xt_percpu_counter_alloc();
-	if (IS_ERR_VALUE(e->counters.pcnt))
-		return -ENOMEM;
-
-	j = 0;
-	mtpar.net	= net;
-	mtpar.table     = name;
-	mtpar.entryinfo = &e->ip;
-	mtpar.hook_mask = e->comefrom;
-	mtpar.family    = NFPROTO_IPV4;
-	xt_ematch_foreach(ematch, e) {
-		ret = check_match(ematch, &mtpar);
-		if (ret != 0)
-			goto cleanup_matches;
-		++j;
-	}
-
-	ret = check_target(e, net, name);
-	if (ret)
-		goto cleanup_matches;
-	return 0;
-
- cleanup_matches:
-	xt_ematch_foreach(ematch, e) {
-		if (j-- == 0)
-			break;
-		cleanup_match(ematch, net);
-	}
-
-	xt_percpu_counter_free(e->counters.pcnt);
-
-	return ret;
 }
 
 static int
 translate_compat_table(struct net *net,
-		       const char *name,
-		       unsigned int valid_hooks,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
-		       unsigned int total_size,
-		       unsigned int number,
-		       unsigned int *hook_entries,
-		       unsigned int *underflows)
+		       const struct compat_ipt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_ipt_entry *iter0;
-	struct ipt_entry *iter1;
+	struct ipt_replace repl;
 	unsigned int size;
 	int ret;
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
-
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
-	xt_compat_init_offsets(AF_INET, number);
+	xt_compat_init_offsets(AF_INET, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries;
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone.
+	 * entry1/newinfo contains a 64bit ruleset that looks exactly as
+	 * generated by 64bit userspace.
+	 *
+	 * Call standard translate_table() to validate all hook_entrys,
+	 * underflows, check for loops, etc.
+	 */
 	xt_compat_flush_offsets(AF_INET);
 	xt_compat_unlock(AF_INET);
-	if (ret)
-		goto free_newinfo;
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(ipt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1, net);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(net, newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
+
 	*pinfo = newinfo;
 	*pentry0 = entry1;
 	xt_free_table_info(info);
@@ -1784,17 +1642,16 @@ translate_compat_table(struct net *net,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(AF_INET);
+	xt_compat_unlock(AF_INET);
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(AF_INET);
-	xt_compat_unlock(AF_INET);
-	goto out;
 }
 
 static int
@@ -1830,10 +1687,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb42100e9a..ea91058b5f6f 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index aa67e0e64b69..37a3b05d175c 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -154,17 +154,18 @@ void ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 
@@ -645,6 +646,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
+	if (!skb)
+		return 0;
 	pfh->wcheck = csum_partial((char *)&pfh->icmph,
 		sizeof(struct icmphdr), pfh->wcheck);
 	pfh->icmph.checksum = csum_fold(pfh->wcheck);
@@ -660,6 +663,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
 
+	/* Must have at least a full ICMP header. */
+	if (len < icmph_len)
+		return -EINVAL;
+
 	/*
 	 *	Check the flags.
 	 */
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7113bae4e6a0..8f2cd7d09720 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -354,6 +354,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			       rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct iphdr))
+		return -EINVAL;
+
 	if (flags&MSG_PROBE)
 		goto out;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02c62299d717..0294f7c99c85 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -747,7 +747,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	if (!n)
+		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
@@ -1239,7 +1241,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)
@@ -1354,8 +1356,12 @@ static void rt_add_uncached_list(struct rtable *rt)
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
 {
+	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *) dst;
 
+	if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+		kfree(p);
+
 	if (!list_empty(&rt->rt_uncached)) {
 		struct uncached_list *ul = rt->rt_uncached_list;
 
@@ -1407,7 +1413,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			rt->rt_gateway = nh->nh_gw;
 			rt->rt_uses_gateway = 1;
 		}
-		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
+		if (fi->fib_metrics != &dst_default_metrics) {
+			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+			atomic_inc(&fi->fib_metrics->refcnt);
+		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
@@ -1956,6 +1966,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	int res;
 
+	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
 
 	/* Multicast recognition logic is moved from route cache to here.
@@ -2045,6 +2056,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
@@ -2416,7 +2439,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
 	r->rtm_tos	= fl4->flowi4_tos;
-	r->rtm_table	= table_id;
+	r->rtm_table	= table_id < 256 ? table_id : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table_id))
 		goto nla_put_failure;
 	r->rtm_type	= rt->rt_type;
@@ -2480,7 +2503,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 		    IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
 			int err = ipmr_get_route(net, skb,
 						 fl4->saddr, fl4->daddr,
-						 r, nowait);
+						 r, nowait, portid);
+
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
@@ -2543,7 +2567,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	skb_reset_network_header(skb);
 
 	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
-	ip_hdr(skb)->protocol = IPPROTO_ICMP;
+	ip_hdr(skb)->protocol = IPPROTO_UDP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 4cbe9f0a4281..731b91409625 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -337,6 +337,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a0bd7a55193e..70fb352e317f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -97,11 +97,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -110,10 +110,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock(&net->ipv4.ping_group_range.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock(&net->ipv4.ping_group_range.lock);
 }
 
 /* Validate changes from /proc interface. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 036a76ba2ac2..0870a86e9d96 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -783,6 +783,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
@@ -1065,9 +1071,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
+	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
 	if (tp->fastopen_req)
 		return -EALREADY; /* Another Fast Open is in progress */
@@ -1080,7 +1089,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *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,
+	err = __inet_stream_connect(sk->sk_socket, uaddr,
 				    msg->msg_namelen, flags);
 	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
@@ -1212,7 +1221,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == sysctl_max_skb_frags || !sg) {
+				if (i >= sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -2254,6 +2263,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	dst_release(sk->sk_rx_dst);
+	sk->sk_rx_dst = NULL;
+	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 882caa4e72bc..aafe68134763 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -183,6 +183,7 @@ void tcp_init_congestion_control(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
+	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
 		icsk->icsk_ca_ops->init(sk);
 	if (tcp_ca_needs_ecn(sk))
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 7e538f71f5fb..55d7da1d2ce9 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -56,6 +56,7 @@ struct dctcp {
 	u32 next_seq;
 	u32 ce_state;
 	u32 delayed_ack_reserved;
+	u32 loss_cwnd;
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
 		ca->delayed_ack_reserved = 0;
+		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
 		dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
 
 static u32 dctcp_ssthresh(struct sock *sk)
 {
-	const struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	ca->loss_cwnd = tp->snd_cwnd;
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
@@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
 static struct tcp_congestion_ops dctcp __read_mostly = {
 	.init		= dctcp_init,
 	.in_ack_event   = dctcp_update_alpha,
 	.cwnd_event	= dctcp_cwnd_event,
 	.ssthresh	= dctcp_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
+	.undo_cwnd	= dctcp_cwnd_undo,
 	.set_state	= dctcp_state,
 	.get_info	= dctcp_get_info,
 	.flags		= TCP_CONG_NEEDS_ECN,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 55be6ac70cff..fca618272a01 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -112,7 +112,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		struct tcp_fastopen_cookie tmp;
 
 		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
-			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
@@ -161,6 +161,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * scaled. So correct it appropriately.
 	 */
 	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+	tp->max_window = tp->snd_wnd;
 
 	/* Activate the retrans timer so that SYNACK can be retransmitted.
 	 * The request socket is not added to the ehash
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d4c51158470f..c4bbf704ff9c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 /* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
 
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
@@ -1134,13 +1134,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 		 */
 		if (pkt_len > mss) {
 			unsigned int new_len = (pkt_len / mss) * mss;
-			if (!in_sack && new_len < pkt_len) {
+			if (!in_sack && new_len < pkt_len)
 				new_len += mss;
-				if (new_len >= skb->len)
-					return 0;
-			}
 			pkt_len = new_len;
 		}
+
+		if (pkt_len >= skb->len && !in_sack)
+			return 0;
+
 		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
@@ -2164,8 +2165,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int cnt, oldcnt;
-	int err;
+	int cnt, oldcnt, lost;
 	unsigned int mss;
 	/* Use SACK to deduce losses of new sequences sent during recovery */
 	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;
@@ -2205,9 +2205,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 				break;
 
 			mss = tcp_skb_mss(skb);
-			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
-					   mss, GFP_ATOMIC);
-			if (err < 0)
+			/* If needed, chop off the prefix to mark as lost. */
+			lost = (packets - oldcnt) * mss;
+			if (lost < skb->len &&
+			    tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
 				break;
 			cnt = packets;
 		}
@@ -2324,10 +2325,9 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
 			 msg,
-			 &np->daddr, ntohs(inet->inet_dport),
+			 &sk->sk_v6_daddr, ntohs(inet->inet_dport),
 			 tp->snd_cwnd, tcp_left_out(tp),
 			 tp->snd_ssthresh, tp->prior_ssthresh,
 			 tp->packets_out);
@@ -2503,8 +2503,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
-	    (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
+	if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+	    (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
 		tp->snd_cwnd = tp->snd_ssthresh;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
 	}
@@ -3028,8 +3028,7 @@ void tcp_rearm_rto(struct sock *sk)
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta > 0)
-				rto = delta;
+			rto = max(delta, 1);
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
@@ -3220,7 +3219,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			int delta;
 
 			/* Non-retransmitted hole got filled? That's reordering */
-			if (reord < prior_fackets)
+			if (reord < prior_fackets && reord <= tp->fackets_out)
 				tcp_update_reordering(sk, tp->fackets_out - reord, 0);
 
 			delta = tcp_is_fack(tp) ? pkts_acked :
@@ -3390,6 +3389,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 	return flag;
 }
 
+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
+				   u32 *last_oow_ack_time)
+{
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 /* Return true if we're currently rate-limiting out-of-window ACKs and
  * thus shouldn't send a dupack right now. We rate-limit dupacks in
  * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
@@ -3403,21 +3419,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 	/* Data packets without SYNs are not likely part of an ACK loop. */
 	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
 	    !tcp_hdr(skb)->syn)
-		goto not_rate_limited;
-
-	if (*last_oow_ack_time) {
-		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
-
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
-			NET_INC_STATS_BH(net, mib_idx);
-			return true;	/* rate-limited: don't send yet! */
-		}
-	}
-
-	*last_oow_ack_time = tcp_time_stamp;
+		return false;
 
-not_rate_limited:
-	return false;	/* not rate-limited: go ahead, send dupack now! */
+	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
 }
 
 /* RFC 5961 7 [ACK Throttling] */
@@ -3427,21 +3431,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 now;
+	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (tcp_oow_rate_limited(sock_net(sk), skb,
-				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
-				 &tp->last_oow_ack_time))
+	if (__tcp_oow_rate_limited(sock_net(sk),
+				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				   &tp->last_oow_ack_time))
 		return;
 
-	/* Then check the check host-wide RFC 5961 rate limit. */
+	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
+		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
 		challenge_timestamp = now;
-		challenge_count = 0;
+		WRITE_ONCE(challenge_count, half +
+			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
 	}
-	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+	count = READ_ONCE(challenge_count);
+	if (count > 0) {
+		WRITE_ONCE(challenge_count, count - 1);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
@@ -5426,6 +5435,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5638,7 +5648,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8c7e63163e92..198fc2314c82 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -271,10 +271,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
@@ -320,8 +323,6 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 	/* ICMPs are not backlogged, hence we cannot get
 	 * an established socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else if (abort) {
@@ -422,7 +423,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
@@ -810,8 +812,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
 					     tcp_sk(sk)->snd_nxt;
 
+	/* RFC 7323 2.3
+	 * The window field (SEG.WND) of every outgoing segment, with the
+	 * exception of <SYN> segments, MUST be right-shifted by
+	 * Rcv.Wind.Shift bits:
+	 */
 	tcp_v4_send_ack(sock_net(sk), skb, seq,
-			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+			tcp_rsk(req)->rcv_nxt,
+			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp,
 			req->ts_recent,
 			0,
@@ -1529,6 +1537,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_prequeue);
 
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcphdr *th = (struct tcphdr *)skb->data;
+	unsigned int eaten = skb->len;
+	int err;
+
+	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+	if (!err) {
+		eaten -= skb->len;
+		TCP_SKB_CB(skb)->end_seq -= eaten;
+	}
+	return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
 /*
  *	From tcp_input.c
  */
@@ -1634,8 +1657,10 @@ process:
 
 	nf_reset(skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	iph = ip_hdr(skb);
 
 	skb->dev = NULL;
 
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 1e70fa8fa793..3861dedd5365 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -264,13 +264,15 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct lp *lp = inet_csk_ca(sk);
+	u32 delta;
 
 	if (rtt_us > 0)
 		tcp_lp_rtt_sample(sk, rtt_us);
 
 	/* calc inference */
-	if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
-		lp->inference = 3 * (tcp_time_stamp - tp->rx_opt.rcv_tsecr);
+	delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+	if ((s32)delta > 0)
+		lp->inference = 3 * delta;
 
 	/* test if within inference */
 	if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference))
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index c8cbc2b4b792..a726d7853ce5 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -550,7 +550,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ac6b1961ffeb..4c1c94fa8f08 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -458,7 +458,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 		newtp->rcv_wup = newtp->copied_seq =
 		newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->segs_in = 0;
+		newtp->segs_in = 1;
 
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
@@ -472,6 +472,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		newtp->rtt_min[0].rtt = ~0U;
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
@@ -546,6 +547,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 			newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 		newtp->rx_opt.mss_clamp = req->mss;
 		tcp_ecn_openreq_child(newtp, req);
+		newtp->fastopen_req = NULL;
 		newtp->fastopen_rsk = NULL;
 		newtp->syn_data_acked = 0;
 		newtp->rack.mstamp.v64 = 0;
@@ -818,6 +820,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
+	tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9bfc39ff2285..850d1b5bfd81 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		/* Set window scaling on max possible window
 		 * See RFC1323 for an explanation of the limit to 14
 		 */
-		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+		space = max_t(u32, space, sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		while (space > 65535 && (*rcv_wscale) < 14) {
 			space >>= 1;
@@ -1220,7 +1221,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
  * eventually). The difference is that pulled data not copied, but
  * immediately discarded.
  */
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
 {
 	struct skb_shared_info *shinfo;
 	int i, k, eat;
@@ -1230,7 +1231,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 		__skb_pull(skb, eat);
 		len -= eat;
 		if (!len)
-			return;
+			return 0;
 	}
 	eat = len;
 	k = 0;
@@ -1256,23 +1257,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	skb_reset_tail_pointer(skb);
 	skb->data_len -= len;
 	skb->len = skb->data_len;
+	return len;
 }
 
 /* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
+	u32 delta_truesize;
+
 	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
-	__pskb_trim_head(skb, len);
+	delta_truesize = __pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
-	skb->truesize	     -= len;
-	sk->sk_wmem_queued   -= len;
-	sk_mem_uncharge(sk, len);
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	if (delta_truesize) {
+		skb->truesize	   -= delta_truesize;
+		sk->sk_wmem_queued -= delta_truesize;
+		sk_mem_uncharge(sk, delta_truesize);
+		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
@@ -1949,12 +1955,14 @@ static int tcp_mtu_probe(struct sock *sk)
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
 		copy = min_t(int, skb->len, probe_size - len);
-		if (nskb->ip_summed)
+		if (nskb->ip_summed) {
 			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
-		else
-			nskb->csum = skb_copy_and_csum_bits(skb, 0,
-							    skb_put(nskb, copy),
-							    copy, nskb->csum);
+		} else {
+			__wsum csum = skb_copy_and_csum_bits(skb, 0,
+							     skb_put(nskb, copy),
+							     copy, 0);
+			nskb->csum = csum_block_add(nskb->csum, csum, len);
+		}
 
 		if (skb->len <= copy) {
 			/* We've eaten all the data from this skb.
@@ -2380,9 +2388,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
@@ -2568,7 +2578,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 * copying overhead: fragmentation, tunneling, mangling etc.
 	 */
 	if (atomic_read(&sk->sk_wmem_alloc) >
-	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+	    min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+		  sk->sk_sndbuf))
 		return -EAGAIN;
 
 	if (skb_still_in_host_queue(sk, skb))
@@ -2625,8 +2636,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
@@ -3243,6 +3256,9 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 193ba1fa8a9a..1ec12a4f327e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -223,7 +223,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -504,7 +505,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
@@ -604,7 +606,8 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
+	if (!sock_flag(sk, SOCK_KEEPOPEN) ||
+	    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)))
 		goto out;
 
 	elapsed = keepalive_time_when(tp);
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 3e6a472e6b88..92ab5bc91592 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -75,7 +75,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	if (!tcp_is_cwnd_limited(sk))
 		return;
 
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
+	if (tcp_in_slow_start(tp))
 		tcp_slow_start(tp, acked);
 
 	else if (!yeah->doing_reno_now) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7f8ab46adf61..301e60829c7e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -819,7 +819,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx && !skb_is_gso(skb)) {   /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -1275,6 +1275,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	int peeked, off = 0;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	bool checksum_valid = false;
 	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
@@ -1300,11 +1301,12 @@ try_again:
 	 */
 
 	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
-		if (udp_lib_checksum_complete(skb))
+		checksum_valid = !udp_lib_checksum_complete(skb);
+		if (!checksum_valid)
 			goto csum_copy_err;
 	}
 
-	if (skb_csum_unnecessary(skb))
+	if (checksum_valid || skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
@@ -1340,7 +1342,7 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
@@ -1531,7 +1533,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
@@ -1990,10 +1992,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f9386160cbee..6dfc3daf7c21 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -231,7 +231,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	/* Fragment the skb. IP headers of the fragments are updated in
 	 * inet_gso_segment()
@@ -299,14 +299,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
-	if (NAPI_GRO_CB(skb)->udp_mark ||
+	if (NAPI_GRO_CB(skb)->encap_mark ||
 	    (skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
 	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
-	/* mark that this skb passed once through the udp gro layer */
-	NAPI_GRO_CB(skb)->udp_mark = 1;
+	/* mark that this skb passed once through the tunnel gro layer */
+	NAPI_GRO_CB(skb)->encap_mark = 1;
 
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
@@ -339,8 +339,8 @@ unflush:
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-	pp = uo_priv->offload->callbacks.gro_receive(head, skb,
-						     uo_priv->offload);
+	pp = call_gro_receive_udp(uo_priv->offload->callbacks.gro_receive,
+				  head, skb, uo_priv->offload);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index aba428626b52..280a9bdeddee 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -89,6 +89,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e8d3da0817d3..735b22b1b4ea 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -291,9 +291,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
 static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
 				   unsigned long delay)
 {
-	if (!delayed_work_pending(&ifp->dad_work))
-		in6_ifa_hold(ifp);
-	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
+	in6_ifa_hold(ifp);
+	if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay))
+		in6_ifa_put(ifp);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -1772,17 +1772,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
 
 static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 {
-	if (ifp->flags&IFA_F_PERMANENT) {
-		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_work(ifp);
-		ifp->flags |= IFA_F_TENTATIVE;
-		if (dad_failed)
-			ifp->flags |= IFA_F_DADFAILED;
-		spin_unlock_bh(&ifp->lock);
-		if (dad_failed)
-			ipv6_ifa_notify(0, ifp);
-		in6_ifa_put(ifp);
-	} else if (ifp->flags&IFA_F_TEMPORARY) {
+	if (ifp->flags&IFA_F_TEMPORARY) {
 		struct inet6_ifaddr *ifpub;
 		spin_lock_bh(&ifp->lock);
 		ifpub = ifp->ifpub;
@@ -1795,6 +1785,16 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
+	} else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) {
+		spin_lock_bh(&ifp->lock);
+		addrconf_del_dad_work(ifp);
+		ifp->flags |= IFA_F_TENTATIVE;
+		if (dad_failed)
+			ifp->flags |= IFA_F_DADFAILED;
+		spin_unlock_bh(&ifp->lock);
+		if (dad_failed)
+			ipv6_ifa_notify(0, ifp);
+		in6_ifa_put(ifp);
 	} else {
 		ipv6_del_addr(ifp);
 	}
@@ -1898,6 +1898,7 @@ errdad:
 	spin_unlock_bh(&ifp->lock);
 
 	addrconf_mod_dad_work(ifp, 0);
+	in6_ifa_put(ifp);
 }
 
 /* Join to solicited addr multicast group.
@@ -2915,7 +2916,7 @@ static void init_loopback(struct net_device *dev)
 				 * lo device down, release this obsolete dst and
 				 * reallocate a new router for ifa.
 				 */
-				if (sp_ifa->rt->dst.obsolete > 0) {
+				if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
 					ip6_rt_put(sp_ifa->rt);
 					sp_ifa->rt = NULL;
 				} else {
@@ -3142,6 +3143,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct inet6_dev *idev = __in6_dev_get(dev);
+	struct net *net = dev_net(dev);
 	int run_pending = 0;
 	int err;
 
@@ -3157,7 +3159,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGEMTU:
 		/* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */
 		if (dev->mtu < IPV6_MIN_MTU) {
-			addrconf_ifdown(dev, 1);
+			addrconf_ifdown(dev, dev != net->loopback_dev);
 			break;
 		}
 
@@ -3210,9 +3212,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			}
 
 			if (idev) {
-				if (idev->if_flags & IF_READY)
-					/* device is already configured. */
+				if (idev->if_flags & IF_READY) {
+					/* device is already configured -
+					 * but resend MLD reports, we might
+					 * have roamed and need to update
+					 * multicast snooping switches
+					 */
+					ipv6_mc_up(idev);
 					break;
+				}
 				idev->if_flags |= IF_READY;
 			}
 
@@ -3264,7 +3272,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			 * IPV6_MIN_MTU stop IPv6 on this interface.
 			 */
 			if (dev->mtu < IPV6_MIN_MTU)
-				addrconf_ifdown(dev, 1);
+				addrconf_ifdown(dev, dev != net->loopback_dev);
 		}
 		break;
 
@@ -3305,6 +3313,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
  */
 static struct notifier_block ipv6_dev_notf = {
 	.notifier_call = addrconf_notify,
+	.priority = ADDRCONF_NOTIFY_PRIORITY,
 };
 
 static void addrconf_type_change(struct net_device *dev, unsigned long event)
@@ -3609,6 +3618,7 @@ static void addrconf_dad_work(struct work_struct *w)
 		addrconf_dad_begin(ifp);
 		goto out;
 	} else if (action == DAD_ABORT) {
+		in6_ifa_hold(ifp);
 		addrconf_dad_stop(ifp, 1);
 		goto out;
 	}
@@ -5242,8 +5252,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 	struct net_device *dev;
 	struct inet6_dev *idev;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		idev = __in6_dev_get(dev);
 		if (idev) {
 			int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5252,7 +5261,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 				dev_disable_change(idev);
 		}
 	}
-	rcu_read_unlock();
 }
 
 static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
@@ -5940,6 +5948,8 @@ int __init addrconf_init(void)
 		goto errlo;
 	}
 
+	ip6_route_init_special_entries();
+
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		INIT_HLIST_HEAD(&inet6_addr_lst[i]);
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 428162155280..cae37bfd12ab 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -76,18 +76,22 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a
 		}
 	}
 
-	addr_type = ipv6_addr_type(&usin->sin6_addr);
-
-	if (addr_type == IPV6_ADDR_ANY) {
+	if (ipv6_addr_any(&usin->sin6_addr)) {
 		/*
 		 *	connect to self
 		 */
-		usin->sin6_addr.s6_addr[15] = 0x01;
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
 	}
 
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+
 	daddr = &usin->sin6_addr;
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		struct sockaddr_in sin;
 
 		if (__ipv6_only_sock(sk)) {
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 060a60b2f8a6..111ba55fd512 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -418,7 +418,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 		esph = (void *)skb_push(skb, 4);
 		*seqhi = esph->spi;
 		esph->spi = esph->seq_no;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi);
+		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
 		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
 	}
 
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 5c5d23e59da5..9508a20fbf61 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index ed33abf57abd..9ac4f0cef27d 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -32,7 +32,6 @@ struct fib6_rule {
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
-	struct rt6_info *rt;
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
 		.flags = FIB_LOOKUP_NOREF,
@@ -41,21 +40,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	fib_rules_lookup(net->ipv6.fib6_rules_ops,
 			 flowi6_to_flowi(fl6), flags, &arg);
 
-	rt = arg.result;
+	if (arg.result)
+		return arg.result;
 
-	if (!rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return &net->ipv6.ip6_null_entry->dst;
-	}
-
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
-		ip6_rt_put(rt);
-		rt = net->ipv6.ip6_null_entry;
-		dst_hold(&rt->dst);
-	}
-
-	return &rt->dst;
+	dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
 }
 
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
@@ -116,7 +105,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			flp6->saddr = saddr;
 		}
 		err = rt->dst.error;
-		goto out;
+		if (err != -EAGAIN)
+			goto out;
 	}
 again:
 	ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0c7e276c230e..aad8cdf15472 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -179,6 +179,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		}
 	}
 
+	free_percpu(non_pcpu_rt->rt6i_pcpu);
 	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
@@ -289,8 +290,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	struct rt6_info *rt;
 
 	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
+	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put(rt);
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
@@ -767,10 +767,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 				goto next_iter;
 			}
 
-			if (iter->dst.dev == rt->dst.dev &&
-			    iter->rt6i_idev == rt->rt6i_idev &&
-			    ipv6_addr_equal(&iter->rt6i_gateway,
-					    &rt->rt6i_gateway)) {
+			if (rt6_duplicate_nexthop(iter, rt)) {
 				if (rt->rt6i_nsiblings)
 					rt->rt6i_nsiblings = 0;
 				if (!(iter->rt6i_flags & RTF_EXPIRES))
@@ -895,6 +892,8 @@ add:
 		}
 		nsiblings = iter->rt6i_nsiblings;
 		fib6_purge_rt(iter, fn, info->nl_net);
+		if (fn->rr_ptr == iter)
+			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {
@@ -902,9 +901,13 @@ add:
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
+					if (fn->rr_ptr == iter)
+						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
 				} else {
@@ -993,7 +996,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			/* Create subtree root node */
 			sfn = node_alloc();
 			if (!sfn)
-				goto st_failure;
+				goto failure;
 
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
@@ -1009,12 +1012,12 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
-				   root, and then (in st_failure) stale node
+				   root, and then (in failure) stale node
 				   in main tree.
 				 */
 				node_free(sfn);
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 
 			/* Now link new subtree to main tree */
@@ -1028,7 +1031,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 		}
 
@@ -1070,22 +1073,22 @@ out:
 			atomic_inc(&pn->leaf->rt6i_ref);
 		}
 #endif
-		if (!(rt->dst.flags & DST_NOCACHE))
-			dst_free(&rt->dst);
+		goto failure;
 	}
 	return err;
 
-#ifdef CONFIG_IPV6_SUBTREES
-	/* Subtree creation failed, probably main tree node
-	   is orphan. If it is, shoot it.
+failure:
+	/* fn->leaf could be NULL if fn is an intermediate node and we
+	 * failed to add the new route to it in both subtree creation
+	 * failure and fib6_add_rt2node() failure case.
+	 * In both cases, fib6_repair_tree() should be called to fix
+	 * fn->leaf.
 	 */
-st_failure:
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
 		fib6_repair_tree(info->nl_net, fn);
 	if (!(rt->dst.flags & DST_NOCACHE))
 		dst_free(&rt->dst);
 	return err;
-#endif
 }
 
 /*
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e5ea177d34c6..e89135828c3d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -55,6 +55,7 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 #include <net/ip6_tunnel.h>
+#include <net/gre.h>
 
 
 static bool log_ecn_error = true;
@@ -367,35 +368,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 
 static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		u8 type, u8 code, int offset, __be32 info)
+		       u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
-	__be16 *p = (__be16 *)(skb->data + offset);
-	int grehlen = offset + 4;
+	const struct gre_base_hdr *greh;
+	const struct ipv6hdr *ipv6h;
+	int grehlen = sizeof(*greh);
 	struct ip6_tnl *t;
+	int key_off = 0;
 	__be16 flags;
+	__be32 key;
 
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			return;
-		if (flags&GRE_KEY) {
-			grehlen += 4;
-			if (flags&GRE_CSUM)
-				grehlen += 4;
-		}
+	if (!pskb_may_pull(skb, offset + grehlen))
+		return;
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	flags = greh->flags;
+	if (flags & (GRE_VERSION | GRE_ROUTING))
+		return;
+	if (flags & GRE_CSUM)
+		grehlen += 4;
+	if (flags & GRE_KEY) {
+		key_off = grehlen + offset;
+		grehlen += 4;
 	}
 
-	/* If only 8 bytes returned, keyed message will be dropped here */
-	if (!pskb_may_pull(skb, grehlen))
+	if (!pskb_may_pull(skb, offset + grehlen))
 		return;
 	ipv6h = (const struct ipv6hdr *)skb->data;
-	p = (__be16 *)(skb->data + offset);
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
 
 	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
-				flags & GRE_KEY ?
-				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
-				p[1]);
+				 key, greh->protocol);
 	if (!t)
 		return;
 
@@ -778,6 +781,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	__u32 mtu;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
@@ -884,7 +889,6 @@ static int ip6gre_xmit_other(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 = skb->protocol;
 
 	err = ip6gre_xmit2(skb, dev, 0, &fl6, encap_limit, &mtu);
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index eeca943f12dc..9e2ea4ae840d 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -62,7 +62,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	const struct net_offload *ops;
 	int proto;
 	struct frag_hdr *fptr;
-	unsigned int unfrag_ip6hlen;
 	u8 *prevhdr;
 	int offset = 0;
 	bool encap, udpfrag;
@@ -121,8 +120,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {
-			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
-			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
+			int err = ip6_find_1stfragopt(skb, &prevhdr);
+			if (err < 0) {
+				kfree_skb_list(segs);
+				return ERR_PTR(err);
+			}
+			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
 				fptr->frag_off |= htons(IP6_MF);
@@ -196,6 +199,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive) {
 		__pskb_pull(skb, skb_gro_offset(skb));
+		skb_gro_frag0_invalidate(skb);
 		proto = ipv6_gso_pull_exthdrs(skb, proto);
 		skb_gro_pull(skb, -skb_transport_offset(skb));
 		skb_reset_transport_header(skb);
@@ -247,7 +251,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -258,6 +262,19 @@ out:
 	return pp;
 }
 
+static struct sk_buff **sit_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	if (NAPI_GRO_CB(skb)->encap_mark) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	return ipv6_gro_receive(head, skb);
+}
+
 static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
@@ -302,7 +319,7 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive    = ipv6_gro_receive,
+		.gro_receive    = sit_gro_receive,
 		.gro_complete   = sit_gro_complete,
 	},
 };
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 31144c486c52..e22339fad10b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -571,7 +571,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
 
-	hlen = ip6_find_1stfragopt(skb, &prevhdr);
+	err = ip6_find_1stfragopt(skb, &prevhdr);
+	if (err < 0)
+		goto fail;
+	hlen = err;
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);
@@ -644,8 +647,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -742,13 +743,14 @@ slow_path:
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -763,8 +765,6 @@ slow_path:
 		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
 				 hroom + troom, GFP_ATOMIC);
 		if (!frag) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -793,6 +793,10 @@ slow_path:
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
 		/*
 		 *	Build fragment header.
 		 */
@@ -996,6 +1000,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		}
 	}
 #endif
+	if (ipv6_addr_v4mapped(&fl6->saddr) &&
+	    !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) {
+		err = -EAFNOSUPPORT;
+		goto out_err_release;
+	}
 
 	return 0;
 
@@ -1072,17 +1081,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
@@ -1091,8 +1095,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags,
-			const struct flowi6 *fl6)
+			int exthdrlen, int transhdrlen, int mtu,
+			unsigned int flags, const struct flowi6 *fl6)
 
 {
 	struct sk_buff *skb;
@@ -1117,7 +1121,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, exthdrlen);
 
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
@@ -1353,13 +1357,14 @@ emsgsize:
 	 */
 
 	cork->length += length;
-	if (((length > mtu) ||
-	     (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    (((length + (skb ? skb->len : headersize)) > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
-	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
-					  hh_len, fragheaderlen,
+					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
 		if (err)
 			goto error;
@@ -1429,6 +1434,11 @@ alloc_new_skb:
 			 */
 			alloclen += sizeof(struct frag_hdr);
 
+			copy = datalen - transhdrlen - fraggap;
+			if (copy < 0) {
+				err = -EINVAL;
+				goto error;
+			}
 			if (transhdrlen) {
 				skb = sock_alloc_send_skb(sk,
 						alloclen + hh_len,
@@ -1478,13 +1488,9 @@ alloc_new_skb:
 				data += fraggap;
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
-			copy = datalen - transhdrlen - fraggap;
-
-			if (copy < 0) {
-				err = -EINVAL;
-				kfree_skb(skb);
-				goto error;
-			} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+			if (copy > 0 &&
+			    getfrag(from, data + transhdrlen, offset,
+				    copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 137fca42aaa6..97cb02dc5f02 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -246,6 +246,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_any(&t->parms.raddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -253,6 +254,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    ipv6_addr_any(&t->parms.laddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -343,12 +345,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
@@ -477,18 +479,19 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
-	__u8 nexthdr = ipv6h->nexthdr;
-	__u16 off = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+	unsigned int nhoff = raw - skb->data;
+	unsigned int off = nhoff + sizeof(*ipv6h);
+	u8 next, nexthdr = ipv6h->nexthdr;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
-		__u16 optlen = 0;
 		struct ipv6_opt_hdr *hdr;
-		if (raw + off + sizeof(*hdr) > skb->data &&
-		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+		u16 optlen;
+
+		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;
 
-		hdr = (struct ipv6_opt_hdr *) (raw + off);
+		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
 			if (frag_hdr->frag_off)
@@ -499,20 +502,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
+		/* cache hdr->nexthdr, since pskb_may_pull() might
+		 * invalidate hdr
+		 */
+		next = hdr->nexthdr;
 		if (nexthdr == NEXTHDR_DEST) {
-			__u16 i = off + 2;
+			u16 i = 2;
+
+			/* Remember : hdr is no longer valid at this point. */
+			if (!pskb_may_pull(skb, off + optlen))
+				break;
+
 			while (1) {
 				struct ipv6_tlv_tnl_enc_lim *tel;
 
 				/* No more room for encapsulation limit */
-				if (i + sizeof (*tel) > off + optlen)
+				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+				tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-					return i;
+					return i + off - nhoff;
 				/* else jump to next option */
 				if (tel->type)
 					i += tel->length + 2;
@@ -520,7 +532,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 					i++;
 			}
 		}
-		nexthdr = hdr->nexthdr;
+		nexthdr = next;
 		off += optlen;
 	}
 	return 0;
@@ -1037,10 +1049,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
+	bool use_cache = false;
 	int mtu;
 	unsigned int max_headroom = sizeof(struct ipv6hdr);
 	u8 proto;
@@ -1048,27 +1061,37 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
 
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
 
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
+
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
 
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
 
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
+	} else if (!(t->parms.flags &
+		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only only if the routing decision does
+		 * not depend on the current inner header value
+		 */
+		use_cache = true;
+	}
 
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
-	} else if (!fl6->flowi6_mark)
+	if (use_cache)
 		dst = ip6_tnl_dst_get(t);
 
 	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
@@ -1132,7 +1155,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		skb = new_skb;
 	}
 
-	if (!fl6->flowi6_mark && ndst)
+	if (use_cache && ndst)
 		ip6_tnl_dst_set(t, ndst);
 	skb_dst_set(skb, dst);
 
@@ -1180,6 +1203,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 0a8610b33d79..bdcc4d9cedd3 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -680,6 +680,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
 	u->link = p->link;
 	u->i_key = p->i_key;
 	u->o_key = p->o_key;
+	if (u->i_key)
+		u->i_flags |= GRE_KEY;
+	if (u->o_key)
+		u->o_flags |= GRE_KEY;
 	u->proto = p->proto;
 
 	memcpy(u->name, p->name, sizeof(u->name));
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a10e77103c88..8361d73ab653 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -774,7 +774,8 @@ failure:
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+		       struct list_head *head)
 {
 	struct mif_device *v;
 	struct net_device *dev;
@@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 					     dev->ifindex, &in6_dev->cnf);
 	}
 
-	if (v->flags & MIFF_REGISTER)
+	if ((v->flags & MIFF_REGISTER) && !notify)
 		unregister_netdevice_queue(dev, head);
 
 	dev_put(dev);
@@ -1074,6 +1075,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (!c)
 		return NULL;
+	c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 	c->mfc_un.res.minvif = MAXMIFS;
 	return c;
 }
@@ -1329,7 +1331,6 @@ static int ip6mr_device_event(struct notifier_block *this,
 	struct mr6_table *mrt;
 	struct mif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
@@ -1338,10 +1339,9 @@ static int ip6mr_device_event(struct notifier_block *this,
 		v = &mrt->vif6_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				mif6_delete(mrt, ct, &list);
+				mif6_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 
 	return NOTIFY_DONE;
 }
@@ -1550,7 +1550,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 	for (i = 0; i < mrt->maxvif; i++) {
 		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
 			continue;
-		mif6_delete(mrt, i, &list);
+		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1703,7 +1703,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
-		ret = mif6_delete(mrt, mifi, NULL);
+		ret = mif6_delete(mrt, mifi, 0, NULL);
 		rtnl_unlock();
 		return ret;
 
@@ -2275,8 +2275,8 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	return 1;
 }
 
-int ip6mr_get_route(struct net *net,
-		    struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
+		    int nowait, u32 portid)
 {
 	int err;
 	struct mr6_table *mrt;
@@ -2321,6 +2321,7 @@ int ip6mr_get_route(struct net *net,
 			return -ENOMEM;
 		}
 
+		NETLINK_CB(skb2).portid = portid;
 		skb_reset_transport_header(skb2);
 
 		skb_put(skb2, sizeof(struct ipv6hdr));
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 5ee56d0a8699..d64ee7e83664 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 99425cf2819b..22f39e00bef3 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -198,11 +198,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ip6t_ip6 *ipv6)
+static inline bool unconditional(const struct ip6t_entry *e)
 {
 	static const struct ip6t_ip6 uncond;
 
-	return memcmp(ipv6, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ip6t_entry) &&
+	       memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0;
 }
 
 static inline const struct xt_entry_target *
@@ -258,11 +259,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ip6t_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		    t->verdict < 0 &&
-		    unconditional(&s->ipv6)) {
+		    t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP6_TRACE_COMMENT_POLICY]
@@ -455,6 +455,18 @@ ip6t_do_table(struct sk_buff *skb,
 #endif
 }
 
+static bool find_jump_target(const struct xt_table_info *t,
+			     const struct ip6t_entry *target)
+{
+	struct ip6t_entry *iter;
+
+	xt_entry_foreach(iter, t->entries, t->size) {
+		 if (iter == target)
+			return true;
+	}
+	return false;
+}
+
 /* Figures out from what hook each rule can be called: returns 0 if
    there are loops.  Puts hook bitmask in comefrom. */
 static int
@@ -488,11 +500,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ip6t_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 &&
-			     unconditional(&e->ipv6)) || visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -533,6 +544,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct ip6t_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -551,9 +564,15 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					e = (struct ip6t_entry *)
+						(entry0 + newpos);
+					if (!find_jump_target(newinfo, e))
+						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct ip6t_entry *)
 					(entry0 + newpos);
@@ -580,27 +599,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 	module_put(par.match->me);
 }
 
-static int
-check_entry(const struct ip6t_entry *e, const char *name)
-{
-	const struct xt_entry_target *t;
-
-	if (!ip6_checkentry(&e->ipv6)) {
-		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
-		return -EINVAL;
-	}
-
-	if (e->target_offset + sizeof(struct xt_entry_target) >
-	    e->next_offset)
-		return -EINVAL;
-
-	t = ip6t_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
 {
 	const struct ip6t_ip6 *ipv6 = par->entryinfo;
@@ -679,10 +677,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	e->counters.pcnt = xt_percpu_counter_alloc();
 	if (IS_ERR_VALUE(e->counters.pcnt))
 		return -ENOMEM;
@@ -733,7 +727,7 @@ static bool check_underflow(const struct ip6t_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ipv6))
+	if (!unconditional(e))
 		return false;
 	t = ip6t_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -753,9 +747,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -767,6 +763,14 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 		return -EINVAL;
 	}
 
+	if (!ip6_checkentry(&e->ipv6))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -775,9 +779,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
@@ -1321,55 +1325,16 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 	unsigned int i;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	struct ip6t_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
-
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
 
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
-
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
-
-	t = xt_find_table_lock(net, AF_INET6, name);
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
+	t = xt_find_table_lock(net, AF_INET6, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1377,7 +1342,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
@@ -1456,7 +1421,6 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr,
 
 static int
 compat_find_calc_match(struct xt_entry_match *m,
-		       const char *name,
 		       const struct ip6t_ip6 *ipv6,
 		       int *size)
 {
@@ -1491,21 +1455,19 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned char *limit)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
 	unsigned int j;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
@@ -1517,8 +1479,11 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ip6t_entry *)e, name);
+	if (!ip6_checkentry(&e->ipv6))
+		return -EINVAL;
+
+	ret = xt_compat_check_entry_offsets(e, e->elems,
+					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
@@ -1526,7 +1491,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	entry_offset = (void *)e - (void *)base;
 	j = 0;
 	xt_ematch_foreach(ematch, e) {
-		ret = compat_find_calc_match(ematch, name, &e->ipv6, &off);
+		ret = compat_find_calc_match(ematch, &e->ipv6, &off);
 		if (ret != 0)
 			goto release_matches;
 		++j;
@@ -1549,17 +1514,6 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	if (ret)
 		goto out;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 out:
@@ -1573,18 +1527,17 @@ release_matches:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
 	struct ip6t_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 	struct xt_entry_match *ematch;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct ip6t_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct ip6t_entry));
@@ -1593,11 +1546,9 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 	*dstptr += sizeof(struct ip6t_entry);
 	*size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry);
 
-	xt_ematch_foreach(ematch, e) {
-		ret = xt_compat_match_from_user(ematch, dstptr, size);
-		if (ret != 0)
-			return ret;
-	}
+	xt_ematch_foreach(ematch, e)
+		xt_compat_match_from_user(ematch, dstptr, size);
+
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ip6t_get_target(e);
 	xt_compat_target_from_user(t, dstptr, size);
@@ -1609,183 +1560,83 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
-}
-
-static int compat_check_entry(struct ip6t_entry *e, struct net *net,
-			      const char *name)
-{
-	unsigned int j;
-	int ret = 0;
-	struct xt_mtchk_param mtpar;
-	struct xt_entry_match *ematch;
-
-	e->counters.pcnt = xt_percpu_counter_alloc();
-	if (IS_ERR_VALUE(e->counters.pcnt))
-		return -ENOMEM;
-	j = 0;
-	mtpar.net	= net;
-	mtpar.table     = name;
-	mtpar.entryinfo = &e->ipv6;
-	mtpar.hook_mask = e->comefrom;
-	mtpar.family    = NFPROTO_IPV6;
-	xt_ematch_foreach(ematch, e) {
-		ret = check_match(ematch, &mtpar);
-		if (ret != 0)
-			goto cleanup_matches;
-		++j;
-	}
-
-	ret = check_target(e, net, name);
-	if (ret)
-		goto cleanup_matches;
-	return 0;
-
- cleanup_matches:
-	xt_ematch_foreach(ematch, e) {
-		if (j-- == 0)
-			break;
-		cleanup_match(ematch, net);
-	}
-
-	xt_percpu_counter_free(e->counters.pcnt);
-
-	return ret;
 }
 
 static int
 translate_compat_table(struct net *net,
-		       const char *name,
-		       unsigned int valid_hooks,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
-		       unsigned int total_size,
-		       unsigned int number,
-		       unsigned int *hook_entries,
-		       unsigned int *underflows)
+		       const struct compat_ip6t_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_ip6t_entry *iter0;
-	struct ip6t_entry *iter1;
+	struct ip6t_replace repl;
 	unsigned int size;
 	int ret = 0;
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
-
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET6);
-	xt_compat_init_offsets(AF_INET6, number);
+	xt_compat_init_offsets(AF_INET6, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries;
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone. */
 	xt_compat_flush_offsets(AF_INET6);
 	xt_compat_unlock(AF_INET6);
-	if (ret)
-		goto free_newinfo;
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(ip6t_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1, net);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(net, newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
+
 	*pinfo = newinfo;
 	*pentry0 = entry1;
 	xt_free_table_info(info);
@@ -1793,17 +1644,16 @@ translate_compat_table(struct net *net,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(AF_INET6);
+	xt_compat_unlock(AF_INET6);
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(AF_INET6);
-	xt_compat_unlock(AF_INET6);
-	goto out;
 }
 
 static int
@@ -1839,10 +1689,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 462f2a76b5c2..f9f02581c4ca 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -78,15 +78,15 @@ EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
-	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
+	unsigned int offset = sizeof(struct ipv6hdr);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
 	*nexthdr = &ipv6_hdr(skb)->nexthdr;
 
-	while (offset + 1 <= packet_len) {
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
+		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -107,13 +107,19 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			return offset;
 		}
 
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+			return -EINVAL;
+
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
+		len = ipv6_optlen(exthdr);
+		if (len + offset >= IPV6_MAXPLEN)
+			return -EINVAL;
+		offset += len;
+		*nexthdr = &exthdr->nexthdr;
 	}
 
-	return offset;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ip6_find_1stfragopt);
 
@@ -148,6 +154,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(len);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
+	skb->protocol = htons(ETH_P_IPV6);
+
 	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
 		       net, sk, skb, NULL, skb_dst(skb)->dev,
 		       dst_output);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 263a5164a6f5..a830b68e63c9 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -50,7 +50,7 @@ static struct inet_protosw pingv6_protosw = {
 	.type =      SOCK_DGRAM,
 	.protocol =  IPPROTO_ICMPV6,
 	.prot =      &pingv6_prot,
-	.ops =       &inet6_dgram_ops,
+	.ops =       &inet6_sockraw_ops,
 	.flags =     INET_PROTOSW_REUSE,
 };
 
@@ -150,8 +150,10 @@ int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	rt = (struct rt6_info *) dst;
 
 	np = inet6_sk(sk);
-	if (!np)
-		return -EBADF;
+	if (!np) {
+		err = -EBADF;
+		goto dst_err_out;
+	}
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
 		fl6.flowi6_oif = np->mcast_oif;
@@ -186,6 +188,9 @@ int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 	release_sock(sk);
 
+dst_err_out:
+	dst_release(dst);
+
 	if (err)
 		return err;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 99140986e887..4d52a0e2f60d 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -589,7 +589,11 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	}
 
 	offset += skb_transport_offset(skb);
-	BUG_ON(skb_copy_bits(skb, offset, &csum, 2));
+	err = skb_copy_bits(skb, offset, &csum, 2);
+	if (err < 0) {
+		ip6_flush_pending_frames(sk);
+		goto out;
+	}
 
 	/* in case cksum was not initialized */
 	if (unlikely(csum))
@@ -626,6 +630,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct ipv6hdr))
+		return -EINVAL;
 	if (flags&MSG_PROBE)
 		goto out;
 
@@ -1140,8 +1146,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
@@ -1298,7 +1303,7 @@ void raw6_proc_exit(void)
 #endif	/* CONFIG_PROC_FS */
 
 /* Same as inet6_dgram_ops, sans udp_poll.  */
-static const struct proto_ops inet6_sockraw_ops = {
+const struct proto_ops inet6_sockraw_ops = {
 	.family		   = PF_INET6,
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 45f5ae51de65..a234552a7e3d 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -496,10 +496,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_COMPLETE)
-		head->csum = csum_partial(skb_network_header(head),
-					  skb_network_header_len(head),
-					  head->csum);
+	skb_postpush_rcsum(head, skb_network_header(head),
+			   skb_network_header_len(head));
 
 	rcu_read_lock();
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3f164d3aaee2..ef335070e98a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1727,6 +1727,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 		} else {
 			val = nla_get_u32(nla);
 		}
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			goto err;
 
@@ -1756,6 +1758,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 	int addr_type;
 	int err = -EINVAL;
 
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU)
+		goto out;
+
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
 		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
@@ -2082,6 +2088,8 @@ static int ip6_route_del(struct fib6_config *cfg)
 				continue;
 			if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
 				continue;
+			if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
+				continue;
 			dst_hold(&rt->dst);
 			read_unlock_bh(&table->tb6_lock);
 
@@ -2825,17 +2833,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
 				 struct rt6_info *rt, struct fib6_config *r_cfg)
 {
 	struct rt6_nh *nh;
-	struct rt6_info *rtnh;
 	int err = -EEXIST;
 
 	list_for_each_entry(nh, rt6_nh_list, next) {
 		/* check if rt6_info already exists */
-		rtnh = nh->rt6_info;
-
-		if (rtnh->dst.dev == rt->dst.dev &&
-		    rtnh->rt6i_idev == rt->rt6i_idev &&
-		    ipv6_addr_equal(&rtnh->rt6i_gateway,
-				    &rt->rt6i_gateway))
+		if (rt6_duplicate_nexthop(nh->rt6_info, rt))
 			return err;
 	}
 
@@ -3138,7 +3140,9 @@ static int rt6_fill_node(struct net *net,
 	if (iif) {
 #ifdef CONFIG_IPV6_MROUTE
 		if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
-			int err = ip6mr_get_route(net, skb, rtm, nowait);
+			int err = ip6mr_get_route(net, skb, rtm, nowait,
+						  portid);
+
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
@@ -3192,7 +3196,8 @@ static int rt6_fill_node(struct net *net,
 	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
 		goto nla_put_failure;
 
-	lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+	if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
 	return 0;
@@ -3352,7 +3357,10 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
-	if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
+	if (!(dev->flags & IFF_LOOPBACK))
+		return NOTIFY_OK;
+
+	if (event == NETDEV_REGISTER) {
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -3361,6 +3369,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
 		net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
 #endif
+	 } else if (event == NETDEV_UNREGISTER) {
+		in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+		in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev);
+		in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev);
+#endif
 	}
 
 	return NOTIFY_OK;
@@ -3667,9 +3681,24 @@ static struct pernet_operations ip6_route_net_late_ops = {
 
 static struct notifier_block ip6_route_dev_notifier = {
 	.notifier_call = ip6_route_dev_notify,
-	.priority = 0,
+	.priority = ADDRCONF_NOTIFY_PRIORITY - 10,
 };
 
+void __init ip6_route_init_special_entries(void)
+{
+	/* Registering of the loopback is done before this portion of code,
+	 * the loopback reference in rt6_info will not be taken, do it
+	 * manually for init_net */
+	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
+	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #endif
+}
+
 int __init ip6_route_init(void)
 {
 	int ret;
@@ -3696,17 +3725,6 @@ int __init ip6_route_init(void)
 
 	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
 
-	/* Registering of the loopback is done before this portion of code,
-	 * the loopback reference in rt6_info will not be taken, do it
-	 * manually for init_net */
-	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #endif
 	ret = fib6_init();
 	if (ret)
 		goto out_register_subsys;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dcccae86190f..184f0fe35dc6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -560,13 +560,13 @@ 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->parms.link, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
 		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      IPPROTO_IPV6, 0);
+			      iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
@@ -681,14 +681,15 @@ static int ipip6_rcv(struct sk_buff *skb)
 		skb->mac_header = skb->network_header;
 		skb_reset_network_header(skb);
 		IPCB(skb)->flags = 0;
-		skb->protocol = htons(ETH_P_IPV6);
+		skb->dev = tunnel->dev;
 
 		if (packet_is_spoofed(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
 			goto out;
 		}
 
-		__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
+		if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6)))
+			goto out;
 
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
@@ -1388,6 +1389,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
 	if (!tunnel->dst_cache) {
 		free_percpu(dev->tstats);
+		dev->tstats = NULL;
 		return -ENOMEM;
 	}
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index eaf7ac496d50..aee87282d352 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -210,6 +210,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->snt_synack.v64	= 0;
 	treq->rcv_isn = ntohl(th->seq) - 1;
 	treq->snt_isn = cookie;
+	treq->txhash = net_tx_rndhash();
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b8d405623f4f..59c908ff251a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -149,8 +149,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	connect() to INADDR_ANY means loopback (BSD'ism).
 	 */
 
-	if (ipv6_addr_any(&usin->sin6_addr))
-		usin->sin6_addr.s6_addr[15] = 0x1;
+	if (ipv6_addr_any(&usin->sin6_addr)) {
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
+	}
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
@@ -189,7 +194,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	TCP over IPv4
 	 */
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		u32 exthdrlen = icsk->icsk_ext_hdr_len;
 		struct sockaddr_in sin;
 
@@ -376,10 +381,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
@@ -932,9 +939,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
+	/* RFC 7323 2.3
+	 * The window field (SEG.WND) of every outgoing segment, with the
+	 * exception of <SYN> segments, MUST be right-shifted by
+	 * Rcv.Wind.Shift bits:
+	 */
 	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
-			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+			tcp_rsk(req)->rcv_nxt,
+			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
@@ -968,6 +981,16 @@ drop:
 	return 0; /* don't send reset */
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
@@ -1015,6 +1038,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
 #endif
 
+		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
@@ -1084,6 +1108,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	   First: no IPv4 options.
 	 */
 	newinet->inet_opt = NULL;
+	newnp->ipv6_mc_list = NULL;
 	newnp->ipv6_ac_list = NULL;
 	newnp->ipv6_fl_list = NULL;
 
@@ -1157,8 +1182,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 						      sk_gfp_atomic(sk, GFP_ATOMIC));
 			consume_skb(ireq->pktopts);
 			ireq->pktopts = NULL;
-			if (newnp->pktoptions)
+			if (newnp->pktoptions) {
+				tcp_v6_restore_cb(newnp->pktoptions);
 				skb_set_owner_r(newnp->pktoptions, newsk);
+			}
 		}
 	}
 
@@ -1198,7 +1225,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_do_rcv(sk, skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard;
 
 	/*
@@ -1302,6 +1329,7 @@ ipv6_pktoptions:
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
+			tcp_v6_restore_cb(opt_skb);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
 			__kfree_skb(opt_skb);
@@ -1335,15 +1363,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->sacked = 0;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
@@ -1430,8 +1449,10 @@ process:
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	hdr = ipv6_hdr(skb);
 
 	skb->dev = NULL;
 
@@ -1706,7 +1727,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9da3287a3923..6fd4af3b5b79 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -402,6 +402,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int peeked, off = 0;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	bool checksum_valid = false;
 	int is_udp4;
 	bool slow;
 
@@ -433,11 +434,12 @@ try_again:
 	 */
 
 	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
-		if (udp_lib_checksum_complete(skb))
+		checksum_valid = !udp_lib_checksum_complete(skb);
+		if (!checksum_valid)
 			goto csum_copy_err;
 	}
 
-	if (skb_csum_unnecessary(skb))
+	if (checksum_valid || skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
@@ -496,7 +498,8 @@ try_again:
 
 	if (is_udp4) {
 		if (inet->cmsg_flags)
-			ip_cmsg_recv(msg, skb);
+			ip_cmsg_recv_offset(msg, skb,
+					    sizeof(struct udphdr), off);
 	} else {
 		if (np->rxopt.all)
 			ip6_datagram_recv_specific_ctl(sk, msg, skb);
@@ -647,7 +650,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
@@ -837,8 +840,8 @@ start_lookup:
 		flush_stack(stack, count, skb, count - 1);
 	} else {
 		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
+			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					  proto == IPPROTO_UDPLITE);
 		consume_skb(skb);
 	}
 	return 0;
@@ -916,11 +919,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
+		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
-			return -ret;
+			return ret;
 
 		return 0;
 	}
@@ -1135,6 +1136,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			if (addr_len < SIN6_LEN_RFC2133)
 				return -EINVAL;
 			daddr = &sin6->sin6_addr;
+			if (ipv6_addr_any(daddr) &&
+			    ipv6_addr_v4mapped(&np->saddr))
+				ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+						       daddr);
 			break;
 		case AF_INET:
 			goto do_udp_sendmsg;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 7441e1e63893..2e3c12eeca07 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	u8 frag_hdr_sz = sizeof(struct frag_hdr);
 	__wsum csum;
 	int tnl_hlen;
+	int err;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -85,7 +86,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
 
-		skb->ip_summed = CHECKSUM_NONE;
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		/* Check if there is enough headroom to insert fragment header. */
 		tnl_hlen = skb_tnl_header_len(skb);
@@ -97,7 +98,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		/* Find the unfragmentable header and shift it left by frag_hdr_sz
 		 * bytes to insert fragment header.
 		 */
-		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index 0e015906f9ca..07d36573f50b 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -47,6 +47,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ipv6_hdr(skb);
 
 	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
 	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->transport_header = skb->network_header + hdr_len;
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 4e344105b3fd..1d3bbe6e1183 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -28,6 +28,8 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ipv6_hdr(skb);
 
 	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
 	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
 	skb_set_network_header(skb, -x->props.header_len);
 	skb->transport_header = skb->network_header + hdr_len;
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 48d0dc89b58d..e735f781e4f3 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1168,11 +1168,10 @@ static int ipxitf_ioctl(unsigned int cmd, void __user *arg)
 		sipx->sipx_network	= ipxif->if_netnum;
 		memcpy(sipx->sipx_node, ipxif->if_node,
 			sizeof(sipx->sipx_node));
-		rc = -EFAULT;
+		rc = 0;
 		if (copy_to_user(arg, &ifr, sizeof(ifr)))
-			break;
+			rc = -EFAULT;
 		ipxitf_put(ipxif);
-		rc = 0;
 		break;
 	}
 	case SIOCAIPXITFCRT:
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 923abd6b3064..4a116d766c15 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	}
 
 	/* Check if we have opened a local TSAP */
-	if (!self->tsap)
-		irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+	if (!self->tsap) {
+		err = irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+		if (err)
+			goto out;
+	}
 
 	/* Move to connecting socket, start sending Connect Requests */
 	sock->state = SS_CONNECTING;
@@ -2224,7 +2227,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
-	struct irda_device_list list;
+	struct irda_device_list list = { 0 };
 	struct irda_device_info *discoveries;
 	struct irda_ias_set *	ias_opt;	/* IAS get/query params */
 	struct ias_object *	ias_obj;	/* Object in IAS */
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index 4a7ae32afa09..1138eaf5c682 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
 
 	self->magic = IAS_MAGIC;
 	self->mode = mode;
-	if (mode == IAS_CLIENT)
-		iriap_register_lsap(self, slsap_sel, mode);
+	if (mode == IAS_CLIENT) {
+		if (iriap_register_lsap(self, slsap_sel, mode)) {
+			kfree(self);
+			return NULL;
+		}
+	}
 
 	self->confirm = callback;
 	self->priv = priv;
diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index acbe61c7e683..160dc89335e2 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new);
  *    for deallocating this structure if it's complex. If not the user can
  *    just supply kfree, which should take care of the job.
  */
-#ifdef CONFIG_LOCKDEP
-static int hashbin_lock_depth = 0;
-#endif
 int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 {
 	irda_queue_t* queue;
@@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;);
 
 	/* Synchronize */
-	if ( hashbin->hb_type & HB_LOCK ) {
-		spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags,
-					 hashbin_lock_depth++);
-	}
+	if (hashbin->hb_type & HB_LOCK)
+		spin_lock_irqsave(&hashbin->hb_spinlock, flags);
 
 	/*
 	 *  Free the entries in the hashbin, TODO: use hashbin_clear when
 	 *  it has been shown to work
 	 */
 	for (i = 0; i < HASHBIN_SIZE; i ++ ) {
-		queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
-		while (queue ) {
-			if (free_func)
-				(*free_func)(queue);
-			queue = dequeue_first(
-				(irda_queue_t**) &hashbin->hb_queue[i]);
+		while (1) {
+			queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
+
+			if (!queue)
+				break;
+
+			if (free_func) {
+				if (hashbin->hb_type & HB_LOCK)
+					spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
+				free_func(queue);
+				if (hashbin->hb_type & HB_LOCK)
+					spin_lock_irqsave(&hashbin->hb_spinlock, flags);
+			}
 		}
 	}
 
@@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	hashbin->magic = ~HB_MAGIC;
 
 	/* Release lock */
-	if ( hashbin->hb_type & HB_LOCK) {
+	if (hashbin->hb_type & HB_LOCK)
 		spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
-#ifdef CONFIG_LOCKDEP
-		hashbin_lock_depth--;
-#endif
-	}
 
 	/*
 	 *  Free the hashbin structure
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f9c9ecb0cdd3..94bf810ad242 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -63,8 +63,13 @@ struct pfkey_sock {
 		} u;
 		struct sk_buff	*skb;
 	} dump;
+	struct mutex dump_lock;
 };
 
+static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
+			       xfrm_address_t *saddr, xfrm_address_t *daddr,
+			       u16 *family);
+
 static inline struct pfkey_sock *pfkey_sk(struct sock *sk)
 {
 	return (struct pfkey_sock *)sk;
@@ -139,6 +144,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
 	struct sock *sk;
+	struct pfkey_sock *pfk;
 	int err;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -153,6 +159,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	if (sk == NULL)
 		goto out;
 
+	pfk = pfkey_sk(sk);
+	mutex_init(&pfk->dump_lock);
+
 	sock->ops = &pfkey_ops;
 	sock_init_data(sock, sk);
 
@@ -219,7 +228,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 #define BROADCAST_ONE		1
 #define BROADCAST_REGISTERED	2
 #define BROADCAST_PROMISC_ONLY	4
-static int pfkey_broadcast(struct sk_buff *skb,
+static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 			   int broadcast_flags, struct sock *one_sk,
 			   struct net *net)
 {
@@ -269,7 +278,7 @@ static int pfkey_broadcast(struct sk_buff *skb,
 	rcu_read_unlock();
 
 	if (one_sk != NULL)
-		err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk);
+		err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
 
 	kfree_skb(skb2);
 	kfree_skb(skb);
@@ -281,23 +290,36 @@ static int pfkey_do_dump(struct pfkey_sock *pfk)
 	struct sadb_msg *hdr;
 	int rc;
 
+	mutex_lock(&pfk->dump_lock);
+	if (!pfk->dump.dump) {
+		rc = 0;
+		goto out;
+	}
+
 	rc = pfk->dump.dump(pfk);
-	if (rc == -ENOBUFS)
-		return 0;
+	if (rc == -ENOBUFS) {
+		rc = 0;
+		goto out;
+	}
 
 	if (pfk->dump.skb) {
-		if (!pfkey_can_dump(&pfk->sk))
-			return 0;
+		if (!pfkey_can_dump(&pfk->sk)) {
+			rc = 0;
+			goto out;
+		}
 
 		hdr = (struct sadb_msg *) pfk->dump.skb->data;
 		hdr->sadb_msg_seq = 0;
 		hdr->sadb_msg_errno = rc;
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 		pfk->dump.skb = NULL;
 	}
 
 	pfkey_terminate_dump(pfk);
+
+out:
+	mutex_unlock(&pfk->dump_lock);
 	return rc;
 }
 
@@ -333,7 +355,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) /
 			     sizeof(uint64_t));
 
-	pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1135,6 +1157,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 			goto out;
 	}
 
+	err = -ENOBUFS;
 	key = ext_hdrs[SADB_EXT_KEY_AUTH - 1];
 	if (sa->sadb_sa_auth) {
 		int keysize = 0;
@@ -1146,8 +1169,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 		if (key)
 			keysize = (key->sadb_key_bits + 7) / 8;
 		x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL);
-		if (!x->aalg)
+		if (!x->aalg) {
+			err = -ENOMEM;
 			goto out;
+		}
 		strcpy(x->aalg->alg_name, a->name);
 		x->aalg->alg_key_len = 0;
 		if (key) {
@@ -1166,8 +1191,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 				goto out;
 			}
 			x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL);
-			if (!x->calg)
+			if (!x->calg) {
+				err = -ENOMEM;
 				goto out;
+			}
 			strcpy(x->calg->alg_name, a->name);
 			x->props.calgo = sa->sadb_sa_encrypt;
 		} else {
@@ -1181,8 +1208,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 			if (key)
 				keysize = (key->sadb_key_bits + 7) / 8;
 			x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL);
-			if (!x->ealg)
+			if (!x->ealg) {
+				err = -ENOMEM;
 				goto out;
+			}
 			strcpy(x->ealg->alg_name, a->name);
 			x->ealg->alg_key_len = 0;
 			if (key) {
@@ -1227,8 +1256,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 		struct xfrm_encap_tmpl *natt;
 
 		x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL);
-		if (!x->encap)
+		if (!x->encap) {
+			err = -ENOMEM;
 			goto out;
+		}
 
 		natt = x->encap;
 		n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1];
@@ -1365,7 +1396,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 
 	xfrm_state_put(x);
 
-	pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net);
+	pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net);
 
 	return 0;
 }
@@ -1452,7 +1483,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c)
 	hdr->sadb_msg_seq = c->seq;
 	hdr->sadb_msg_pid = c->portid;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x));
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x));
 
 	return 0;
 }
@@ -1565,7 +1596,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg
 	out_hdr->sadb_msg_reserved = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1670,8 +1701,8 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		return -ENOBUFS;
 	}
 
-	pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk));
-
+	pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk,
+			sock_net(sk));
 	return 0;
 }
 
@@ -1689,7 +1720,8 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr)
 	hdr->sadb_msg_errno = (uint8_t) 0;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 
-	return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk,
+			       sock_net(sk));
 }
 
 static int key_notify_sa_flush(const struct km_event *c)
@@ -1710,7 +1742,7 @@ static int key_notify_sa_flush(const struct km_event *c)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 
 	return 0;
 }
@@ -1767,7 +1799,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -1793,19 +1825,26 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	struct xfrm_address_filter *filter = NULL;
 	struct pfkey_sock *pfk = pfkey_sk(sk);
 
-	if (pfk->dump.dump != NULL)
+	mutex_lock(&pfk->dump_lock);
+	if (pfk->dump.dump != NULL) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EBUSY;
+	}
 
 	proto = pfkey_satype2proto(hdr->sadb_msg_satype);
-	if (proto == 0)
+	if (proto == 0) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EINVAL;
+	}
 
 	if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
 		struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
 
 		filter = kmalloc(sizeof(*filter), GFP_KERNEL);
-		if (filter == NULL)
+		if (filter == NULL) {
+			mutex_unlock(&pfk->dump_lock);
 			return -ENOMEM;
+		}
 
 		memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr,
 		       sizeof(xfrm_address_t));
@@ -1821,6 +1860,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	pfk->dump.dump = pfkey_dump_sa;
 	pfk->dump.done = pfkey_dump_sa_done;
 	xfrm_state_walk_init(&pfk->dump.u.state, proto, filter);
+	mutex_unlock(&pfk->dump_lock);
 
 	return pfkey_do_dump(pfk);
 }
@@ -1847,7 +1887,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb
 		new_hdr->sadb_msg_errno = 0;
 	}
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk));
 	return 0;
 }
 
@@ -1913,19 +1953,14 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 
 	/* addresses present only in tunnel mode */
 	if (t->mode == XFRM_MODE_TUNNEL) {
-		u8 *sa = (u8 *) (rq + 1);
-		int family, socklen;
-
-		family = pfkey_sockaddr_extract((struct sockaddr *)sa,
-						&t->saddr);
-		if (!family)
-			return -EINVAL;
+		int err;
 
-		socklen = pfkey_sockaddr_len(family);
-		if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen),
-					   &t->id.daddr) != family)
-			return -EINVAL;
-		t->encap_family = family;
+		err = parse_sockaddr_pair(
+			(struct sockaddr *)(rq + 1),
+			rq->sadb_x_ipsecrequest_len - sizeof(*rq),
+			&t->saddr, &t->id.daddr, &t->encap_family);
+		if (err)
+			return err;
 	} else
 		t->encap_family = xp->family;
 
@@ -1945,7 +1980,11 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol)
 	if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy))
 		return -EINVAL;
 
-	while (len >= sizeof(struct sadb_x_ipsecrequest)) {
+	while (len >= sizeof(*rq)) {
+		if (len < rq->sadb_x_ipsecrequest_len ||
+		    rq->sadb_x_ipsecrequest_len < sizeof(*rq))
+			return -EINVAL;
+
 		if ((err = parse_ipsecrequest(xp, rq)) < 0)
 			return err;
 		len -= rq->sadb_x_ipsecrequest_len;
@@ -2181,7 +2220,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = c->seq;
 	out_hdr->sadb_msg_pid = c->portid;
-	pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp));
 	return 0;
 
 }
@@ -2401,14 +2440,13 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp));
 	err = 0;
 
 out:
 	return err;
 }
 
-#ifdef CONFIG_NET_KEY_MIGRATE
 static int pfkey_sockaddr_pair_size(sa_family_t family)
 {
 	return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2);
@@ -2420,7 +2458,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
 {
 	int af, socklen;
 
-	if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
+	if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
 		return -EINVAL;
 
 	af = pfkey_sockaddr_extract(sa, saddr);
@@ -2436,6 +2474,7 @@ static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
 	return 0;
 }
 
+#ifdef CONFIG_NET_KEY_MIGRATE
 static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 				    struct xfrm_migrate *m)
 {
@@ -2443,13 +2482,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 	struct sadb_x_ipsecrequest *rq2;
 	int mode;
 
-	if (len <= sizeof(struct sadb_x_ipsecrequest) ||
-	    len < rq1->sadb_x_ipsecrequest_len)
+	if (len < sizeof(*rq1) ||
+	    len < rq1->sadb_x_ipsecrequest_len ||
+	    rq1->sadb_x_ipsecrequest_len < sizeof(*rq1))
 		return -EINVAL;
 
 	/* old endoints */
 	err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1),
-				  rq1->sadb_x_ipsecrequest_len,
+				  rq1->sadb_x_ipsecrequest_len - sizeof(*rq1),
 				  &m->old_saddr, &m->old_daddr,
 				  &m->old_family);
 	if (err)
@@ -2458,13 +2498,14 @@ static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
 	rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len);
 	len -= rq1->sadb_x_ipsecrequest_len;
 
-	if (len <= sizeof(struct sadb_x_ipsecrequest) ||
-	    len < rq2->sadb_x_ipsecrequest_len)
+	if (len <= sizeof(*rq2) ||
+	    len < rq2->sadb_x_ipsecrequest_len ||
+	    rq2->sadb_x_ipsecrequest_len < sizeof(*rq2))
 		return -EINVAL;
 
 	/* new endpoints */
 	err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1),
-				  rq2->sadb_x_ipsecrequest_len,
+				  rq2->sadb_x_ipsecrequest_len - sizeof(*rq2),
 				  &m->new_saddr, &m->new_daddr,
 				  &m->new_family);
 	if (err)
@@ -2655,7 +2696,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -2679,14 +2720,18 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb
 {
 	struct pfkey_sock *pfk = pfkey_sk(sk);
 
-	if (pfk->dump.dump != NULL)
+	mutex_lock(&pfk->dump_lock);
+	if (pfk->dump.dump != NULL) {
+		mutex_unlock(&pfk->dump_lock);
 		return -EBUSY;
+	}
 
 	pfk->dump.msg_version = hdr->sadb_msg_version;
 	pfk->dump.msg_portid = hdr->sadb_msg_pid;
 	pfk->dump.dump = pfkey_dump_sp;
 	pfk->dump.done = pfkey_dump_sp_done;
 	xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN);
+	mutex_unlock(&pfk->dump_lock);
 
 	return pfkey_do_dump(pfk);
 }
@@ -2708,7 +2753,7 @@ static int key_notify_policy_flush(const struct km_event *c)
 	hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
-	pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 	return 0;
 
 }
@@ -2770,7 +2815,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL),
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
 			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
@@ -2992,7 +3037,8 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c)
 	out_hdr->sadb_msg_seq = 0;
 	out_hdr->sadb_msg_pid = 0;
 
-	pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			xs_net(x));
 	return 0;
 }
 
@@ -3182,7 +3228,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 		       xfrm_ctx->ctx_len);
 	}
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,
@@ -3380,7 +3427,8 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	n_port->sadb_x_nat_t_port_port = sport;
 	n_port->sadb_x_nat_t_port_reserved = 0;
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 #ifdef CONFIG_NET_KEY_MIGRATE
@@ -3572,7 +3620,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
 
 	return 0;
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index afca2eb4dfa7..d3dec414fd44 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 }
 EXPORT_SYMBOL_GPL(l2tp_session_find);
 
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref)
 {
 	int hash;
 	struct l2tp_session *session;
@@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}
@@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.
@@ -1581,7 +1585,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 5871537af387..555d962a62d2 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -243,7 +243,8 @@ out:
 struct l2tp_session *l2tp_session_find(struct net *net,
 				       struct l2tp_tunnel *tunnel,
 				       u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref);
 struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
 struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
@@ -273,6 +274,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
 			 const struct l2tp_nl_cmd_ops *ops);
 void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
 /* Session reference counts. Incremented when code obtains a reference
  * to a session.
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a2ae34..d100aed3d06f 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
 	}
 
 	/* Show the tunnel or session context */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ec22078b0914..48ab93842322 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/ioctls.h>
 #include <linux/icmp.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
@@ -123,12 +124,11 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -156,6 +156,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
@@ -249,8 +252,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int ret;
 	int chk_addr_ret;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr_len < sizeof(struct sockaddr_l2tpip))
 		return -EINVAL;
 	if (addr->l2tp_family != AF_INET)
@@ -265,6 +266,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	read_unlock_bh(&l2tp_ip_lock);
 
 	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out;
+
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
 		goto out;
 
@@ -379,7 +383,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 drop:
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
-	return -1;
+	return 0;
 }
 
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
@@ -552,6 +556,30 @@ out:
 	return err ? err : copied;
 }
 
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+	struct sk_buff *skb;
+	int amount;
+
+	switch (cmd) {
+	case SIOCOUTQ:
+		amount = sk_wmem_alloc_get(sk);
+		break;
+	case SIOCINQ:
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
+		amount = skb ? skb->len : 0;
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		break;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return put_user(amount, (int __user *)arg);
+}
+EXPORT_SYMBOL(l2tp_ioctl);
+
 static struct proto l2tp_ip_prot = {
 	.name		   = "L2TP/IP",
 	.owner		   = THIS_MODULE,
@@ -560,7 +588,7 @@ static struct proto l2tp_ip_prot = {
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
 	.disconnect	   = l2tp_ip_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a2c8747d2936..bcdab1cba773 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
@@ -264,8 +266,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int addr_type;
 	int err;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr->l2tp_family != AF_INET6)
 		return -EINVAL;
 	if (addr_len < sizeof(*addr))
@@ -291,6 +291,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	lock_sock(sk);
 
 	err = -EINVAL;
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_unlock;
+
 	if (sk->sk_state != TCP_CLOSE)
 		goto out_unlock;
 
@@ -711,7 +714,7 @@ static struct proto l2tp_ip6_prot = {
 	.bind		   = l2tp_ip6_bind,
 	.connect	   = l2tp_ip6_connect,
 	.disconnect	   = l2tp_ip6_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip6_destroy_sock,
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 2caaa84ce92d..665cc74df5c5 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -827,7 +827,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 				goto out;
 		}
 
-		session = l2tp_session_find_nth(tunnel, si);
+		session = l2tp_session_get_nth(tunnel, si, false);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;
@@ -837,8 +837,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) < 0)
+					 session, L2TP_CMD_SESSION_GET) < 0) {
+			l2tp_session_dec_refcount(session);
 			break;
+		}
+		l2tp_session_dec_refcount(session);
 
 		si++;
 	}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1ad18c55064c..8ab9c5d74416 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -467,6 +467,10 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 static void pppol2tp_session_destruct(struct sock *sk)
 {
 	struct l2tp_session *session = sk->sk_user_data;
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+
 	if (session) {
 		sk->sk_user_data = NULL;
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);
@@ -505,9 +509,6 @@ static int pppol2tp_release(struct socket *sock)
 		l2tp_session_queue_purge(session);
 		sock_put(sk);
 	}
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-
 	release_sock(sk);
 
 	/* This will delete the session context via
@@ -1574,7 +1575,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -1701,10 +1702,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
 
 	/* Show the tunnel or session context.
 	 */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		pppol2tp_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
@@ -1863,4 +1868,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(PPPOL2TP_DRV_VERSION);
 MODULE_ALIAS("pppox-proto-" __stringify(PX_PROTO_OL2TP));
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 8dab4e569571..bb8edb9ef506 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
 	if (llc->cmsg_flags & LLC_CMSG_PKTINFO) {
 		struct llc_pktinfo info;
 
+		memset(&info, 0, sizeof(info));
 		info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex;
 		llc_pdu_decode_dsap(skb, &info.lpi_sap);
 		llc_pdu_decode_da(skb, info.lpi_mac);
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821daf9dd4..8bc5a1bd2d45 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 		 * another trick required to cope with how the PROCOM state
 		 * machine works. -acme
 		 */
+		skb_orphan(skb);
+		sock_hold(sk);
 		skb->sk = sk;
+		skb->destructor = sock_efree;
 	}
 	if (!sock_owned_by_user(sk))
 		llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e804ebd7..5404d0d195cc 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
 
 	ev->type   = LLC_SAP_EV_TYPE_PDU;
 	ev->reason = 0;
+	skb_orphan(skb);
+	sock_hold(sk);
 	skb->sk = sk;
+	skb->destructor = sock_efree;
 	llc_sap_state_process(sap, skb);
 }
 
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 367784be5df2..a830356b94ac 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -7,6 +7,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
+ * Copyright(c) 2015 Intel Deutschland GmbH
  *
  * 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
@@ -61,6 +62,14 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 {
 	struct ieee80211_local *local = sta->local;
 	struct tid_ampdu_rx *tid_rx;
+	struct ieee80211_ampdu_params params = {
+		.sta = &sta->sta,
+		.action = IEEE80211_AMPDU_RX_STOP,
+		.tid = tid,
+		.amsdu = false,
+		.timeout = 0,
+		.ssn = 0,
+	};
 
 	lockdep_assert_held(&sta->ampdu_mlme.mtx);
 
@@ -78,8 +87,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
 	       initiator == WLAN_BACK_RECIPIENT ? "recipient" : "inititator",
 	       (int)reason);
 
-	if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP,
-			     &sta->sta, tid, NULL, 0, false))
+	if (drv_ampdu_action(local, sta->sdata, &params))
 		sdata_info(sta->sdata,
 			   "HW problem - can not stop rx aggregation for %pM tid %d\n",
 			   sta->sta.addr, tid);
@@ -237,6 +245,15 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 {
 	struct ieee80211_local *local = sta->sdata->local;
 	struct tid_ampdu_rx *tid_agg_rx;
+	struct ieee80211_ampdu_params params = {
+		.sta = &sta->sta,
+		.action = IEEE80211_AMPDU_RX_START,
+		.tid = tid,
+		.amsdu = false,
+		.timeout = timeout,
+		.ssn = start_seq_num,
+	};
+
 	int i, ret = -EOPNOTSUPP;
 	u16 status = WLAN_STATUS_REQUEST_DECLINED;
 
@@ -273,8 +290,12 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 		buf_size = IEEE80211_MAX_AMPDU_BUF;
 
 	/* make sure the size doesn't exceed the maximum supported by the hw */
-	if (buf_size > local->hw.max_rx_aggregation_subframes)
-		buf_size = local->hw.max_rx_aggregation_subframes;
+	if (buf_size > sta->sta.max_rx_aggregation_subframes)
+		buf_size = sta->sta.max_rx_aggregation_subframes;
+	params.buf_size = buf_size;
+
+	ht_dbg(sta->sdata, "AddBA Req buf_size=%d for %pM\n",
+	       buf_size, sta->sta.addr);
 
 	/* examine state machine */
 	mutex_lock(&sta->ampdu_mlme.mtx);
@@ -322,8 +343,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	for (i = 0; i < buf_size; i++)
 		__skb_queue_head_init(&tid_agg_rx->reorder_buf[i]);
 
-	ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START,
-			       &sta->sta, tid, &start_seq_num, 0, false);
+	ret = drv_ampdu_action(local, sta->sdata, &params);
 	ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n",
 	       sta->sta.addr, tid, ret);
 	if (ret) {
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index ff757181b0a8..4932e9f243a2 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -7,6 +7,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
+ * Copyright(c) 2015 Intel Deutschland GmbH
  *
  * 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
@@ -295,7 +296,14 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 {
 	struct ieee80211_local *local = sta->local;
 	struct tid_ampdu_tx *tid_tx;
-	enum ieee80211_ampdu_mlme_action action;
+	struct ieee80211_ampdu_params params = {
+		.sta = &sta->sta,
+		.tid = tid,
+		.buf_size = 0,
+		.amsdu = false,
+		.timeout = 0,
+		.ssn = 0,
+	};
 	int ret;
 
 	lockdep_assert_held(&sta->ampdu_mlme.mtx);
@@ -304,10 +312,10 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 	case AGG_STOP_DECLINED:
 	case AGG_STOP_LOCAL_REQUEST:
 	case AGG_STOP_PEER_REQUEST:
-		action = IEEE80211_AMPDU_TX_STOP_CONT;
+		params.action = IEEE80211_AMPDU_TX_STOP_CONT;
 		break;
 	case AGG_STOP_DESTROY_STA:
-		action = IEEE80211_AMPDU_TX_STOP_FLUSH;
+		params.action = IEEE80211_AMPDU_TX_STOP_FLUSH;
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -330,9 +338,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 		spin_unlock_bh(&sta->lock);
 		if (reason != AGG_STOP_DESTROY_STA)
 			return -EALREADY;
-		ret = drv_ampdu_action(local, sta->sdata,
-				       IEEE80211_AMPDU_TX_STOP_FLUSH_CONT,
-				       &sta->sta, tid, NULL, 0, false);
+		params.action = IEEE80211_AMPDU_TX_STOP_FLUSH_CONT;
+		ret = drv_ampdu_action(local, sta->sdata, &params);
 		WARN_ON_ONCE(ret);
 		return 0;
 	}
@@ -381,8 +388,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 					WLAN_BACK_INITIATOR;
 	tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST;
 
-	ret = drv_ampdu_action(local, sta->sdata, action,
-			       &sta->sta, tid, NULL, 0, false);
+	ret = drv_ampdu_action(local, sta->sdata, &params);
 
 	/* HW shall not deny going back to legacy */
 	if (WARN_ON(ret)) {
@@ -445,7 +451,14 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	struct tid_ampdu_tx *tid_tx;
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	u16 start_seq_num;
+	struct ieee80211_ampdu_params params = {
+		.sta = &sta->sta,
+		.action = IEEE80211_AMPDU_TX_START,
+		.tid = tid,
+		.buf_size = 0,
+		.amsdu = false,
+		.timeout = 0,
+	};
 	int ret;
 
 	tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
@@ -467,10 +480,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	 */
 	synchronize_net();
 
-	start_seq_num = sta->tid_seq[tid] >> 4;
-
-	ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START,
-			       &sta->sta, tid, &start_seq_num, 0, false);
+	params.ssn = sta->tid_seq[tid] >> 4;
+	ret = drv_ampdu_action(local, sdata, &params);
 	if (ret) {
 		ht_dbg(sdata,
 		       "BA request denied - HW unavailable for %pM tid %d\n",
@@ -499,7 +510,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 
 	/* send AddBA request */
 	ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
-				     tid_tx->dialog_token, start_seq_num,
+				     tid_tx->dialog_token, params.ssn,
 				     IEEE80211_MAX_AMPDU_BUF,
 				     tid_tx->timeout);
 }
@@ -684,18 +695,24 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
 					 struct sta_info *sta, u16 tid)
 {
 	struct tid_ampdu_tx *tid_tx;
+	struct ieee80211_ampdu_params params = {
+		.sta = &sta->sta,
+		.action = IEEE80211_AMPDU_TX_OPERATIONAL,
+		.tid = tid,
+		.timeout = 0,
+		.ssn = 0,
+	};
 
 	lockdep_assert_held(&sta->ampdu_mlme.mtx);
 
 	tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
+	params.buf_size = tid_tx->buf_size;
+	params.amsdu = tid_tx->amsdu;
 
 	ht_dbg(sta->sdata, "Aggregation is on for %pM tid %d\n",
 	       sta->sta.addr, tid);
 
-	drv_ampdu_action(local, sta->sdata,
-			 IEEE80211_AMPDU_TX_OPERATIONAL,
-			 &sta->sta, tid, NULL, tid_tx->buf_size,
-			 tid_tx->amsdu);
+	drv_ampdu_action(local, sta->sdata, &params);
 
 	/*
 	 * synchronize with TX path, while splicing the TX path
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c12f348138ac..19322c047386 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -865,7 +865,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 
 	/* free all potentially still buffered bcast frames */
 	local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf);
-	skb_queue_purge(&sdata->u.ap.ps.bc_buf);
+	ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf);
 
 	mutex_lock(&local->mtx);
 	ieee80211_vif_copy_chanctx_to_vlans(sdata, true);
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index ca1fe5576103..c258f1041d33 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -284,9 +284,7 @@ int drv_switch_vif_chanctx(struct ieee80211_local *local,
 
 int drv_ampdu_action(struct ieee80211_local *local,
 		     struct ieee80211_sub_if_data *sdata,
-		     enum ieee80211_ampdu_mlme_action action,
-		     struct ieee80211_sta *sta, u16 tid,
-		     u16 *ssn, u8 buf_size, bool amsdu)
+		     struct ieee80211_ampdu_params *params)
 {
 	int ret = -EOPNOTSUPP;
 
@@ -296,12 +294,10 @@ int drv_ampdu_action(struct ieee80211_local *local,
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
-	trace_drv_ampdu_action(local, sdata, action, sta, tid,
-			       ssn, buf_size, amsdu);
+	trace_drv_ampdu_action(local, sdata, params);
 
 	if (local->ops->ampdu_action)
-		ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action,
-					       sta, tid, ssn, buf_size, amsdu);
+		ret = local->ops->ampdu_action(&local->hw, &sdata->vif, params);
 
 	trace_drv_return_int(local, ret);
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 154ce4b13406..18b0d65baff0 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -585,9 +585,7 @@ static inline int drv_tx_last_beacon(struct ieee80211_local *local)
 
 int drv_ampdu_action(struct ieee80211_local *local,
 		     struct ieee80211_sub_if_data *sdata,
-		     enum ieee80211_ampdu_mlme_action action,
-		     struct ieee80211_sta *sta, u16 tid,
-		     u16 *ssn, u8 buf_size, bool amsdu);
+		     struct ieee80211_ampdu_params *params);
 
 static inline int drv_get_survey(struct ieee80211_local *local, int idx,
 				struct survey_info *survey)
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 6a12b0f5cac8..24ba31601fc9 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -7,6 +7,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2009, Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright(c) 2016 Intel Deutschland GmbH
  *
  * 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
@@ -65,6 +66,8 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		    2 + (IEEE80211_MAX_SUPP_RATES - 8) +
 		    2 + sizeof(struct ieee80211_ht_cap) +
 		    2 + sizeof(struct ieee80211_ht_operation) +
+		    2 + sizeof(struct ieee80211_vht_cap) +
+		    2 + sizeof(struct ieee80211_vht_operation) +
 		    ifibss->ie_len;
 	presp = kzalloc(sizeof(*presp) + frame_len, GFP_KERNEL);
 	if (!presp)
@@ -485,14 +488,14 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	struct beacon_data *presp, *old_presp;
 	struct cfg80211_bss *cbss;
 	const struct cfg80211_bss_ies *ies;
-	u16 capability = 0;
+	u16 capability = WLAN_CAPABILITY_IBSS;
 	u64 tsf;
 	int ret = 0;
 
 	sdata_assert_lock(sdata);
 
 	if (ifibss->privacy)
-		capability = WLAN_CAPABILITY_PRIVACY;
+		capability |= WLAN_CAPABILITY_PRIVACY;
 
 	cbss = cfg80211_get_bss(sdata->local->hw.wiphy, ifibss->chandef.chan,
 				ifibss->bssid, ifibss->ssid,
@@ -1484,14 +1487,21 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
 
 		sdata_info(sdata, "Trigger new scan to find an IBSS to join\n");
 
-		num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy,
-							 &ifibss->chandef,
-							 channels,
-							 ARRAY_SIZE(channels));
 		scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef);
-		ieee80211_request_ibss_scan(sdata, ifibss->ssid,
-					    ifibss->ssid_len, channels, num,
-					    scan_width);
+
+		if (ifibss->fixed_channel) {
+			num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy,
+								 &ifibss->chandef,
+								 channels,
+								 ARRAY_SIZE(channels));
+			ieee80211_request_ibss_scan(sdata, ifibss->ssid,
+						    ifibss->ssid_len, channels,
+						    num, scan_width);
+		} else {
+			ieee80211_request_ibss_scan(sdata, ifibss->ssid,
+						    ifibss->ssid_len, NULL,
+						    0, scan_width);
+		}
 	} else {
 		int interval = IEEE80211_SCAN_INTERVAL;
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index c9e325d2e120..bcb0a1b64556 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -977,7 +977,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.txq) {
 		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
 
+		spin_lock_bh(&txqi->queue.lock);
 		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+		spin_unlock_bh(&txqi->queue.lock);
+
 		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
 	}
 
@@ -1747,7 +1750,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		ret = dev_alloc_name(ndev, ndev->name);
 		if (ret < 0) {
-			free_netdev(ndev);
+			ieee80211_if_free(ndev);
 			return ret;
 		}
 
@@ -1833,7 +1836,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		ret = register_netdevice(ndev);
 		if (ret) {
-			free_netdev(ndev);
+			ieee80211_if_free(ndev);
 			return ret;
 		}
 	}
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 175ffcf7fb06..2ee53dc1ddf7 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -891,12 +891,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
 
-		if (sband->ht_cap.ht_supported)
-			local->rx_chains =
-				max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
-				    local->rx_chains);
+		if (!sband->ht_cap.ht_supported)
+			continue;
 
 		/* TODO: consider VHT for RX chains, hopefully it's the same */
+		local->rx_chains =
+			max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs),
+			    local->rx_chains);
+
+		/* no need to mask, SM_PS_DISABLED has all bits set */
+		sband->ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED <<
+			             IEEE80211_HT_CAP_SM_PS_SHIFT;
 	}
 
 	/* if low-level driver supports AP, we also support VLAN */
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 6f85b6ab8e51..9063e8e736ad 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -151,19 +151,26 @@ u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
 void mesh_sta_cleanup(struct sta_info *sta)
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	u32 changed;
+	u32 changed = 0;
 
 	/*
 	 * maybe userspace handles peer allocation and peering, but in either
 	 * case the beacon is still generated by the kernel and we might need
 	 * an update.
 	 */
-	changed = mesh_accept_plinks_update(sdata);
+	if (sdata->u.mesh.user_mpm &&
+	    sta->mesh->plink_state == NL80211_PLINK_ESTAB)
+		changed |= mesh_plink_dec_estab_count(sdata);
+	changed |= mesh_accept_plinks_update(sdata);
 	if (!sdata->u.mesh.user_mpm) {
 		changed |= mesh_plink_deactivate(sta);
 		del_timer_sync(&sta->mesh->plink_timer);
 	}
 
+	/* make sure no readers can access nexthop sta from here on */
+	mesh_path_flush_by_nexthop(sta);
+	synchronize_net();
+
 	if (changed)
 		ieee80211_mbss_info_change_notify(sdata, changed);
 }
@@ -348,7 +355,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata,
 	/* fast-forward to vendor IEs */
 	offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0);
 
-	if (offset) {
+	if (offset < ifmsh->ie_len) {
 		len = ifmsh->ie_len - offset;
 		data = ifmsh->ie + offset;
 		if (skb_tailroom(skb) < len)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 83097c3832d1..23095d5e0199 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2517,7 +2517,7 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
 }
 
 static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
-					 bool assoc)
+					 bool assoc, bool abandon)
 {
 	struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data;
 
@@ -2539,6 +2539,9 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
 		mutex_lock(&sdata->local->mtx);
 		ieee80211_vif_release_channel(sdata);
 		mutex_unlock(&sdata->local->mtx);
+
+		if (abandon)
+			cfg80211_abandon_assoc(sdata->dev, assoc_data->bss);
 	}
 
 	kfree(assoc_data);
@@ -2768,7 +2771,7 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
 			   bssid, reason_code,
 			   ieee80211_get_reason_code_string(reason_code));
 
-		ieee80211_destroy_assoc_data(sdata, false);
+		ieee80211_destroy_assoc_data(sdata, false, true);
 
 		cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len);
 		return;
@@ -3173,14 +3176,14 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	if (status_code != WLAN_STATUS_SUCCESS) {
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
-		ieee80211_destroy_assoc_data(sdata, false);
+		ieee80211_destroy_assoc_data(sdata, false, false);
 		event.u.mlme.status = MLME_DENIED;
 		event.u.mlme.reason = status_code;
 		drv_event_callback(sdata->local, sdata, &event);
 	} else {
 		if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) {
 			/* oops -- internal error -- send timeout for now */
-			ieee80211_destroy_assoc_data(sdata, false);
+			ieee80211_destroy_assoc_data(sdata, false, false);
 			cfg80211_assoc_timeout(sdata->dev, bss);
 			return;
 		}
@@ -3193,7 +3196,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		 * recalc after assoc_data is NULL but before associated
 		 * is set can cause the interface to go idle
 		 */
-		ieee80211_destroy_assoc_data(sdata, true);
+		ieee80211_destroy_assoc_data(sdata, true, false);
 
 		/* get uapsd queues configuration */
 		uapsd_queues = 0;
@@ -3888,7 +3891,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
 				.u.mlme.status = MLME_TIMEOUT,
 			};
 
-			ieee80211_destroy_assoc_data(sdata, false);
+			ieee80211_destroy_assoc_data(sdata, false, false);
 			cfg80211_assoc_timeout(sdata->dev, bss);
 			drv_event_callback(sdata->local, sdata, &event);
 		}
@@ -4029,7 +4032,7 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 					       WLAN_REASON_DEAUTH_LEAVING,
 					       false, frame_buf);
 		if (ifmgd->assoc_data)
-			ieee80211_destroy_assoc_data(sdata, false);
+			ieee80211_destroy_assoc_data(sdata, false, true);
 		if (ifmgd->auth_data)
 			ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
@@ -4905,7 +4908,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 					       IEEE80211_STYPE_DEAUTH,
 					       req->reason_code, tx,
 					       frame_buf);
-		ieee80211_destroy_assoc_data(sdata, false);
+		ieee80211_destroy_assoc_data(sdata, false, true);
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
 					    req->reason_code);
@@ -4980,7 +4983,7 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
 	sdata_lock(sdata);
 	if (ifmgd->assoc_data) {
 		struct cfg80211_bss *bss = ifmgd->assoc_data->bss;
-		ieee80211_destroy_assoc_data(sdata, false);
+		ieee80211_destroy_assoc_data(sdata, false, false);
 		cfg80211_assoc_timeout(sdata->dev, bss);
 	}
 	if (ifmgd->auth_data)
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 00a43a70e1fc..0402fa45b343 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -168,6 +168,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 			break;
 		}
 
+		flush_delayed_work(&sdata->dec_tailroom_needed_wk);
 		drv_remove_interface(local, sdata);
 	}
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 4cbf36cae806..3bcabc2ba4a6 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1455,12 +1455,16 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 	 */
 	if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) &&
 	    !ieee80211_has_morefrags(hdr->frame_control) &&
+	    !ieee80211_is_back_req(hdr->frame_control) &&
 	    !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) &&
 	    (rx->sdata->vif.type == NL80211_IFTYPE_AP ||
 	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) &&
-	    /* PM bit is only checked in frames where it isn't reserved,
+	    /*
+	     * PM bit is only checked in frames where it isn't reserved,
 	     * in AP mode it's reserved in non-bufferable management frames
 	     * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field)
+	     * BAR frames should be ignored as specified in
+	     * IEEE 802.11-2012 10.2.1.2.
 	     */
 	    (!ieee80211_is_mgmt(hdr->frame_control) ||
 	     ieee80211_is_bufferable_mmpdu(hdr->frame_control))) {
@@ -2203,16 +2207,22 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 	if (!(status->rx_flags & IEEE80211_RX_AMSDU))
 		return RX_CONTINUE;
 
-	if (ieee80211_has_a4(hdr->frame_control) &&
-	    rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-	    !rx->sdata->u.vlan.sta)
-		return RX_DROP_UNUSABLE;
+	if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
+		switch (rx->sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+			if (!rx->sdata->u.vlan.sta)
+				return RX_DROP_UNUSABLE;
+			break;
+		case NL80211_IFTYPE_STATION:
+			if (!rx->sdata->u.mgd.use_4addr)
+				return RX_DROP_UNUSABLE;
+			break;
+		default:
+			return RX_DROP_UNUSABLE;
+		}
+	}
 
-	if (is_multicast_ether_addr(hdr->addr1) &&
-	    ((rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-	      rx->sdata->u.vlan.sta) ||
-	     (rx->sdata->vif.type == NL80211_IFTYPE_STATION &&
-	      rx->sdata->u.mgd.use_4addr)))
+	if (is_multicast_ether_addr(hdr->addr1))
 		return RX_DROP_UNUSABLE;
 
 	skb->dev = dev;
@@ -2250,7 +2260,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	struct ieee80211_local *local = rx->local;
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
-	u16 q, hdrlen;
+	u16 ac, q, hdrlen;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
@@ -2319,7 +2329,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	    ether_addr_equal(sdata->vif.addr, hdr->addr3))
 		return RX_CONTINUE;
 
-	q = ieee80211_select_queue_80211(sdata, skb, hdr);
+	ac = ieee80211_select_queue_80211(sdata, skb, hdr);
+	q = sdata->vif.hw_queue[ac];
 	if (ieee80211_queue_stopped(&local->hw, q)) {
 		IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion);
 		return RX_DROP_MONITOR;
@@ -3389,6 +3400,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 			    !ether_addr_equal(bssid, hdr->addr1))
 				return false;
 		}
+
+		/*
+		 * 802.11-2016 Table 9-26 says that for data frames, A1 must be
+		 * the BSSID - we've checked that already but may have accepted
+		 * the wildcard (ff:ff:ff:ff:ff:ff).
+		 *
+		 * It also says:
+		 *	The BSSID of the Data frame is determined as follows:
+		 *	a) If the STA is contained within an AP or is associated
+		 *	   with an AP, the BSSID is the address currently in use
+		 *	   by the STA contained in the AP.
+		 *
+		 * So we should not accept data frames with an address that's
+		 * multicast.
+		 *
+		 * Accepting it also opens a security problem because stations
+		 * could encrypt it with the GTK and inject traffic that way.
+		 */
+		if (ieee80211_is_data(hdr->frame_control) && multicast)
+			return false;
+
 		return true;
 	case NL80211_IFTYPE_WDS:
 		if (bssid || !ieee80211_is_data(hdr->frame_control))
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f91d1873218c..63ea6cbac5ad 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -256,11 +256,11 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 }
 
 /* Caller must hold local->sta_mtx */
-static void sta_info_hash_add(struct ieee80211_local *local,
-			      struct sta_info *sta)
+static int sta_info_hash_add(struct ieee80211_local *local,
+			     struct sta_info *sta)
 {
-	rhashtable_insert_fast(&local->sta_hash, &sta->hash_node,
-			       sta_rht_params);
+	return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node,
+				      sta_rht_params);
 }
 
 static void sta_deliver_ps_frames(struct work_struct *wk)
@@ -329,6 +329,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 
 	memcpy(sta->addr, addr, ETH_ALEN);
 	memcpy(sta->sta.addr, addr, ETH_ALEN);
+	sta->sta.max_rx_aggregation_subframes =
+		local->hw.max_rx_aggregation_subframes;
+
 	sta->local = local;
 	sta->sdata = sdata;
 	sta->rx_stats.last_rx = jiffies;
@@ -484,11 +487,17 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct station_info sinfo;
+	struct station_info *sinfo;
 	int err = 0;
 
 	lockdep_assert_held(&local->sta_mtx);
 
+	sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL);
+	if (!sinfo) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
 	/* check if STA exists already */
 	if (sta_info_get_bss(sdata, sta->sta.addr)) {
 		err = -EEXIST;
@@ -503,7 +512,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	set_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
 	/* make the station visible */
-	sta_info_hash_add(local, sta);
+	err = sta_info_hash_add(local, sta);
+	if (err)
+		goto out_drop_sta;
 
 	list_add_tail_rcu(&sta->list, &local->sta_list);
 
@@ -520,10 +531,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	ieee80211_sta_debugfs_add(sta);
 	rate_control_add_sta_debugfs(sta);
 
-	memset(&sinfo, 0, sizeof(sinfo));
-	sinfo.filled = 0;
-	sinfo.generation = local->sta_generation;
-	cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL);
+	sinfo->generation = local->sta_generation;
+	cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL);
+	kfree(sinfo);
 
 	sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr);
 
@@ -538,6 +548,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
  out_remove:
 	sta_info_hash_del(local, sta);
 	list_del_rcu(&sta->list);
+ out_drop_sta:
 	local->num_sta--;
 	synchronize_net();
 	__cleanup_single_sta(sta);
@@ -882,7 +893,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 {
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct station_info sinfo = {};
+	struct station_info *sinfo;
 	int ret;
 
 	/*
@@ -920,8 +931,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
 
 	sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr);
 
-	sta_set_sinfo(sta, &sinfo);
-	cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL);
+	sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+	if (sinfo)
+		sta_set_sinfo(sta, sinfo);
+	cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL);
+	kfree(sinfo);
 
 	rate_control_remove_sta_debugfs(sta);
 	ieee80211_sta_debugfs_remove(sta);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 2cafb21b422f..15b0150283b6 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -269,7 +269,7 @@ struct ieee80211_fast_tx {
 	u8 sa_offs, da_offs, pn_offs;
 	u8 band;
 	u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
-	       sizeof(rfc1042_header)];
+	       sizeof(rfc1042_header)] __aligned(2);
 
 	struct rcu_head rcu_head;
 };
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 56c6d6cfa5a1..913e959b03cf 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -80,7 +80,23 @@
 #define KEY_PR_FMT	" cipher:0x%x, flags=%#x, keyidx=%d, hw_key_idx=%d"
 #define KEY_PR_ARG	__entry->cipher, __entry->flags, __entry->keyidx, __entry->hw_key_idx
 
-
+#define AMPDU_ACTION_ENTRY	__field(enum ieee80211_ampdu_mlme_action,		\
+					ieee80211_ampdu_mlme_action)			\
+				STA_ENTRY						\
+				__field(u16, tid)					\
+				__field(u16, ssn)					\
+				__field(u8, buf_size)					\
+				__field(bool, amsdu)					\
+				__field(u16, timeout)
+#define AMPDU_ACTION_ASSIGN	STA_NAMED_ASSIGN(params->sta);				\
+				__entry->tid = params->tid;				\
+				__entry->ssn = params->ssn;				\
+				__entry->buf_size = params->buf_size;			\
+				__entry->amsdu = params->amsdu;				\
+				__entry->timeout = params->timeout;
+#define AMPDU_ACTION_PR_FMT	STA_PR_FMT " tid %d, ssn %d, buf_size %u, amsdu %d, timeout %d"
+#define AMPDU_ACTION_PR_ARG	STA_PR_ARG, __entry->tid, __entry->ssn,			\
+				__entry->buf_size, __entry->amsdu, __entry->timeout
 
 /*
  * Tracing for driver callbacks.
@@ -970,38 +986,25 @@ DEFINE_EVENT(local_only_evt, drv_tx_last_beacon,
 TRACE_EVENT(drv_ampdu_action,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
-		 enum ieee80211_ampdu_mlme_action action,
-		 struct ieee80211_sta *sta, u16 tid,
-		 u16 *ssn, u8 buf_size, bool amsdu),
+		 struct ieee80211_ampdu_params *params),
 
-	TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size, amsdu),
+	TP_ARGS(local, sdata, params),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
-		STA_ENTRY
-		__field(u32, action)
-		__field(u16, tid)
-		__field(u16, ssn)
-		__field(u8, buf_size)
-		__field(bool, amsdu)
 		VIF_ENTRY
+		AMPDU_ACTION_ENTRY
 	),
 
 	TP_fast_assign(
 		LOCAL_ASSIGN;
 		VIF_ASSIGN;
-		STA_ASSIGN;
-		__entry->action = action;
-		__entry->tid = tid;
-		__entry->ssn = ssn ? *ssn : 0;
-		__entry->buf_size = buf_size;
-		__entry->amsdu = amsdu;
+		AMPDU_ACTION_ASSIGN;
 	),
 
 	TP_printk(
-		LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d amsdu:%d",
-		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action,
-		__entry->tid, __entry->buf_size, __entry->amsdu
+		LOCAL_PR_FMT VIF_PR_FMT AMPDU_ACTION_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG, AMPDU_ACTION_PR_ARG
 	)
 );
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index bdc224d5053a..ea5dfefd765a 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -365,7 +365,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local)
 		skb = skb_dequeue(&ps->bc_buf);
 		if (skb) {
 			purged++;
-			dev_kfree_skb(skb);
+			ieee80211_free_txskb(&local->hw, skb);
 		}
 		total += skb_queue_len(&ps->bc_buf);
 	}
@@ -448,7 +448,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
 	if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) {
 		ps_dbg(tx->sdata,
 		       "BC TX buffer full - dropping the oldest frame\n");
-		dev_kfree_skb(skb_dequeue(&ps->bc_buf));
+		ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf));
 	} else
 		tx->local->total_ps_buffered++;
 
@@ -2699,7 +2699,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 	int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2);
 	int hw_headroom = sdata->local->hw.extra_tx_headroom;
 	struct ethhdr eth;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_info *info;
 	struct ieee80211_hdr *hdr = (void *)fast_tx->hdr;
 	struct ieee80211_tx_data tx;
 	ieee80211_tx_result r;
@@ -2761,6 +2761,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 	memcpy(skb->data + fast_tx->da_offs, eth.h_dest, ETH_ALEN);
 	memcpy(skb->data + fast_tx->sa_offs, eth.h_source, ETH_ALEN);
 
+	info = IEEE80211_SKB_CB(skb);
 	memset(info, 0, sizeof(*info));
 	info->band = fast_tx->band;
 	info->control.vif = &sdata->vif;
@@ -3781,7 +3782,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
 		if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb))
 			break;
-		dev_kfree_skb_any(skb);
+		ieee80211_free_txskb(hw, skb);
 	}
 
 	info = IEEE80211_SKB_CB(skb);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index d824c38971ed..e19ea1c53afa 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -16,6 +16,7 @@
 #include <asm/unaligned.h>
 #include <net/mac80211.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 
 #include "ieee80211_i.h"
 #include "michael.h"
@@ -152,7 +153,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx)
 	data_len = skb->len - hdrlen - MICHAEL_MIC_LEN;
 	key = &rx->key->conf.key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY];
 	michael_mic(key, hdr, data, data_len, mic);
-	if (memcmp(mic, data + data_len, MICHAEL_MIC_LEN) != 0)
+	if (crypto_memneq(mic, data + data_len, MICHAEL_MIC_LEN))
 		goto mic_fail;
 
 	/* remove Michael MIC from payload */
@@ -1044,7 +1045,7 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx)
 		bip_aad(skb, aad);
 		ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad,
 				   skb->data + 24, skb->len - 24, mic);
-		if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+		if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) {
 			key->u.aes_cmac.icverrors++;
 			return RX_DROP_UNUSABLE;
 		}
@@ -1094,7 +1095,7 @@ ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx)
 		bip_aad(skb, aad);
 		ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad,
 				       skb->data + 24, skb->len - 24, mic);
-		if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+		if (crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) {
 			key->u.aes_cmac.icverrors++;
 			return RX_DROP_UNUSABLE;
 		}
@@ -1198,7 +1199,7 @@ ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx)
 		if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce,
 				       skb->data + 24, skb->len - 24,
 				       mic) < 0 ||
-		    memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+		    crypto_memneq(mic, mmie->mic, sizeof(mmie->mic))) {
 			key->u.aes_gmac.icverrors++;
 			return RX_DROP_UNUSABLE;
 		}
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c32fc411a911..52cfc4478511 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -518,6 +518,9 @@ static struct net_device *find_outdev(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 
+	if (IS_ERR(dev))
+		return dev;
+
 	/* The caller is holding rtnl anyways, so release the dev reference */
 	dev_put(dev);
 
@@ -1564,6 +1567,7 @@ static void mpls_net_exit(struct net *net)
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index f57b4dcdb233..dd1649caa2b2 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -845,10 +845,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 {
 	unsigned int verdict = NF_DROP;
 
-	if (IP_VS_FWD_METHOD(cp) != 0) {
-		pr_err("shouldn't reach here, because the box is on the "
-		       "half connection in the tun/dr module.\n");
-	}
+	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+		goto ignore_cp;
 
 	/* Ensure the checksum is correct */
 	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
@@ -882,6 +880,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 0);
+
+ignore_cp:
 	verdict = NF_ACCEPT;
 
 out:
@@ -1242,8 +1242,11 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 	 */
 	cp = pp->conn_out_get(ipvs, af, skb, &iph);
 
-	if (likely(cp))
+	if (likely(cp)) {
+		if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+			goto ignore_cp;
 		return handle_response(af, skb, pd, cp, &iph, hooknum);
+	}
 	if (sysctl_nat_icmp_send(ipvs) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
@@ -1285,9 +1288,15 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 			}
 		}
 	}
+
+out:
 	IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
 		      "ip_vs_out: packet continues traversal as normal");
 	return NF_ACCEPT;
+
+ignore_cp:
+	__ip_vs_conn_put(cp);
+	goto out;
 }
 
 /*
@@ -1757,15 +1766,34 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	cp = pp->conn_in_get(ipvs, af, skb, &iph);
 
 	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs &&
-	    is_new_conn(skb, &iph) && cp &&
-	    ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
-	      unlikely(!atomic_read(&cp->dest->weight))) ||
-	     unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) {
-		if (!atomic_read(&cp->n_control))
-			ip_vs_conn_expire_now(cp);
-		__ip_vs_conn_put(cp);
-		cp = NULL;
+	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		bool uses_ct = false, resched = false;
+
+		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
+		    unlikely(!atomic_read(&cp->dest->weight))) {
+			resched = true;
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+			uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+			if (!atomic_read(&cp->n_control)) {
+				resched = true;
+			} else {
+				/* Do not reschedule controlling connection
+				 * that uses conntrack while it is still
+				 * referenced by controlled connection(s).
+				 */
+				resched = !uses_ct;
+			}
+		}
+
+		if (resched) {
+			if (!atomic_read(&cp->n_control))
+				ip_vs_conn_expire_now(cp);
+			__ip_vs_conn_put(cp);
+			if (uses_ct)
+				return NF_DROP;
+			cp = NULL;
+		}
 	}
 
 	if (unlikely(!cp)) {
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 1b8d594e493a..0a6eb5c0d9e9 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -70,10 +70,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	const char *dptr;
 	int retc;
 
-	ip_vs_fill_iph_skb(p->af, skb, false, &iph);
+	retc = ip_vs_fill_iph_skb(p->af, skb, false, &iph);
 
 	/* Only useful with UDP */
-	if (iph.protocol != IPPROTO_UDP)
+	if (!retc || iph.protocol != IPPROTO_UDP)
 		return -EINVAL;
 	/* todo: IPv6 fragments:
 	 *       I think this only should be done for the first fragment. /HS
@@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	dptr = skb->data + dataoff;
 	datalen = skb->len - dataoff;
 
-	if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
+	if (get_callid(dptr, 0, datalen, &matchoff, &matchlen))
 		return -EINVAL;
 
 	/* N.B: pe_data is only set on success,
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 803001a45aa1..1b07578bedf3 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1545,7 +1545,8 @@ error:
 /*
  *      Set up receiving multicast socket over UDP
  */
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id)
+static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
+					int ifindex)
 {
 	/* multicast addr */
 	union ipvs_sockaddr mcast_addr;
@@ -1566,6 +1567,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id)
 		set_sock_size(sock->sk, 0, result);
 
 	get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
+	sock->sk->sk_bound_dev_if = ifindex;
 	result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
 	if (result < 0) {
 		pr_err("Error binding to the multicast addr\n");
@@ -1868,7 +1870,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		if (state == IP_VS_STATE_MASTER)
 			sock = make_send_sock(ipvs, id);
 		else
-			sock = make_receive_sock(ipvs, id);
+			sock = make_receive_sock(ipvs, id, dev->ifindex);
 		if (IS_ERR(sock)) {
 			result = PTR_ERR(sock);
 			goto outtinfo;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3cb3cb831591..86a3c6f0c871 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1757,6 +1757,7 @@ void nf_conntrack_init_end(void)
 
 int nf_conntrack_init_net(struct net *net)
 {
+	static atomic64_t unique_id;
 	int ret = -ENOMEM;
 	int cpu;
 
@@ -1779,7 +1780,8 @@ int nf_conntrack_init_net(struct net *net)
 	if (!net->ct.stat)
 		goto err_pcpu_lists;
 
-	net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
+	net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%llu",
+				(u64)atomic64_inc_return(&unique_id));
 	if (!net->ct.slabname)
 		goto err_slabname;
 
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 1a9545965c0d..531ca55f1af6 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -53,7 +53,11 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id,
 
 	rcu_read_lock();
 	t = rcu_dereference(nf_ct_ext_types[id]);
-	BUG_ON(t == NULL);
+	if (!t) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
 	off = ALIGN(sizeof(struct nf_ct_ext), t->align);
 	len = off + t->len + var_alloc_len;
 	alloc_size = t->alloc_size + var_alloc_len;
@@ -88,7 +92,10 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
 
 	rcu_read_lock();
 	t = rcu_dereference(nf_ct_ext_types[id]);
-	BUG_ON(t == NULL);
+	if (!t) {
+		rcu_read_unlock();
+		return NULL;
+	}
 
 	newoff = ALIGN(old->len, t->align);
 	newlen = newoff + t->len + var_alloc_len;
@@ -186,6 +193,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type)
 	RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
 	update_alloc_size(type);
 	mutex_unlock(&nf_ct_ext_type_mutex);
-	rcu_barrier(); /* Wait for completion of call_rcu()'s */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9f5272968abb..e565b2becb14 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -45,6 +45,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l4proto.h>
@@ -1798,6 +1800,8 @@ ctnetlink_create_conntrack(struct net *net,
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
 	nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC);
 	nf_ct_labels_ext_add(ct);
+	nfct_seqadj_ext_add(ct);
+	nfct_synproxy_ext_add(ct);
 
 	/* we must add conntrack extensions before confirmation. */
 	ct->status |= IPS_CONFIRMED;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index a5d41dfa9f05..2c89f90cd7bc 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -401,7 +401,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 	size_t size = *lenp;
 	int r = 0;
 	int tindex = (unsigned long)table->extra1;
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = table->extra2;
 
 	if (write) {
 		if (size > sizeof(buf))
@@ -453,7 +453,6 @@ static int netfilter_log_sysctl_init(struct net *net)
 				 3, "%d", i);
 			nf_log_sysctl_table[i].procname	=
 				nf_log_sysctl_fnames[i];
-			nf_log_sysctl_table[i].data = NULL;
 			nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN;
 			nf_log_sysctl_table[i].mode = 0644;
 			nf_log_sysctl_table[i].proc_handler =
@@ -463,6 +462,9 @@ static int netfilter_log_sysctl_init(struct net *net)
 		}
 	}
 
+	for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
+		table[i].extra2 = net;
+
 	net->nf.nf_log_dir_header = register_net_sysctl(net,
 						"net/netfilter/nf_log",
 						table);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 77afe913d03d..9adedba78eea 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -326,10 +326,12 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
-		    skb->len < nlh->nlmsg_len) {
-			err = -EINVAL;
-			goto ack;
+		if (nlh->nlmsg_len < NLMSG_HDRLEN ||
+		    skb->len < nlh->nlmsg_len ||
+		    nlmsg_len(nlh) < sizeof(struct nfgenmsg)) {
+			nfnl_err_reset(&err_list);
+			status |= NFNL_BATCH_FAILURE;
+			goto done;
 		}
 
 		/* Only requests are handled by the kernel */
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 9dec3bd1b63c..0a5df0cbaa28 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -140,7 +140,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
-		timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT]));
+		timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
+						tb[NFTA_DYNSET_TIMEOUT])));
 	}
 
 	priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
@@ -227,7 +228,8 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		goto nla_put_failure;
 	if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
 		goto nla_put_failure;
-	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout)))
+	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
+			 cpu_to_be64(jiffies_to_msecs(priv->timeout))))
 		goto nla_put_failure;
 	if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
 		goto nla_put_failure;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index d4aaad747ea9..2fc6ca9d1286 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -415,6 +415,47 @@ int xt_check_match(struct xt_mtchk_param *par,
 }
 EXPORT_SYMBOL_GPL(xt_check_match);
 
+/** xt_check_entry_match - check that matches end before start of target
+ *
+ * @match: beginning of xt_entry_match
+ * @target: beginning of this rules target (alleged end of matches)
+ * @alignment: alignment requirement of match structures
+ *
+ * Validates that all matches add up to the beginning of the target,
+ * and that each match covers at least the base structure size.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int xt_check_entry_match(const char *match, const char *target,
+				const size_t alignment)
+{
+	const struct xt_entry_match *pos;
+	int length = target - match;
+
+	if (length == 0) /* no matches */
+		return 0;
+
+	pos = (struct xt_entry_match *)match;
+	do {
+		if ((unsigned long)pos % alignment)
+			return -EINVAL;
+
+		if (length < (int)sizeof(struct xt_entry_match))
+			return -EINVAL;
+
+		if (pos->u.match_size < sizeof(struct xt_entry_match))
+			return -EINVAL;
+
+		if (pos->u.match_size > length)
+			return -EINVAL;
+
+		length -= pos->u.match_size;
+		pos = ((void *)((char *)(pos) + (pos)->u.match_size));
+	} while (length > 0);
+
+	return 0;
+}
+
 #ifdef CONFIG_COMPAT
 int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
@@ -484,13 +525,14 @@ int xt_compat_match_offset(const struct xt_match *match)
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_offset);
 
-int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
-			      unsigned int *size)
+void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+			       unsigned int *size)
 {
 	const struct xt_match *match = m->u.kernel.match;
 	struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
 	int pad, off = xt_compat_match_offset(match);
 	u_int16_t msize = cm->u.user.match_size;
+	char name[sizeof(m->u.user.name)];
 
 	m = *dstptr;
 	memcpy(m, cm, sizeof(*cm));
@@ -504,10 +546,12 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 
 	msize += off;
 	m->u.user.match_size = msize;
+	strlcpy(name, match->name, sizeof(name));
+	module_put(match->me);
+	strncpy(m->u.user.name, name, sizeof(m->u.user.name));
 
 	*size += off;
 	*dstptr += msize;
-	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_from_user);
 
@@ -538,8 +582,125 @@ int xt_compat_match_to_user(const struct xt_entry_match *m,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xt_compat_match_to_user);
+
+/* non-compat version may have padding after verdict */
+struct compat_xt_standard_target {
+	struct compat_xt_entry_target t;
+	compat_uint_t verdict;
+};
+
+int xt_compat_check_entry_offsets(const void *base, const char *elems,
+				  unsigned int target_offset,
+				  unsigned int next_offset)
+{
+	long size_of_base_struct = elems - (const char *)base;
+	const struct compat_xt_entry_target *t;
+	const char *e = base;
+
+	if (target_offset < size_of_base_struct)
+		return -EINVAL;
+
+	if (target_offset + sizeof(*t) > next_offset)
+		return -EINVAL;
+
+	t = (void *)(e + target_offset);
+	if (t->u.target_size < sizeof(*t))
+		return -EINVAL;
+
+	if (target_offset + t->u.target_size > next_offset)
+		return -EINVAL;
+
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
+		return -EINVAL;
+
+	/* compat_xt_entry match has less strict aligment requirements,
+	 * otherwise they are identical.  In case of padding differences
+	 * we need to add compat version of xt_check_entry_match.
+	 */
+	BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match));
+
+	return xt_check_entry_match(elems, base + target_offset,
+				    __alignof__(struct compat_xt_entry_match));
+}
+EXPORT_SYMBOL(xt_compat_check_entry_offsets);
 #endif /* CONFIG_COMPAT */
 
+/**
+ * xt_check_entry_offsets - validate arp/ip/ip6t_entry
+ *
+ * @base: pointer to arp/ip/ip6t_entry
+ * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems
+ * @target_offset: the arp/ip/ip6_t->target_offset
+ * @next_offset: the arp/ip/ip6_t->next_offset
+ *
+ * validates that target_offset and next_offset are sane and that all
+ * match sizes (if any) align with the target offset.
+ *
+ * This function does not validate the targets or matches themselves, it
+ * only tests that all the offsets and sizes are correct, that all
+ * match structures are aligned, and that the last structure ends where
+ * the target structure begins.
+ *
+ * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
+ *
+ * The arp/ip/ip6t_entry structure @base must have passed following tests:
+ * - it must point to a valid memory location
+ * - base to base + next_offset must be accessible, i.e. not exceed allocated
+ *   length.
+ *
+ * A well-formed entry looks like this:
+ *
+ * ip(6)t_entry   match [mtdata]  match [mtdata] target [tgdata] ip(6)t_entry
+ * e->elems[]-----'                              |               |
+ *                matchsize                      |               |
+ *                                matchsize      |               |
+ *                                               |               |
+ * target_offset---------------------------------'               |
+ * next_offset---------------------------------------------------'
+ *
+ * elems[]: flexible array member at end of ip(6)/arpt_entry struct.
+ *          This is where matches (if any) and the target reside.
+ * target_offset: beginning of target.
+ * next_offset: start of the next rule; also: size of this rule.
+ * Since targets have a minimum size, target_offset + minlen <= next_offset.
+ *
+ * Every match stores its size, sum of sizes must not exceed target_offset.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int xt_check_entry_offsets(const void *base,
+			   const char *elems,
+			   unsigned int target_offset,
+			   unsigned int next_offset)
+{
+	long size_of_base_struct = elems - (const char *)base;
+	const struct xt_entry_target *t;
+	const char *e = base;
+
+	/* target start is within the ip/ip6/arpt_entry struct */
+	if (target_offset < size_of_base_struct)
+		return -EINVAL;
+
+	if (target_offset + sizeof(*t) > next_offset)
+		return -EINVAL;
+
+	t = (void *)(e + target_offset);
+	if (t->u.target_size < sizeof(*t))
+		return -EINVAL;
+
+	if (target_offset + t->u.target_size > next_offset)
+		return -EINVAL;
+
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
+	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
+		return -EINVAL;
+
+	return xt_check_entry_match(elems, base + target_offset,
+				    __alignof__(struct xt_entry_match));
+}
+EXPORT_SYMBOL(xt_check_entry_offsets);
+
 int xt_check_target(struct xt_tgchk_param *par,
 		    unsigned int size, u_int8_t proto, bool inv_proto)
 {
@@ -590,6 +751,80 @@ int xt_check_target(struct xt_tgchk_param *par,
 }
 EXPORT_SYMBOL_GPL(xt_check_target);
 
+/**
+ * xt_copy_counters_from_user - copy counters and metadata from userspace
+ *
+ * @user: src pointer to userspace memory
+ * @len: alleged size of userspace memory
+ * @info: where to store the xt_counters_info metadata
+ * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel
+ *
+ * Copies counter meta data from @user and stores it in @info.
+ *
+ * vmallocs memory to hold the counters, then copies the counter data
+ * from @user to the new memory and returns a pointer to it.
+ *
+ * If @compat is true, @info gets converted automatically to the 64bit
+ * representation.
+ *
+ * The metadata associated with the counters is stored in @info.
+ *
+ * Return: returns pointer that caller has to test via IS_ERR().
+ * If IS_ERR is false, caller has to vfree the pointer.
+ */
+void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
+				 struct xt_counters_info *info, bool compat)
+{
+	void *mem;
+	u64 size;
+
+#ifdef CONFIG_COMPAT
+	if (compat) {
+		/* structures only differ in size due to alignment */
+		struct compat_xt_counters_info compat_tmp;
+
+		if (len <= sizeof(compat_tmp))
+			return ERR_PTR(-EINVAL);
+
+		len -= sizeof(compat_tmp);
+		if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
+			return ERR_PTR(-EFAULT);
+
+		strlcpy(info->name, compat_tmp.name, sizeof(info->name));
+		info->num_counters = compat_tmp.num_counters;
+		user += sizeof(compat_tmp);
+	} else
+#endif
+	{
+		if (len <= sizeof(*info))
+			return ERR_PTR(-EINVAL);
+
+		len -= sizeof(*info);
+		if (copy_from_user(info, user, sizeof(*info)) != 0)
+			return ERR_PTR(-EFAULT);
+
+		info->name[sizeof(info->name) - 1] = '\0';
+		user += sizeof(*info);
+	}
+
+	size = sizeof(struct xt_counters);
+	size *= info->num_counters;
+
+	if (size != (u64)len)
+		return ERR_PTR(-EINVAL);
+
+	mem = vmalloc(len);
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(mem, user, len) == 0)
+		return mem;
+
+	vfree(mem);
+	return ERR_PTR(-EFAULT);
+}
+EXPORT_SYMBOL_GPL(xt_copy_counters_from_user);
+
 #ifdef CONFIG_COMPAT
 int xt_compat_target_offset(const struct xt_target *target)
 {
@@ -605,6 +840,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 	struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
 	int pad, off = xt_compat_target_offset(target);
 	u_int16_t tsize = ct->u.user.target_size;
+	char name[sizeof(t->u.user.name)];
 
 	t = *dstptr;
 	memcpy(t, ct, sizeof(*ct));
@@ -618,6 +854,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 
 	tsize += off;
 	t->u.user.target_size = tsize;
+	strlcpy(name, target->name, sizeof(name));
+	module_put(target->me);
+	strncpy(t->u.user.name, name, sizeof(t->u.user.name));
 
 	*size += off;
 	*dstptr += tsize;
@@ -658,6 +897,12 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	struct xt_table_info *info = NULL;
 	size_t sz = sizeof(*info) + size;
 
+	if (sz < sizeof(*info))
+		return NULL;
+
+	if (sz < sizeof(*info))
+		return NULL;
+
 	/* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */
 	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages)
 		return NULL;
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index b7c43def0dc6..00f798b20b20 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -104,7 +104,7 @@ tcpmss_mangle_packet(struct sk_buff *skb,
 	tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
 	tcp_hdrlen = tcph->doff * 4;
 
-	if (len < tcp_hdrlen)
+	if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr))
 		return -1;
 
 	if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
@@ -156,6 +156,10 @@ tcpmss_mangle_packet(struct sk_buff *skb,
 	if (len > tcp_hdrlen)
 		return 0;
 
+	/* tcph->doff has 4 bits, do not wrap it to 0 */
+	if (tcp_hdrlen >= 15 * 4)
+		return 0;
+
 	/*
 	 * MSS Option not found ?! add it..
 	 */
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 28cddc85b700..bfa2b6d5b5cf 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -824,7 +824,11 @@ socket_setattr_return:
  */
 void netlbl_sock_delattr(struct sock *sk)
 {
-	cipso_v4_sock_delattr(sk);
+	switch (sk->sk_family) {
+	case AF_INET:
+		cipso_v4_sock_delattr(sk);
+		break;
+	}
 }
 
 /**
@@ -987,7 +991,11 @@ req_setattr_return:
 */
 void netlbl_req_delattr(struct request_sock *req)
 {
-	cipso_v4_req_delattr(req);
+	switch (req->rsk_ops->family) {
+	case AF_INET:
+		cipso_v4_req_delattr(req);
+		break;
+	}
 }
 
 /**
diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig
index 2c5e95e9bfbd..5d6e8c05b3d4 100644
--- a/net/netlink/Kconfig
+++ b/net/netlink/Kconfig
@@ -2,15 +2,6 @@
 # Netlink Sockets
 #
 
-config NETLINK_MMAP
-	bool "NETLINK: mmaped IO"
-	---help---
-	  This option enables support for memory mapped netlink IO. This
-	  reduces overhead by avoiding copying data between kernel- and
-	  userspace.
-
-	  If unsure, say N.
-
 config NETLINK_DIAG
 	tristate "NETLINK: socket monitoring interface"
 	default n
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 59651af8cc27..acfb16fdcd55 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -225,7 +225,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 
 	dev_hold(dev);
 
-	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+	if (is_vmalloc_addr(skb->head))
 		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
 	else
 		nskb = skb_clone(skb, GFP_ATOMIC);
@@ -300,610 +300,8 @@ static void netlink_rcv_wake(struct sock *sk)
 		wake_up_interruptible(&nlk->wait);
 }
 
-#ifdef CONFIG_NETLINK_MMAP
-static bool netlink_rx_is_mmaped(struct sock *sk)
-{
-	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
-}
-
-static bool netlink_tx_is_mmaped(struct sock *sk)
-{
-	return nlk_sk(sk)->tx_ring.pg_vec != NULL;
-}
-
-static __pure struct page *pgvec_to_page(const void *addr)
-{
-	if (is_vmalloc_addr(addr))
-		return vmalloc_to_page(addr);
-	else
-		return virt_to_page(addr);
-}
-
-static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len)
-{
-	unsigned int i;
-
-	for (i = 0; i < len; i++) {
-		if (pg_vec[i] != NULL) {
-			if (is_vmalloc_addr(pg_vec[i]))
-				vfree(pg_vec[i]);
-			else
-				free_pages((unsigned long)pg_vec[i], order);
-		}
-	}
-	kfree(pg_vec);
-}
-
-static void *alloc_one_pg_vec_page(unsigned long order)
-{
-	void *buffer;
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO |
-			  __GFP_NOWARN | __GFP_NORETRY;
-
-	buffer = (void *)__get_free_pages(gfp_flags, order);
-	if (buffer != NULL)
-		return buffer;
-
-	buffer = vzalloc((1 << order) * PAGE_SIZE);
-	if (buffer != NULL)
-		return buffer;
-
-	gfp_flags &= ~__GFP_NORETRY;
-	return (void *)__get_free_pages(gfp_flags, order);
-}
-
-static void **alloc_pg_vec(struct netlink_sock *nlk,
-			   struct nl_mmap_req *req, unsigned int order)
-{
-	unsigned int block_nr = req->nm_block_nr;
-	unsigned int i;
-	void **pg_vec;
-
-	pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL);
-	if (pg_vec == NULL)
-		return NULL;
-
-	for (i = 0; i < block_nr; i++) {
-		pg_vec[i] = alloc_one_pg_vec_page(order);
-		if (pg_vec[i] == NULL)
-			goto err1;
-	}
-
-	return pg_vec;
-err1:
-	free_pg_vec(pg_vec, order, block_nr);
-	return NULL;
-}
-
-
-static void
-__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
-		   unsigned int order)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct sk_buff_head *queue;
-	struct netlink_ring *ring;
-
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
-	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
-	spin_lock_bh(&queue->lock);
-
-	ring->frame_max		= req->nm_frame_nr - 1;
-	ring->head		= 0;
-	ring->frame_size	= req->nm_frame_size;
-	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-	swap(ring->pg_vec_len, req->nm_block_nr);
-	swap(ring->pg_vec_order, order);
-	swap(ring->pg_vec, pg_vec);
-
-	__skb_queue_purge(queue);
-	spin_unlock_bh(&queue->lock);
-
-	WARN_ON(atomic_read(&nlk->mapped));
-
-	if (pg_vec)
-		free_pg_vec(pg_vec, order, req->nm_block_nr);
-}
-
-static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool tx_ring)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	void **pg_vec = NULL;
-	unsigned int order = 0;
-
-	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
-	if (atomic_read(&nlk->mapped))
-		return -EBUSY;
-	if (atomic_read(&ring->pending))
-		return -EBUSY;
-
-	if (req->nm_block_nr) {
-		if (ring->pg_vec != NULL)
-			return -EBUSY;
-
-		if ((int)req->nm_block_size <= 0)
-			return -EINVAL;
-		if (!PAGE_ALIGNED(req->nm_block_size))
-			return -EINVAL;
-		if (req->nm_frame_size < NL_MMAP_HDRLEN)
-			return -EINVAL;
-		if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT))
-			return -EINVAL;
-
-		ring->frames_per_block = req->nm_block_size /
-					 req->nm_frame_size;
-		if (ring->frames_per_block == 0)
-			return -EINVAL;
-		if (ring->frames_per_block * req->nm_block_nr !=
-		    req->nm_frame_nr)
-			return -EINVAL;
-
-		order = get_order(req->nm_block_size);
-		pg_vec = alloc_pg_vec(nlk, req, order);
-		if (pg_vec == NULL)
-			return -ENOMEM;
-	} else {
-		if (req->nm_frame_nr)
-			return -EINVAL;
-	}
-
-	mutex_lock(&nlk->pg_vec_lock);
-	if (atomic_read(&nlk->mapped) == 0) {
-		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
-		mutex_unlock(&nlk->pg_vec_lock);
-		return 0;
-	}
-
-	mutex_unlock(&nlk->pg_vec_lock);
-
-	if (pg_vec)
-		free_pg_vec(pg_vec, order, req->nm_block_nr);
-
-	return -EBUSY;
-}
-
-static void netlink_mm_open(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct socket *sock = file->private_data;
-	struct sock *sk = sock->sk;
-
-	if (sk)
-		atomic_inc(&nlk_sk(sk)->mapped);
-}
-
-static void netlink_mm_close(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct socket *sock = file->private_data;
-	struct sock *sk = sock->sk;
-
-	if (sk)
-		atomic_dec(&nlk_sk(sk)->mapped);
-}
-
-static const struct vm_operations_struct netlink_mmap_ops = {
-	.open	= netlink_mm_open,
-	.close	= netlink_mm_close,
-};
-
-static int netlink_mmap(struct file *file, struct socket *sock,
-			struct vm_area_struct *vma)
-{
-	struct sock *sk = sock->sk;
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	unsigned long start, size, expected;
-	unsigned int i;
-	int err = -EINVAL;
-
-	if (vma->vm_pgoff)
-		return -EINVAL;
-
-	mutex_lock(&nlk->pg_vec_lock);
-
-	expected = 0;
-	for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
-		if (ring->pg_vec == NULL)
-			continue;
-		expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE;
-	}
-
-	if (expected == 0)
-		goto out;
-
-	size = vma->vm_end - vma->vm_start;
-	if (size != expected)
-		goto out;
-
-	start = vma->vm_start;
-	for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
-		if (ring->pg_vec == NULL)
-			continue;
-
-		for (i = 0; i < ring->pg_vec_len; i++) {
-			struct page *page;
-			void *kaddr = ring->pg_vec[i];
-			unsigned int pg_num;
-
-			for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) {
-				page = pgvec_to_page(kaddr);
-				err = vm_insert_page(vma, start, page);
-				if (err < 0)
-					goto out;
-				start += PAGE_SIZE;
-				kaddr += PAGE_SIZE;
-			}
-		}
-	}
-
-	atomic_inc(&nlk->mapped);
-	vma->vm_ops = &netlink_mmap_ops;
-	err = 0;
-out:
-	mutex_unlock(&nlk->pg_vec_lock);
-	return err;
-}
-
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
-{
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
-	struct page *p_start, *p_end;
-
-	/* First page is flushed through netlink_{get,set}_status */
-	p_start = pgvec_to_page(hdr + PAGE_SIZE);
-	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
-	while (p_start <= p_end) {
-		flush_dcache_page(p_start);
-		p_start++;
-	}
-#endif
-}
-
-static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
-{
-	smp_rmb();
-	flush_dcache_page(pgvec_to_page(hdr));
-	return hdr->nm_status;
-}
-
-static void netlink_set_status(struct nl_mmap_hdr *hdr,
-			       enum nl_mmap_status status)
-{
-	smp_mb();
-	hdr->nm_status = status;
-	flush_dcache_page(pgvec_to_page(hdr));
-}
-
-static struct nl_mmap_hdr *
-__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos)
-{
-	unsigned int pg_vec_pos, frame_off;
-
-	pg_vec_pos = pos / ring->frames_per_block;
-	frame_off  = pos % ring->frames_per_block;
-
-	return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size);
-}
-
-static struct nl_mmap_hdr *
-netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos,
-		     enum nl_mmap_status status)
-{
-	struct nl_mmap_hdr *hdr;
-
-	hdr = __netlink_lookup_frame(ring, pos);
-	if (netlink_get_status(hdr) != status)
-		return NULL;
-
-	return hdr;
-}
-
-static struct nl_mmap_hdr *
-netlink_current_frame(const struct netlink_ring *ring,
-		      enum nl_mmap_status status)
-{
-	return netlink_lookup_frame(ring, ring->head, status);
-}
-
-static void netlink_increment_head(struct netlink_ring *ring)
-{
-	ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0;
-}
-
-static void netlink_forward_ring(struct netlink_ring *ring)
-{
-	unsigned int head = ring->head;
-	const struct nl_mmap_hdr *hdr;
-
-	do {
-		hdr = __netlink_lookup_frame(ring, ring->head);
-		if (hdr->nm_status == NL_MMAP_STATUS_UNUSED)
-			break;
-		if (hdr->nm_status != NL_MMAP_STATUS_SKIP)
-			break;
-		netlink_increment_head(ring);
-	} while (ring->head != head);
-}
-
-static bool netlink_has_valid_frame(struct netlink_ring *ring)
-{
-	unsigned int head = ring->head, pos = head;
-	const struct nl_mmap_hdr *hdr;
-
-	do {
-		hdr = __netlink_lookup_frame(ring, pos);
-		if (hdr->nm_status == NL_MMAP_STATUS_VALID)
-			return true;
-		pos = pos != 0 ? pos - 1 : ring->frame_max;
-	} while (pos != head);
-
-	return false;
-}
-
-static bool netlink_dump_space(struct netlink_sock *nlk)
-{
-	struct netlink_ring *ring = &nlk->rx_ring;
-	struct nl_mmap_hdr *hdr;
-	unsigned int n;
-
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL)
-		return false;
-
-	n = ring->head + ring->frame_max / 2;
-	if (n > ring->frame_max)
-		n -= ring->frame_max;
-
-	hdr = __netlink_lookup_frame(ring, n);
-
-	return hdr->nm_status == NL_MMAP_STATUS_UNUSED;
-}
-
-static unsigned int netlink_poll(struct file *file, struct socket *sock,
-				 poll_table *wait)
-{
-	struct sock *sk = sock->sk;
-	struct netlink_sock *nlk = nlk_sk(sk);
-	unsigned int mask;
-	int err;
-
-	if (nlk->rx_ring.pg_vec != NULL) {
-		/* Memory mapped sockets don't call recvmsg(), so flow control
-		 * for dumps is performed here. A dump is allowed to continue
-		 * if at least half the ring is unused.
-		 */
-		while (nlk->cb_running && netlink_dump_space(nlk)) {
-			err = netlink_dump(sk);
-			if (err < 0) {
-				sk->sk_err = -err;
-				sk->sk_error_report(sk);
-				break;
-			}
-		}
-		netlink_rcv_wake(sk);
-	}
-
-	mask = datagram_poll(file, sock, wait);
-
-	/* We could already have received frames in the normal receive
-	 * queue, that will show up as NL_MMAP_STATUS_COPY in the ring,
-	 * so if mask contains pollin/etc already, there's no point
-	 * walking the ring.
-	 */
-	if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) {
-		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (nlk->rx_ring.pg_vec) {
-			if (netlink_has_valid_frame(&nlk->rx_ring))
-				mask |= POLLIN | POLLRDNORM;
-		}
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-	}
-
-	spin_lock_bh(&sk->sk_write_queue.lock);
-	if (nlk->tx_ring.pg_vec) {
-		if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED))
-			mask |= POLLOUT | POLLWRNORM;
-	}
-	spin_unlock_bh(&sk->sk_write_queue.lock);
-
-	return mask;
-}
-
-static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb)
-{
-	return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN);
-}
-
-static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
-				   struct netlink_ring *ring,
-				   struct nl_mmap_hdr *hdr)
-{
-	unsigned int size;
-	void *data;
-
-	size = ring->frame_size - NL_MMAP_HDRLEN;
-	data = (void *)hdr + NL_MMAP_HDRLEN;
-
-	skb->head	= data;
-	skb->data	= data;
-	skb_reset_tail_pointer(skb);
-	skb->end	= skb->tail + size;
-	skb->len	= 0;
-
-	skb->destructor	= netlink_skb_destructor;
-	NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED;
-	NETLINK_CB(skb).sk = sk;
-}
-
-static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
-				u32 dst_portid, u32 dst_group,
-				struct scm_cookie *scm)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	struct nl_mmap_hdr *hdr;
-	struct sk_buff *skb;
-	unsigned int maxlen;
-	int err = 0, len = 0;
-
-	mutex_lock(&nlk->pg_vec_lock);
-
-	ring   = &nlk->tx_ring;
-	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-
-	do {
-		unsigned int nm_len;
-
-		hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
-		if (hdr == NULL) {
-			if (!(msg->msg_flags & MSG_DONTWAIT) &&
-			    atomic_read(&nlk->tx_ring.pending))
-				schedule();
-			continue;
-		}
-
-		nm_len = ACCESS_ONCE(hdr->nm_len);
-		if (nm_len > maxlen) {
-			err = -EINVAL;
-			goto out;
-		}
-
-		netlink_frame_flush_dcache(hdr, nm_len);
-
-		skb = alloc_skb(nm_len, GFP_KERNEL);
-		if (skb == NULL) {
-			err = -ENOBUFS;
-			goto out;
-		}
-		__skb_put(skb, nm_len);
-		memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
-		netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
-
-		netlink_increment_head(ring);
-
-		NETLINK_CB(skb).portid	  = nlk->portid;
-		NETLINK_CB(skb).dst_group = dst_group;
-		NETLINK_CB(skb).creds	  = scm->creds;
-
-		err = security_netlink_send(sk, skb);
-		if (err) {
-			kfree_skb(skb);
-			goto out;
-		}
-
-		if (unlikely(dst_group)) {
-			atomic_inc(&skb->users);
-			netlink_broadcast(sk, skb, dst_portid, dst_group,
-					  GFP_KERNEL);
-		}
-		err = netlink_unicast(sk, skb, dst_portid,
-				      msg->msg_flags & MSG_DONTWAIT);
-		if (err < 0)
-			goto out;
-		len += err;
-
-	} while (hdr != NULL ||
-		 (!(msg->msg_flags & MSG_DONTWAIT) &&
-		  atomic_read(&nlk->tx_ring.pending)));
-
-	if (len > 0)
-		err = len;
-out:
-	mutex_unlock(&nlk->pg_vec_lock);
-	return err;
-}
-
-static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
-{
-	struct nl_mmap_hdr *hdr;
-
-	hdr = netlink_mmap_hdr(skb);
-	hdr->nm_len	= skb->len;
-	hdr->nm_group	= NETLINK_CB(skb).dst_group;
-	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
-	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
-	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_frame_flush_dcache(hdr, hdr->nm_len);
-	netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
-
-	NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
-	kfree_skb(skb);
-}
-
-static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring = &nlk->rx_ring;
-	struct nl_mmap_hdr *hdr;
-
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL) {
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-		kfree_skb(skb);
-		netlink_overrun(sk);
-		return;
-	}
-	netlink_increment_head(ring);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-
-	hdr->nm_len	= skb->len;
-	hdr->nm_group	= NETLINK_CB(skb).dst_group;
-	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
-	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
-	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_set_status(hdr, NL_MMAP_STATUS_COPY);
-}
-
-#else /* CONFIG_NETLINK_MMAP */
-#define netlink_rx_is_mmaped(sk)	false
-#define netlink_tx_is_mmaped(sk)	false
-#define netlink_mmap			sock_no_mmap
-#define netlink_poll			datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm)	0
-#endif /* CONFIG_NETLINK_MMAP */
-
 static void netlink_skb_destructor(struct sk_buff *skb)
 {
-#ifdef CONFIG_NETLINK_MMAP
-	struct nl_mmap_hdr *hdr;
-	struct netlink_ring *ring;
-	struct sock *sk;
-
-	/* If a packet from the kernel to userspace was freed because of an
-	 * error without being delivered to userspace, the kernel must reset
-	 * the status. In the direction userspace to kernel, the status is
-	 * always reset here after the packet was processed and freed.
-	 */
-	if (netlink_skb_is_mmaped(skb)) {
-		hdr = netlink_mmap_hdr(skb);
-		sk = NETLINK_CB(skb).sk;
-
-		if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) {
-			netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
-			ring = &nlk_sk(sk)->tx_ring;
-		} else {
-			if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) {
-				hdr->nm_len = 0;
-				netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
-			}
-			ring = &nlk_sk(sk)->rx_ring;
-		}
-
-		WARN_ON(atomic_read(&ring->pending) == 0);
-		atomic_dec(&ring->pending);
-		sock_put(sk);
-
-		skb->head = NULL;
-	}
-#endif
 	if (is_vmalloc_addr(skb->head)) {
 		if (!skb->cloned ||
 		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
@@ -931,24 +329,11 @@ static void netlink_sock_destruct(struct sock *sk)
 	if (nlk->cb_running) {
 		if (nlk->cb.done)
 			nlk->cb.done(&nlk->cb);
-
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
 
 	skb_queue_purge(&sk->sk_receive_queue);
-#ifdef CONFIG_NETLINK_MMAP
-	if (1) {
-		struct nl_mmap_req req;
-
-		memset(&req, 0, sizeof(req));
-		if (nlk->rx_ring.pg_vec)
-			__netlink_set_ring(sk, &req, false, NULL, 0);
-		memset(&req, 0, sizeof(req));
-		if (nlk->tx_ring.pg_vec)
-			__netlink_set_ring(sk, &req, true, NULL, 0);
-	}
-#endif /* CONFIG_NETLINK_MMAP */
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
 		printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
@@ -960,6 +345,14 @@ static void netlink_sock_destruct(struct sock *sk)
 	WARN_ON(nlk_sk(sk)->groups);
 }
 
+static void netlink_sock_destruct_work(struct work_struct *work)
+{
+	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
+						work);
+
+	sk_free(&nlk->sk);
+}
+
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
  * SMP. Look, when several writers sleep and reader wakes them up, all but one
  * immediately hit write lock and grab all the cpus. Exclusive sleep solves
@@ -1194,9 +587,6 @@ static int __netlink_create(struct net *net, struct socket *sock,
 		mutex_init(nlk->cb_mutex);
 	}
 	init_waitqueue_head(&nlk->wait);
-#ifdef CONFIG_NETLINK_MMAP
-	mutex_init(&nlk->pg_vec_lock);
-#endif
 
 	sk->sk_destruct = netlink_sock_destruct;
 	sk->sk_protocol = protocol;
@@ -1265,8 +655,18 @@ out_module:
 static void deferred_put_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+	struct sock *sk = &nlk->sk;
+
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
 
-	sock_put(&nlk->sk);
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
+
+	sk_free(sk);
 }
 
 static int netlink_release(struct socket *sock)
@@ -1305,7 +705,7 @@ static int netlink_release(struct socket *sock)
 
 	skb_queue_purge(&sk->sk_write_queue);
 
-	if (nlk->portid) {
+	if (nlk->portid && nlk->bound) {
 		struct netlink_notify n = {
 						.net = sock_net(sk),
 						.protocol = sk->sk_protocol,
@@ -1728,8 +1128,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	nlk = nlk_sk(sk);
 
 	if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
-	    !netlink_skb_is_mmaped(skb)) {
+	     test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
 		DECLARE_WAITQUEUE(wait, current);
 		if (!*timeo) {
 			if (!ssk || netlink_is_kernel(ssk))
@@ -1767,14 +1166,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 
 	netlink_deliver_tap(skb);
 
-#ifdef CONFIG_NETLINK_MMAP
-	if (netlink_skb_is_mmaped(skb))
-		netlink_queue_mmaped_skb(sk, skb);
-	else if (netlink_rx_is_mmaped(sk))
-		netlink_ring_set_copied(sk, skb);
-	else
-#endif /* CONFIG_NETLINK_MMAP */
-		skb_queue_tail(&sk->sk_receive_queue, skb);
+	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk);
 	return len;
 }
@@ -1798,9 +1190,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
 	int delta;
 
 	WARN_ON(skb->sk != NULL);
-	if (netlink_skb_is_mmaped(skb))
-		return skb;
-
 	delta = skb->end - skb->tail;
 	if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize)
 		return skb;
@@ -1880,71 +1269,6 @@ struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size,
 				    unsigned int ldiff, u32 dst_portid,
 				    gfp_t gfp_mask)
 {
-#ifdef CONFIG_NETLINK_MMAP
-	unsigned int maxlen, linear_size;
-	struct sock *sk = NULL;
-	struct sk_buff *skb;
-	struct netlink_ring *ring;
-	struct nl_mmap_hdr *hdr;
-
-	sk = netlink_getsockbyportid(ssk, dst_portid);
-	if (IS_ERR(sk))
-		goto out;
-
-	ring = &nlk_sk(sk)->rx_ring;
-	/* fast-path without atomic ops for common case: non-mmaped receiver */
-	if (ring->pg_vec == NULL)
-		goto out_put;
-
-	/* We need to account the full linear size needed as a ring
-	 * slot cannot have non-linear parts.
-	 */
-	linear_size = size + ldiff;
-	if (ring->frame_size - NL_MMAP_HDRLEN < linear_size)
-		goto out_put;
-
-	skb = alloc_skb_head(gfp_mask);
-	if (skb == NULL)
-		goto err1;
-
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	/* check again under lock */
-	if (ring->pg_vec == NULL)
-		goto out_free;
-
-	/* check again under lock */
-	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-	if (maxlen < linear_size)
-		goto out_free;
-
-	netlink_forward_ring(ring);
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL)
-		goto err2;
-
-	netlink_ring_setup_skb(skb, sk, ring, hdr);
-	netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
-	atomic_inc(&ring->pending);
-	netlink_increment_head(ring);
-
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-	return skb;
-
-err2:
-	kfree_skb(skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-	netlink_overrun(sk);
-err1:
-	sock_put(sk);
-	return NULL;
-
-out_free:
-	kfree_skb(skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-out_put:
-	sock_put(sk);
-out:
-#endif
 	return alloc_skb(size, gfp_mask);
 }
 EXPORT_SYMBOL_GPL(__netlink_alloc_skb);
@@ -2225,8 +1549,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	if (level != SOL_NETLINK)
 		return -ENOPROTOOPT;
 
-	if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING &&
-	    optlen >= sizeof(int) &&
+	if (optlen >= sizeof(int) &&
 	    get_user(val, (unsigned int __user *)optval))
 		return -EFAULT;
 
@@ -2279,25 +1602,6 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		}
 		err = 0;
 		break;
-#ifdef CONFIG_NETLINK_MMAP
-	case NETLINK_RX_RING:
-	case NETLINK_TX_RING: {
-		struct nl_mmap_req req;
-
-		/* Rings might consume more memory than queue limits, require
-		 * CAP_NET_ADMIN.
-		 */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		if (optlen < sizeof(req))
-			return -EINVAL;
-		if (copy_from_user(&req, optval, sizeof(req)))
-			return -EFAULT;
-		err = netlink_set_ring(sk, &req,
-				       optname == NETLINK_TX_RING);
-		break;
-	}
-#endif /* CONFIG_NETLINK_MMAP */
 	case NETLINK_LISTEN_ALL_NSID:
 		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
 			return -EPERM;
@@ -2467,18 +1771,6 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		smp_rmb();
 	}
 
-	/* It's a really convoluted way for userland to ask for mmaped
-	 * sendmsg(), but that's what we've got...
-	 */
-	if (netlink_tx_is_mmaped(sk) &&
-	    iter_is_iovec(&msg->msg_iter) &&
-	    msg->msg_iter.nr_segs == 1 &&
-	    msg->msg_iter.iov->iov_base == NULL) {
-		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
-					   &scm);
-		goto out;
-	}
-
 	err = -EMSGSIZE;
 	if (len > sk->sk_sndbuf - 32)
 		goto out;
@@ -2557,7 +1849,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	/* Record the max length of recvmsg() calls for future allocations */
 	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
 	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
-				     16384);
+				     SKB_WITH_OVERHEAD(32768));
 
 	copied = data_skb->len;
 	if (len < copied) {
@@ -2784,6 +2076,7 @@ static int netlink_dump(struct sock *sk)
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
+	struct module *module;
 	int len, err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
@@ -2794,8 +2087,7 @@ static int netlink_dump(struct sock *sk)
 		goto errout_skb;
 	}
 
-	if (!netlink_rx_is_mmaped(sk) &&
-	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
 
 	/* NLMSG_GOODSIZE is small to avoid high order allocations being
@@ -2809,9 +2101,8 @@ static int netlink_dump(struct sock *sk)
 	if (alloc_min_size < nlk->max_recvmsg_len) {
 		alloc_size = nlk->max_recvmsg_len;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
-					GFP_KERNEL |
-					__GFP_NOWARN |
-					__GFP_NORETRY);
+					(GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) |
+					__GFP_NOWARN | __GFP_NORETRY);
 	}
 	if (!skb) {
 		alloc_size = alloc_min_size;
@@ -2863,9 +2154,11 @@ static int netlink_dump(struct sock *sk)
 		cb->done(cb);
 
 	nlk->cb_running = false;
+	module = cb->module;
+	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
-	module_put(cb->module);
-	consume_skb(cb->skb);
+	module_put(module);
+	consume_skb(skb);
 	return 0;
 
 errout_skb:
@@ -2883,16 +2176,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	struct netlink_sock *nlk;
 	int ret;
 
-	/* Memory mapped dump requests need to be copied to avoid looping
-	 * on the pending state in netlink_mmap_sendmsg() while the CB hold
-	 * a reference to the skb.
-	 */
-	if (netlink_skb_is_mmaped(skb)) {
-		skb = skb_copy(skb, GFP_KERNEL);
-		if (skb == NULL)
-			return -ENOBUFS;
-	} else
-		atomic_inc(&skb->users);
+	atomic_inc(&skb->users);
 
 	sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
 	if (sk == NULL) {
@@ -3236,7 +2520,7 @@ static const struct proto_ops netlink_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	netlink_getname,
-	.poll =		netlink_poll,
+	.poll =		datagram_poll,
 	.ioctl =	sock_no_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -3244,7 +2528,7 @@ static const struct proto_ops netlink_ops = {
 	.getsockopt =	netlink_getsockopt,
 	.sendmsg =	netlink_sendmsg,
 	.recvmsg =	netlink_recvmsg,
-	.mmap =		netlink_mmap,
+	.mmap =		sock_no_mmap,
 	.sendpage =	sock_no_sendpage,
 };
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 14437d9b1965..ea4600aea6b0 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -3,6 +3,7 @@
 
 #include <linux/rhashtable.h>
 #include <linux/atomic.h>
+#include <linux/workqueue.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -44,15 +45,10 @@ struct netlink_sock {
 	int			(*netlink_bind)(struct net *net, int group);
 	void			(*netlink_unbind)(struct net *net, int group);
 	struct module		*module;
-#ifdef CONFIG_NETLINK_MMAP
-	struct mutex		pg_vec_lock;
-	struct netlink_ring	rx_ring;
-	struct netlink_ring	tx_ring;
-	atomic_t		mapped;
-#endif /* CONFIG_NETLINK_MMAP */
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
+	struct work_struct	work;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
@@ -60,15 +56,6 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
-static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-#ifdef CONFIG_NETLINK_MMAP
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-#else
-	return false;
-#endif /* CONFIG_NETLINK_MMAP */
-}
-
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 3ee63a3cff30..8dd836a8dd60 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -8,41 +8,6 @@
 
 #include "af_netlink.h"
 
-#ifdef CONFIG_NETLINK_MMAP
-static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type,
-			    struct sk_buff *nlskb)
-{
-	struct netlink_diag_ring ndr;
-
-	ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT;
-	ndr.ndr_block_nr   = ring->pg_vec_len;
-	ndr.ndr_frame_size = ring->frame_size;
-	ndr.ndr_frame_nr   = ring->frame_max + 1;
-
-	return nla_put(nlskb, nl_type, sizeof(ndr), &ndr);
-}
-
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	int ret;
-
-	mutex_lock(&nlk->pg_vec_lock);
-	ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb);
-	if (!ret)
-		ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING,
-				       nlskb);
-	mutex_unlock(&nlk->pg_vec_lock);
-
-	return ret;
-}
-#else
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	return 0;
-}
-#endif
-
 static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -87,10 +52,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
-	if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) &&
-	    sk_diag_put_rings_cfg(sk, skb))
-		goto out_nlmsg_trim;
-
 	nlmsg_end(skb, nlh);
 	return 0;
 
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 1fe3d3b362c0..c5a2c7e733b3 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -969,6 +969,8 @@ static void nfc_release(struct device *d)
 			kfree(se);
 	}
 
+	ida_simple_remove(&nfc_index_ida, dev->idx);
+
 	kfree(dev);
 }
 
@@ -1043,6 +1045,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 				    int tx_headroom, int tx_tailroom)
 {
 	struct nfc_dev *dev;
+	int rc;
 
 	if (!ops->start_poll || !ops->stop_poll || !ops->activate_target ||
 	    !ops->deactivate_target || !ops->im_transceive)
@@ -1055,6 +1058,15 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 	if (!dev)
 		return NULL;
 
+	rc = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL);
+	if (rc < 0)
+		goto err_free_dev;
+	dev->idx = rc;
+
+	dev->dev.class = &nfc_class;
+	dev_set_name(&dev->dev, "nfc%d", dev->idx);
+	device_initialize(&dev->dev);
+
 	dev->ops = ops;
 	dev->supported_protocols = supported_protocols;
 	dev->tx_headroom = tx_headroom;
@@ -1077,6 +1089,11 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 	}
 
 	return dev;
+
+err_free_dev:
+	kfree(dev);
+
+	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL(nfc_allocate_device);
 
@@ -1091,14 +1108,6 @@ int nfc_register_device(struct nfc_dev *dev)
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
-	dev->idx = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL);
-	if (dev->idx < 0)
-		return dev->idx;
-
-	dev->dev.class = &nfc_class;
-	dev_set_name(&dev->dev, "nfc%d", dev->idx);
-	device_initialize(&dev->dev);
-
 	mutex_lock(&nfc_devlist_mutex);
 	nfc_devlist_generation++;
 	rc = device_add(&dev->dev);
@@ -1136,12 +1145,10 @@ EXPORT_SYMBOL(nfc_register_device);
  */
 void nfc_unregister_device(struct nfc_dev *dev)
 {
-	int rc, id;
+	int rc;
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
-	id = dev->idx;
-
 	if (dev->rfkill) {
 		rfkill_unregister(dev->rfkill);
 		rfkill_destroy(dev->rfkill);
@@ -1166,8 +1173,6 @@ void nfc_unregister_device(struct nfc_dev *dev)
 	nfc_devlist_generation++;
 	device_del(&dev->dev);
 	mutex_unlock(&nfc_devlist_mutex);
-
-	ida_simple_remove(&nfc_index_ida, id);
 }
 EXPORT_SYMBOL(nfc_unregister_device);
 
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ecf0a0196f18..9c222a106c7f 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -76,7 +76,8 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	struct sockaddr_nfc_llcp llcp_addr;
 	int len, ret = 0;
 
-	if (!addr || addr->sa_family != AF_NFC)
+	if (!addr || alen < offsetofend(struct sockaddr, sa_family) ||
+	    addr->sa_family != AF_NFC)
 		return -EINVAL;
 
 	pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family);
@@ -150,7 +151,8 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr,
 	struct sockaddr_nfc_llcp llcp_addr;
 	int len, ret = 0;
 
-	if (!addr || addr->sa_family != AF_NFC)
+	if (!addr || alen < offsetofend(struct sockaddr, sa_family) ||
+	    addr->sa_family != AF_NFC)
 		return -EINVAL;
 
 	pr_debug("sk %p addr %p family %d\n", sk, addr, addr->sa_family);
@@ -655,8 +657,7 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 
 	pr_debug("sock %p sk %p flags 0x%x\n", sock, sk, flags);
 
-	if (!addr || len < sizeof(struct sockaddr_nfc) ||
-	    addr->sa_family != AF_NFC)
+	if (!addr || len < sizeof(*addr) || addr->sa_family != AF_NFC)
 		return -EINVAL;
 
 	if (addr->service_name_len == 0 && addr->dsap == 0)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 10c99a578421..67583ad7f610 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1084,8 +1084,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 	return ndev;
 
 free_nfc:
-	kfree(ndev->nfc_dev);
-
+	nfc_free_device(ndev->nfc_dev);
 free_nci:
 	kfree(ndev);
 	return NULL;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index f58c1fba1026..12dfb457275d 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -873,7 +873,9 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info)
 	u32 device_idx, target_idx, protocol;
 	int rc;
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
+	    !info->attrs[NFC_ATTR_TARGET_INDEX] ||
+	    !info->attrs[NFC_ATTR_PROTOCOLS])
 		return -EINVAL;
 
 	device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c88d0f2d3e01..7cb8184ac165 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -158,9 +158,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
 	*new_mpls_lse = mpls->mpls_lse;
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
-							     MPLS_HLEN, 0));
+	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
 
 	hdr = eth_hdr(skb);
 	hdr->h_proto = mpls->mpls_ethertype;
@@ -280,7 +278,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
 			       mask->eth_dst);
 
-	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+	skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
 	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
 	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
@@ -463,7 +461,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
 
 		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
-			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
 				      true);
 			memcpy(&flow_key->ipv6.addr.src, masked,
 			       sizeof(flow_key->ipv6.addr.src));
@@ -485,7 +483,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 							     NULL, &flags)
 					       != NEXTHDR_ROUTING);
 
-			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
 				      recalc_csum);
 			memcpy(&flow_key->ipv6.addr.dst, masked,
 			       sizeof(flow_key->ipv6.addr.dst));
@@ -639,7 +637,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	/* Reconstruct the MAC header.  */
 	skb_push(skb, data->l2_len);
 	memcpy(skb->data, &data->l2_data, data->l2_len);
-	ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+	skb_postpush_rcsum(skb, skb->data, data->l2_len);
 	skb_reset_mac_header(skb);
 
 	ovs_vport_send(vport, skb);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e004067ec24a..6a2507f24b0f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -501,7 +501,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 	/* The conntrack module expects to be working at L3. */
 	nh_ofs = skb_network_offset(skb);
-	skb_pull(skb, nh_ofs);
+	skb_pull_rcsum(skb, nh_ofs);
 
 	if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
 		err = handle_fragments(net, key, info->zone.id, skb);
@@ -527,6 +527,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 					&info->labels.mask);
 err:
 	skb_push(skb, nh_ofs);
+	skb_postpush_rcsum(skb, skb->data, nh_ofs);
 	if (err)
 		kfree_skb(skb);
 	return err;
@@ -576,8 +577,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		int maxlen = ovs_ct_attr_lens[type].maxlen;
-		int minlen = ovs_ct_attr_lens[type].minlen;
+		int maxlen;
+		int minlen;
 
 		if (type > OVS_CT_ATTR_MAX) {
 			OVS_NLERR(log,
@@ -585,6 +586,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				  type, OVS_CT_ATTR_MAX);
 			return -EINVAL;
 		}
+
+		maxlen = ovs_ct_attr_lens[type].maxlen;
+		minlen = ovs_ct_attr_lens[type].minlen;
 		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
 			OVS_NLERR(log,
 				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index d1bd4a45ca2d..d26b28def310 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
-			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
 					nla_get_in6_addr(a), is_mask);
 			ipv6 = true;
 			break;
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 6b0190b987ec..76fcaf1fd2a9 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -58,7 +58,7 @@ static void netdev_port_receive(struct sk_buff *skb)
 		return;
 
 	skb_push(skb, ETH_HLEN);
-	ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
 	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
 	return;
 error:
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index d933cb89efac..5eb7694348b5 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -91,6 +91,8 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	struct vxlan_config conf = {
 		.no_share = true,
 		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
 	};
 
 	if (!options) {
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 8ea3a96980ac..6e2b62f9d595 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -184,13 +184,6 @@ static inline struct vport *vport_from_priv(void *priv)
 int ovs_vport_receive(struct vport *, struct sk_buff *,
 		      const struct ip_tunnel_info *);
 
-static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
-				      const void *start, unsigned int len)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
-}
-
 static inline const char *ovs_vport_name(struct vport *vport)
 {
 	return vport->dev->name;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 992396aa635c..148ec130d99d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -249,7 +249,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	netdev_features_t features;
+	struct sk_buff *orig_skb = skb;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
 
@@ -257,9 +257,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
 		     !netif_carrier_ok(dev)))
 		goto drop;
 
-	features = netif_skb_features(skb);
-	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb))
+	skb = validate_xmit_skb_list(skb, dev);
+	if (skb != orig_skb)
 		goto drop;
 
 	txq = skb_get_tx_queue(dev, skb);
@@ -279,7 +278,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
 
@@ -1341,7 +1340,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb_get_hash(skb), num);
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1498,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	f->arr[f->num_members] = sk;
 	smp_wmb();
 	f->num_members++;
+	if (f->num_members == 1)
+		dev_add_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1514,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	BUG_ON(i >= f->num_members);
 	f->arr[i] = f->arr[f->num_members - 1];
 	f->num_members--;
+	if (f->num_members == 0)
+		__dev_remove_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1624,6 +1627,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1646,23 +1650,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1692,7 +1701,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1709,36 +1717,40 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
+	mutex_lock(&fanout_mutex);
 	f = po->fanout;
-	if (!f)
-		return;
+	if (f) {
+		po->fanout = NULL;
 
-	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+		if (atomic_dec_and_test(&f->sk_ref))
+			list_del(&f->list);
+		else
+			f = NULL;
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
 
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
+	return f;
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -1916,6 +1928,10 @@ retry:
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2326,18 +2342,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static bool ll_header_truncated(const struct net_device *dev, int len)
-{
-	/* net device doesn't like empty head */
-	if (unlikely(len < dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2420,19 +2424,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		if (ll_header_truncated(dev, tp_len))
-			return -EINVAL;
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2646,7 +2650,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	int vnet_hdr_len;
 	struct packet_sock *po = pkt_sk(sk);
 	unsigned short gso_type = 0;
-	int hlen, tlen;
+	int hlen, tlen, linear;
 	int extra_len = 0;
 	ssize_t n;
 
@@ -2750,8 +2754,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+	linear = max(linear, min_t(int, len, dev->hard_header_len));
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2763,9 +2768,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
@@ -2773,6 +2775,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
@@ -2851,6 +2859,7 @@ static int packet_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po;
+	struct packet_fanout *f;
 	struct net *net;
 	union tpacket_req_u req_u;
 
@@ -2890,9 +2899,14 @@ static int packet_release(struct socket *sock)
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
 
-	fanout_release(sk);
+	f = fanout_release(sk);
 
 	synchronize_net();
+
+	if (f) {
+		fanout_release_data(f);
+		kfree(f);
+	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
 	 */
@@ -3007,7 +3021,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3015,7 +3029,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+	name[sizeof(uaddr->sa_data)] = 0;
 
 	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
@@ -3441,6 +3459,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
 	i->ifindex = mreq->mr_ifindex;
 	i->alen = mreq->mr_alen;
 	memcpy(i->addr, mreq->mr_address, i->alen);
+	memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
 	i->count = 1;
 	i->next = po->mclist;
 	po->mclist = i;
@@ -3577,19 +3596,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 		switch (val) {
 		case TPACKET_V1:
 		case TPACKET_V2:
 		case TPACKET_V3:
-			po->tp_version = val;
-			return 0;
+			break;
 		default:
 			return -EINVAL;
 		}
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_version = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_RESERVE:
 	{
@@ -3597,12 +3622,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_reserve = val;
-		return 0;
+		if (val > INT_MAX)
+			return -EINVAL;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_reserve = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_LOSS:
 	{
@@ -4071,6 +4103,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
+	lock_sock(sk);
 	/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
 	if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
 		WARN(1, "Tx-ring is not supported.\n");
@@ -4112,8 +4145,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
-		    (int)(req->tp_block_size -
-			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+		    req->tp_block_size <=
+			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
@@ -4124,6 +4157,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;
@@ -4152,7 +4187,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 	}
 
-	lock_sock(sk);
 
 	/* Detach socket from network */
 	spin_lock(&po->bind_lock);
@@ -4196,16 +4230,16 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		register_prot_hook(sk);
 	}
 	spin_unlock(&po->bind_lock);
-	if (closing && (po->tp_version > TPACKET_V2)) {
+	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
-	release_sock(sk);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
+	release_sock(sk);
 	return err;
 }
 
diff --git a/net/rds/cong.c b/net/rds/cong.c
index e6144b8246fd..6641bcf7c185 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -299,7 +299,7 @@ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port)
 	i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS;
 	off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS;
 
-	__set_bit_le(off, (void *)map->m_page_addrs[i]);
+	set_bit_le(off, (void *)map->m_page_addrs[i]);
 }
 
 void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port)
@@ -313,7 +313,7 @@ void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port)
 	i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS;
 	off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS;
 
-	__clear_bit_le(off, (void *)map->m_page_addrs[i]);
+	clear_bit_le(off, (void *)map->m_page_addrs[i]);
 }
 
 static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port)
diff --git a/net/rds/recv.c b/net/rds/recv.c
index a00462b0d01d..0514af3ab378 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -545,5 +545,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 		minfo.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo.flags = 0;
+
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 9d6ddbacd875..18e50a8fc05f 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -421,7 +421,7 @@ static int rds_tcp_init(void)
 
 	ret = rds_tcp_recv_init();
 	if (ret)
-		goto out_slab;
+		goto out_pernet;
 
 	ret = rds_trans_register(&rds_tcp_transport);
 	if (ret)
@@ -433,8 +433,9 @@ static int rds_tcp_init(void)
 
 out_recv:
 	rds_tcp_recv_exit();
-out_slab:
+out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
+out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 0936a4a32b47..e353e3255206 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -78,7 +78,7 @@ int rds_tcp_accept_one(struct socket *sock)
 	struct inet_sock *inet;
 	struct rds_tcp_connection *rs_tcp;
 
-	ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
+	ret = sock_create_lite(sock->sk->sk_family,
 			       sock->sk->sk_type, sock->sk->sk_protocol,
 			       &new_sock);
 	if (ret)
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index da3cc09f683e..91d43ab3a961 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -215,7 +215,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ,
 				       unsigned int *_toklen)
 {
 	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, n_parts, loop, tmp;
+	unsigned int toklen = *_toklen, n_parts, loop, tmp, paddedlen;
 
 	/* there must be at least one name, and at least #names+1 length
 	 * words */
@@ -245,16 +245,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ,
 		toklen -= 4;
 		if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX)
 			return -EINVAL;
-		if (tmp > toklen)
+		paddedlen = (tmp + 3) & ~3;
+		if (paddedlen > toklen)
 			return -EINVAL;
 		princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL);
 		if (!princ->name_parts[loop])
 			return -ENOMEM;
 		memcpy(princ->name_parts[loop], xdr, tmp);
 		princ->name_parts[loop][tmp] = 0;
-		tmp = (tmp + 3) & ~3;
-		toklen -= tmp;
-		xdr += tmp >> 2;
+		toklen -= paddedlen;
+		xdr += paddedlen >> 2;
 	}
 
 	if (toklen < 4)
@@ -263,16 +263,16 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ,
 	toklen -= 4;
 	if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX)
 		return -EINVAL;
-	if (tmp > toklen)
+	paddedlen = (tmp + 3) & ~3;
+	if (paddedlen > toklen)
 		return -EINVAL;
 	princ->realm = kmalloc(tmp + 1, GFP_KERNEL);
 	if (!princ->realm)
 		return -ENOMEM;
 	memcpy(princ->realm, xdr, tmp);
 	princ->realm[tmp] = 0;
-	tmp = (tmp + 3) & ~3;
-	toklen -= tmp;
-	xdr += tmp >> 2;
+	toklen -= paddedlen;
+	xdr += paddedlen >> 2;
 
 	_debug("%s/...@%s", princ->name_parts[0], princ->realm);
 
@@ -291,7 +291,7 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td,
 					 unsigned int *_toklen)
 {
 	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, len;
+	unsigned int toklen = *_toklen, len, paddedlen;
 
 	/* there must be at least one tag and one length word */
 	if (toklen <= 8)
@@ -305,15 +305,17 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td,
 	toklen -= 8;
 	if (len > max_data_size)
 		return -EINVAL;
+	paddedlen = (len + 3) & ~3;
+	if (paddedlen > toklen)
+		return -EINVAL;
 	td->data_len = len;
 
 	if (len > 0) {
 		td->data = kmemdup(xdr, len, GFP_KERNEL);
 		if (!td->data)
 			return -ENOMEM;
-		len = (len + 3) & ~3;
-		toklen -= len;
-		xdr += len >> 2;
+		toklen -= paddedlen;
+		xdr += paddedlen >> 2;
 	}
 
 	_debug("tag %x len %x", td->tag, td->data_len);
@@ -385,7 +387,7 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
 				    const __be32 **_xdr, unsigned int *_toklen)
 {
 	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, len;
+	unsigned int toklen = *_toklen, len, paddedlen;
 
 	/* there must be at least one length word */
 	if (toklen <= 4)
@@ -397,6 +399,9 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
 	toklen -= 4;
 	if (len > AFSTOKEN_K5_TIX_MAX)
 		return -EINVAL;
+	paddedlen = (len + 3) & ~3;
+	if (paddedlen > toklen)
+		return -EINVAL;
 	*_tktlen = len;
 
 	_debug("ticket len %u", len);
@@ -405,9 +410,8 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
 		*_ticket = kmemdup(xdr, len, GFP_KERNEL);
 		if (!*_ticket)
 			return -ENOMEM;
-		len = (len + 3) & ~3;
-		toklen -= len;
-		xdr += len >> 2;
+		toklen -= paddedlen;
+		xdr += paddedlen >> 2;
 	}
 
 	*_xdr = xdr;
@@ -550,7 +554,7 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 {
 	const __be32 *xdr = prep->data, *token;
 	const char *cp;
-	unsigned int len, tmp, loop, ntoken, toklen, sec_ix;
+	unsigned int len, paddedlen, loop, ntoken, toklen, sec_ix;
 	size_t datalen = prep->datalen;
 	int ret;
 
@@ -576,22 +580,21 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 	if (len < 1 || len > AFSTOKEN_CELL_MAX)
 		goto not_xdr;
 	datalen -= 4;
-	tmp = (len + 3) & ~3;
-	if (tmp > datalen)
+	paddedlen = (len + 3) & ~3;
+	if (paddedlen > datalen)
 		goto not_xdr;
 
 	cp = (const char *) xdr;
 	for (loop = 0; loop < len; loop++)
 		if (!isprint(cp[loop]))
 			goto not_xdr;
-	if (len < tmp)
-		for (; loop < tmp; loop++)
-			if (cp[loop])
-				goto not_xdr;
+	for (; loop < paddedlen; loop++)
+		if (cp[loop])
+			goto not_xdr;
 	_debug("cellname: [%u/%u] '%*.*s'",
-	       len, tmp, len, len, (const char *) xdr);
-	datalen -= tmp;
-	xdr += tmp >> 2;
+	       len, paddedlen, len, len, (const char *) xdr);
+	datalen -= paddedlen;
+	xdr += paddedlen >> 2;
 
 	/* get the token count */
 	if (datalen < 12)
@@ -612,10 +615,11 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 		sec_ix = ntohl(*xdr);
 		datalen -= 4;
 		_debug("token: [%x/%zx] %x", toklen, datalen, sec_ix);
-		if (toklen < 20 || toklen > datalen)
+		paddedlen = (toklen + 3) & ~3;
+		if (toklen < 20 || toklen > datalen || paddedlen > datalen)
 			goto not_xdr;
-		datalen -= (toklen + 3) & ~3;
-		xdr += (toklen + 3) >> 2;
+		datalen -= paddedlen;
+		xdr += paddedlen >> 2;
 
 	} while (--loop > 0);
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 06e7c4a37245..694a06f1e0d5 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -820,10 +820,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 
 	err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a);
-	if (err < 0)
+	if (err <= 0)
 		goto out_module_put;
-	if (err == 0)
-		goto noflush_out;
 
 	nla_nest_end(skb, nest);
 
@@ -840,7 +838,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 out_module_put:
 	module_put(a.ops->owner);
 err_out:
-noflush_out:
 	kfree_skb(skb);
 	return err;
 }
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index bb41699c6c49..7ecb14f3db54 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -109,6 +109,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b07c535ba8e7..eeb3eb3ea9eb 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -105,9 +105,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
 	int hl = ihl + jhl;
 
 	if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
-	    (skb_cloned(skb) &&
-	     !skb_clone_writable(skb, hl + ntkoff) &&
-	     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+	    skb_try_make_writable(skb, hl + ntkoff))
 		return NULL;
 	else
 		return (void *)(skb_network_header(skb) + ihl);
@@ -365,9 +363,7 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
 	}
 
 	if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, sizeof(*iph) + ntkoff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
 			goto fail;
 
 		ip_send_check(ip_hdr(skb));
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index d05869646515..075b0d22f213 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -34,6 +34,7 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
+	struct ipt_entry e = {};
 	int ret = 0;
 
 	target = xt_request_find_target(AF_INET, t->u.user.name,
@@ -42,8 +43,9 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int
 		return PTR_ERR(target);
 
 	t->u.kernel.target = target;
+	memset(&par, 0, sizeof(par));
 	par.table     = table;
-	par.entryinfo = NULL;
+	par.entryinfo = &e;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 32fcdecdb9e2..1090a52c03cd 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -36,14 +36,15 @@ static DEFINE_SPINLOCK(mirred_list_lock);
 static void tcf_mirred_release(struct tc_action *a, int bind)
 {
 	struct tcf_mirred *m = to_mirred(a);
-	struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1);
+	struct net_device *dev;
 
 	/* We could be called either in a RCU callback or with RTNL lock held. */
 	spin_lock_bh(&mirred_list_lock);
 	list_del(&m->tcfm_list);
-	spin_unlock_bh(&mirred_list_lock);
+	dev = rcu_dereference_protected(m->tcfm_dev, 1);
 	if (dev)
 		dev_put(dev);
+	spin_unlock_bh(&mirred_list_lock);
 }
 
 static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
@@ -170,7 +171,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb->mac_len);
+			skb_push_rcsum(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index b7c4ead8b5a8..27607b863aba 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -126,9 +126,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		addr = iph->daddr;
 
 	if (!((old_addr ^ addr) & mask)) {
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, sizeof(*iph) + noff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, sizeof(*iph) + noff))
 			goto drop;
 
 		new_addr &= mask;
@@ -156,9 +154,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		struct tcphdr *tcph;
 
 		if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
-		    (skb_cloned(skb) &&
-		     !skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) &&
-		     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+		    skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
 			goto drop;
 
 		tcph = (void *)(skb_network_header(skb) + ihl);
@@ -171,9 +167,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		struct udphdr *udph;
 
 		if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
-		    (skb_cloned(skb) &&
-		     !skb_clone_writable(skb, ihl + sizeof(*udph) + noff) &&
-		     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+		    skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
 			goto drop;
 
 		udph = (void *)(skb_network_header(skb) + ihl);
@@ -213,10 +207,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		if ((old_addr ^ addr) & mask)
 			break;
 
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, ihl + sizeof(*icmph) +
-					     sizeof(*iph) + noff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
+					  sizeof(*iph) + noff))
 			goto drop;
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index e38a7701f154..c3434e902445 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -104,6 +104,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind)
 	kfree(keys);
 }
 
+static bool offset_valid(struct sk_buff *skb, int offset)
+{
+	if (offset > 0 && offset > skb->len)
+		return false;
+
+	if  (offset < 0 && -offset > skb_headroom(skb))
+		return false;
+
+	return true;
+}
+
 static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 		     struct tcf_result *res)
 {
@@ -130,6 +141,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			if (tkey->offmask) {
 				char *d, _d;
 
+				if (!offset_valid(skb, off + tkey->at)) {
+					pr_info("tc filter pedit 'at' offset %d out of bounds\n",
+						off + tkey->at);
+					goto bad;
+				}
 				d = skb_header_pointer(skb, off + tkey->at, 1,
 						       &_d);
 				if (!d)
@@ -142,10 +158,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 					" offset must be on 32 bit boundaries\n");
 				goto bad;
 			}
-			if (offset > 0 && offset > skb->len) {
-				pr_info("tc filter pedit"
-					" offset %d can't exceed pkt length %d\n",
-				       offset, skb->len);
+
+			if (!offset_valid(skb, off + offset)) {
+				pr_info("tc filter pedit offset %d out of bounds\n",
+					offset);
 				goto bad;
 			}
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 796785e0bf96..d7edba4536bd 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -33,6 +33,12 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	bstats_update(&v->tcf_bstats, skb);
 	action = v->tcf_action;
 
+	/* Ensure 'data' points at mac_header prior calling vlan manipulating
+	 * functions.
+	 */
+	if (skb_at_tc_ingress(skb))
+		skb_push_rcsum(skb, skb->mac_len);
+
 	switch (v->tcfv_action) {
 	case TCA_VLAN_ACT_POP:
 		err = skb_vlan_pop(skb);
@@ -54,6 +60,9 @@ drop:
 	action = TC_ACT_SHOT;
 	v->tcf_qstats.drops++;
 unlock:
+	if (skb_at_tc_ingress(skb))
+		skb_pull_rcsum(skb, skb->mac_len);
+
 	spin_unlock(&v->tcf_lock);
 	return action;
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a75864d93142..20b2f867c5a1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -137,13 +137,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
@@ -315,7 +317,8 @@ replay:
 			if (err == 0) {
 				struct tcf_proto *next = rtnl_dereference(tp->next);
 
-				tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+				tfilter_notify(net, skb, n, tp,
+					       t->tcm_handle, RTM_DELTFILTER);
 				if (tcf_destroy(tp, false))
 					RCU_INIT_POINTER(*back, next);
 			}
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 0b8c3ace671f..1bf1f4517db6 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(f, &head->flist, link) {
 		if (f->handle == handle) {
 			l = (unsigned long) f;
@@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force)
 		tcf_unbind_filter(tp, &f->res);
 		call_rcu(&f->rcu, basic_delete_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 5faaa5425f7b..3eef0215e53f 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -199,7 +199,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
 		call_rcu(&prog->rcu, __cls_bpf_delete_prog);
 	}
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
@@ -210,9 +209,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	struct cls_bpf_prog *prog;
 	unsigned long ret = 0UL;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(prog, &head->plist, link) {
 		if (prog->handle == handle) {
 			ret = (unsigned long) prog;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 4c85bd3a750c..c104c2019feb 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -130,11 +130,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
 
 	if (!force)
 		return false;
-
-	if (head) {
-		RCU_INIT_POINTER(tp->root, NULL);
+	/* Head can still be NULL due to cls_cgroup_init(). */
+	if (head)
 		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
-	}
+
 	return true;
 }
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index fbfec6a18839..d7ba2b4ff0f3 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -583,7 +583,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, flow_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 95b021243233..e5a58c82728a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/rhashtable.h>
+#include <linux/workqueue.h>
 
 #include <linux/if_ether.h>
 #include <linux/in6.h>
@@ -55,7 +56,10 @@ struct cls_fl_head {
 	bool mask_assigned;
 	struct list_head filters;
 	struct rhashtable_params ht_params;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 };
 
 struct cls_fl_filter {
@@ -165,6 +169,24 @@ static void fl_destroy_filter(struct rcu_head *head)
 	kfree(f);
 }
 
+static void fl_destroy_sleepable(struct work_struct *work)
+{
+	struct cls_fl_head *head = container_of(work, struct cls_fl_head,
+						work);
+	if (head->mask_assigned)
+		rhashtable_destroy(&head->ht);
+	kfree(head);
+	module_put(THIS_MODULE);
+}
+
+static void fl_destroy_rcu(struct rcu_head *rcu)
+{
+	struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu);
+
+	INIT_WORK(&head->work, fl_destroy_sleepable);
+	schedule_work(&head->work);
+}
+
 static bool fl_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
@@ -177,10 +199,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, fl_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
-	if (head->mask_assigned)
-		rhashtable_destroy(&head->ht);
-	kfree_rcu(head, rcu);
+
+	__module_get(THIS_MODULE);
+	call_rcu(&head->rcu, fl_destroy_rcu);
 	return true;
 }
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index f9c9fc075fe6..9992dfac6938 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		return -1;
 	nhptr = ip_hdr(skb);
 #endif
-
+	if (unlikely(!head))
+		return -1;
 restart:
 
 #if RSVP_DST_LEN == 4
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 944c8ff45055..403746b20263 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -503,7 +503,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force)
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	call_rcu(&p->rcu, __tcindex_destroy);
 	return true;
 }
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index af1acf009866..6d340cd6e2a7 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
@@ -1002,6 +1004,9 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 
 		return sch;
 	}
+	/* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */
+	if (ops->destroy)
+		ops->destroy(sch);
 err_out3:
 	dev_put(dev);
 	kfree((char *) sch - sch->padded);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index c538d9e4a8f6..baafddf229ce 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
@@ -1914,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
@@ -1922,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 5ffb8b8337c7..0a08c860eee4 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -456,6 +456,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -467,11 +468,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 535007d5f0b5..9b7e2980ee5c 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -116,7 +117,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -156,10 +157,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index f26bdea875c1..d6e3ad43cecb 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
@@ -226,11 +227,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index f357f34d02d2..d0dff0cd8186 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -73,13 +73,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
@@ -264,6 +258,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -286,6 +281,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -401,6 +397,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac0a61e..2e4bd2c0a50c 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -37,14 +37,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
+	unsigned int prev_backlog;
+
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
+	prev_backlog = sch->qstats.backlog;
 	/* queue full, remove one skb to fulfill the limit */
 	__qdisc_queue_drop_head(sch, &sch->q);
 	qdisc_qstats_drop(sch);
 	qdisc_enqueue_tail(skb, sch);
 
+	qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_CN;
 }
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 109b2322778f..3c6a47d66a04 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -662,6 +662,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -736,10 +737,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 4c834e93dafb..d3fc8f9dd3d4 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -175,7 +175,7 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -203,6 +203,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -211,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -241,6 +242,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -259,6 +261,7 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -276,12 +279,14 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -372,11 +377,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 16bc83b2842a..aa4725038f94 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	if (validate)
 		skb = validate_xmit_skb_list(skb, dev);
 
-	if (skb) {
+	if (likely(skb)) {
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 		HARD_TX_UNLOCK(dev, txq);
+	} else {
+		spin_lock(root_lock);
+		return qdisc_qlen(q);
 	}
 	spin_lock(root_lock);
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b7ebe2c87586..d783d7cc3348 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
@@ -1215,11 +1216,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 86b04e31e60b..45d4b2f22f62 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -382,6 +382,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
 	struct wdrr_bucket *bucket;
+	unsigned int prev_backlog;
 
 	idx = hhf_classify(skb, sch);
 
@@ -409,6 +410,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
@@ -417,7 +419,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -527,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -577,12 +579,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	qlen = sch->q.qlen;
+	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
 		kfree_skb(skb);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
+				  prev_backlog - sch->qstats.backlog);
 
 	sch_tree_unlock(sch);
 	return 0;
@@ -632,7 +636,9 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt)
 			q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN *
 						      sizeof(u32));
 			if (!q->hhf_arrays[i]) {
-				hhf_destroy(sch);
+				/* Note: hhf_destroy() will be called
+				 * by our caller.
+				 */
 				return -ENOMEM;
 			}
 		}
@@ -643,7 +649,9 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt)
 			q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN /
 							  BITS_PER_BYTE);
 			if (!q->hhf_valid_bits[i]) {
-				hhf_destroy(sch);
+				/* Note: hhf_destroy() will be called
+				 * by our caller.
+				 */
 				return -ENOMEM;
 			}
 		}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 15ccd7f8fb2a..87b02ed3d5f2 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		htb_activate(q, cl);
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch)
 			unsigned int len;
 			if (cl->un.leaf.q->ops->drop &&
 			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
+				sch->qstats.backlog -= len;
 				sch->q.qlen--;
 				if (!cl->un.leaf.q->q.qlen)
 					htb_deactivate(q, cl);
@@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch)
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
-
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
@@ -1163,14 +1166,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 				     cl->common.classid)) == NULL)
 		return -ENOBUFS;
 
-	sch_tree_lock(sch);
-	*old = cl->un.leaf.q;
-	cl->un.leaf.q = new;
-	if (*old != NULL) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->un.leaf.q);
 	return 0;
 }
 
@@ -1272,7 +1268,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	unsigned int qlen;
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
@@ -1292,9 +1287,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	if (!cl->level) {
-		qlen = cl->un.leaf.q->q.qlen;
+		unsigned int qlen = cl->un.leaf.q->q.qlen;
+		unsigned int backlog = cl->un.leaf.q->qstats.backlog;
+
 		qdisc_reset(cl->un.leaf.q);
-		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
+		qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog);
 	}
 
 	/* delete from hash and active; remainder in destroy_class */
@@ -1428,10 +1425,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
 			unsigned int qlen = parent->un.leaf.q->q.qlen;
+			unsigned int backlog = parent->un.leaf.q->qstats.backlog;
 
 			/* turn parent into inner node */
 			qdisc_reset(parent->un.leaf.q);
-			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
+			qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog);
 			qdisc_destroy(parent->un.leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 3e82f047caaf..d9c84328e7eb 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -52,7 +52,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 	/* pre-allocate qdiscs, attachment can't fail */
 	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
 			       GFP_KERNEL);
-	if (priv->qdiscs == NULL)
+	if (!priv->qdiscs)
 		return -ENOMEM;
 
 	for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
@@ -60,18 +60,14 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 		qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
 					  TC_H_MAKE(TC_H_MAJ(sch->handle),
 						    TC_H_MIN(ntx + 1)));
-		if (qdisc == NULL)
-			goto err;
+		if (!qdisc)
+			return -ENOMEM;
 		priv->qdiscs[ntx] = qdisc;
 		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
 	return 0;
-
-err:
-	mq_destroy(sch);
-	return -ENOMEM;
 }
 
 static void mq_attach(struct Qdisc *sch)
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index ad70ecf57ce7..66bccc5ff4ea 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -117,20 +117,17 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 	/* pre-allocate qdisc, attachment can't fail */
 	priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
 			       GFP_KERNEL);
-	if (priv->qdiscs == NULL) {
-		err = -ENOMEM;
-		goto err;
-	}
+	if (!priv->qdiscs)
+		return -ENOMEM;
 
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		dev_queue = netdev_get_tx_queue(dev, i);
 		qdisc = qdisc_create_dflt(dev_queue, default_qdisc_ops,
 					  TC_H_MAKE(TC_H_MAJ(sch->handle),
 						    TC_H_MIN(i + 1)));
-		if (qdisc == NULL) {
-			err = -ENOMEM;
-			goto err;
-		}
+		if (!qdisc)
+			return -ENOMEM;
+
 		priv->qdiscs[i] = qdisc;
 		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
@@ -143,7 +140,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 		priv->hw_owned = 1;
 		err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc);
 		if (err)
-			goto err;
+			return err;
 	} else {
 		netdev_set_num_tc(dev, qopt->num_tc);
 		for (i = 0; i < qopt->num_tc; i++)
@@ -157,10 +154,6 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 
 	sch->flags |= TCQ_F_MQROOT;
 	return 0;
-
-err:
-	mqprio_destroy(sch);
-	return err;
 }
 
 static void mqprio_attach(struct Qdisc *sch)
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 4e904ca0af9d..bcdd54bb101c 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen,
+						  child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
@@ -303,13 +305,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5abd1d9de989..b7c29d5b6f04 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_reshape_fail(skb, sch);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
 	struct sk_buff *skb2;
+	struct sk_buff *segs = NULL;
+	unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
+	int nb = 0;
 	int count = 1;
+	int rc = NET_XMIT_SUCCESS;
 
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
@@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * do it now in software before we mangle it.
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+		if (skb_is_gso(skb)) {
+			segs = netem_segment(skb, sch);
+			if (!segs)
+				return NET_XMIT_DROP;
+		} else {
+			segs = skb;
+		}
+
+		skb = segs;
+		segs = segs->next;
+
 		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
 		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+		     skb_checksum_help(skb))) {
+			rc = qdisc_drop(skb, sch);
+			goto finish_segs;
+		}
 
 		skb->data[prandom_u32() % skb_headlen(skb)] ^=
 			1<<(prandom_u32() % 8);
@@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (segs) {
+		while (segs) {
+			skb2 = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		sch->q.qlen += nb;
+		if (nb > 1)
+			qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	}
 	return NET_XMIT_SUCCESS;
 }
 
@@ -593,13 +650,14 @@ deliver:
 #endif
 
 			if (q->qdisc) {
+				unsigned int pkt_len = qdisc_pkt_len(skb);
 				int err = qdisc_enqueue(skb, q->qdisc);
 
-				if (unlikely(err != NET_XMIT_SUCCESS)) {
-					if (net_xmit_drop_count(err)) {
-						qdisc_qstats_drop(sch);
-						qdisc_tree_decrease_qlen(sch, 1);
-					}
+				if (err != NET_XMIT_SUCCESS &&
+				    net_xmit_drop_count(err)) {
+					qdisc_qstats_drop(sch);
+					qdisc_tree_reduce_backlog(sch, 1,
+								  pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
@@ -1037,15 +1095,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b783a446d884..71ae3b9629f9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index ba6487f2741f..fee1b15506b2 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		struct Qdisc *child = q->queues[i];
 		q->queues[i] = &noop_qdisc;
 		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
@@ -268,13 +269,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3dc3a6e56052..8d2d8d953432 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -220,9 +220,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 static void qfq_purge_queue(struct qfq_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
@@ -617,11 +618,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6c0534cc7758..8c0508c0e287 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
@@ -313,12 +314,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5bbb6332ec57..c69611640fa5 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -510,7 +510,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 
-	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+				  q->qdisc->qstats.backlog);
 	qdisc_destroy(q->qdisc);
 	q->qdisc = child;
 
@@ -606,12 +607,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 3abab534eb5c..3f2c3eed04da 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -346,7 +346,7 @@ static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
+	unsigned int hash, dropped;
 	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
@@ -434,6 +434,7 @@ congestion_drop:
 		qdisc_drop(head, sch);
 
 		slot_queue_add(slot, skb);
+		qdisc_tree_reduce_backlog(sch, 0, delta);
 		return NET_XMIT_CN;
 	}
 
@@ -461,15 +462,17 @@ enqueue:
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
-	sfq_drop(sch);
+	dropped = sfq_drop(sch);
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
-	if (qlen != slot->qlen)
+	if (qlen != slot->qlen) {
+		qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb));
 		return NET_XMIT_CN;
+	}
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, dropped);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -537,6 +540,7 @@ static void sfq_rehash(struct Qdisc *sch)
 	struct sfq_slot *slot;
 	struct sk_buff_head list;
 	int dropped = 0;
+	unsigned int drop_len = 0;
 
 	__skb_queue_head_init(&list);
 
@@ -565,6 +569,7 @@ static void sfq_rehash(struct Qdisc *sch)
 			if (x >= SFQ_MAX_FLOWS) {
 drop:
 				qdisc_qstats_backlog_dec(sch, skb);
+				drop_len += qdisc_pkt_len(skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
@@ -594,7 +599,7 @@ drop:
 		}
 	}
 	sch->q.qlen -= dropped;
-	qdisc_tree_decrease_qlen(sch, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
 static void sfq_perturbation(unsigned long arg)
@@ -618,7 +623,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
 	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
@@ -667,8 +672,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
-		sfq_drop(sch);
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+		dropped += sfq_drop(sch);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
@@ -740,9 +745,10 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->ht = sfq_alloc(sizeof(q->ht[0]) * q->divisor);
 	q->slots = sfq_alloc(sizeof(q->slots[0]) * q->maxflows);
 	if (!q->ht || !q->slots) {
-		sfq_destroy(sch);
+		/* Note: sfq_destroy() will be called by our caller */
 		return -ENOMEM;
 	}
+
 	for (i = 0; i < q->divisor; i++)
 		q->ht[i] = SFQ_EMPTY_SLOT;
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4afde14e865..c2fbde742f37 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		nskb = segs->next;
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
@@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	sch->q.qlen += nb;
 	if (nb > 1)
-		qdisc_tree_decrease_qlen(sch, 1 - nb);
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
 	consume_skb(skb);
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
@@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
@@ -502,13 +505,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sctp/input.c b/net/sctp/input.c
index b6493b3f11a9..2d7859c03fd2 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -472,15 +472,14 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 			     struct sctp_association **app,
 			     struct sctp_transport **tpp)
 {
+	struct sctp_init_chunk *chunkhdr, _chunkhdr;
 	union sctp_addr saddr;
 	union sctp_addr daddr;
 	struct sctp_af *af;
 	struct sock *sk = NULL;
 	struct sctp_association *asoc;
 	struct sctp_transport *transport = NULL;
-	struct sctp_init_chunk *chunkhdr;
 	__u32 vtag = ntohl(sctphdr->vtag);
-	int len = skb->len - ((void *)sctphdr - (void *)skb->data);
 
 	*app = NULL; *tpp = NULL;
 
@@ -515,13 +514,16 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 	 * discard the packet.
 	 */
 	if (vtag == 0) {
-		chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
-		if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t)
-			  + sizeof(__be32) ||
+		/* chunk header + first 4 octects of init header */
+		chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) +
+					      sizeof(struct sctphdr),
+					      sizeof(struct sctp_chunkhdr) +
+					      sizeof(__be32), &_chunkhdr);
+		if (!chunkhdr ||
 		    chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
-		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) {
+		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag)
 			goto out;
-		}
+
 	} else if (vtag != asoc->c.peer_vtag) {
 		goto out;
 	}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ec529121f38a..e33e9bd4ed5a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -239,12 +239,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	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;
 
 	memset(fl6, 0, sizeof(struct flowi6));
@@ -311,23 +309,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		if (!laddr->valid)
+		struct dst_entry *bdst;
+		__u8 bmatchlen;
+
+		if (!laddr->valid ||
+		    laddr->state != SCTP_ADDR_SRC ||
+		    laddr->a.sa.sa_family != AF_INET6 ||
+		    scope > sctp_scope(&laddr->a))
 			continue;
-		if ((laddr->state == SCTP_ADDR_SRC) &&
-		    (laddr->a.sa.sa_family == AF_INET6) &&
-		    (scope <= sctp_scope(&laddr->a))) {
-			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-			if (!baddr || (matchlen < bmatchlen)) {
-				baddr = &laddr->a;
-				matchlen = bmatchlen;
-			}
-		}
-	}
-	if (baddr) {
-		fl6->saddr = baddr->v6.sin6_addr;
-		fl6->fl6_sport = baddr->v6.sin6_port;
+
+		fl6->saddr = laddr->a.v6.sin6_addr;
+		fl6->fl6_sport = laddr->a.v6.sin6_port;
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+		if (!IS_ERR(bdst) &&
+		    ipv6_chk_addr(dev_net(bdst->dev),
+				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+			if (!IS_ERR_OR_NULL(dst))
+				dst_release(dst);
+			dst = bdst;
+			break;
+		}
+
+		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+		if (matchlen > bmatchlen)
+			continue;
+
+		if (!IS_ERR_OR_NULL(dst))
+			dst_release(dst);
+		dst = bdst;
+		matchlen = bmatchlen;
 	}
 	rcu_read_unlock();
 
@@ -498,7 +510,9 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 {
 	addr->sa.sa_family = AF_INET6;
 	addr->v6.sin6_port = port;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = *saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Compare addresses exactly.
@@ -526,6 +540,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
 		}
 		return 0;
 	}
+	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
+		return 0;
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
 	/* If this is a linklocal address, compare the scope_id. */
@@ -660,6 +676,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	newnp = inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 
 	rcu_read_lock();
 	opt = rcu_dereference(np->opt);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 22c2bf367d7e..29c7c43de108 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3426,6 +3426,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
+		/* Report violation if chunk len overflows */
+		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
+		if (ch_end > skb_tail_pointer(skb))
+			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+						  commands);
+
 		/* Now that we know we at least have a chunk header,
 		 * do things that are type appropriate.
 		 */
@@ -3457,12 +3463,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			}
 		}
 
-		/* Report violation if chunk len overflows */
-		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
-		if (ch_end > skb_tail_pointer(skb))
-			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
-						  commands);
-
 		ch = (sctp_chunkhdr_t *) ch_end;
 	} while (ch_end < skb_tail_pointer(skb));
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index be1489fc3234..3ebf3b652d60 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -235,8 +235,12 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk,
 					      sctp_assoc_t id)
 {
 	struct sctp_association *addr_asoc = NULL, *id_asoc = NULL;
-	struct sctp_transport *transport;
+	struct sctp_af *af = sctp_get_af_specific(addr->ss_family);
 	union sctp_addr *laddr = (union sctp_addr *)addr;
+	struct sctp_transport *transport;
+
+	if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len))
+		return NULL;
 
 	addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep,
 					       laddr,
@@ -1212,9 +1216,12 @@ static int __sctp_connect(struct sock *sk,
 
 	timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
 
-	err = sctp_wait_for_connect(asoc, &timeo);
-	if ((err == 0 || err == -EINPROGRESS) && assoc_id)
+	if (assoc_id)
 		*assoc_id = asoc->assoc_id;
+	err = sctp_wait_for_connect(asoc, &timeo);
+	/* Note: the asoc may be freed after the return of
+	 * sctp_wait_for_connect.
+	 */
 
 	/* Don't free association on exit. */
 	asoc = NULL;
@@ -4371,7 +4378,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len <= 0)
+	if (len == 0)
 		return -EINVAL;
 	if (len > sizeof(struct sctp_event_subscribe))
 		len = sizeof(struct sctp_event_subscribe);
@@ -4419,6 +4426,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	if (!asoc)
 		return -EINVAL;
 
+	/* If there is a thread waiting on more sndbuf space for
+	 * sending on this asoc, it cannot be peeled.
+	 */
+	if (waitqueue_active(&asoc->wait))
+		return -EBUSY;
+
 	/* An association cannot be branched off from an already peeled-off
 	 * socket, nor is this supported for tcp style sockets.
 	 */
@@ -5972,6 +5985,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	if (len < 0)
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	switch (optname) {
@@ -6382,6 +6398,9 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 	if (sock->state != SS_UNCONNECTED)
 		goto out;
 
+	if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+		goto out;
+
 	/* If backlog is zero, disable listening. */
 	if (!backlog) {
 		if (sctp_sstate(sk, CLOSED))
@@ -6954,7 +6973,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		BUG_ON(sk != asoc->base.sk);
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
diff --git a/net/socket.c b/net/socket.c
index d730ef9dfbf0..fbfa9d2492cf 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2041,6 +2041,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		if (err)
 			break;
 		++datagrams;
+		if (msg_data_left(&msg_sys))
+			break;
 	}
 
 	fput_light(sock->file, fput_needed);
@@ -2183,8 +2185,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		return err;
 
 	err = sock_error(sock->sk);
-	if (err)
+	if (err) {
+		datagrams = err;
 		goto out_put;
+	}
 
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;
@@ -2238,31 +2242,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			break;
 	}
 
-out_put:
-	fput_light(sock->file, fput_needed);
-
 	if (err == 0)
-		return datagrams;
+		goto out_put;
+
+	if (datagrams == 0) {
+		datagrams = err;
+		goto out_put;
+	}
 
-	if (datagrams != 0) {
+	/*
+	 * We may return less entries than requested (vlen) if the
+	 * sock is non block and there aren't enough datagrams...
+	 */
+	if (err != -EAGAIN) {
 		/*
-		 * We may return less entries than requested (vlen) if the
-		 * sock is non block and there aren't enough datagrams...
+		 * ... or  if recvmsg returns an error after we
+		 * received some datagrams, where we record the
+		 * error to return on the next call or if the
+		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		if (err != -EAGAIN) {
-			/*
-			 * ... or  if recvmsg returns an error after we
-			 * received some datagrams, where we record the
-			 * error to return on the next call or if the
-			 * app asks about it using getsockopt(SO_ERROR).
-			 */
-			sock->sk->sk_err = -err;
-		}
-
-		return datagrams;
+		sock->sk->sk_err = -err;
 	}
+out_put:
+	fput_light(sock->file, fput_needed);
 
-	return err;
+	return datagrams;
 }
 
 SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 799e65b944b9..1f0687d8e3d7 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg)
 }
 
 static struct gss_upcall_msg *
-__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid)
+__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth)
 {
 	struct gss_upcall_msg *pos;
 	list_for_each_entry(pos, &pipe->in_downcall, list) {
 		if (!uid_eq(pos->uid, uid))
 			continue;
+		if (auth && pos->auth->service != auth->service)
+			continue;
 		atomic_inc(&pos->count);
 		dprintk("RPC:       %s found msg %p\n", __func__, pos);
 		return pos;
@@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg)
 	struct gss_upcall_msg *old;
 
 	spin_lock(&pipe->lock);
-	old = __gss_find_upcall(pipe, gss_msg->uid);
+	old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth);
 	if (old == NULL) {
 		atomic_inc(&gss_msg->count);
 		list_add(&gss_msg->list, &pipe->in_downcall);
@@ -539,9 +541,13 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred)
 		return gss_new;
 	gss_msg = gss_add_msg(gss_new);
 	if (gss_msg == gss_new) {
-		int res = rpc_queue_upcall(gss_new->pipe, &gss_new->msg);
+		int res;
+		atomic_inc(&gss_msg->count);
+		res = rpc_queue_upcall(gss_new->pipe, &gss_new->msg);
 		if (res) {
 			gss_unhash_msg(gss_new);
+			atomic_dec(&gss_msg->count);
+			gss_release_msg(gss_new);
 			gss_msg = ERR_PTR(res);
 		}
 	} else
@@ -714,7 +720,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	err = -ENOENT;
 	/* Find a matching upcall */
 	spin_lock(&pipe->lock);
-	gss_msg = __gss_find_upcall(pipe, uid);
+	gss_msg = __gss_find_upcall(pipe, uid, NULL);
 	if (gss_msg == NULL) {
 		spin_unlock(&pipe->lock);
 		goto err_put_ctx;
@@ -834,6 +840,7 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 			warn_gssd();
 		gss_release_msg(gss_msg);
 	}
+	gss_release_msg(gss_msg);
 }
 
 static void gss_pipe_dentry_destroy(struct dentry *dir,
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index eeeba5adee6d..2410d557ae39 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -260,7 +260,7 @@ static int gssx_dec_option_array(struct xdr_stream *xdr,
 	if (!oa->data)
 		return -ENOMEM;
 
-	creds = kmalloc(sizeof(struct svc_cred), GFP_KERNEL);
+	creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL);
 	if (!creds) {
 		kfree(oa->data);
 		return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 1095be9c80ab..033fec307528 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -857,8 +857,8 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
 		goto out;
 	if (svc_getnl(&buf->head[0]) != seq)
 		goto out;
-	/* trim off the mic at the end before returning */
-	xdr_buf_trim(buf, mic.len + 4);
+	/* trim off the mic and padding at the end before returning */
+	xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4);
 	stat = 0;
 out:
 	kfree(mic.data);
@@ -1481,7 +1481,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 	case RPC_GSS_PROC_DESTROY:
 		if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq))
 			goto auth_err;
-		rsci->h.expiry_time = get_seconds();
+		rsci->h.expiry_time = seconds_since_boot();
 		set_bit(CACHE_NEGATIVE, &rsci->h.flags);
 		if (resv->iov_len + 4 > PAGE_SIZE)
 			goto drop;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 21e20353178e..63fb5ee212cf 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1182,14 +1182,14 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h)
 	}
 
 	crq->q.reader = 0;
-	crq->item = cache_get(h);
 	crq->buf = buf;
 	crq->len = 0;
 	crq->readers = 0;
 	spin_lock(&queue_lock);
-	if (test_bit(CACHE_PENDING, &h->flags))
+	if (test_bit(CACHE_PENDING, &h->flags)) {
+		crq->item = cache_get(h);
 		list_add_tail(&crq->q.list, &detail->queue);
-	else
+	} else
 		/* Lost a race, no longer PENDING, so don't enqueue */
 		ret = -EAGAIN;
 	spin_unlock(&queue_lock);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 23608eb0ded2..f28aeb2cfd32 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -337,6 +337,11 @@ out:
 
 static DEFINE_IDA(rpc_clids);
 
+void rpc_cleanup_clids(void)
+{
+	ida_destroy(&rpc_clids);
+}
+
 static int rpc_alloc_clid(struct rpc_clnt *clnt)
 {
 	int clid;
@@ -442,7 +447,7 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
-struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 					struct rpc_xprt *xprt)
 {
 	struct rpc_clnt *clnt = NULL;
@@ -474,7 +479,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	return clnt;
 }
-EXPORT_SYMBOL_GPL(rpc_create_xprt);
 
 /**
  * rpc_create - create an RPC client and transport with one call
@@ -500,6 +504,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	};
 	char servername[48];
 
+	if (args->bc_xprt) {
+		WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+		xprt = args->bc_xprt->xpt_bc_xprt;
+		if (xprt) {
+			xprt_get(xprt);
+			return rpc_create_xprt(args, xprt);
+		}
+	}
+
 	if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS)
 		xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS;
 	if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT)
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index ee5d3d253102..3142f38d1104 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -119,6 +119,7 @@ out:
 static void __exit
 cleanup_sunrpc(void)
 {
+	rpc_cleanup_clids();
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
 	svc_cleanup_xprt_sock();
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index cc9852897395..c5b0cb4f4056 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1188,11 +1188,17 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
+		if (*statp == rpc_drop_reply ||
+		    test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
 		}
+		if (*statp == rpc_autherr_badcred) {
+			if (procp->pc_release)
+				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+			goto err_bad_auth;
+		}
 		if (*statp == rpc_success &&
 		    (xdr = procp->pc_encode) &&
 		    !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index ff4f01e527ec..d4e0d648bcea 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -346,8 +346,6 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	atomic_inc(&rdma_stat_read);
 	return ret;
  err:
-	ib_dma_unmap_sg(xprt->sc_cm_id->device,
-			frmr->sg, frmr->sg_nents, frmr->direction);
 	svc_rdma_put_context(ctxt, 0);
 	svc_rdma_put_frmr(xprt, frmr);
 	return ret;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 027c9ef8a263..27b6f55fa43a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -474,7 +474,16 @@ 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);
+	if (ret == -EAGAIN) {
+		struct socket_wq *wq;
+
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
+		rcu_read_unlock();
+
+		sk->sk_write_space(sk);
+	}
 	return ret;
 }
 
@@ -2286,6 +2295,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		/* SYN_SENT! */
 		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
 			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+		break;
+	case -EADDRNOTAVAIL:
+		/* Source port number is unavailable. Try a new one! */
+		transport->srcport = 0;
 	}
 out:
 	return ret;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index d5d7132ac847..1b58866175e6 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1169,6 +1169,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = nlflags,
@@ -1177,8 +1178,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	/* Don't offload route if using custom ip rules or if
 	 * IPv4 FIB offloading has been disabled completely.
 	 */
@@ -1222,6 +1221,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = 0,
@@ -1230,8 +1230,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
 		return 0;
 
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index ed98c1fc3de1..46a71c701e7c 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -46,7 +46,7 @@ static int net_ctl_permissions(struct ctl_table_header *head,
 	kgid_t root_gid = make_kgid(net->user_ns, 0);
 
 	/* Allow network administrator to have same access as root. */
-	if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
+	if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN) ||
 	    uid_eq(root_uid, current_euid())) {
 		int mode = (table->mode >> 6) & 7;
 		return (mode << 6) | (mode << 3) | mode;
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 648f2a67f314..cb1381513c82 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -381,6 +381,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 	dev = dev_get_by_name(net, driver_name);
 	if (!dev)
 		return -ENODEV;
+	if (tipc_mtu_bad(dev, 0)) {
+		dev_put(dev);
+		return -EINVAL;
+	}
 
 	/* Associate TIPC bearer with L2 bearer */
 	rcu_assign_pointer(b->media_ptr, dev);
@@ -570,14 +574,19 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 	if (!b_ptr)
 		return NOTIFY_DONE;
 
-	b_ptr->mtu = dev->mtu;
-
 	switch (evt) {
 	case NETDEV_CHANGE:
 		if (netif_carrier_ok(dev))
 			break;
 	case NETDEV_GOING_DOWN:
+		tipc_reset_bearer(net, b_ptr);
+		break;
 	case NETDEV_CHANGEMTU:
+		if (tipc_mtu_bad(dev, 0)) {
+			bearer_disable(net, b_ptr);
+			break;
+		}
+		b_ptr->mtu = dev->mtu;
 		tipc_reset_bearer(net, b_ptr);
 		break;
 	case NETDEV_CHANGEADDR:
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 552185bc4773..5f11e18b1fa1 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -39,6 +39,7 @@
 
 #include "netlink.h"
 #include "core.h"
+#include "msg.h"
 #include <net/genetlink.h>
 
 #define MAX_MEDIA	3
@@ -61,6 +62,9 @@
 #define TIPC_MEDIA_TYPE_IB	2
 #define TIPC_MEDIA_TYPE_UDP	3
 
+/* minimum bearer MTU */
+#define TIPC_MIN_BEARER_MTU	(MAX_H_SIZE + INT_H_SIZE)
+
 /**
  * struct tipc_node_map - set of node identifiers
  * @count: # of nodes in set
@@ -226,4 +230,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
 void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
 			 struct sk_buff_head *xmitq);
 
+/* check if device MTU is too low for tipc headers */
+static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve)
+{
+	if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve)
+		return false;
+	netdev_warn(dev, "MTU too low for tipc bearer\n");
+	return true;
+}
+
 #endif	/* _TIPC_BEARER_H */
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 03a842870c52..e2bdb07a49a2 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -69,6 +69,7 @@ static int __net_init tipc_init_net(struct net *net)
 	if (err)
 		goto out_nametbl;
 
+	INIT_LIST_HEAD(&tn->dist_queue);
 	err = tipc_topsrv_start(net);
 	if (err)
 		goto out_subscr;
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 18e95a8020cd..fe3b89e9cde4 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -103,6 +103,9 @@ struct tipc_net {
 	spinlock_t nametbl_lock;
 	struct name_table *nametbl;
 
+	/* Name dist queue */
+	struct list_head dist_queue;
+
 	/* Topology subscription server */
 	struct tipc_server *topsrv;
 	atomic_t subscription_count;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 91aea071ab27..72268eac4ec7 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1262,6 +1262,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		/* fall thru' */
 
 	case ACTIVATE_MSG:
+		skb_linearize(skb);
+		hdr = buf_msg(skb);
 
 		/* Complete own link name with peer's interface name */
 		if_name =  strrchr(l->name, ':') + 1;
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index c07612bab95c..c4c151bc000c 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -40,11 +40,6 @@
 
 int sysctl_tipc_named_timeout __read_mostly = 2000;
 
-/**
- * struct tipc_dist_queue - queue holding deferred name table updates
- */
-static struct list_head tipc_dist_queue = LIST_HEAD_INIT(tipc_dist_queue);
-
 struct distr_queue_item {
 	struct distr_item i;
 	u32 dtype;
@@ -67,6 +62,8 @@ static void publ_to_item(struct distr_item *i, struct publication *p)
 
 /**
  * named_prepare_buf - allocate & initialize a publication message
+ *
+ * The buffer returned is of size INT_H_SIZE + payload size
  */
 static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
 					 u32 dest)
@@ -171,9 +168,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
 	struct publication *publ;
 	struct sk_buff *skb = NULL;
 	struct distr_item *item = NULL;
-	uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) *
-			ITEM_SIZE;
-	uint msg_rem = msg_dsz;
+	u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) /
+			ITEM_SIZE) * ITEM_SIZE;
+	u32 msg_rem = msg_dsz;
 
 	list_for_each_entry(publ, pls, local_list) {
 		/* Prepare next buffer: */
@@ -340,9 +337,11 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
  * tipc_named_add_backlog - add a failed name table update to the backlog
  *
  */
-static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
+static void tipc_named_add_backlog(struct net *net, struct distr_item *i,
+				   u32 type, u32 node)
 {
 	struct distr_queue_item *e;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	unsigned long now = get_jiffies_64();
 
 	e = kzalloc(sizeof(*e), GFP_ATOMIC);
@@ -352,7 +351,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
 	e->node = node;
 	e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout);
 	memcpy(e, i, sizeof(*i));
-	list_add_tail(&e->next, &tipc_dist_queue);
+	list_add_tail(&e->next, &tn->dist_queue);
 }
 
 /**
@@ -362,10 +361,11 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
 void tipc_named_process_backlog(struct net *net)
 {
 	struct distr_queue_item *e, *tmp;
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	char addr[16];
 	unsigned long now = get_jiffies_64();
 
-	list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) {
+	list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
 		if (time_after(e->expires, now)) {
 			if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype))
 				continue;
@@ -397,6 +397,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
 
 	spin_lock_bh(&tn->nametbl_lock);
 	for (skb = skb_dequeue(inputq); skb; skb = skb_dequeue(inputq)) {
+		skb_linearize(skb);
 		msg = buf_msg(skb);
 		mtype = msg_type(msg);
 		item = (struct distr_item *)msg_data(msg);
@@ -404,7 +405,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
 		node = msg_orignode(msg);
 		while (count--) {
 			if (!tipc_update_nametbl(net, item, node, mtype))
-				tipc_named_add_backlog(item, mtype, node);
+				tipc_named_add_backlog(net, item, mtype, node);
 			item++;
 		}
 		kfree_skb(skb);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 1eadc95e1132..f86c6555a539 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -258,13 +258,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
 		kfree_skb(msg->rep);
+		msg->rep = NULL;
 		return -ENOMEM;
 	}
 
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
-	if (err)
+	if (err) {
 		kfree_skb(msg->rep);
-
+		msg->rep = NULL;
+	}
 	kfree_skb(arg);
 
 	return err;
@@ -574,7 +576,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
 			    &link_info, sizeof(link_info));
@@ -802,7 +805,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		goto out;
 
 	tipc_tlv_sprintf(msg->rep, "%-10u %s",
-			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
 			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
 out:
 	tipc_tlv_sprintf(msg->rep, "\n");
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 3926b561f873..2df0b98d4a32 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -102,9 +102,10 @@ static unsigned int tipc_hashfn(u32 addr)
 
 static void tipc_node_kref_release(struct kref *kref)
 {
-	struct tipc_node *node = container_of(kref, struct tipc_node, kref);
+	struct tipc_node *n = container_of(kref, struct tipc_node, kref);
 
-	tipc_node_delete(node);
+	kfree(n->bc_entry.link);
+	kfree_rcu(n, rcu);
 }
 
 void tipc_node_put(struct tipc_node *node)
@@ -216,21 +217,20 @@ static void tipc_node_delete(struct tipc_node *node)
 {
 	list_del_rcu(&node->list);
 	hlist_del_rcu(&node->hash);
-	kfree(node->bc_entry.link);
-	kfree_rcu(node, rcu);
+	tipc_node_put(node);
+
+	del_timer_sync(&node->timer);
+	tipc_node_put(node);
 }
 
 void tipc_node_stop(struct net *net)
 {
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_net *tn = tipc_net(net);
 	struct tipc_node *node, *t_node;
 
 	spin_lock_bh(&tn->node_list_lock);
-	list_for_each_entry_safe(node, t_node, &tn->node_list, list) {
-		if (del_timer(&node->timer))
-			tipc_node_put(node);
-		tipc_node_put(node);
-	}
+	list_for_each_entry_safe(node, t_node, &tn->node_list, list)
+		tipc_node_delete(node);
 	spin_unlock_bh(&tn->node_list_lock);
 }
 
@@ -313,9 +313,7 @@ static void tipc_node_timeout(unsigned long data)
 		if (rc & TIPC_LINK_DOWN_EVT)
 			tipc_node_link_down(n, bearer_id, false);
 	}
-	if (!mod_timer(&n->timer, jiffies + n->keepalive_intv))
-		tipc_node_get(n);
-	tipc_node_put(n);
+	mod_timer(&n->timer, jiffies + n->keepalive_intv);
 }
 
 /**
@@ -730,7 +728,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
 			state = SELF_UP_PEER_UP;
 			break;
 		case SELF_LOST_CONTACT_EVT:
-			state = SELF_DOWN_PEER_LEAVING;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_ESTABL_CONTACT_EVT:
 		case PEER_LOST_CONTACT_EVT:
@@ -749,7 +747,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
 			state = SELF_UP_PEER_UP;
 			break;
 		case PEER_LOST_CONTACT_EVT:
-			state = SELF_LEAVING_PEER_DOWN;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_LOST_CONTACT_EVT:
 		case PEER_ESTABL_CONTACT_EVT:
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 922e04a43396..50f5b0ca7b3c 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -452,6 +452,11 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 	if (!con)
 		return -EINVAL;
 
+	if (!test_bit(CF_CONNECTED, &con->flags)) {
+		conn_put(con);
+		return 0;
+	}
+
 	e = tipc_alloc_entry(data, len);
 	if (!e) {
 		conn_put(con);
@@ -465,12 +470,8 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 	list_add_tail(&e->list, &con->outqueue);
 	spin_unlock_bh(&con->outqueue_lock);
 
-	if (test_bit(CF_CONNECTED, &con->flags)) {
-		if (!queue_work(s->send_wq, &con->swork))
-			conn_put(con);
-	} else {
+	if (!queue_work(s->send_wq, &con->swork))
 		conn_put(con);
-	}
 	return 0;
 }
 
@@ -494,7 +495,7 @@ static void tipc_send_to_sock(struct tipc_conn *con)
 	int ret;
 
 	spin_lock_bh(&con->outqueue_lock);
-	while (1) {
+	while (test_bit(CF_CONNECTED, &con->flags)) {
 		e = list_entry(con->outqueue.next, struct outqueue_entry,
 			       list);
 		if ((struct list_head *) e == &con->outqueue)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b53246fb0412..65171f8e8c45 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -673,7 +673,7 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct iov_iter save = msg->msg_iter;
 	uint mtu;
 	int rc;
@@ -687,14 +687,16 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	msg_set_nameupper(mhdr, seq->upper);
 	msg_set_hdr_sz(mhdr, MCAST_H_SIZE);
 
+	skb_queue_head_init(&pktchain);
+
 new_mtu:
 	mtu = tipc_bcast_get_mtu(net);
-	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
 
 	do {
-		rc = tipc_bcast_xmit(net, pktchain);
+		rc = tipc_bcast_xmit(net, &pktchain);
 		if (likely(!rc))
 			return dsz;
 
@@ -704,7 +706,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			msg->msg_iter = save;
 			goto new_mtu;
@@ -775,9 +777,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
  * @tsk: receiving socket
  * @skb: pointer to message buffer.
  */
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
+static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+			      struct sk_buff_head *xmitq)
 {
 	struct sock *sk = &tsk->sk;
+	u32 onode = tsk_own_node(tsk);
 	struct tipc_msg *hdr = buf_msg(skb);
 	int mtyp = msg_type(hdr);
 	int conn_cong;
@@ -790,7 +794,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
 
 	if (mtyp == CONN_PROBE) {
 		msg_set_type(hdr, CONN_PROBE_REPLY);
-		tipc_sk_respond(sk, skb, TIPC_OK);
+		if (tipc_msg_reverse(onode, &skb, TIPC_OK))
+			__skb_queue_tail(xmitq, skb);
 		return;
 	} else if (mtyp == CONN_ACK) {
 		conn_cong = tsk_conn_cong(tsk);
@@ -863,7 +868,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
 	u32 dnode, dport;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct sk_buff *skb;
 	struct tipc_name_seq *seq;
 	struct iov_iter save;
@@ -924,17 +929,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
 	}
 
+	skb_queue_head_init(&pktchain);
 	save = m->msg_iter;
 new_mtu:
 	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
-	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain);
 	if (rc < 0)
 		return rc;
 
 	do {
-		skb = skb_peek(pktchain);
+		skb = skb_peek(&pktchain);
 		TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
-		rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid);
+		rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
 		if (likely(!rc)) {
 			if (sock->state != SS_READY)
 				sock->state = SS_CONNECTING;
@@ -946,7 +952,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			m->msg_iter = save;
 			goto new_mtu;
@@ -1016,7 +1022,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	u32 portid = tsk->portid;
 	int rc = -EINVAL;
@@ -1044,17 +1050,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 
 	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	dnode = tsk_peer_node(tsk);
+	skb_queue_head_init(&pktchain);
 
 next:
 	save = m->msg_iter;
 	mtu = tsk->max_pkt;
 	send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
-	rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
+
 	do {
 		if (likely(!tsk_conn_cong(tsk))) {
-			rc = tipc_node_xmit(net, pktchain, dnode, portid);
+			rc = tipc_node_xmit(net, &pktchain, dnode, portid);
 			if (likely(!rc)) {
 				tsk->sent_unacked++;
 				sent += send;
@@ -1063,7 +1071,7 @@ next:
 				goto next;
 			}
 			if (rc == -EMSGSIZE) {
-				__skb_queue_purge(pktchain);
+				__skb_queue_purge(&pktchain);
 				tsk->max_pkt = tipc_node_get_mtu(net, dnode,
 								 portid);
 				m->msg_iter = save;
@@ -1077,7 +1085,7 @@ next:
 		rc = tipc_wait_for_sndpkt(sock, &timeo);
 	} while (!rc);
 
-	__skb_queue_purge(pktchain);
+	__skb_queue_purge(&pktchain);
 	return sent ? sent : rc;
 }
 
@@ -1642,7 +1650,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
  *
  * Returns true if message was added to socket receive queue, otherwise false
  */
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
+static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
+		       struct sk_buff_head *xmitq)
 {
 	struct socket *sock = sk->sk_socket;
 	struct tipc_sock *tsk = tipc_sk(sk);
@@ -1652,7 +1661,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
 	int usr = msg_user(hdr);
 
 	if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
-		tipc_sk_proto_rcv(tsk, skb);
+		tipc_sk_proto_rcv(tsk, skb, xmitq);
 		return false;
 	}
 
@@ -1695,7 +1704,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
 	return true;
 
 reject:
-	tipc_sk_respond(sk, skb, err);
+	if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
+		__skb_queue_tail(xmitq, skb);
 	return false;
 }
 
@@ -1711,9 +1721,24 @@ reject:
 static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int truesize = skb->truesize;
+	struct sk_buff_head xmitq;
+	u32 dnode, selector;
+
+	__skb_queue_head_init(&xmitq);
 
-	if (likely(filter_rcv(sk, skb)))
+	if (likely(filter_rcv(sk, skb, &xmitq))) {
 		atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
+		return 0;
+	}
+
+	if (skb_queue_empty(&xmitq))
+		return 0;
+
+	/* Send response/rejected message */
+	skb = __skb_dequeue(&xmitq);
+	dnode = msg_destnode(buf_msg(skb));
+	selector = msg_origport(buf_msg(skb));
+	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
 	return 0;
 }
 
@@ -1727,12 +1752,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
  * Caller must hold socket lock
  */
 static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
-			    u32 dport)
+			    u32 dport, struct sk_buff_head *xmitq)
 {
+	unsigned long time_limit = jiffies + 2;
+	struct sk_buff *skb;
 	unsigned int lim;
 	atomic_t *dcnt;
-	struct sk_buff *skb;
-	unsigned long time_limit = jiffies + 2;
+	u32 onode;
 
 	while (skb_queue_len(inputq)) {
 		if (unlikely(time_after_eq(jiffies, time_limit)))
@@ -1744,20 +1770,22 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 
 		/* Add message directly to receive queue if possible */
 		if (!sock_owned_by_user(sk)) {
-			filter_rcv(sk, skb);
+			filter_rcv(sk, skb, xmitq);
 			continue;
 		}
 
 		/* Try backlog, compensating for double-counted bytes */
 		dcnt = &tipc_sk(sk)->dupl_rcvcnt;
-		if (sk->sk_backlog.len)
+		if (!sk->sk_backlog.len)
 			atomic_set(dcnt, 0);
 		lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
 		if (likely(!sk_add_backlog(sk, skb, lim)))
 			continue;
 
 		/* Overload => reject message back to sender */
-		tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD);
+		onode = tipc_own_addr(sock_net(sk));
+		if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+			__skb_queue_tail(xmitq, skb);
 		break;
 	}
 }
@@ -1770,12 +1798,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
  */
 void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 {
+	struct sk_buff_head xmitq;
 	u32 dnode, dport = 0;
 	int err;
 	struct tipc_sock *tsk;
 	struct sock *sk;
 	struct sk_buff *skb;
 
+	__skb_queue_head_init(&xmitq);
 	while (skb_queue_len(inputq)) {
 		dport = tipc_skb_peek_port(inputq, dport);
 		tsk = tipc_sk_lookup(net, dport);
@@ -1783,9 +1813,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
 		if (likely(tsk)) {
 			sk = &tsk->sk;
 			if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
-				tipc_sk_enqueue(inputq, sk, dport);
+				tipc_sk_enqueue(inputq, sk, dport, &xmitq);
 				spin_unlock_bh(&sk->sk_lock.slock);
 			}
+			/* Send pending response/rejected messages, if any */
+			while ((skb = __skb_dequeue(&xmitq))) {
+				dnode = msg_destnode(buf_msg(skb));
+				tipc_node_xmit_skb(net, skb, dnode, dport);
+			}
 			sock_put(sk);
 			continue;
 		}
@@ -2106,7 +2141,8 @@ restart:
 					      TIPC_CONN_MSG, SHORT_H_SIZE,
 					      0, dnode, onode, dport, oport,
 					      TIPC_CONN_SHUTDOWN);
-			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
+			if (skb)
+				tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
 		}
 		tsk->connected = 0;
 		sock->state = SS_DISCONNECTING;
@@ -2809,6 +2845,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err)
 			return err;
 
+		if (!attrs[TIPC_NLA_SOCK])
+			return -EINVAL;
+
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
 				       tipc_nl_sock_policy);
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 69ee2eeef968..f9ff73a8d815 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid,
 	if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
 		return tipc_conn_terminate(tn->topsrv, subscrb->conid);
 
-	tipc_nametbl_subscribe(sub);
+	if (sub)
+		tipc_nametbl_subscribe(sub);
 }
 
 /* Handle one request to establish a new subscriber */
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 70c03271b798..78d6b78de29d 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -48,12 +48,11 @@
 #include <linux/tipc_netlink.h>
 #include "core.h"
 #include "bearer.h"
-#include "msg.h"
 
 /* IANA assigned UDP port */
 #define UDP_PORT_DEFAULT	6118
 
-#define UDP_MIN_HEADROOM        28
+#define UDP_MIN_HEADROOM        48
 
 static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = {
 	[TIPC_NLA_UDP_UNSPEC]	= {.type = NLA_UNSPEC},
@@ -224,10 +223,6 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_bearer *ub;
 	struct tipc_bearer *b;
-	int usr = msg_user(buf_msg(skb));
-
-	if ((usr == LINK_PROTOCOL) || (usr == NAME_DISTRIBUTOR))
-		skb_linearize(skb);
 
 	ub = rcu_dereference_sk_user_data(sk);
 	if (!ub) {
@@ -381,6 +376,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
 		udp_conf.use_udp_checksums = false;
 		ub->ifindex = dev->ifindex;
+		if (tipc_mtu_bad(dev, sizeof(struct iphdr) +
+				      sizeof(struct udphdr))) {
+			err = -EINVAL;
+			goto err;
+		}
 		b->mtu = dev->mtu - sizeof(struct iphdr)
 			- sizeof(struct udphdr);
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 898a53a562b8..e05ec54ac53f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -315,7 +315,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i)
 		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
 		struct dentry *dentry = unix_sk(s)->path.dentry;
 
-		if (dentry && d_backing_inode(dentry) == i) {
+		if (dentry && d_real_inode(dentry) == i) {
 			sock_hold(s);
 			goto found;
 		}
@@ -661,11 +661,11 @@ static int unix_set_peek_off(struct sock *sk, int val)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	if (mutex_lock_interruptible(&u->readlock))
+	if (mutex_lock_interruptible(&u->iolock))
 		return -EINTR;
 
 	sk->sk_peek_off = val;
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 
 	return 0;
 }
@@ -778,7 +778,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	spin_lock_init(&u->lock);
 	atomic_long_set(&u->inflight, 0);
 	INIT_LIST_HEAD(&u->link);
-	mutex_init(&u->readlock); /* single task reading lock */
+	mutex_init(&u->iolock); /* single task reading lock */
+	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
 	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
@@ -847,7 +848,7 @@ static int unix_autobind(struct socket *sock)
 	int err;
 	unsigned int retries = 0;
 
-	err = mutex_lock_interruptible(&u->readlock);
+	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
 		return err;
 
@@ -894,7 +895,7 @@ retry:
 	spin_unlock(&unix_table_lock);
 	err = 0;
 
-out:	mutex_unlock(&u->readlock);
+out:	mutex_unlock(&u->bindlock);
 	return err;
 }
 
@@ -911,7 +912,7 @@ static struct sock *unix_find_other(struct net *net,
 		err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
 		if (err)
 			goto fail;
-		inode = d_backing_inode(path.dentry);
+		inode = d_real_inode(path.dentry);
 		err = inode_permission(inode, MAY_WRITE);
 		if (err)
 			goto put_fail;
@@ -953,20 +954,32 @@ fail:
 	return NULL;
 }
 
-static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode,
-		      struct path *res)
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
 {
-	int err;
+	struct dentry *dentry;
+	struct path path;
+	int err = 0;
+	/*
+	 * Get the parent directory, calculate the hash for last
+	 * component.
+	 */
+	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+	err = PTR_ERR(dentry);
+	if (IS_ERR(dentry))
+		return err;
 
-	err = security_path_mknod(path, dentry, mode, 0);
+	/*
+	 * All right, let's create it.
+	 */
+	err = security_path_mknod(&path, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
+		err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
 		if (!err) {
-			res->mnt = mntget(path->mnt);
+			res->mnt = mntget(path.mnt);
 			res->dentry = dget(dentry);
 		}
 	}
-
+	done_path_create(&path, dentry);
 	return err;
 }
 
@@ -977,15 +990,15 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
-	int err, name_err;
+	int err;
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
-	struct path path;
-	struct dentry *dentry;
+	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
-	if (sunaddr->sun_family != AF_UNIX)
+	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
+	    sunaddr->sun_family != AF_UNIX)
 		goto out;
 
 	if (addr_len == sizeof(short)) {
@@ -998,34 +1011,25 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
-	name_err = 0;
-	dentry = NULL;
 	if (sun_path[0]) {
-		/* Get the parent directory, calculate the hash for last
-		 * component.
-		 */
-		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-
-		if (IS_ERR(dentry)) {
-			/* delay report until after 'already bound' check */
-			name_err = PTR_ERR(dentry);
-			dentry = NULL;
+		umode_t mode = S_IFSOCK |
+		       (SOCK_INODE(sock)->i_mode & ~current_umask());
+		err = unix_mknod(sun_path, mode, &path);
+		if (err) {
+			if (err == -EEXIST)
+				err = -EADDRINUSE;
+			goto out;
 		}
 	}
 
-	err = mutex_lock_interruptible(&u->readlock);
+	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
-		goto out_path;
+		goto out_put;
 
 	err = -EINVAL;
 	if (u->addr)
 		goto out_up;
 
-	if (name_err) {
-		err = name_err == -EEXIST ? -EADDRINUSE : name_err;
-		goto out_up;
-	}
-
 	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
@@ -1036,21 +1040,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	addr->hash = hash ^ sk->sk_type;
 	atomic_set(&addr->refcnt, 1);
 
-	if (dentry) {
-		struct path u_path;
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(dentry, &path, mode, &u_path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			unix_release_addr(addr);
-			goto out_up;
-		}
+	if (sun_path[0]) {
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+		hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
-		u->path = u_path;
+		u->path = path;
 		list = &unix_socket_table[hash];
 	} else {
 		spin_lock(&unix_table_lock);
@@ -1072,11 +1066,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
-	mutex_unlock(&u->readlock);
-out_path:
-	if (dentry)
-		done_path_create(&path, dentry);
-
+	mutex_unlock(&u->bindlock);
+out_put:
+	if (err)
+		path_put(&path);
 out:
 	return err;
 }
@@ -1116,6 +1109,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 	unsigned int hash;
 	int err;
 
+	err = -EINVAL;
+	if (alen < offsetofend(struct sockaddr, sa_family))
+		goto out;
+
 	if (addr->sa_family != AF_UNSPEC) {
 		err = unix_mkname(sunaddr, alen, &hash);
 		if (err < 0)
@@ -1971,17 +1968,17 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
 	if (false) {
 alloc_skb:
 		unix_state_unlock(other);
-		mutex_unlock(&unix_sk(other)->readlock);
+		mutex_unlock(&unix_sk(other)->iolock);
 		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
 					      &err, 0);
 		if (!newskb)
 			goto err;
 	}
 
-	/* we must acquire readlock as we modify already present
+	/* we must acquire iolock as we modify already present
 	 * skbs in the sk_receive_queue and mess with skb->len
 	 */
-	err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+	err = mutex_lock_interruptible(&unix_sk(other)->iolock);
 	if (err) {
 		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
 		goto err;
@@ -2048,7 +2045,7 @@ alloc_skb:
 	}
 
 	unix_state_unlock(other);
-	mutex_unlock(&unix_sk(other)->readlock);
+	mutex_unlock(&unix_sk(other)->iolock);
 
 	other->sk_data_ready(other);
 	scm_destroy(&scm);
@@ -2057,7 +2054,7 @@ alloc_skb:
 err_state_unlock:
 	unix_state_unlock(other);
 err_unlock:
-	mutex_unlock(&unix_sk(other)->readlock);
+	mutex_unlock(&unix_sk(other)->iolock);
 err:
 	kfree_skb(newskb);
 	if (send_sigpipe && !(flags & MSG_NOSIGNAL))
@@ -2122,7 +2119,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 	if (flags&MSG_OOB)
 		goto out;
 
-	err = mutex_lock_interruptible(&u->readlock);
+	err = mutex_lock_interruptible(&u->iolock);
 	if (unlikely(err)) {
 		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
 		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
@@ -2198,7 +2195,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 out_free:
 	skb_free_datagram(sk, skb);
 out_unlock:
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 out:
 	return err;
 }
@@ -2207,7 +2204,8 @@ out:
  *	Sleep until more data has arrived. But check for races..
  */
 static long unix_stream_data_wait(struct sock *sk, long timeo,
-				  struct sk_buff *last, unsigned int last_len)
+				  struct sk_buff *last, unsigned int last_len,
+				  bool freezable)
 {
 	struct sk_buff *tail;
 	DEFINE_WAIT(wait);
@@ -2228,7 +2226,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 
 		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		unix_state_unlock(sk);
-		timeo = freezable_schedule_timeout(timeo);
+		if (freezable)
+			timeo = freezable_schedule_timeout(timeo);
+		else
+			timeo = schedule_timeout(timeo);
 		unix_state_lock(sk);
 
 		if (sock_flag(sk, SOCK_DEAD))
@@ -2258,7 +2259,8 @@ struct unix_stream_read_state {
 	unsigned int splice_flags;
 };
 
-static int unix_stream_read_generic(struct unix_stream_read_state *state)
+static int unix_stream_read_generic(struct unix_stream_read_state *state,
+				    bool freezable)
 {
 	struct scm_cookie scm;
 	struct socket *sock = state->socket;
@@ -2293,7 +2295,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
-	mutex_lock(&u->readlock);
+	mutex_lock(&u->iolock);
 
 	if (flags & MSG_PEEK)
 		skip = sk_peek_offset(sk, flags);
@@ -2334,10 +2336,10 @@ again:
 				break;
 			}
 
-			mutex_unlock(&u->readlock);
+			mutex_unlock(&u->iolock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
-						      last_len);
+						      last_len, freezable);
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
@@ -2345,7 +2347,7 @@ again:
 				goto out;
 			}
 
-			mutex_lock(&u->readlock);
+			mutex_lock(&u->iolock);
 			continue;
 unlock:
 			unix_state_unlock(sk);
@@ -2448,7 +2450,7 @@ unlock:
 		}
 	} while (size);
 
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 	if (state->msg)
 		scm_recv(sock, state->msg, &scm, flags);
 	else
@@ -2479,7 +2481,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, true);
 }
 
 static ssize_t skb_unix_socket_splice(struct sock *sk,
@@ -2489,9 +2491,9 @@ static ssize_t skb_unix_socket_splice(struct sock *sk,
 	int ret;
 	struct unix_sock *u = unix_sk(sk);
 
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 	ret = splice_to_pipe(pipe, spd);
-	mutex_lock(&u->readlock);
+	mutex_lock(&u->iolock);
 
 	return ret;
 }
@@ -2525,7 +2527,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock,  loff_t *ppos,
 	    flags & SPLICE_F_NONBLOCK)
 		state.flags = MSG_DONTWAIT;
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, false);
 }
 
 static int unix_shutdown(struct socket *sock, int mode)
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d48525fcf..c36757e72844 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
+		BUG_ON(!atomic_long_read(&u->inflight));
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
+	/* Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, inc_inflight, &hitlist);
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
@@ -350,14 +359,6 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/* Now gc_candidates contains only garbage.  Restore original
-	 * inflight counters for these as well, and remove the skbuffs
-	 * which are creating the cycle(s).
-	 */
-	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
-	scan_children(&u->sk, inc_inflight, &hitlist);
-
 	spin_unlock(&unix_gc_lock);
 
 	/* Here we are. Hitlist is filled. Die. */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7fd1220fbfa0..9b5bd6d142dc 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1794,27 +1794,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	else if (sk->sk_shutdown & RCV_SHUTDOWN)
 		err = 0;
 
-	if (copied > 0) {
-		/* We only do these additional bookkeeping/notification steps
-		 * if we actually copied something out of the queue pair
-		 * instead of just peeking ahead.
-		 */
-
-		if (!(flags & MSG_PEEK)) {
-			/* If the other side has shutdown for sending and there
-			 * is nothing more to read, then modify the socket
-			 * state.
-			 */
-			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
-				if (vsock_stream_has_data(vsk) <= 0) {
-					sk->sk_state = SS_UNCONNECTED;
-					sock_set_flag(sk, SOCK_DONE);
-					sk->sk_state_change(sk);
-				}
-			}
-		}
+	if (copied > 0)
 		err = copied;
-	}
 
 out_wait:
 	finish_wait(sk_sleep(sk), &wait);
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 0a369bb440e7..662bdd20a748 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -842,7 +842,7 @@ static void vmci_transport_peer_detach_cb(u32 sub_id,
 	 * qp_handle.
 	 */
 	if (vmci_handle_is_invalid(e_payload->handle) ||
-	    vmci_handle_is_equal(trans->qp_handle, e_payload->handle))
+	    !vmci_handle_is_equal(trans->qp_handle, e_payload->handle))
 		return;
 
 	/* We don't ask for delayed CBs when we subscribe to this event (we
@@ -2154,7 +2154,7 @@ module_exit(vmci_transport_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMCI transport for Virtual Sockets");
-MODULE_VERSION("1.0.2.0-k");
+MODULE_VERSION("1.0.3.0-k");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("vmware_vsock");
 MODULE_ALIAS_NETPROTO(PF_VSOCK);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index a618b4b86fa4..47ea169aa0a3 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -72,6 +72,7 @@ struct cfg80211_registered_device {
 	struct list_head bss_list;
 	struct rb_root bss_tree;
 	u32 bss_generation;
+	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
 	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
@@ -397,6 +398,7 @@ void cfg80211_sme_disassoc(struct wireless_dev *wdev);
 void cfg80211_sme_deauth(struct wireless_dev *wdev);
 void cfg80211_sme_auth_timeout(struct wireless_dev *wdev);
 void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev);
+void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev);
 
 /* internal helpers */
 bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher);
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index fb44fa3bf4ef..c0e02f72e931 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -149,6 +149,18 @@ void cfg80211_assoc_timeout(struct net_device *dev, struct cfg80211_bss *bss)
 }
 EXPORT_SYMBOL(cfg80211_assoc_timeout);
 
+void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss)
+{
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct wiphy *wiphy = wdev->wiphy;
+
+	cfg80211_sme_abandon_assoc(wdev);
+
+	cfg80211_unhold_bss(bss_from_pub(bss));
+	cfg80211_put_bss(wiphy, bss);
+}
+EXPORT_SYMBOL(cfg80211_abandon_assoc);
+
 void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 75b0d23ee882..de10e3c0e2a4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -302,8 +302,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 },
 	[NL80211_ATTR_PID] = { .type = NLA_U32 },
 	[NL80211_ATTR_4ADDR] = { .type = NLA_U8 },
-	[NL80211_ATTR_PMKID] = { .type = NLA_BINARY,
-				 .len = WLAN_PMKID_LEN },
+	[NL80211_ATTR_PMKID] = { .len = WLAN_PMKID_LEN },
 	[NL80211_ATTR_DURATION] = { .type = NLA_U32 },
 	[NL80211_ATTR_COOKIE] = { .type = NLA_U64 },
 	[NL80211_ATTR_TX_RATES] = { .type = NLA_NESTED },
@@ -359,6 +358,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
 	[NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 },
 	[NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 },
+	[NL80211_ATTR_LOCAL_MESH_POWER_MODE] = {. type = NLA_U32 },
 	[NL80211_ATTR_ACL_POLICY] = {. type = NLA_U32 },
 	[NL80211_ATTR_MAC_ADDRS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_STA_CAPABILITY] = { .type = NLA_U16 },
@@ -492,21 +492,17 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 {
 	int err;
 
-	rtnl_lock();
-
 	if (!cb->args[0]) {
 		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
 				  nl80211_fam.attrbuf, nl80211_fam.maxattr,
 				  nl80211_policy);
 		if (err)
-			goto out_unlock;
+			return err;
 
 		*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk),
 						   nl80211_fam.attrbuf);
-		if (IS_ERR(*wdev)) {
-			err = PTR_ERR(*wdev);
-			goto out_unlock;
-		}
+		if (IS_ERR(*wdev))
+			return PTR_ERR(*wdev);
 		*rdev = wiphy_to_rdev((*wdev)->wiphy);
 		/* 0 is the first index - add 1 to parse only once */
 		cb->args[0] = (*rdev)->wiphy_idx + 1;
@@ -516,10 +512,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 		struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
 		struct wireless_dev *tmp;
 
-		if (!wiphy) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!wiphy)
+			return -ENODEV;
 		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
@@ -530,21 +524,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			}
 		}
 
-		if (!*wdev) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!*wdev)
+			return -ENODEV;
 	}
 
 	return 0;
- out_unlock:
-	rtnl_unlock();
-	return err;
-}
-
-static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev)
-{
-	rtnl_unlock();
 }
 
 /* IE validation */
@@ -3884,9 +3868,10 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	int sta_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!wdev->netdev) {
 		err = -EINVAL;
@@ -3922,7 +3907,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	cb->args[2] = sta_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 
 	return err;
 }
@@ -4639,9 +4624,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!rdev->ops->dump_mpath) {
 		err = -EOPNOTSUPP;
@@ -4675,7 +4661,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return err;
 }
 
@@ -4835,9 +4821,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out_err;
 
 	if (!rdev->ops->dump_mpp) {
 		err = -EOPNOTSUPP;
@@ -4870,7 +4857,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return err;
 }
 
@@ -5718,6 +5705,10 @@ static int validate_scan_freqs(struct nlattr *freqs)
 	struct nlattr *attr1, *attr2;
 	int n_channels = 0, tmp1, tmp2;
 
+	nla_for_each_nested(attr1, freqs, tmp1)
+		if (nla_len(attr1) != sizeof(u32))
+			return 0;
+
 	nla_for_each_nested(attr1, freqs, tmp1) {
 		n_channels++;
 		/*
@@ -6628,7 +6619,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 
 		params.n_counter_offsets_presp = len / sizeof(u16);
 		if (rdev->wiphy.max_num_csa_counters &&
-		    (params.n_counter_offsets_beacon >
+		    (params.n_counter_offsets_presp >
 		     rdev->wiphy.max_num_csa_counters))
 			return -EINVAL;
 
@@ -6806,9 +6797,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	int start = cb->args[2], idx = 0;
 	int err;
 
+	rtnl_lock();
 	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
-	if (err)
+	if (err) {
+		rtnl_unlock();
 		return err;
+	}
 
 	wdev_lock(wdev);
 	spin_lock_bh(&rdev->bss_lock);
@@ -6831,7 +6825,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	wdev_unlock(wdev);
 
 	cb->args[2] = idx;
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 
 	return skb->len;
 }
@@ -6915,9 +6909,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 	int res;
 	bool radio_stats;
 
+	rtnl_lock();
 	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
-		return res;
+		goto out_err;
 
 	/* prepare_wdev_dump parsed the attributes */
 	radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
@@ -6958,7 +6953,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 	cb->args[2] = survey_idx;
 	res = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(rdev);
+	rtnl_unlock();
 	return res;
 }
 
@@ -10158,17 +10153,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 	void *data = NULL;
 	unsigned int data_len = 0;
 
-	rtnl_lock();
-
 	if (cb->args[0]) {
 		/* subtract the 1 again here */
 		struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
 		struct wireless_dev *tmp;
 
-		if (!wiphy) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
+		if (!wiphy)
+			return -ENODEV;
 		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
@@ -10189,13 +10180,11 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 			  nl80211_fam.attrbuf, nl80211_fam.maxattr,
 			  nl80211_policy);
 	if (err)
-		goto out_unlock;
+		return err;
 
 	if (!nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID] ||
-	    !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) {
-		err = -EINVAL;
-		goto out_unlock;
-	}
+	    !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD])
+		return -EINVAL;
 
 	*wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk),
 					   nl80211_fam.attrbuf);
@@ -10204,10 +10193,8 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 
 	*rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk),
 					   nl80211_fam.attrbuf);
-	if (IS_ERR(*rdev)) {
-		err = PTR_ERR(*rdev);
-		goto out_unlock;
-	}
+	if (IS_ERR(*rdev))
+		return PTR_ERR(*rdev);
 
 	vid = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID]);
 	subcmd = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]);
@@ -10220,19 +10207,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 		if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
 			continue;
 
-		if (!vcmd->dumpit) {
-			err = -EOPNOTSUPP;
-			goto out_unlock;
-		}
+		if (!vcmd->dumpit)
+			return -EOPNOTSUPP;
 
 		vcmd_idx = i;
 		break;
 	}
 
-	if (vcmd_idx < 0) {
-		err = -EOPNOTSUPP;
-		goto out_unlock;
-	}
+	if (vcmd_idx < 0)
+		return -EOPNOTSUPP;
 
 	if (nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]) {
 		data = nla_data(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]);
@@ -10249,9 +10232,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 
 	/* keep rtnl locked in successful case */
 	return 0;
- out_unlock:
-	rtnl_unlock();
-	return err;
 }
 
 static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
@@ -10266,9 +10246,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
 	int err;
 	struct nlattr *vendor_data;
 
+	rtnl_lock();
 	err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev);
 	if (err)
-		return err;
+		goto out;
 
 	vcmd_idx = cb->args[2];
 	data = (void *)cb->args[3];
@@ -10277,18 +10258,26 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
 
 	if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
 			   WIPHY_VENDOR_CMD_NEED_NETDEV)) {
-		if (!wdev)
-			return -EINVAL;
+		if (!wdev) {
+			err = -EINVAL;
+			goto out;
+		}
 		if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
-		    !wdev->netdev)
-			return -EINVAL;
+		    !wdev->netdev) {
+			err = -EINVAL;
+			goto out;
+		}
 
 		if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
 			if (wdev->netdev &&
-			    !netif_running(wdev->netdev))
-				return -ENETDOWN;
-			if (!wdev->netdev && !wdev->p2p_started)
-				return -ENETDOWN;
+			    !netif_running(wdev->netdev)) {
+				err = -ENETDOWN;
+				goto out;
+			}
+			if (!wdev->netdev && !wdev->p2p_started) {
+				err = -ENETDOWN;
+				goto out;
+			}
 		}
 	}
 
@@ -13161,20 +13150,24 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	struct wireless_dev *wdev;
 	struct cfg80211_beacon_registration *reg, *tmp;
 
-	if (state != NETLINK_URELEASE)
+	if (state != NETLINK_URELEASE || notify->protocol != NETLINK_GENERIC)
 		return NOTIFY_DONE;
 
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
 		bool schedule_destroy_work = false;
-		bool schedule_scan_stop = false;
 		struct cfg80211_sched_scan_request *sched_scan_req =
 			rcu_dereference(rdev->sched_scan_req);
 
 		if (sched_scan_req && notify->portid &&
-		    sched_scan_req->owner_nlportid == notify->portid)
-			schedule_scan_stop = true;
+		    sched_scan_req->owner_nlportid == notify->portid) {
+			sched_scan_req->owner_nlportid = 0;
+
+			if (rdev->ops->sched_scan_stop &&
+			    rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+				schedule_work(&rdev->sched_scan_stop_wk);
+		}
 
 		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
@@ -13205,12 +13198,6 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 				spin_unlock(&rdev->destroy_list_lock);
 				schedule_work(&rdev->destroy_work);
 			}
-		} else if (schedule_scan_stop) {
-			sched_scan_req->owner_nlportid = 0;
-
-			if (rdev->ops->sched_scan_stop &&
-			    rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
-				schedule_work(&rdev->sched_scan_stop_wk);
 		}
 	}
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 14d5369eb778..8dde12a11725 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -56,6 +56,19 @@
  * also linked into the probe response struct.
  */
 
+/*
+ * Limit the number of BSS entries stored in mac80211. Each one is
+ * a bit over 4k at most, so this limits to roughly 4-5M of memory.
+ * If somebody wants to really attack this though, they'd likely
+ * use small beacons, and only one type of frame, limiting each of
+ * the entries to a much smaller size (in order to generate more
+ * entries in total, so overhead is bigger.)
+ */
+static int bss_entries_limit = 1000;
+module_param(bss_entries_limit, int, 0644);
+MODULE_PARM_DESC(bss_entries_limit,
+                 "limit to number of scan BSS entries (per wiphy, default 1000)");
+
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
 static void bss_free(struct cfg80211_internal_bss *bss)
@@ -136,6 +149,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 
 	list_del_init(&bss->list);
 	rb_erase(&bss->rbn, &rdev->bss_tree);
+	rdev->bss_entries--;
+	WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list),
+		  "rdev bss entries[%d]/list[empty:%d] corruption\n",
+		  rdev->bss_entries, list_empty(&rdev->bss_list));
 	bss_ref_put(rdev, bss);
 	return true;
 }
@@ -162,6 +179,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev,
 		rdev->bss_generation++;
 }
 
+static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_internal_bss *bss, *oldest = NULL;
+	bool ret;
+
+	lockdep_assert_held(&rdev->bss_lock);
+
+	list_for_each_entry(bss, &rdev->bss_list, list) {
+		if (atomic_read(&bss->hold))
+			continue;
+
+		if (!list_empty(&bss->hidden_list) &&
+		    !bss->pub.hidden_beacon_bss)
+			continue;
+
+		if (oldest && time_before(oldest->ts, bss->ts))
+			continue;
+		oldest = bss;
+	}
+
+	if (WARN_ON(!oldest))
+		return false;
+
+	/*
+	 * The callers make sure to increase rdev->bss_generation if anything
+	 * gets removed (and a new entry added), so there's no need to also do
+	 * it here.
+	 */
+
+	ret = __cfg80211_unlink_bss(rdev, oldest);
+	WARN_ON(!ret);
+	return ret;
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
@@ -687,6 +738,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	const u8 *ie;
 	int i, ssidlen;
 	u8 fold = 0;
+	u32 n_entries = 0;
 
 	ies = rcu_access_pointer(new->pub.beacon_ies);
 	if (WARN_ON(!ies))
@@ -710,6 +762,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	/* This is the bad part ... */
 
 	list_for_each_entry(bss, &rdev->bss_list, list) {
+		/*
+		 * we're iterating all the entries anyway, so take the
+		 * opportunity to validate the list length accounting
+		 */
+		n_entries++;
+
 		if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid))
 			continue;
 		if (bss->pub.channel != new->pub.channel)
@@ -738,6 +796,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 				   new->pub.beacon_ies);
 	}
 
+	WARN_ONCE(n_entries != rdev->bss_entries,
+		  "rdev bss entries[%d]/list[len:%d] corruption\n",
+		  rdev->bss_entries, n_entries);
+
 	return true;
 }
 
@@ -890,7 +952,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 			}
 		}
 
+		if (rdev->bss_entries >= bss_entries_limit &&
+		    !cfg80211_bss_expire_oldest(rdev)) {
+			kfree(new);
+			goto drop;
+		}
+
 		list_add_tail(&new->list, &rdev->bss_list);
+		rdev->bss_entries++;
 		rb_insert_bss(rdev, new);
 		found = new;
 	}
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 8020b5b094d4..18b4a652cf41 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -39,6 +39,7 @@ struct cfg80211_conn {
 		CFG80211_CONN_ASSOCIATING,
 		CFG80211_CONN_ASSOC_FAILED,
 		CFG80211_CONN_DEAUTH,
+		CFG80211_CONN_ABANDON,
 		CFG80211_CONN_CONNECTED,
 	} state;
 	u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN];
@@ -204,6 +205,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 		cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid,
 				     NULL, 0,
 				     WLAN_REASON_DEAUTH_LEAVING, false);
+		/* fall through */
+	case CFG80211_CONN_ABANDON:
 		/* free directly, disconnected event already sent */
 		cfg80211_sme_free(wdev);
 		return 0;
@@ -423,6 +426,17 @@ void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev)
 	schedule_work(&rdev->conn_work);
 }
 
+void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+
+	if (!wdev->conn)
+		return;
+
+	wdev->conn->state = CFG80211_CONN_ABANDON;
+	schedule_work(&rdev->conn_work);
+}
+
 static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev,
 				     const u8 *ies, size_t ies_len,
 				     const u8 **out_ies, size_t *out_ies_len)
diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7ecd04c21360..997ff7b2509b 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	memset(&theirs, 0, sizeof(theirs));
 	memcpy(new, ours, sizeof(*new));
+	memset(dte, 0, sizeof(*dte));
 
 	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
 	if (len < 0)
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index ad7f5b3f9b61..1c4ad477ce93 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		skb_dst_force(skb);
+		dev_hold(skb->dev);
 
 		nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
 resume:
+		dev_put(skb->dev);
+
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
 			if (nexthdr == -EBADMSG) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b5e665b3cfb0..0e01250f2072 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1216,7 +1216,7 @@ static inline int policy_to_flow_dir(int dir)
 }
 
 static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
-						 const struct flowi *fl)
+						 const struct flowi *fl, u16 family)
 {
 	struct xfrm_policy *pol;
 	struct net *net = sock_net(sk);
@@ -1225,8 +1225,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
 	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	pol = rcu_dereference(sk->sk_policy[dir]);
 	if (pol != NULL) {
-		bool match = xfrm_selector_match(&pol->selector, fl,
-						 sk->sk_family);
+		bool match = xfrm_selector_match(&pol->selector, fl, family);
 		int err = 0;
 
 		if (match) {
@@ -1776,43 +1775,6 @@ free_dst:
 	goto out;
 }
 
-#ifdef CONFIG_XFRM_SUB_POLICY
-static int xfrm_dst_alloc_copy(void **target, const void *src, int size)
-{
-	if (!*target) {
-		*target = kmalloc(size, GFP_ATOMIC);
-		if (!*target)
-			return -ENOMEM;
-	}
-
-	memcpy(*target, src, size);
-	return 0;
-}
-#endif
-
-static int xfrm_dst_update_parent(struct dst_entry *dst,
-				  const struct xfrm_selector *sel)
-{
-#ifdef CONFIG_XFRM_SUB_POLICY
-	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
-	return xfrm_dst_alloc_copy((void **)&(xdst->partner),
-				   sel, sizeof(*sel));
-#else
-	return 0;
-#endif
-}
-
-static int xfrm_dst_update_origin(struct dst_entry *dst,
-				  const struct flowi *fl)
-{
-#ifdef CONFIG_XFRM_SUB_POLICY
-	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
-	return xfrm_dst_alloc_copy((void **)&(xdst->origin), fl, sizeof(*fl));
-#else
-	return 0;
-#endif
-}
-
 static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 				struct xfrm_policy **pols,
 				int *num_pols, int *num_xfrms)
@@ -1884,16 +1846,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 
 	xdst = (struct xfrm_dst *)dst;
 	xdst->num_xfrms = err;
-	if (num_pols > 1)
-		err = xfrm_dst_update_parent(dst, &pols[1]->selector);
-	else
-		err = xfrm_dst_update_origin(dst, fl);
-	if (unlikely(err)) {
-		dst_free(dst);
-		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-		return ERR_PTR(err);
-	}
-
 	xdst->num_pols = num_pols;
 	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
@@ -2221,7 +2173,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	sk = sk_const_to_full_sk(sk);
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
 		num_pols = 1;
-		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
 		err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 		if (err < 0)
@@ -2500,7 +2452,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	pol = NULL;
 	sk = sk_to_full_sk(sk);
 	if (sk && sk->sk_policy[dir]) {
-		pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
 		if (IS_ERR(pol)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 			return 0;
@@ -3030,6 +2982,11 @@ static int __net_init xfrm_net_init(struct net *net)
 {
 	int rv;
 
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	rwlock_init(&net->xfrm.xfrm_policy_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
 	rv = xfrm_statistics_init(net);
 	if (rv < 0)
 		goto out_statistics;
@@ -3046,11 +3003,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	if (rv < 0)
 		goto out;
 
-	/* Initialize the per-net locks here */
-	spin_lock_init(&net->xfrm.xfrm_state_lock);
-	rwlock_init(&net->xfrm.xfrm_policy_lock);
-	mutex_init(&net->xfrm.xfrm_cfg_mutex);
-
 	return 0;
 
 out:
@@ -3323,9 +3275,15 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	struct xfrm_state *x_new[XFRM_MAX_DEPTH];
 	struct xfrm_migrate *mp;
 
+	/* Stage 0 - sanity checks */
 	if ((err = xfrm_migrate_check(m, num_migrate)) < 0)
 		goto out;
 
+	if (dir >= XFRM_POLICY_MAX) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	/* Stage 1 - find policy */
 	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
 		err = -ENOENT;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 805681a7d356..7a5a64e70b4d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -412,7 +412,14 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es
 	up = nla_data(rp);
 	ulen = xfrm_replay_state_esn_len(up);
 
-	if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen)
+	/* Check the overall length and the internal bitmap length to avoid
+	 * potential overflow. */
+	if (nla_len(rp) < ulen ||
+	    xfrm_replay_state_esn_len(replay_esn) != ulen ||
+	    replay_esn->bmp_len != up->bmp_len)
+		return -EINVAL;
+
+	if (up->replay_window > up->bmp_len * sizeof(__u32) * 8)
 		return -EINVAL;
 
 	return 0;
diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c
index 8d8d1ec429eb..9b96f4fb8cea 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output_kern.c
@@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx)
 		u64 cookie;
 	} data;
 
-	memset(&data, 0, sizeof(data));
 	data.pid = bpf_get_current_pid_tgid();
 	data.cookie = 0x12345678;
 
diff --git a/Documentation/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore
index 8b7c72f07c92..8b7c72f07c92 100644
--- a/Documentation/mic/mpssd/.gitignore
+++ b/samples/mic/mpssd/.gitignore
diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile
new file mode 100644
index 000000000000..3e3ef91fed6b
--- /dev/null
+++ b/samples/mic/mpssd/Makefile
@@ -0,0 +1,27 @@
+ifndef CROSS_COMPILE
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+
+ifeq ($(ARCH),x86)
+
+PROGS := mpssd
+CC = $(CROSS_COMPILE)gcc
+CFLAGS := -I../../../usr/include -I../../../tools/include
+
+ifdef DEBUG
+CFLAGS += -DDEBUG=$(DEBUG)
+endif
+
+all: $(PROGS)
+mpssd: mpssd.c sysfs.c
+	$(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread
+
+install:
+	install mpssd /usr/sbin/mpssd
+	install micctrl /usr/sbin/micctrl
+
+clean:
+	rm -fr $(PROGS)
+
+endif
+endif
diff --git a/Documentation/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl
index 8f2629b41c5f..8f2629b41c5f 100755..100644
--- a/Documentation/mic/mpssd/micctrl
+++ b/samples/mic/mpssd/micctrl
diff --git a/Documentation/mic/mpssd/mpss b/samples/mic/mpssd/mpss
index 09ea90931649..09ea90931649 100755..100644
--- a/Documentation/mic/mpssd/mpss
+++ b/samples/mic/mpssd/mpss
diff --git a/Documentation/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c
index aaeafa18d99b..c99a75968c01 100644
--- a/Documentation/mic/mpssd/mpssd.c
+++ b/samples/mic/mpssd/mpssd.c
@@ -1538,9 +1538,9 @@ set_cmdline(struct mic_info *mic)
 
 	len = snprintf(buffer, PATH_MAX,
 		"clocksource=tsc highres=off nohz=off ");
-	len += snprintf(buffer + len, PATH_MAX,
+	len += snprintf(buffer + len, PATH_MAX - len,
 		"cpufreq_on;corec6_off;pc3_off;pc6_off ");
-	len += snprintf(buffer + len, PATH_MAX,
+	len += snprintf(buffer + len, PATH_MAX - len,
 		"ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0",
 		mic->id + 1);
 
diff --git a/Documentation/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h
index 8bd64944aacc..8bd64944aacc 100644
--- a/Documentation/mic/mpssd/mpssd.h
+++ b/samples/mic/mpssd/mpssd.h
diff --git a/Documentation/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c
index 8dd326936083..8dd326936083 100644
--- a/Documentation/mic/mpssd/sysfs.c
+++ b/samples/mic/mpssd/sysfs.c
diff --git a/samples/seccomp/bpf-helper.h b/samples/seccomp/bpf-helper.h
index 38ee70f3cd5b..1d8de9edd858 100644
--- a/samples/seccomp/bpf-helper.h
+++ b/samples/seccomp/bpf-helper.h
@@ -138,7 +138,7 @@ union arg64 {
 #define ARG_32(idx) \
 	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx))
 
-/* Loads hi into A and lo in X */
+/* Loads lo into M[0] and hi into M[1] and A */
 #define ARG_64(idx) \
 	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)), \
 	BPF_STMT(BPF_ST, 0), /* lo -> M[0] */ \
@@ -153,88 +153,107 @@ union arg64 {
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 1, 0), \
 	jt
 
-/* Checks the lo, then swaps to check the hi. A=lo,X=hi */
+#define JA32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \
+	jt
+
+#define JGE32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \
+	jt
+
+#define JGT32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \
+	jt
+
+#define JLE32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \
+	jt
+
+#define JLT32(value, jt) \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \
+	jt
+
+/*
+ * All the JXX64 checks assume lo is saved in M[0] and hi is saved in both
+ * A and M[1]. This invariant is kept by restoring A if necessary.
+ */
 #define JEQ64(lo, hi, jt) \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
 	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	/* if (lo != arg.lo) goto NOMATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
 #define JNE64(lo, hi, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 5, 0), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	/* if (hi != arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo != arg.lo) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
-
-#define JA32(value, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \
-	jt
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
 #define JA64(lo, hi, jt) \
+	/* if (hi & arg.hi) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo & arg.lo) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
-#define JGE32(value, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \
-	jt
-
-#define JLT32(value, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \
-	jt
-
-/* Shortcut checking if hi > arg.hi. */
 #define JGE64(lo, hi, jt) \
+	/* if (hi > arg.hi) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo >= arg.lo) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
-	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
-
-#define JLT64(lo, hi, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
-	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
-	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
-#define JGT32(value, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \
-	jt
-
-#define JLE32(value, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \
-	jt
-
-/* Check hi > args.hi first, then do the GE checking */
 #define JGT64(lo, hi, jt) \
+	/* if (hi > arg.hi) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo > arg.lo) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
 #define JLE64(lo, hi, jt) \
-	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 6, 0), \
-	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \
-	BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+	/* if (hi < arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo <= arg.lo) goto MATCH; */ \
 	BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
-	BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
+	jt, \
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
+
+#define JLT64(lo, hi, jt) \
+	/* if (hi < arg.hi) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+	/* if (hi != arg.hi) goto NOMATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+	BPF_STMT(BPF_LD+BPF_MEM, 0), \
+	/* if (lo < arg.lo) goto MATCH; */ \
+	BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 2, 0), \
+	BPF_STMT(BPF_LD+BPF_MEM, 1), \
 	jt, \
-	BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+	BPF_STMT(BPF_LD+BPF_MEM, 1)
 
 #define LOAD_SYSCALL_NR \
 	BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 4efedcbe4165..da3386a9d244 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -24,6 +24,7 @@ warning-1 += $(call cc-option, -Wmissing-prototypes)
 warning-1 += -Wold-style-definition
 warning-1 += $(call cc-option, -Wmissing-include-dirs)
 warning-1 += $(call cc-option, -Wunused-but-set-variable)
+warning-1 += $(call cc-option, -Wunused-const-variable)
 warning-1 += $(call cc-disable-warning, missing-field-initializers)
 
 warning-2 := -Waggregate-return
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 2b3c22808c3b..6ac6550d751c 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3252,7 +3252,7 @@ sub process {
 				$fixedline =~ s/\s*=\s*$/ = {/;
 				fix_insert_line($fixlinenr, $fixedline);
 				$fixedline = $line;
-				$fixedline =~ s/^(.\s*){\s*/$1/;
+				$fixedline =~ s/^(.\s*)\{\s*/$1/;
 				fix_insert_line($fixlinenr, $fixedline);
 			}
 		}
@@ -3602,7 +3602,7 @@ sub process {
 				my $fixedline = rtrim($prevrawline) . " {";
 				fix_insert_line($fixlinenr, $fixedline);
 				$fixedline = $rawline;
-				$fixedline =~ s/^(.\s*){\s*/$1\t/;
+				$fixedline =~ s/^(.\s*)\{\s*/$1\t/;
 				if ($fixedline !~ /^\+\s*$/) {
 					fix_insert_line($fixlinenr, $fixedline);
 				}
@@ -4091,7 +4091,7 @@ sub process {
 			if (ERROR("SPACING",
 				  "space required before the open brace '{'\n" . $herecurr) &&
 			    $fix) {
-				$fixed[$fixlinenr] =~ s/^(\+.*(?:do|\))){/$1 {/;
+				$fixed[$fixlinenr] =~ s/^(\+.*(?:do|\)))\{/$1 {/;
 			}
 		}
 
diff --git a/scripts/coccinelle/iterators/use_after_iter.cocci b/scripts/coccinelle/iterators/use_after_iter.cocci
index f085f5968c52..ce8cc9c006e5 100644
--- a/scripts/coccinelle/iterators/use_after_iter.cocci
+++ b/scripts/coccinelle/iterators/use_after_iter.cocci
@@ -123,7 +123,7 @@ list_remove_head(x,c,...)
 |
 sizeof(<+...c...+>)
 |
-&c->member
+ &c->member
 |
 c = E
 |
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
index 973e8c141567..17867e723a51 100755
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ b/scripts/gcc-x86_64-has-stack-protector.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
 if [ "$?" -eq "0" ] ; then
 	echo y
 else
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index d79cba4ce3eb..ebced77deb9c 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -96,13 +96,15 @@ savedefconfig: $(obj)/conf
 defconfig: $(obj)/conf
 ifeq ($(KBUILD_DEFCONFIG),)
 	$< $(silent) --defconfig $(Kconfig)
-else ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)),)
+else
+ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG)),)
 	@$(kecho) "*** Default configuration is based on '$(KBUILD_DEFCONFIG)'"
 	$(Q)$< $(silent) --defconfig=arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG) $(Kconfig)
 else
 	@$(kecho) "*** Default configuration is based on target '$(KBUILD_DEFCONFIG)'"
 	$(Q)$(MAKE) -f $(srctree)/Makefile $(KBUILD_DEFCONFIG)
 endif
+endif
 
 %_defconfig: $(obj)/conf
 	$(Q)$< $(silent) --defconfig=arch/$(SRCARCH)/configs/$@ $(Kconfig)
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 0b7dc2fd7bac..dd243d2abd87 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -267,10 +267,8 @@ int conf_read_simple(const char *name, int def)
 		if (in)
 			goto load;
 		sym_add_change_count(1);
-		if (!sym_defconfig_list) {
-			sym_calc_value(modules_sym);
+		if (!sym_defconfig_list)
 			return 1;
-		}
 
 		for_all_defaults(sym_defconfig_list, prop) {
 			if (expr_calc_value(prop->visible.expr) == no ||
@@ -403,7 +401,6 @@ setsym:
 	}
 	free(line);
 	fclose(in);
-	sym_calc_value(modules_sym);
 	return 0;
 }
 
@@ -414,8 +411,12 @@ int conf_read(const char *name)
 
 	sym_set_change_count(0);
 
-	if (conf_read_simple(name, S_DEF_USER))
+	if (conf_read_simple(name, S_DEF_USER)) {
+		sym_calc_value(modules_sym);
 		return 1;
+	}
+
+	sym_calc_value(modules_sym);
 
 	for_all_symbols(i, sym) {
 		sym_calc_value(sym);
@@ -846,6 +847,7 @@ static int conf_split_config(void)
 
 	name = conf_get_autoconfig_name();
 	conf_read_simple(name, S_DEF_AUTO);
+	sym_calc_value(modules_sym);
 
 	if (chdir("include/config"))
 		return 1;
diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c
index 8275f0e55106..4b2f44c20caf 100644
--- a/scripts/kconfig/nconf.gui.c
+++ b/scripts/kconfig/nconf.gui.c
@@ -364,12 +364,14 @@ int dialog_inputbox(WINDOW *main_window,
 	WINDOW *prompt_win;
 	WINDOW *form_win;
 	PANEL *panel;
-	int i, x, y;
+	int i, x, y, lines, columns, win_lines, win_cols;
 	int res = -1;
 	int cursor_position = strlen(init);
 	int cursor_form_win;
 	char *result = *resultp;
 
+	getmaxyx(stdscr, lines, columns);
+
 	if (strlen(init)+1 > *result_len) {
 		*result_len = strlen(init)+1;
 		*resultp = result = realloc(result, *result_len);
@@ -386,14 +388,19 @@ int dialog_inputbox(WINDOW *main_window,
 	if (title)
 		prompt_width = max(prompt_width, strlen(title));
 
+	win_lines = min(prompt_lines+6, lines-2);
+	win_cols = min(prompt_width+7, columns-2);
+	prompt_lines = max(win_lines-6, 0);
+	prompt_width = max(win_cols-7, 0);
+
 	/* place dialog in middle of screen */
-	y = (getmaxy(stdscr)-(prompt_lines+4))/2;
-	x = (getmaxx(stdscr)-(prompt_width+4))/2;
+	y = (lines-win_lines)/2;
+	x = (columns-win_cols)/2;
 
 	strncpy(result, init, *result_len);
 
 	/* create the windows */
-	win = newwin(prompt_lines+6, prompt_width+7, y, x);
+	win = newwin(win_lines, win_cols, y, x);
 	prompt_win = derwin(win, prompt_lines+1, prompt_width, 2, 2);
 	form_win = derwin(win, 1, prompt_width, prompt_lines+3, 2);
 	keypad(form_win, TRUE);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 5b96206e9aab..9f5cdd49ff0b 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -695,7 +695,7 @@ static int do_of_entry (const char *filename, void *symval, char *alias)
 	len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*",
 		      (*type)[0] ? *type : "*");
 
-	if (compatible[0])
+	if ((*compatible)[0])
 		sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "",
 			*compatible);
 
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index 1aca224e8597..493e226356ca 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -52,7 +52,7 @@ rpm-pkg rpm: FORCE
 	$(call cmd,src_tar,$(KERNELPATH),kernel.spec)
 	$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
 	mv -f $(objtree)/.tmp_version $(objtree)/.version
-	rpmbuild --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
+	rpmbuild $(RPMOPTS) --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
 	rm $(KERNELPATH).tar.gz kernel.spec
 
 # binrpm-pkg
@@ -63,7 +63,7 @@ binrpm-pkg: FORCE
 	$(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
 	mv -f $(objtree)/.tmp_version $(objtree)/.version
 
-	rpmbuild --define "_builddir $(objtree)" --target \
+	rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \
 		$(UTS_MACHINE) -bb $(objtree)/binkernel.spec
 	rm binkernel.spec
 
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index 71004daefe31..fe44d68e9344 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -131,11 +131,11 @@ echo 'rm -rf $RPM_BUILD_ROOT'
 echo ""
 echo "%post"
 echo "if [ -x /sbin/installkernel -a -r /boot/vmlinuz-$KERNELRELEASE -a -r /boot/System.map-$KERNELRELEASE ]; then"
-echo "cp /boot/vmlinuz-$KERNELRELEASE /boot/vmlinuz-$KERNELRELEASE-rpm"
-echo "cp /boot/System.map-$KERNELRELEASE /boot/System.map-$KERNELRELEASE-rpm"
+echo "cp /boot/vmlinuz-$KERNELRELEASE /boot/.vmlinuz-$KERNELRELEASE-rpm"
+echo "cp /boot/System.map-$KERNELRELEASE /boot/.System.map-$KERNELRELEASE-rpm"
 echo "rm -f /boot/vmlinuz-$KERNELRELEASE /boot/System.map-$KERNELRELEASE"
-echo "/sbin/installkernel $KERNELRELEASE /boot/vmlinuz-$KERNELRELEASE-rpm /boot/System.map-$KERNELRELEASE-rpm"
-echo "rm -f /boot/vmlinuz-$KERNELRELEASE-rpm /boot/System.map-$KERNELRELEASE-rpm"
+echo "/sbin/installkernel $KERNELRELEASE /boot/.vmlinuz-$KERNELRELEASE-rpm /boot/.System.map-$KERNELRELEASE-rpm"
+echo "rm -f /boot/.vmlinuz-$KERNELRELEASE-rpm /boot/.System.map-$KERNELRELEASE-rpm"
 echo "fi"
 echo ""
 echo "%files"
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index e167592793a7..42396a74405d 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -33,10 +33,17 @@
 #include <string.h>
 #include <unistd.h>
 
+/*
+ * glibc synced up and added the metag number but didn't add the relocations.
+ * Work around this in a crude manner for now.
+ */
 #ifndef EM_METAG
-/* Remove this when these make it to the standard system elf.h. */
 #define EM_METAG      174
+#endif
+#ifndef R_METAG_ADDR32
 #define R_METAG_ADDR32                   2
+#endif
+#ifndef R_METAG_NONE
 #define R_METAG_NONE                     3
 #endif
 
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index ad4fa49ad1db..9068369f8a1b 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -331,6 +331,7 @@ static int aa_fs_seq_hash_show(struct seq_file *seq, void *v)
 			seq_printf(seq, "%.2x", profile->hash[i]);
 		seq_puts(seq, "\n");
 	}
+	aa_put_profile(profile);
 
 	return 0;
 }
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index dc0027b28b04..53426a6ee6dc 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -623,8 +623,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 	/* released below */
 	cred = get_current_cred();
 	cxt = cred_cxt(cred);
-	profile = aa_cred_profile(cred);
-	previous_profile = cxt->previous;
+	profile = aa_get_newest_profile(aa_cred_profile(cred));
+	previous_profile = aa_get_newest_profile(cxt->previous);
 
 	if (unconfined(profile)) {
 		info = "unconfined";
@@ -720,6 +720,8 @@ audit:
 out:
 	aa_put_profile(hat);
 	kfree(name);
+	aa_put_profile(profile);
+	aa_put_profile(previous_profile);
 	put_cred(cred);
 
 	return error;
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 1d950fbb2aec..2d1fe34781fa 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -202,7 +202,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	} hash;
 
 	if (xattr_value)
-		*xattr_len = ima_read_xattr(file->f_path.dentry, xattr_value);
+		*xattr_len = ima_read_xattr(file_dentry(file), xattr_value);
 
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 1873b5536f80..9ce9d5003dcc 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -189,7 +189,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 {
 	static const char op[] = "appraise_data";
 	char *cause = "unknown";
-	struct dentry *dentry = file->f_path.dentry;
+	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = d_backing_inode(dentry);
 	enum integrity_status status = INTEGRITY_UNKNOWN;
 	int rc = xattr_len, hash_start = 0;
@@ -203,10 +203,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 
 		cause = "missing-hash";
 		status = INTEGRITY_NOLABEL;
-		if (opened & FILE_CREATED) {
+		if (opened & FILE_CREATED)
 			iint->flags |= IMA_NEW_FILE;
+		if ((iint->flags & IMA_NEW_FILE) &&
+		    !(iint->flags & IMA_DIGSIG_REQUIRED))
 			status = INTEGRITY_PASS;
-		}
 		goto out;
 	}
 
@@ -289,7 +290,7 @@ out:
  */
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
 {
-	struct dentry *dentry = file->f_path.dentry;
+	struct dentry *dentry = file_dentry(file);
 	int rc = 0;
 
 	/* do not collect and update hash for digital signatures */
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 696ccfa08d10..31898856682e 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -428,7 +428,7 @@ static int init_blkcipher_desc(struct blkcipher_desc *desc, const u8 *key,
 static struct key *request_master_key(struct encrypted_key_payload *epayload,
 				      const u8 **master_key, size_t *master_keylen)
 {
-	struct key *mkey = NULL;
+	struct key *mkey = ERR_PTR(-EINVAL);
 
 	if (!strncmp(epayload->master_desc, KEY_TRUSTED_PREFIX,
 		     KEY_TRUSTED_PREFIX_LEN)) {
diff --git a/security/keys/gc.c b/security/keys/gc.c
index addf060399e0..9cb4fe4478a1 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -46,7 +46,7 @@ static unsigned long key_gc_flags;
  * immediately unlinked.
  */
 struct key_type key_type_dead = {
-	.name = "dead",
+	.name = ".dead",
 };
 
 /*
diff --git a/security/keys/key.c b/security/keys/key.c
index ab7997ded725..09c10b181881 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -578,7 +578,7 @@ int key_reject_and_link(struct key *key,
 
 	mutex_unlock(&key_construction_mutex);
 
-	if (keyring)
+	if (keyring && link_ret == 0)
 		__key_link_end(keyring, &key->index_key, edit);
 
 	/* wake up anyone waiting for a key to be constructed */
@@ -934,12 +934,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen)
 	/* the key must be writable */
 	ret = key_permission(key_ref, KEY_NEED_WRITE);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	/* attempt to update it if supported */
-	ret = -EOPNOTSUPP;
 	if (!key->type->update)
-		goto error;
+		return -EOPNOTSUPP;
 
 	memset(&prep, 0, sizeof(prep));
 	prep.data = payload;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 1c3872aeed14..671709d8610d 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -97,7 +97,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
-	if (_payload) {
+	if (plen) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL | __GFP_NOWARN);
 		if (!payload) {
@@ -271,7 +271,8 @@ error:
  * Create and join an anonymous session keyring or join a named session
  * keyring, creating it if necessary.  A named session keyring must have Search
  * permission for it to be joined.  Session keyrings without this permit will
- * be skipped over.
+ * be skipped over.  It is not permitted for userspace to create or join
+ * keyrings whose name begin with a dot.
  *
  * If successful, the ID of the joined session keyring will be returned.
  */
@@ -288,12 +289,16 @@ long keyctl_join_session_keyring(const char __user *_name)
 			ret = PTR_ERR(name);
 			goto error;
 		}
+
+		ret = -EPERM;
+		if (name[0] == '.')
+			goto error_name;
 	}
 
 	/* join the session */
 	ret = join_session_keyring(name);
+error_name:
 	kfree(name);
-
 error:
 	return ret;
 }
@@ -322,7 +327,7 @@ long keyctl_update_key(key_serial_t id,
 
 	/* pull the payload in if one was supplied */
 	payload = NULL;
-	if (_payload) {
+	if (plen) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
 		if (!payload)
@@ -1223,8 +1228,8 @@ error:
  * Read or set the default keyring in which request_key() will cache keys and
  * return the old setting.
  *
- * If a process keyring is specified then this will be created if it doesn't
- * yet exist.  The old setting will be returned if successful.
+ * If a thread or process keyring is specified then it will be created if it
+ * doesn't yet exist.  The old setting will be returned if successful.
  */
 long keyctl_set_reqkey_keyring(int reqkey_defl)
 {
@@ -1249,11 +1254,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl)
 
 	case KEY_REQKEY_DEFL_PROCESS_KEYRING:
 		ret = install_process_keyring_to_cred(new);
-		if (ret < 0) {
-			if (ret != -EEXIST)
-				goto error;
-			ret = 0;
-		}
+		if (ret < 0)
+			goto error;
 		goto set;
 
 	case KEY_REQKEY_DEFL_DEFAULT:
diff --git a/security/keys/proc.c b/security/keys/proc.c
index f0611a6368cd..b9f531c9e4fa 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -181,7 +181,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	struct timespec now;
 	unsigned long timo;
 	key_ref_t key_ref, skey_ref;
-	char xbuf[12];
+	char xbuf[16];
 	int rc;
 
 	struct keyring_search_context ctx = {
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index e6d50172872f..4ed909142956 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -125,13 +125,18 @@ error:
 }
 
 /*
- * Install a fresh thread keyring directly to new credentials.  This keyring is
- * allowed to overrun the quota.
+ * Install a thread keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
  */
 int install_thread_keyring_to_cred(struct cred *new)
 {
 	struct key *keyring;
 
+	if (new->thread_keyring)
+		return 0;
+
 	keyring = keyring_alloc("_tid", new->uid, new->gid, new,
 				KEY_POS_ALL | KEY_USR_VIEW,
 				KEY_ALLOC_QUOTA_OVERRUN, NULL);
@@ -143,7 +148,9 @@ int install_thread_keyring_to_cred(struct cred *new)
 }
 
 /*
- * Install a fresh thread keyring, discarding the old one.
+ * Install a thread keyring to the current task if it didn't have one already.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
  */
 static int install_thread_keyring(void)
 {
@@ -154,8 +161,6 @@ static int install_thread_keyring(void)
 	if (!new)
 		return -ENOMEM;
 
-	BUG_ON(new->thread_keyring);
-
 	ret = install_thread_keyring_to_cred(new);
 	if (ret < 0) {
 		abort_creds(new);
@@ -166,17 +171,17 @@ static int install_thread_keyring(void)
 }
 
 /*
- * Install a process keyring directly to a credentials struct.
+ * Install a process keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
  *
- * Returns -EEXIST if there was already a process keyring, 0 if one installed,
- * and other value on any other error
+ * Return: 0 if a process keyring is now present; -errno on failure.
  */
 int install_process_keyring_to_cred(struct cred *new)
 {
 	struct key *keyring;
 
 	if (new->process_keyring)
-		return -EEXIST;
+		return 0;
 
 	keyring = keyring_alloc("_pid", new->uid, new->gid, new,
 				KEY_POS_ALL | KEY_USR_VIEW,
@@ -189,11 +194,9 @@ int install_process_keyring_to_cred(struct cred *new)
 }
 
 /*
- * Make sure a process keyring is installed for the current process.  The
- * existing process keyring is not replaced.
+ * Install a process keyring to the current task if it didn't have one already.
  *
- * Returns 0 if there is a process keyring by the end of this function, some
- * error otherwise.
+ * Return: 0 if a process keyring is now present; -errno on failure.
  */
 static int install_process_keyring(void)
 {
@@ -207,14 +210,18 @@ static int install_process_keyring(void)
 	ret = install_process_keyring_to_cred(new);
 	if (ret < 0) {
 		abort_creds(new);
-		return ret != -EEXIST ? ret : 0;
+		return ret;
 	}
 
 	return commit_creds(new);
 }
 
 /*
- * Install a session keyring directly to a credentials struct.
+ * Install the given keyring as the session keyring of the given credentials
+ * struct, replacing the existing one if any.  If the given keyring is NULL,
+ * then install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
  */
 int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 {
@@ -249,8 +256,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 }
 
 /*
- * Install a session keyring, discarding the old one.  If a keyring is not
- * supplied, an empty one is invented.
+ * Install the given keyring as the session keyring of the current task,
+ * replacing the existing one if any.  If the given keyring is NULL, then
+ * install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
  */
 static int install_session_keyring(struct key *keyring)
 {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index d0cfaa9f19d0..4b56c3b6c25f 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5640,7 +5640,7 @@ static int selinux_setprocattr(struct task_struct *p,
 		return error;
 
 	/* Obtain a SID for the context, if one was specified. */
-	if (size && str[1] && str[1] != '\n') {
+	if (size && str[0] && str[0] != '\n') {
 		if (str[size-1] == '\n') {
 			str[size-1] = 0;
 			size--;
diff --git a/sound/core/control.c b/sound/core/control.c
index a85d45595d02..bd01d492f46a 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -160,6 +160,8 @@ void snd_ctl_notify(struct snd_card *card, unsigned int mask,
 	
 	if (snd_BUG_ON(!card || !id))
 		return;
+	if (card->shutdown)
+		return;
 	read_lock(&card->ctl_files_rwlock);
 #if IS_ENABLED(CONFIG_SND_MIXER_OSS)
 	card->mixer_oss_change_count++;
@@ -1124,7 +1126,7 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol,
 		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
-			change = memcmp(ue->tlv_data, new_data, size);
+			change = memcmp(ue->tlv_data, new_data, size) != 0;
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
diff --git a/sound/core/info.c b/sound/core/info.c
index 895362a696c9..8ab72e0f5932 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -325,10 +325,15 @@ static ssize_t snd_info_text_entry_write(struct file *file,
 	size_t next;
 	int err = 0;
 
+	if (!entry->c.text.write)
+		return -EIO;
 	pos = *offset;
 	if (!valid_pos(pos, count))
 		return -EIO;
 	next = pos + count;
+	/* don't handle too large text inputs */
+	if (next > 16 * 1024)
+		return -EIO;
 	mutex_lock(&entry->access);
 	buf = data->wbuffer;
 	if (!buf) {
@@ -366,7 +371,9 @@ static int snd_info_seq_show(struct seq_file *seq, void *p)
 	struct snd_info_private_data *data = seq->private;
 	struct snd_info_entry *entry = data->entry;
 
-	if (entry->c.text.read) {
+	if (!entry->c.text.read) {
+		return -EIO;
+	} else {
 		data->rbuffer->buffer = (char *)seq; /* XXX hack! */
 		entry->c.text.read(entry, data->rbuffer);
 	}
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 308c9ecf73db..8e980aa678d0 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -849,6 +849,14 @@ int snd_pcm_new_internal(struct snd_card *card, const char *id, int device,
 }
 EXPORT_SYMBOL(snd_pcm_new_internal);
 
+static void free_chmap(struct snd_pcm_str *pstr)
+{
+	if (pstr->chmap_kctl) {
+		snd_ctl_remove(pstr->pcm->card, pstr->chmap_kctl);
+		pstr->chmap_kctl = NULL;
+	}
+}
+
 static void snd_pcm_free_stream(struct snd_pcm_str * pstr)
 {
 	struct snd_pcm_substream *substream, *substream_next;
@@ -871,6 +879,7 @@ static void snd_pcm_free_stream(struct snd_pcm_str * pstr)
 		kfree(setup);
 	}
 #endif
+	free_chmap(pstr);
 	if (pstr->substream_count)
 		put_device(&pstr->dev);
 }
@@ -1135,10 +1144,7 @@ static int snd_pcm_dev_disconnect(struct snd_device *device)
 	for (cidx = 0; cidx < 2; cidx++) {
 		if (!pcm->internal)
 			snd_unregister_device(&pcm->streams[cidx].dev);
-		if (pcm->streams[cidx].chmap_kctl) {
-			snd_ctl_remove(pcm->card, pcm->streams[cidx].chmap_kctl);
-			pcm->streams[cidx].chmap_kctl = NULL;
-		}
+		free_chmap(&pcm->streams[cidx]);
 	}
 	mutex_unlock(&pcm->open_mutex);
 	mutex_unlock(&register_mutex);
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 6b5a811e01a5..0aca39762ed0 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -322,7 +322,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 			char name[16];
 			snd_pcm_debug_name(substream, name, sizeof(name));
 			pcm_err(substream->pcm,
-				"BUG: %s, pos = %ld, buffer size = %ld, period size = %ld\n",
+				"invalid position: %s, pos = %ld, buffer size = %ld, period size = %ld\n",
 				name, pos, runtime->buffer_size,
 				runtime->period_size);
 		}
@@ -1886,8 +1886,8 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream)
 		snd_timer_interrupt(substream->timer, 1);
 #endif
  _end:
-	snd_pcm_stream_unlock_irqrestore(substream, flags);
 	kill_fasync(&runtime->fasync, SIGIO, POLL_IN);
+	snd_pcm_stream_unlock_irqrestore(substream, flags);
 }
 
 EXPORT_SYMBOL(snd_pcm_period_elapsed);
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 795437b10082..b450a27588c8 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -1633,11 +1633,13 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
+	mutex_unlock(&register_mutex);
 	err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
 				  rmidi->card, rmidi->device,
 				  &snd_rawmidi_f_ops, rmidi, &rmidi->dev);
 	if (err < 0) {
 		rmidi_err(rmidi, "unable to register\n");
+		mutex_lock(&register_mutex);
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
@@ -1645,6 +1647,7 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 	if (rmidi->ops && rmidi->ops->dev_register &&
 	    (err = rmidi->ops->dev_register(rmidi)) < 0) {
 		snd_unregister_device(&rmidi->dev);
+		mutex_lock(&register_mutex);
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
@@ -1677,7 +1680,6 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		}
 	}
 #endif /* CONFIG_SND_OSSEMUL */
-	mutex_unlock(&register_mutex);
 	sprintf(name, "midi%d", rmidi->device);
 	entry = snd_info_create_card_entry(rmidi->card, name, rmidi->card->proc_root);
 	if (entry) {
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 58e79e02f217..e326c1d80416 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1530,19 +1530,14 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client,
 				      void __user *arg)
 {
 	struct snd_seq_queue_info info;
-	int result;
 	struct snd_seq_queue *q;
 
 	if (copy_from_user(&info, arg, sizeof(info)))
 		return -EFAULT;
 
-	result = snd_seq_queue_alloc(client->number, info.locked, info.flags);
-	if (result < 0)
-		return result;
-
-	q = queueptr(result);
-	if (q == NULL)
-		return -EINVAL;
+	q = snd_seq_queue_alloc(client->number, info.locked, info.flags);
+	if (IS_ERR(q))
+		return PTR_ERR(q);
 
 	info.queue = q->queue;
 	info.locked = q->locked;
@@ -1552,7 +1547,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client,
 	if (! info.name[0])
 		snprintf(info.name, sizeof(info.name), "Queue-%d", q->queue);
 	strlcpy(q->name, info.name, sizeof(q->name));
-	queuefree(q);
+	snd_use_lock_free(&q->use_lock);
 
 	if (copy_to_user(arg, &info, sizeof(info)))
 		return -EFAULT;
@@ -1921,6 +1916,7 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client,
 	     info.output_pool != client->pool->size)) {
 		if (snd_seq_write_pool_allocated(client)) {
 			/* remove all existing cells */
+			snd_seq_pool_mark_closing(client->pool);
 			snd_seq_queue_client_leave_cells(client->number);
 			snd_seq_pool_done(client->pool);
 		}
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 1d5acbe0c08b..3490d21ab9e7 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -70,6 +70,9 @@ void snd_seq_fifo_delete(struct snd_seq_fifo **fifo)
 		return;
 	*fifo = NULL;
 
+	if (f->pool)
+		snd_seq_pool_mark_closing(f->pool);
+
 	snd_seq_fifo_clear(f);
 
 	/* wake up clients if any */
@@ -135,6 +138,7 @@ int snd_seq_fifo_event_in(struct snd_seq_fifo *f,
 	f->tail = cell;
 	if (f->head == NULL)
 		f->head = cell;
+	cell->next = NULL;
 	f->cells++;
 	spin_unlock_irqrestore(&f->lock, flags);
 
@@ -214,6 +218,8 @@ void snd_seq_fifo_cell_putback(struct snd_seq_fifo *f,
 		spin_lock_irqsave(&f->lock, flags);
 		cell->next = f->head;
 		f->head = cell;
+		if (!f->tail)
+			f->tail = cell;
 		f->cells++;
 		spin_unlock_irqrestore(&f->lock, flags);
 	}
@@ -259,6 +265,10 @@ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize)
 	/* NOTE: overflow flag is not cleared */
 	spin_unlock_irqrestore(&f->lock, flags);
 
+	/* close the old pool and wait until all users are gone */
+	snd_seq_pool_mark_closing(oldpool);
+	snd_use_lock_sync(&f->use_lock);
+
 	/* release cells in old pool */
 	for (cell = oldhead; cell; cell = next) {
 		next = cell->next;
diff --git a/sound/core/seq/seq_lock.c b/sound/core/seq/seq_lock.c
index 3b693e924db7..12ba83367b1b 100644
--- a/sound/core/seq/seq_lock.c
+++ b/sound/core/seq/seq_lock.c
@@ -28,19 +28,16 @@
 /* wait until all locks are released */
 void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line)
 {
-	int max_count = 5 * HZ;
+	int warn_count = 5 * HZ;
 
 	if (atomic_read(lockp) < 0) {
 		pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line);
 		return;
 	}
 	while (atomic_read(lockp) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line);
-			break;
-		}
+		if (warn_count-- == 0)
+			pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line);
 		schedule_timeout_uninterruptible(1);
-		max_count--;
 	}
 }
 
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index c850345c43b5..5847c4475bf3 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -414,32 +414,33 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 	return 0;
 }
 
+/* refuse the further insertion to the pool */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool)
+{
+	unsigned long flags;
+
+	if (snd_BUG_ON(!pool))
+		return;
+	spin_lock_irqsave(&pool->lock, flags);
+	pool->closing = 1;
+	spin_unlock_irqrestore(&pool->lock, flags);
+}
+
 /* remove events */
 int snd_seq_pool_done(struct snd_seq_pool *pool)
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *ptr;
-	int max_count = 5 * HZ;
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
 
 	/* wait for closing all threads */
-	spin_lock_irqsave(&pool->lock, flags);
-	pool->closing = 1;
-	spin_unlock_irqrestore(&pool->lock, flags);
-
 	if (waitqueue_active(&pool->output_sleep))
 		wake_up(&pool->output_sleep);
 
-	while (atomic_read(&pool->counter) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: snd_seq_pool_done timeout: %d cells remain\n", atomic_read(&pool->counter));
-			break;
-		}
+	while (atomic_read(&pool->counter) > 0)
 		schedule_timeout_uninterruptible(1);
-		max_count--;
-	}
 	
 	/* release all resources */
 	spin_lock_irqsave(&pool->lock, flags);
@@ -491,6 +492,7 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool)
 	*ppool = NULL;
 	if (pool == NULL)
 		return 0;
+	snd_seq_pool_mark_closing(pool);
 	snd_seq_pool_done(pool);
 	kfree(pool);
 	return 0;
diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h
index 4a2ec779b8a7..32f959c17786 100644
--- a/sound/core/seq/seq_memory.h
+++ b/sound/core/seq/seq_memory.h
@@ -84,6 +84,7 @@ static inline int snd_seq_total_cells(struct snd_seq_pool *pool)
 int snd_seq_pool_init(struct snd_seq_pool *pool);
 
 /* done pool - free events */
+void snd_seq_pool_mark_closing(struct snd_seq_pool *pool);
 int snd_seq_pool_done(struct snd_seq_pool *pool);
 
 /* create pool */
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index 0bec02e89d51..79e0c5604ef8 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -181,23 +181,29 @@ void __exit snd_seq_queues_delete(void)
 	}
 }
 
+static void queue_use(struct snd_seq_queue *queue, int client, int use);
+
 /* allocate a new queue -
- * return queue index value or negative value for error
+ * return pointer to new queue or ERR_PTR(-errno) for error
+ * The new queue's use_lock is set to 1. It is the caller's responsibility to
+ * call snd_use_lock_free(&q->use_lock).
  */
-int snd_seq_queue_alloc(int client, int locked, unsigned int info_flags)
+struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int info_flags)
 {
 	struct snd_seq_queue *q;
 
 	q = queue_new(client, locked);
 	if (q == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	q->info_flags = info_flags;
+	queue_use(q, client, 1);
+	snd_use_lock_use(&q->use_lock);
 	if (queue_list_add(q) < 0) {
+		snd_use_lock_free(&q->use_lock);
 		queue_delete(q);
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	}
-	snd_seq_queue_use(q->queue, client, 1); /* use this queue */
-	return q->queue;
+	return q;
 }
 
 /* delete a queue - queue must be owned by the client */
@@ -502,19 +508,9 @@ int snd_seq_queue_timer_set_tempo(int queueid, int client,
 	return result;
 }
 
-
-/* use or unuse this queue -
- * if it is the first client, starts the timer.
- * if it is not longer used by any clients, stop the timer.
- */
-int snd_seq_queue_use(int queueid, int client, int use)
+/* use or unuse this queue */
+static void queue_use(struct snd_seq_queue *queue, int client, int use)
 {
-	struct snd_seq_queue *queue;
-
-	queue = queueptr(queueid);
-	if (queue == NULL)
-		return -EINVAL;
-	mutex_lock(&queue->timer_mutex);
 	if (use) {
 		if (!test_and_set_bit(client, queue->clients_bitmap))
 			queue->clients++;
@@ -529,6 +525,21 @@ int snd_seq_queue_use(int queueid, int client, int use)
 	} else {
 		snd_seq_timer_close(queue);
 	}
+}
+
+/* use or unuse this queue -
+ * if it is the first client, starts the timer.
+ * if it is not longer used by any clients, stop the timer.
+ */
+int snd_seq_queue_use(int queueid, int client, int use)
+{
+	struct snd_seq_queue *queue;
+
+	queue = queueptr(queueid);
+	if (queue == NULL)
+		return -EINVAL;
+	mutex_lock(&queue->timer_mutex);
+	queue_use(queue, client, use);
 	mutex_unlock(&queue->timer_mutex);
 	queuefree(queue);
 	return 0;
diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h
index 30c8111477f6..719093489a2c 100644
--- a/sound/core/seq/seq_queue.h
+++ b/sound/core/seq/seq_queue.h
@@ -71,7 +71,7 @@ void snd_seq_queues_delete(void);
 
 
 /* create new queue (constructor) */
-int snd_seq_queue_alloc(int client, int locked, unsigned int flags);
+struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int flags);
 
 /* delete queue (destructor) */
 int snd_seq_queue_delete(int client, int queueid);
diff --git a/sound/core/timer.c b/sound/core/timer.c
index f24c9fccf008..48eaccba82a3 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -296,8 +296,21 @@ int snd_timer_open(struct snd_timer_instance **ti,
 		get_device(&timer->card->card_dev);
 	timeri->slave_class = tid->dev_sclass;
 	timeri->slave_id = slave_id;
-	if (list_empty(&timer->open_list_head) && timer->hw.open)
-		timer->hw.open(timer);
+
+	if (list_empty(&timer->open_list_head) && timer->hw.open) {
+		int err = timer->hw.open(timer);
+		if (err) {
+			kfree(timeri->owner);
+			kfree(timeri);
+
+			if (timer->card)
+				put_device(&timer->card->card_dev);
+			module_put(timer->module);
+			mutex_unlock(&register_mutex);
+			return err;
+		}
+	}
+
 	list_add_tail(&timeri->open_list, &timer->open_list_head);
 	snd_timer_check_master(timeri);
 	mutex_unlock(&register_mutex);
@@ -837,6 +850,7 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 	timer->tmr_subdevice = tid->subdevice;
 	if (id)
 		strlcpy(timer->id, id, sizeof(timer->id));
+	timer->sticks = 1;
 	INIT_LIST_HEAD(&timer->device_list);
 	INIT_LIST_HEAD(&timer->open_list_head);
 	INIT_LIST_HEAD(&timer->active_list_head);
@@ -1051,8 +1065,8 @@ static int snd_timer_s_start(struct snd_timer * timer)
 		njiff += timer->sticks - priv->correction;
 		priv->correction = 0;
 	}
-	priv->last_expires = priv->tlist.expires = njiff;
-	add_timer(&priv->tlist);
+	priv->last_expires = njiff;
+	mod_timer(&priv->tlist, njiff);
 	return 0;
 }
 
@@ -1247,6 +1261,7 @@ static void snd_timer_user_ccallback(struct snd_timer_instance *timeri,
 		tu->tstamp = *tstamp;
 	if ((tu->filter & (1 << event)) == 0 || !tu->tread)
 		return;
+	memset(&r1, 0, sizeof(r1));
 	r1.event = event;
 	r1.tstamp = *tstamp;
 	r1.val = resolution;
@@ -1281,6 +1296,7 @@ static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri,
 	}
 	if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) &&
 	    tu->last_resolution != resolution) {
+		memset(&r1, 0, sizeof(r1));
 		r1.event = SNDRV_TIMER_EVENT_RESOLUTION;
 		r1.tstamp = tstamp;
 		r1.val = resolution;
@@ -1605,6 +1621,7 @@ static int snd_timer_user_tselect(struct file *file,
 	if (err < 0)
 		goto __err;
 
+	tu->qhead = tu->qtail = tu->qused = 0;
 	kfree(tu->queue);
 	tu->queue = NULL;
 	kfree(tu->tqueue);
@@ -1684,9 +1701,21 @@ static int snd_timer_user_params(struct file *file,
 		return -EBADFD;
 	if (copy_from_user(&params, _params, sizeof(params)))
 		return -EFAULT;
-	if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE) && params.ticks < 1) {
-		err = -EINVAL;
-		goto _end;
+	if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) {
+		u64 resolution;
+
+		if (params.ticks < 1) {
+			err = -EINVAL;
+			goto _end;
+		}
+
+		/* Don't allow resolution less than 1ms */
+		resolution = snd_timer_resolution(tu->timeri);
+		resolution *= params.ticks;
+		if (resolution < 1000000) {
+			err = -EINVAL;
+			goto _end;
+		}
 	}
 	if (params.queue_size > 0 &&
 	    (params.queue_size < 32 || params.queue_size > 1024)) {
@@ -1746,6 +1775,7 @@ static int snd_timer_user_params(struct file *file,
 	if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) {
 		if (tu->tread) {
 			struct snd_timer_tread tread;
+			memset(&tread, 0, sizeof(tread));
 			tread.event = SNDRV_TIMER_EVENT_EARLY;
 			tread.tstamp.tv_sec = 0;
 			tread.tstamp.tv_nsec = 0;
@@ -1929,6 +1959,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 	tu = file->private_data;
 	unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read);
+	mutex_lock(&tu->ioctl_lock);
 	spin_lock_irq(&tu->qlock);
 	while ((long)count - result >= unit) {
 		while (!tu->qused) {
@@ -1944,7 +1975,9 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 			add_wait_queue(&tu->qchange_sleep, &wait);
 
 			spin_unlock_irq(&tu->qlock);
+			mutex_unlock(&tu->ioctl_lock);
 			schedule();
+			mutex_lock(&tu->ioctl_lock);
 			spin_lock_irq(&tu->qlock);
 
 			remove_wait_queue(&tu->qchange_sleep, &wait);
@@ -1961,6 +1994,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 		qhead = tu->qhead++;
 		tu->qhead %= tu->queue_size;
+		tu->qused--;
 		spin_unlock_irq(&tu->qlock);
 
 		if (tu->tread) {
@@ -1974,7 +2008,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 		}
 
 		spin_lock_irq(&tu->qlock);
-		tu->qused--;
 		if (err < 0)
 			goto _error;
 		result += unit;
@@ -1982,6 +2015,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 	}
  _error:
 	spin_unlock_irq(&tu->qlock);
+	mutex_unlock(&tu->ioctl_lock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index a9f7a75702d2..67628616506e 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -420,6 +420,7 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
 
 static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
 {
+	hrtimer_cancel(&dpcm->timer);
 	tasklet_kill(&dpcm->tasklet);
 }
 
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index c7cb7deafe48..2c316a9bc7f6 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -106,7 +106,6 @@ struct snd_efw {
 	u8 *resp_buf;
 	u8 *pull_ptr;
 	u8 *push_ptr;
-	unsigned int resp_queues;
 };
 
 int snd_efw_transaction_cmd(struct fw_unit *unit,
diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c
index 33df8655fe81..2e1d9a23920c 100644
--- a/sound/firewire/fireworks/fireworks_hwdep.c
+++ b/sound/firewire/fireworks/fireworks_hwdep.c
@@ -25,6 +25,7 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 {
 	unsigned int length, till_end, type;
 	struct snd_efw_transaction *t;
+	u8 *pull_ptr;
 	long count = 0;
 
 	if (remained < sizeof(type) + sizeof(struct snd_efw_transaction))
@@ -38,8 +39,17 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 	buf += sizeof(type);
 
 	/* write into buffer as many responses as possible */
-	while (efw->resp_queues > 0) {
-		t = (struct snd_efw_transaction *)(efw->pull_ptr);
+	spin_lock_irq(&efw->lock);
+
+	/*
+	 * When another task reaches here during this task's access to user
+	 * space, it picks up current position in buffer and can read the same
+	 * series of responses.
+	 */
+	pull_ptr = efw->pull_ptr;
+
+	while (efw->push_ptr != pull_ptr) {
+		t = (struct snd_efw_transaction *)(pull_ptr);
 		length = be32_to_cpu(t->length) * sizeof(__be32);
 
 		/* confirm enough space for this response */
@@ -49,26 +59,39 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 		/* copy from ring buffer to user buffer */
 		while (length > 0) {
 			till_end = snd_efw_resp_buf_size -
-				(unsigned int)(efw->pull_ptr - efw->resp_buf);
+				(unsigned int)(pull_ptr - efw->resp_buf);
 			till_end = min_t(unsigned int, length, till_end);
 
-			if (copy_to_user(buf, efw->pull_ptr, till_end))
+			spin_unlock_irq(&efw->lock);
+
+			if (copy_to_user(buf, pull_ptr, till_end))
 				return -EFAULT;
 
-			efw->pull_ptr += till_end;
-			if (efw->pull_ptr >= efw->resp_buf +
-					     snd_efw_resp_buf_size)
-				efw->pull_ptr -= snd_efw_resp_buf_size;
+			spin_lock_irq(&efw->lock);
+
+			pull_ptr += till_end;
+			if (pull_ptr >= efw->resp_buf + snd_efw_resp_buf_size)
+				pull_ptr -= snd_efw_resp_buf_size;
 
 			length -= till_end;
 			buf += till_end;
 			count += till_end;
 			remained -= till_end;
 		}
-
-		efw->resp_queues--;
 	}
 
+	/*
+	 * All of tasks can read from the buffer nearly simultaneously, but the
+	 * last position for each task is different depending on the length of
+	 * given buffer. Here, for simplicity, a position of buffer is set by
+	 * the latest task. It's better for a listening application to allow one
+	 * thread to read from the buffer. Unless, each task can read different
+	 * sequence of responses depending on variation of buffer length.
+	 */
+	efw->pull_ptr = pull_ptr;
+
+	spin_unlock_irq(&efw->lock);
+
 	return count;
 }
 
@@ -76,14 +99,17 @@ static long
 hwdep_read_locked(struct snd_efw *efw, char __user *buf, long count,
 		  loff_t *offset)
 {
-	union snd_firewire_event event;
+	union snd_firewire_event event = {
+		.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+	};
 
-	memset(&event, 0, sizeof(event));
+	spin_lock_irq(&efw->lock);
 
-	event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
 	event.lock_status.status = (efw->dev_lock_count > 0);
 	efw->dev_lock_changed = false;
 
+	spin_unlock_irq(&efw->lock);
+
 	count = min_t(long, count, sizeof(event.lock_status));
 
 	if (copy_to_user(buf, &event, count))
@@ -98,10 +124,15 @@ hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 {
 	struct snd_efw *efw = hwdep->private_data;
 	DEFINE_WAIT(wait);
+	bool dev_lock_changed;
+	bool queued;
 
 	spin_lock_irq(&efw->lock);
 
-	while ((!efw->dev_lock_changed) && (efw->resp_queues == 0)) {
+	dev_lock_changed = efw->dev_lock_changed;
+	queued = efw->push_ptr != efw->pull_ptr;
+
+	while (!dev_lock_changed && !queued) {
 		prepare_to_wait(&efw->hwdep_wait, &wait, TASK_INTERRUPTIBLE);
 		spin_unlock_irq(&efw->lock);
 		schedule();
@@ -109,15 +140,17 @@ hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		if (signal_pending(current))
 			return -ERESTARTSYS;
 		spin_lock_irq(&efw->lock);
+		dev_lock_changed = efw->dev_lock_changed;
+		queued = efw->push_ptr != efw->pull_ptr;
 	}
 
-	if (efw->dev_lock_changed)
+	spin_unlock_irq(&efw->lock);
+
+	if (dev_lock_changed)
 		count = hwdep_read_locked(efw, buf, count, offset);
-	else if (efw->resp_queues > 0)
+	else if (queued)
 		count = hwdep_read_resp_buf(efw, buf, count, offset);
 
-	spin_unlock_irq(&efw->lock);
-
 	return count;
 }
 
@@ -160,7 +193,7 @@ hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_table *wait)
 	poll_wait(file, &efw->hwdep_wait, wait);
 
 	spin_lock_irq(&efw->lock);
-	if (efw->dev_lock_changed || (efw->resp_queues > 0))
+	if (efw->dev_lock_changed || efw->pull_ptr != efw->push_ptr)
 		events = POLLIN | POLLRDNORM;
 	else
 		events = 0;
diff --git a/sound/firewire/fireworks/fireworks_proc.c b/sound/firewire/fireworks/fireworks_proc.c
index 0639dcb13f7d..beb0a0ffee57 100644
--- a/sound/firewire/fireworks/fireworks_proc.c
+++ b/sound/firewire/fireworks/fireworks_proc.c
@@ -188,8 +188,8 @@ proc_read_queues_state(struct snd_info_entry *entry,
 	else
 		consumed = (unsigned int)(efw->push_ptr - efw->pull_ptr);
 
-	snd_iprintf(buffer, "%d %d/%d\n",
-		    efw->resp_queues, consumed, snd_efw_resp_buf_size);
+	snd_iprintf(buffer, "%d/%d\n",
+		    consumed, snd_efw_resp_buf_size);
 }
 
 static void
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index f550808d1784..36a08ba51ec7 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -121,11 +121,11 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	size_t capacity, till_end;
 	struct snd_efw_transaction *t;
 
-	spin_lock_irq(&efw->lock);
-
 	t = (struct snd_efw_transaction *)data;
 	length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
 
+	spin_lock_irq(&efw->lock);
+
 	if (efw->push_ptr < efw->pull_ptr)
 		capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
 	else
@@ -155,7 +155,6 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	}
 
 	/* for hwdep */
-	efw->resp_queues++;
 	wake_up(&efw->hwdep_wait);
 
 	*rcode = RCODE_COMPLETE;
diff --git a/sound/firewire/lib.h b/sound/firewire/lib.h
index f3f6f84c48d6..bb5f8cdea3e2 100644
--- a/sound/firewire/lib.h
+++ b/sound/firewire/lib.h
@@ -42,7 +42,7 @@ struct snd_fw_async_midi_port {
 
 	struct snd_rawmidi_substream *substream;
 	snd_fw_async_midi_port_fill fill;
-	unsigned int consume_bytes;
+	int consume_bytes;
 };
 
 int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port,
diff --git a/sound/firewire/tascam/tascam-hwdep.c b/sound/firewire/tascam/tascam-hwdep.c
index 131267c3a042..106406cbfaa3 100644
--- a/sound/firewire/tascam/tascam-hwdep.c
+++ b/sound/firewire/tascam/tascam-hwdep.c
@@ -16,31 +16,14 @@
 
 #include "tascam.h"
 
-static long hwdep_read_locked(struct snd_tscm *tscm, char __user *buf,
-			      long count)
-{
-	union snd_firewire_event event;
-
-	memset(&event, 0, sizeof(event));
-
-	event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
-	event.lock_status.status = (tscm->dev_lock_count > 0);
-	tscm->dev_lock_changed = false;
-
-	count = min_t(long, count, sizeof(event.lock_status));
-
-	if (copy_to_user(buf, &event, count))
-		return -EFAULT;
-
-	return count;
-}
-
 static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		       loff_t *offset)
 {
 	struct snd_tscm *tscm = hwdep->private_data;
 	DEFINE_WAIT(wait);
-	union snd_firewire_event event;
+	union snd_firewire_event event = {
+		.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+	};
 
 	spin_lock_irq(&tscm->lock);
 
@@ -54,10 +37,16 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		spin_lock_irq(&tscm->lock);
 	}
 
-	memset(&event, 0, sizeof(event));
-	count = hwdep_read_locked(tscm, buf, count);
+	event.lock_status.status = (tscm->dev_lock_count > 0);
+	tscm->dev_lock_changed = false;
+
 	spin_unlock_irq(&tscm->lock);
 
+	count = min_t(long, count, sizeof(event.lock_status));
+
+	if (copy_to_user(buf, &event, count))
+		return -EFAULT;
+
 	return count;
 }
 
diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c
index 0e6dd5c61f53..e4c306398b35 100644
--- a/sound/firewire/tascam/tascam-stream.c
+++ b/sound/firewire/tascam/tascam-stream.c
@@ -343,7 +343,7 @@ int snd_tscm_stream_init_duplex(struct snd_tscm *tscm)
 	if (err < 0)
 		amdtp_stream_destroy(&tscm->rx_stream);
 
-	return 0;
+	return err;
 }
 
 /* At bus reset, streaming is stopped and some registers are clear. */
diff --git a/sound/hda/array.c b/sound/hda/array.c
index 516795baa7db..5dfa610e4471 100644
--- a/sound/hda/array.c
+++ b/sound/hda/array.c
@@ -21,13 +21,15 @@ void *snd_array_new(struct snd_array *array)
 		return NULL;
 	if (array->used >= array->alloced) {
 		int num = array->alloced + array->alloc_align;
+		int oldsize = array->alloced * array->elem_size;
 		int size = (num + 1) * array->elem_size;
 		void *nlist;
 		if (snd_BUG_ON(num >= 4096))
 			return NULL;
-		nlist = krealloc(array->list, size, GFP_KERNEL | __GFP_ZERO);
+		nlist = krealloc(array->list, size, GFP_KERNEL);
 		if (!nlist)
 			return NULL;
+		memset(nlist + oldsize, 0, size - oldsize);
 		array->list = nlist;
 		array->alloced = num;
 	}
diff --git a/sound/isa/msnd/msnd_midi.c b/sound/isa/msnd/msnd_midi.c
index ffc67fd80c23..58e59cd3c95c 100644
--- a/sound/isa/msnd/msnd_midi.c
+++ b/sound/isa/msnd/msnd_midi.c
@@ -120,24 +120,24 @@ void snd_msndmidi_input_read(void *mpuv)
 	unsigned long flags;
 	struct snd_msndmidi *mpu = mpuv;
 	void *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF;
+	u16 head, tail, size;
 
 	spin_lock_irqsave(&mpu->input_lock, flags);
-	while (readw(mpu->dev->MIDQ + JQS_wTail) !=
-	       readw(mpu->dev->MIDQ + JQS_wHead)) {
-		u16 wTmp, val;
-		val = readw(pwMIDQData + 2 * readw(mpu->dev->MIDQ + JQS_wHead));
-
-			if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER,
-				     &mpu->mode))
-				snd_rawmidi_receive(mpu->substream_input,
-						    (unsigned char *)&val, 1);
-
-		wTmp = readw(mpu->dev->MIDQ + JQS_wHead) + 1;
-		if (wTmp > readw(mpu->dev->MIDQ + JQS_wSize))
-			writew(0,  mpu->dev->MIDQ + JQS_wHead);
-		else
-			writew(wTmp,  mpu->dev->MIDQ + JQS_wHead);
+	head = readw(mpu->dev->MIDQ + JQS_wHead);
+	tail = readw(mpu->dev->MIDQ + JQS_wTail);
+	size = readw(mpu->dev->MIDQ + JQS_wSize);
+	if (head > size || tail > size)
+		goto out;
+	while (head != tail) {
+		unsigned char val = readw(pwMIDQData + 2 * head);
+
+		if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER, &mpu->mode))
+			snd_rawmidi_receive(mpu->substream_input, &val, 1);
+		if (++head > size)
+			head = 0;
+		writew(head, mpu->dev->MIDQ + JQS_wHead);
 	}
+ out:
 	spin_unlock_irqrestore(&mpu->input_lock, flags);
 }
 EXPORT_SYMBOL(snd_msndmidi_input_read);
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 4c072666115d..a31ea6c22d19 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -170,23 +170,24 @@ static irqreturn_t snd_msnd_interrupt(int irq, void *dev_id)
 {
 	struct snd_msnd *chip = dev_id;
 	void *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF;
+	u16 head, tail, size;
 
 	/* Send ack to DSP */
 	/* inb(chip->io + HP_RXL); */
 
 	/* Evaluate queued DSP messages */
-	while (readw(chip->DSPQ + JQS_wTail) != readw(chip->DSPQ + JQS_wHead)) {
-		u16 wTmp;
-
-		snd_msnd_eval_dsp_msg(chip,
-			readw(pwDSPQData + 2 * readw(chip->DSPQ + JQS_wHead)));
-
-		wTmp = readw(chip->DSPQ + JQS_wHead) + 1;
-		if (wTmp > readw(chip->DSPQ + JQS_wSize))
-			writew(0, chip->DSPQ + JQS_wHead);
-		else
-			writew(wTmp, chip->DSPQ + JQS_wHead);
+	head = readw(chip->DSPQ + JQS_wHead);
+	tail = readw(chip->DSPQ + JQS_wTail);
+	size = readw(chip->DSPQ + JQS_wSize);
+	if (head > size || tail > size)
+		goto out;
+	while (head != tail) {
+		snd_msnd_eval_dsp_msg(chip, readw(pwDSPQData + 2 * head));
+		if (++head > size)
+			head = 0;
+		writew(head, chip->DSPQ + JQS_wHead);
 	}
+ out:
 	/* Send ack to DSP */
 	inb(chip->io + HP_RXL);
 	return IRQ_HANDLED;
diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 36470af7eda7..92b819e4f729 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -1408,6 +1408,7 @@ snd_ali_playback_pointer(struct snd_pcm_substream *substream)
 	spin_unlock(&codec->reg_lock);
 	dev_dbg(codec->card->dev, "playback pointer returned cso=%xh.\n", cso);
 
+	cso %= runtime->buffer_size;
 	return cso;
 }
 
@@ -1428,6 +1429,7 @@ static snd_pcm_uframes_t snd_ali_pointer(struct snd_pcm_substream *substream)
 	cso = inw(ALI_REG(codec, ALI_CSO_ALPHA_FMS + 2));
 	spin_unlock(&codec->reg_lock);
 
+	cso %= runtime->buffer_size;
 	return cso;
 }
 
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index 4667c3232b7f..d3125c169684 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -1444,9 +1444,8 @@ static int vortex_wtdma_bufshift(vortex_t * vortex, int wtdma)
 	int page, p, pp, delta, i;
 
 	page =
-	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2)) &
-	     WT_SUBBUF_MASK)
-	    >> WT_SUBBUF_SHIFT;
+	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2))
+	     >> WT_SUBBUF_SHIFT) & WT_SUBBUF_MASK;
 	if (dma->nr_periods >= 4)
 		delta = (page - dma->period_real) & 3;
 	else {
@@ -2151,8 +2150,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 							   stream->resources, en,
 							   VORTEX_RESOURCE_SRC)) < 0) {
 					memset(stream->resources, 0,
-					       sizeof(unsigned char) *
-					       VORTEX_RESOURCE_LAST);
+					       sizeof(stream->resources));
 					return -EBUSY;
 				}
 				if (stream->type != VORTEX_PCM_A3D) {
@@ -2162,7 +2160,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 								   VORTEX_RESOURCE_MIXIN)) < 0) {
 						memset(stream->resources,
 						       0,
-						       sizeof(unsigned char) * VORTEX_RESOURCE_LAST);
+						       sizeof(stream->resources));
 						return -EBUSY;
 					}
 				}
@@ -2175,8 +2173,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 						   stream->resources, en,
 						   VORTEX_RESOURCE_A3D)) < 0) {
 				memset(stream->resources, 0,
-				       sizeof(unsigned char) *
-				       VORTEX_RESOURCE_LAST);
+				       sizeof(stream->resources));
 				dev_err(vortex->card->dev,
 					"out of A3D sources. Sorry\n");
 				return -EBUSY;
@@ -2290,8 +2287,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 						   VORTEX_RESOURCE_MIXOUT))
 			    < 0) {
 				memset(stream->resources, 0,
-				       sizeof(unsigned char) *
-				       VORTEX_RESOURCE_LAST);
+				       sizeof(stream->resources));
 				return -EBUSY;
 			}
 			if ((src[i] =
@@ -2299,8 +2295,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 						   stream->resources, en,
 						   VORTEX_RESOURCE_SRC)) < 0) {
 				memset(stream->resources, 0,
-				       sizeof(unsigned char) *
-				       VORTEX_RESOURCE_LAST);
+				       sizeof(stream->resources));
 				return -EBUSY;
 			}
 		}
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index 9667cbfb0ca2..79edd88d5cd0 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -27,12 +27,6 @@
 #include "cthw20k1.h"
 #include "ct20k1reg.h"
 
-#if BITS_PER_LONG == 32
-#define CT_XFI_DMA_MASK		DMA_BIT_MASK(32) /* 32 bit PTE */
-#else
-#define CT_XFI_DMA_MASK		DMA_BIT_MASK(64) /* 64 bit PTE */
-#endif
-
 struct hw20k1 {
 	struct hw hw;
 	spinlock_t reg_20k1_lock;
@@ -1904,19 +1898,18 @@ static int hw_card_start(struct hw *hw)
 {
 	int err;
 	struct pci_dev *pci = hw->pci;
+	const unsigned int dma_bits = BITS_PER_LONG;
 
 	err = pci_enable_device(pci);
 	if (err < 0)
 		return err;
 
 	/* Set DMA transfer mask */
-	if (dma_set_mask(&pci->dev, CT_XFI_DMA_MASK) < 0 ||
-	    dma_set_coherent_mask(&pci->dev, CT_XFI_DMA_MASK) < 0) {
-		dev_err(hw->card->dev,
-			"architecture does not support PCI busmaster DMA with mask 0x%llx\n",
-			CT_XFI_DMA_MASK);
-		err = -ENXIO;
-		goto error1;
+	if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
+		dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits));
+	} else {
+		dma_set_mask(&pci->dev, DMA_BIT_MASK(32));
+		dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(32));
 	}
 
 	if (!hw->io_base) {
diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c
index 9dc2950e1ab7..d86678c2a957 100644
--- a/sound/pci/ctxfi/cthw20k2.c
+++ b/sound/pci/ctxfi/cthw20k2.c
@@ -26,12 +26,6 @@
 #include "cthw20k2.h"
 #include "ct20k2reg.h"
 
-#if BITS_PER_LONG == 32
-#define CT_XFI_DMA_MASK		DMA_BIT_MASK(32) /* 32 bit PTE */
-#else
-#define CT_XFI_DMA_MASK		DMA_BIT_MASK(64) /* 64 bit PTE */
-#endif
-
 struct hw20k2 {
 	struct hw hw;
 	/* for i2c */
@@ -2029,19 +2023,18 @@ static int hw_card_start(struct hw *hw)
 	int err = 0;
 	struct pci_dev *pci = hw->pci;
 	unsigned int gctl;
+	const unsigned int dma_bits = BITS_PER_LONG;
 
 	err = pci_enable_device(pci);
 	if (err < 0)
 		return err;
 
 	/* Set DMA transfer mask */
-	if (dma_set_mask(&pci->dev, CT_XFI_DMA_MASK) < 0 ||
-	    dma_set_coherent_mask(&pci->dev, CT_XFI_DMA_MASK) < 0) {
-		dev_err(hw->card->dev,
-			"architecture does not support PCI busmaster DMA with mask 0x%llx\n",
-			CT_XFI_DMA_MASK);
-		err = -ENXIO;
-		goto error1;
+	if (!dma_set_mask(&pci->dev, DMA_BIT_MASK(dma_bits))) {
+		dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(dma_bits));
+	} else {
+		dma_set_mask(&pci->dev, DMA_BIT_MASK(32));
+		dma_set_coherent_mask(&pci->dev, DMA_BIT_MASK(32));
 	}
 
 	if (!hw->io_base) {
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 1cb85aeb0cea..286f5e3686a3 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -2200,11 +2200,11 @@ static int snd_echo_resume(struct device *dev)
 	u32 pipe_alloc_mask;
 	int err;
 
-	commpage_bak = kmalloc(sizeof(struct echoaudio), GFP_KERNEL);
+	commpage_bak = kmalloc(sizeof(*commpage), GFP_KERNEL);
 	if (commpage_bak == NULL)
 		return -ENOMEM;
 	commpage = chip->comm_page;
-	memcpy(commpage_bak, commpage, sizeof(struct comm_page));
+	memcpy(commpage_bak, commpage, sizeof(*commpage));
 
 	err = init_hw(chip, chip->pci->device, chip->pci->subsystem_device);
 	if (err < 0) {
diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 9c22f95838ef..19d41da79f93 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -49,7 +49,7 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 		removefunc = true;
 		if (dell_led_set_func(DELL_LED_MICMUTE, false) >= 0) {
 			dell_led_value = 0;
-			if (spec->gen.num_adc_nids > 1)
+			if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
 				codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
 			else {
 				dell_old_cap_hook = spec->gen.cap_sync_hook;
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 7f57a145a47e..a03cf68d0bcd 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -884,6 +884,8 @@ void snd_hda_apply_fixup(struct hda_codec *codec, int action)
 }
 EXPORT_SYMBOL_GPL(snd_hda_apply_fixup);
 
+#define IGNORE_SEQ_ASSOC (~(AC_DEFCFG_SEQUENCE | AC_DEFCFG_DEF_ASSOC))
+
 static bool pin_config_match(struct hda_codec *codec,
 			     const struct hda_pintbl *pins)
 {
@@ -901,7 +903,7 @@ static bool pin_config_match(struct hda_codec *codec,
 		for (; t_pins->nid; t_pins++) {
 			if (t_pins->nid == nid) {
 				found = 1;
-				if (t_pins->val == cfg)
+				if ((t_pins->val & IGNORE_SEQ_ASSOC) == (cfg & IGNORE_SEQ_ASSOC))
 					break;
 				else if ((cfg & 0xf0000000) == 0x40000000 && (t_pins->val & 0xf0000000) == 0x40000000)
 					break;
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 373fcad840ea..776dffa88aee 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -294,6 +294,8 @@ struct hda_codec {
 
 #define list_for_each_codec(c, bus) \
 	list_for_each_entry(c, &(bus)->core.codec_list, core.list)
+#define list_for_each_codec_safe(c, n, bus)				\
+	list_for_each_entry_safe(c, n, &(bus)->core.codec_list, core.list)
 
 /* snd_hda_codec_read/write optional flags */
 #define HDA_RW_NO_RESPONSE_FALLBACK	(1 << 0)
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 22dbfa563919..9c6e10fb479f 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -956,7 +956,7 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 	status = azx_readb(chip, RIRBSTS);
 	if (status & RIRB_INT_MASK) {
 		if (status & RIRB_INT_RESPONSE) {
-			if (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY)
+			if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
 				udelay(80);
 			snd_hdac_bus_update_rirb(bus);
 		}
@@ -1055,11 +1055,6 @@ int azx_bus_init(struct azx *chip, const char *model,
 	if (chip->driver_caps & AZX_DCAPS_CORBRP_SELF_CLEAR)
 		bus->core.corbrp_self_clear = true;
 
-	if (chip->driver_caps & AZX_DCAPS_RIRB_DELAY) {
-		dev_dbg(chip->card->dev, "Enable delay in RIRB handling\n");
-		bus->needs_damn_long_delay = 1;
-	}
-
 	if (chip->driver_caps & AZX_DCAPS_4K_BDLE_BOUNDARY)
 		bus->core.align_bdle_4k = true;
 
@@ -1133,8 +1128,12 @@ EXPORT_SYMBOL_GPL(azx_probe_codecs);
 /* configure each codec instance */
 int azx_codec_configure(struct azx *chip)
 {
-	struct hda_codec *codec;
-	list_for_each_codec(codec, &chip->bus) {
+	struct hda_codec *codec, *next;
+
+	/* use _safe version here since snd_hda_codec_configure() deregisters
+	 * the device upon error and deletes itself from the bus list.
+	 */
+	list_for_each_codec_safe(codec, next, &chip->bus) {
 		snd_hda_codec_configure(codec);
 	}
 	return 0;
diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
index 7b635d68cfe1..b17539537b2e 100644
--- a/sound/pci/hda/hda_controller.h
+++ b/sound/pci/hda/hda_controller.h
@@ -32,8 +32,8 @@
 #define AZX_DCAPS_NO_MSI	(1 << 9)	/* No MSI support */
 #define AZX_DCAPS_SNOOP_MASK	(3 << 10)	/* snoop type mask */
 #define AZX_DCAPS_SNOOP_OFF	(1 << 12)	/* snoop default off */
-#define AZX_DCAPS_RIRB_DELAY	(1 << 13)	/* Long delay in read loop */
-#define AZX_DCAPS_RIRB_PRE_DELAY (1 << 14)	/* Put a delay before read */
+/* 13 unused */
+/* 14 unused */
 #define AZX_DCAPS_CTX_WORKAROUND (1 << 15)	/* X-Fi workaround */
 #define AZX_DCAPS_POSFIX_LPIB	(1 << 16)	/* Use LPIB as default */
 #define AZX_DCAPS_POSFIX_VIA	(1 << 17)	/* Use VIACOMBO as default */
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 5c4fa8eba1d0..689df78f640a 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -843,7 +843,7 @@ static hda_nid_t path_power_update(struct hda_codec *codec,
 				   bool allow_powerdown)
 {
 	hda_nid_t nid, changed = 0;
-	int i, state;
+	int i, state, power;
 
 	for (i = 0; i < path->depth; i++) {
 		nid = path->path[i];
@@ -855,7 +855,9 @@ static hda_nid_t path_power_update(struct hda_codec *codec,
 			state = AC_PWRST_D0;
 		else
 			state = AC_PWRST_D3;
-		if (!snd_hda_check_power_state(codec, nid, state)) {
+		power = snd_hda_codec_read(codec, nid, 0,
+					   AC_VERB_GET_POWER_STATE, 0);
+		if (power != (state | (state << 4))) {
 			snd_hda_codec_write(codec, nid, 0,
 					    AC_VERB_SET_POWER_STATE, state);
 			changed = nid;
@@ -3188,6 +3190,7 @@ static int check_dyn_adc_switch(struct hda_codec *codec)
 						spec->input_paths[i][nums]);
 					spec->input_paths[i][nums] =
 						spec->input_paths[i][n];
+					spec->input_paths[i][n] = 0;
 				}
 			}
 			nums++;
@@ -3992,6 +3995,8 @@ static hda_nid_t set_path_power(struct hda_codec *codec, hda_nid_t nid,
 
 	for (n = 0; n < spec->paths.used; n++) {
 		path = snd_array_elem(&spec->paths, n);
+		if (!path->depth)
+			continue;
 		if (path->path[0] == nid ||
 		    path->path[path->depth - 1] == nid) {
 			bool pin_old = path->pin_enabled;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 2ff692dd2c5f..e6de496bffbe 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -334,8 +334,7 @@ enum {
 
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
-	(AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI | /*AZX_DCAPS_ALIGN_BUFSIZE |*/ \
-	 AZX_DCAPS_NO_64BIT | AZX_DCAPS_CORBRP_SELF_CLEAR |\
+	(AZX_DCAPS_NO_MSI | AZX_DCAPS_CORBRP_SELF_CLEAR |\
 	 AZX_DCAPS_SNOOP_TYPE(NVIDIA))
 
 #define AZX_DCAPS_PRESET_CTHDA \
@@ -359,8 +358,12 @@ enum {
 
 #define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
 #define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_KBL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa171)
+#define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71)
+#define IS_KBL_H(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa2f0)
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \
+			IS_KBL(pci) || IS_KBL_LP(pci) || IS_KBL_H(pci)
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -940,20 +943,23 @@ static int azx_resume(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip;
 	struct hda_intel *hda;
+	struct hdac_bus *bus;
 
 	if (!card)
 		return 0;
 
 	chip = card->private_data;
 	hda = container_of(chip, struct hda_intel, chip);
+	bus = azx_bus(chip);
 	if (chip->disabled || hda->init_failed || !chip->running)
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL
-		&& hda->need_i915_power) {
-		snd_hdac_display_power(azx_bus(chip), true);
-		haswell_set_bclk(hda);
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+		snd_hdac_display_power(bus, true);
+		if (hda->need_i915_power)
+			haswell_set_bclk(hda);
 	}
+
 	if (chip->msi)
 		if (pci_enable_msi(pci) < 0)
 			chip->msi = 0;
@@ -963,6 +969,11 @@ static int azx_resume(struct device *dev)
 
 	hda_intel_init_chip(chip, true);
 
+	/* power down again for link-controlled chips */
+	if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+	    !hda->need_i915_power)
+		snd_hdac_display_power(bus, false);
+
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);
@@ -1042,6 +1053,7 @@ static int azx_runtime_resume(struct device *dev)
 
 	chip = card->private_data;
 	hda = container_of(chip, struct hda_intel, chip);
+	bus = azx_bus(chip);
 	if (chip->disabled || hda->init_failed)
 		return 0;
 
@@ -1049,15 +1061,9 @@ static int azx_runtime_resume(struct device *dev)
 		return 0;
 
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
-		bus = azx_bus(chip);
-		if (hda->need_i915_power) {
-			snd_hdac_display_power(bus, true);
+		snd_hdac_display_power(bus, true);
+		if (hda->need_i915_power)
 			haswell_set_bclk(hda);
-		} else {
-			/* toggle codec wakeup bit for STATESTS read */
-			snd_hdac_set_codec_wakeup(bus, true);
-			snd_hdac_set_codec_wakeup(bus, false);
-		}
 	}
 
 	/* Read STATESTS before controller reset */
@@ -1077,6 +1083,11 @@ static int azx_runtime_resume(struct device *dev)
 	azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
 			~STATESTS_INT_MASK);
 
+	/* power down again for link-controlled chips */
+	if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+	    !hda->need_i915_power)
+		snd_hdac_display_power(bus, false);
+
 	trace_azx_runtime_resume(chip);
 	return 0;
 }
@@ -1252,8 +1263,10 @@ static int azx_free(struct azx *chip)
 	if (use_vga_switcheroo(hda)) {
 		if (chip->disabled && hda->probe_continued)
 			snd_hda_unlock_devices(&chip->bus);
-		if (hda->vga_switcheroo_registered)
+		if (hda->vga_switcheroo_registered) {
 			vga_switcheroo_unregister_client(chip->pci);
+			vga_switcheroo_fini_domain_pm_ops(chip->card->dev);
+		}
 	}
 
 	if (bus->chip_init) {
@@ -1623,6 +1636,11 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 		return err;
 	}
 
+	if (chip->driver_type == AZX_DRIVER_NVIDIA) {
+		dev_dbg(chip->card->dev, "Enable delay in RIRB handling\n");
+		chip->bus.needs_damn_long_delay = 1;
+	}
+
 	err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, chip, &ops);
 	if (err < 0) {
 		dev_err(card->dev, "Error creating device [card]!\n");
@@ -1706,6 +1724,10 @@ static int azx_first_init(struct azx *chip)
 		}
 	}
 
+	/* NVidia hardware normally only supports up to 40 bits of DMA */
+	if (chip->pci->vendor == PCI_VENDOR_ID_NVIDIA)
+		dma_bits = 40;
+
 	/* disable 64bit DMA address on some devices */
 	if (chip->driver_caps & AZX_DCAPS_NO_64BIT) {
 		dev_dbg(card->dev, "Disabling 64bit DMA\n");
@@ -2144,7 +2166,20 @@ static void azx_remove(struct pci_dev *pci)
 		/* cancel the pending probing work */
 		chip = card->private_data;
 		hda = container_of(chip, struct hda_intel, chip);
+		/* FIXME: below is an ugly workaround.
+		 * Both device_release_driver() and driver_probe_device()
+		 * take *both* the device's and its parent's lock before
+		 * calling the remove() and probe() callbacks.  The codec
+		 * probe takes the locks of both the codec itself and its
+		 * parent, i.e. the PCI controller dev.  Meanwhile, when
+		 * the PCI controller is unbound, it takes its lock, too
+		 * ==> ouch, a deadlock!
+		 * As a workaround, we unlock temporarily here the controller
+		 * device during cancel_work_sync() call.
+		 */
+		device_unlock(&pci->dev);
 		cancel_work_sync(&hda->probe_work);
+		device_lock(&pci->dev);
 
 		snd_card_free(card);
 	}
@@ -2186,9 +2221,9 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Lewisburg */
 	{ PCI_DEVICE(0x8086, 0xa1f0),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	{ PCI_DEVICE(0x8086, 0xa270),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Lynx Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
@@ -2204,9 +2239,21 @@ static const struct pci_device_id azx_ids[] = {
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake */
+	{ PCI_DEVICE(0x8086, 0xa171),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake-LP */
+	{ PCI_DEVICE(0x8086, 0x9d71),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake-H */
+	{ PCI_DEVICE(0x8086, 0xa2f0),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Broxton-P(Apollolake) */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
+	/* Broxton-T */
+	{ PCI_DEVICE(0x8086, 0x1a98),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
 	/* Haswell */
 	{ PCI_DEVICE(0x8086, 0x0a0c),
 	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
@@ -2270,10 +2317,14 @@ static const struct pci_device_id azx_ids[] = {
 	{ PCI_DEVICE(0x1022, 0x780d),
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* ATI HDMI */
+	{ PCI_DEVICE(0x1002, 0x0002),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x1308),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x157a),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0x15b3),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x793b),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x7919),
@@ -2336,6 +2387,10 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaae8),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaae0),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaaf0),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	/* VIA VT8251/VT8237A */
 	{ PCI_DEVICE(0x1106, 0x3288),
 	  .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
@@ -2372,14 +2427,12 @@ static const struct pci_device_id azx_ids[] = {
 	  .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8,
 	  .class_mask = 0xffffff,
 	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
-	  AZX_DCAPS_NO_64BIT |
-	  AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
+	  AZX_DCAPS_NO_64BIT | AZX_DCAPS_POSFIX_LPIB },
 #else
 	/* this entry seems still valid -- i.e. without emu20kx chip */
 	{ PCI_DEVICE(0x1102, 0x0009),
 	  .driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
-	  AZX_DCAPS_NO_64BIT |
-	  AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
+	  AZX_DCAPS_NO_64BIT | AZX_DCAPS_POSFIX_LPIB },
 #endif
 	/* CM8888 */
 	{ PCI_DEVICE(0x13f6, 0x5011),
diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c
index 64e0d1d81ca5..9739fce9e032 100644
--- a/sound/pci/hda/hda_sysfs.c
+++ b/sound/pci/hda/hda_sysfs.c
@@ -141,14 +141,6 @@ static int reconfig_codec(struct hda_codec *codec)
 	err = snd_hda_codec_configure(codec);
 	if (err < 0)
 		goto error;
-	/* rebuild PCMs */
-	err = snd_hda_codec_build_pcms(codec);
-	if (err < 0)
-		goto error;
-	/* rebuild mixers */
-	err = snd_hda_codec_build_controls(codec);
-	if (err < 0)
-		goto error;
 	err = snd_card_register(codec->card);
  error:
 	snd_hda_power_down(codec);
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 58c0aad37284..17fd81736d3d 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -464,6 +464,8 @@ static int hda_tegra_create(struct snd_card *card,
 	if (err < 0)
 		return err;
 
+	chip->bus.needs_damn_long_delay = 1;
+
 	err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, chip, &ops);
 	if (err < 0) {
 		dev_err(card->dev, "Error creating device\n");
@@ -481,8 +483,7 @@ MODULE_DEVICE_TABLE(of, hda_tegra_match);
 
 static int hda_tegra_probe(struct platform_device *pdev)
 {
-	const unsigned int driver_flags = AZX_DCAPS_RIRB_DELAY |
-					  AZX_DCAPS_CORBRP_SELF_CLEAR;
+	const unsigned int driver_flags = AZX_DCAPS_CORBRP_SELF_CLEAR;
 	struct snd_card *card;
 	struct azx *chip;
 	struct hda_tegra *hda;
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 9ceb2bc36e68..c146d0de53d8 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -780,6 +780,7 @@ static const struct hda_pintbl alienware_pincfgs[] = {
 static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
 	SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
+	SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
 	{}
 };
 
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index c1c855a6c0af..80bbadc83721 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -174,8 +174,12 @@ static void cs_automute(struct hda_codec *codec)
 	snd_hda_gen_update_outputs(codec);
 
 	if (spec->gpio_eapd_hp || spec->gpio_eapd_speaker) {
-		spec->gpio_data = spec->gen.hp_jack_present ?
-			spec->gpio_eapd_hp : spec->gpio_eapd_speaker;
+		if (spec->gen.automute_speaker)
+			spec->gpio_data = spec->gen.hp_jack_present ?
+				spec->gpio_eapd_hp : spec->gpio_eapd_speaker;
+		else
+			spec->gpio_data =
+				spec->gpio_eapd_hp | spec->gpio_eapd_speaker;
 		snd_hda_codec_write(codec, 0x01, 0,
 				    AC_VERB_SET_GPIO_DATA, spec->gpio_data);
 	}
@@ -357,6 +361,7 @@ static int cs_parse_auto_config(struct hda_codec *codec)
 {
 	struct cs_spec *spec = codec->spec;
 	int err;
+	int i;
 
 	err = snd_hda_parse_pin_defcfg(codec, &spec->gen.autocfg, NULL, 0);
 	if (err < 0)
@@ -366,6 +371,19 @@ static int cs_parse_auto_config(struct hda_codec *codec)
 	if (err < 0)
 		return err;
 
+	/* keep the ADCs powered up when it's dynamically switchable */
+	if (spec->gen.dyn_adc_switch) {
+		unsigned int done = 0;
+		for (i = 0; i < spec->gen.input_mux.num_items; i++) {
+			int idx = spec->gen.dyn_adc_idx[i];
+			if (done & (1 << idx))
+				continue;
+			snd_hda_gen_fix_pin_power(codec,
+						  spec->gen.adc_nids[idx]);
+			done |= 1 << idx;
+		}
+	}
+
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index ef198903c0c3..ac5de4365e15 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -204,8 +204,13 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 
-	if (codec->core.vendor_id != 0x14f150f2)
+	switch (codec->core.vendor_id) {
+	case 0x14f150f2: /* CX20722 */
+	case 0x14f150f4: /* CX20724 */
+		break;
+	default:
 		return;
+	}
 
 	/* Turn the CX20722 codec into D3 to avoid spurious noises
 	   from the internal speaker during (and after) reboot */
@@ -256,6 +261,8 @@ enum {
 	CXT_FIXUP_HP_530,
 	CXT_FIXUP_CAP_MIX_AMP_5047,
 	CXT_FIXUP_MUTE_LED_EAPD,
+	CXT_FIXUP_HP_SPECTRE,
+	CXT_FIXUP_HP_GATE_MIC,
 };
 
 /* for hda_fixup_thinkpad_acpi() */
@@ -627,6 +634,17 @@ static void cxt_fixup_cap_mix_amp_5047(struct hda_codec *codec,
 				  (1 << AC_AMPCAP_MUTE_SHIFT));
 }
 
+static void cxt_fixup_hp_gate_mic_jack(struct hda_codec *codec,
+				       const struct hda_fixup *fix,
+				       int action)
+{
+	/* the mic pin (0x19) doesn't give an unsolicited event;
+	 * probe the mic pin together with the headphone pin (0x16)
+	 */
+	if (action == HDA_FIXUP_ACT_PROBE)
+		snd_hda_jack_set_gating_jack(codec, 0x19, 0x16);
+}
+
 /* ThinkPad X200 & co with cxt5051 */
 static const struct hda_pintbl cxt_pincfg_lenovo_x200[] = {
 	{ 0x16, 0x042140ff }, /* HP (seq# overridden) */
@@ -760,6 +778,18 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_mute_led_eapd,
 	},
+	[CXT_FIXUP_HP_SPECTRE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			/* enable NID 0x1d for the speaker on top */
+			{ 0x1d, 0x91170111 },
+			{ }
+		}
+	},
+	[CXT_FIXUP_HP_GATE_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cxt_fixup_hp_gate_mic_jack,
+	},
 };
 
 static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -809,6 +839,8 @@ 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_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
+	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
+	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
@@ -822,6 +854,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x1c06, 0x2011, "Lemote A1004", CXT_PINCFG_LEMOTE_A1004),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 70c945603379..a8045b8a2a18 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -51,8 +51,10 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
 #define is_broadwell(codec)    ((codec)->core.vendor_id == 0x80862808)
 #define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809)
 #define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a)
+#define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b)
 #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \
-				|| is_skylake(codec) || is_broxton(codec))
+				|| is_skylake(codec) || is_broxton(codec) \
+				|| is_kabylake(codec))
 
 #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882)
 #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883)
@@ -2353,6 +2355,10 @@ static void intel_pin_eld_notify(void *audio_ptr, int port)
 	struct hda_codec *codec = audio_ptr;
 	int pin_nid = port + 0x04;
 
+	/* we assume only from port-B to port-D */
+	if (port < 1 || port > 3)
+		return;
+
 	/* skip notification during system suspend (but not in runtime PM);
 	 * the state will be updated at resume
 	 */
@@ -3580,6 +3586,7 @@ HDA_CODEC_ENTRY(0x80862807, "Haswell HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862808, "Broadwell HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI",	patch_generic_hdmi),
+HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI",	patch_generic_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c2430b36e1ce..5cab24f52825 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -335,6 +335,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
+	case 0x10ec0295:
 	case 0x10ec0298:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
@@ -342,6 +343,14 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0293:
 		alc_update_coef_idx(codec, 0xa, 1<<13, 0);
 		break;
+	case 0x10ec0234:
+	case 0x10ec0274:
+	case 0x10ec0294:
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
+		alc_update_coef_idx(codec, 0x10, 1<<15, 0);
+		break;
 	case 0x10ec0662:
 		if ((coef & 0x00f0) == 0x0030)
 			alc_update_coef_idx(codec, 0x4, 1<<10, 0); /* EAPD Ctrl */
@@ -902,6 +911,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
 	{ 0x10ec0298, 0x1028, 0, "ALC3266" },
 	{ 0x10ec0256, 0x1028, 0, "ALC3246" },
 	{ 0x10ec0225, 0x1028, 0, "ALC3253" },
+	{ 0x10ec0295, 0x1028, 0, "ALC3254" },
 	{ 0x10ec0670, 0x1025, 0, "ALC669X" },
 	{ 0x10ec0676, 0x1025, 0, "ALC679X" },
 	{ 0x10ec0282, 0x1043, 0, "ALC3229" },
@@ -2220,8 +2230,10 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	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(0x1043, 0x8691, "ASUS ROG Ranger VIII", ALC882_FIXUP_GPIO3),
 	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, 0x9060, "Sony Vaio VPCL14M1R", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP),
 
@@ -2647,6 +2659,8 @@ enum {
 	ALC269_TYPE_ALC255,
 	ALC269_TYPE_ALC256,
 	ALC269_TYPE_ALC225,
+	ALC269_TYPE_ALC294,
+	ALC269_TYPE_ALC700,
 };
 
 /*
@@ -2677,6 +2691,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	case ALC269_TYPE_ALC255:
 	case ALC269_TYPE_ALC256:
 	case ALC269_TYPE_ALC225:
+	case ALC269_TYPE_ALC294:
+	case ALC269_TYPE_ALC700:
 		ssids = alc269_ssids;
 		break;
 	default:
@@ -3609,13 +3625,20 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 static void alc_headset_mode_unplugged(struct hda_codec *codec)
 {
 	static struct coef_fw coef0255[] = {
-		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
 		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
 		WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
 		WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
 		{}
 	};
+	static struct coef_fw coef0255_1[] = {
+		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
+		{}
+	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x1b, 0x0c4b), /* LDO and MISC control */
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x1b, 0x0c0b),
 		WRITE_COEF(0x45, 0xc429),
@@ -3668,7 +3691,11 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
+		alc_process_coef_fw(codec, coef0255_1);
+		alc_process_coef_fw(codec, coef0255);
+		break;
 	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
@@ -3690,6 +3717,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 		alc_process_coef_fw(codec, coef0668);
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		break;
 	}
@@ -3790,6 +3818,7 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x31<<10);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
 		alc_process_coef_fw(codec, coef0225);
@@ -3801,6 +3830,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 static void alc_headset_mode_default(struct hda_codec *codec)
 {
+	static struct coef_fw coef0225[] = {
+		UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10),
+		{}
+	};
 	static struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xc089),
 		WRITE_COEF(0x45, 0xc489),
@@ -3842,6 +3875,10 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 	};
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0225:
+	case 0x10ec0295:
+		alc_process_coef_fw(codec, coef0225);
+		break;
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
@@ -3877,6 +3914,12 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xd429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -3917,9 +3960,11 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -3943,6 +3988,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 		alc_process_coef_fw(codec, coef0688);
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		break;
 	}
@@ -3958,6 +4004,12 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xe429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -3998,9 +4050,11 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -4024,6 +4078,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
 		alc_process_coef_fw(codec, coef0688);
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		break;
 	}
@@ -4107,6 +4162,7 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 		is_ctia = (val & 0x1c02) == 0x1c02;
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		msleep(800);
 		val = alc_read_coef_idx(codec, 0x46);
@@ -4244,7 +4300,7 @@ static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
 static void alc255_set_default_jack_type(struct hda_codec *codec)
 {
 	/* Set to iphone type */
-	static struct coef_fw fw[] = {
+	static struct coef_fw alc255fw[] = {
 		WRITE_COEF(0x1b, 0x880b),
 		WRITE_COEF(0x45, 0xd089),
 		WRITE_COEF(0x1b, 0x080b),
@@ -4252,7 +4308,22 @@ static void alc255_set_default_jack_type(struct hda_codec *codec)
 		WRITE_COEF(0x1b, 0x0c0b),
 		{}
 	};
-	alc_process_coef_fw(codec, fw);
+	static struct coef_fw alc256fw[] = {
+		WRITE_COEF(0x1b, 0x884b),
+		WRITE_COEF(0x45, 0xd089),
+		WRITE_COEF(0x1b, 0x084b),
+		WRITE_COEF(0x46, 0x0004),
+		WRITE_COEF(0x1b, 0x0c4b),
+		{}
+	};
+	switch (codec->core.vendor_id) {
+	case 0x10ec0255:
+		alc_process_coef_fw(codec, alc255fw);
+		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, alc256fw);
+		break;
+	}
 	msleep(30);
 }
 
@@ -4605,6 +4676,22 @@ static void alc290_fixup_mono_speakers(struct hda_codec *codec,
 	}
 }
 
+static void alc298_fixup_speaker_volume(struct hda_codec *codec,
+					const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		/* The speaker is routed to the Node 0x06 by a mistake, as a result
+		   we can't adjust the speaker's volume since this node does not has
+		   Amp-out capability. we change the speaker's route to:
+		   Node 0x02 (Audio Output) -> Node 0x0c (Audio Mixer) -> Node 0x17 (
+		   Pin Complex), since Node 0x02 has Amp-out caps, we can adjust
+		   speaker's volume now. */
+
+		hda_nid_t conn1[1] = { 0x0c };
+		snd_hda_override_conn_list(codec, 0x17, 1, conn1);
+	}
+}
+
 /* Hook to update amp GPIO4 for automute */
 static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec,
 					  struct hda_jack_callback *jack)
@@ -4745,11 +4832,18 @@ enum {
 	ALC292_FIXUP_DISABLE_AAMIX,
 	ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK,
 	ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	ALC275_FIXUP_DELL_XPS,
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
 	ALC255_FIXUP_DELL_SPK_NOISE,
+	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC280_FIXUP_HP_HEADSET_MIC,
+	ALC221_FIXUP_HP_FRONT_MIC,
+	ALC292_FIXUP_TPT460,
+	ALC298_FIXUP_SPK_VOLUME,
+	ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5337,6 +5431,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
+	[ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
 	[ALC275_FIXUP_DELL_XPS] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -5375,6 +5478,51 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Disable pass-through path for FRONT 14h */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x36 },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 },
+			{}
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
+	[ALC280_FIXUP_HP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC,
+	},
+	[ALC221_FIXUP_HP_FRONT_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x02a19020 }, /* Front Mic */
+			{ }
+		},
+	},
+	[ALC292_FIXUP_TPT460] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_tpt440_dock,
+		.chained = true,
+		.chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE,
+	},
+	[ALC298_FIXUP_SPK_VOLUME] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_speaker_volume,
+		.chained = true,
+		.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
+	},
+	[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1b, 0x90170151 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5408,6 +5556,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC288_FIXUP_DELL_XPS_13),
+	SND_PCI_QUIRK(0x1028, 0x0669, "Dell Optiplex 9020m", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x069a, "Dell Vostro 5480", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -5417,8 +5566,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
-	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
+	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5479,6 +5632,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5527,8 +5682,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
-	SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+	SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
+	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
+	SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
@@ -5539,7 +5697,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
+	SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x5051, "Thinkpad L460", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
@@ -5621,10 +5783,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
 	{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
+	{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
-	{0x12, 0xb7a60130}, \
 	{0x21, 0x04211020}
 
 #define ALC256_STANDARD_PINS \
@@ -5642,21 +5804,43 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{0x14, 0x90170110}, \
 	{0x15, 0x0221401f}
 
+#define ALC295_STANDARD_PINS \
+	{0x12, 0xb7a60130}, \
+	{0x14, 0x90170110}, \
+	{0x21, 0x04211020}
+
 #define ALC298_STANDARD_PINS \
 	{0x12, 0x90a60130}, \
 	{0x21, 0x03211020}
 
 static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC225_STANDARD_PINS,
+		{0x12, 0xb7a60130},
+		{0x14, 0x901701a0}),
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC225_STANDARD_PINS,
+		{0x12, 0xb7a60130},
+		{0x14, 0x901701b0}),
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
+		{0x12, 0xb7a60150},
 		{0x14, 0x901701a0}),
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
+		{0x12, 0xb7a60150},
 		{0x14, 0x901701b0}),
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC225_STANDARD_PINS,
+		{0x12, 0xb7a60130},
+		{0x1b, 0x90170110}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170130},
+		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
@@ -5665,10 +5849,26 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x14, 0x90170120},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x1b, 0x02011020},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x14, 0x90170130},
 		{0x1b, 0x01014020},
 		{0x21, 0x0221103f}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170130},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221103f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170130},
+		{0x1b, 0x02011020},
+		{0x21, 0x0221103f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x14, 0x90170150},
 		{0x1b, 0x02011020},
 		{0x21, 0x0221105f}),
@@ -5709,11 +5909,30 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60180},
 		{0x14, 0x90170130},
 		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5565", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x1b, 0x01011020},
+		{0x21, 0x02211010}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60170},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell Inspiron 5468", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0xb7a60130},
+		{0x14, 0x90170110},
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
 		{0x12, 0x90a60130},
@@ -5824,6 +6043,16 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x13, 0x90a60140}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC295_STANDARD_PINS,
+		{0x17, 0x21014020},
+		{0x18, 0x21a19030}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC295_STANDARD_PINS,
+		{0x17, 0x21014040},
+		{0x18, 0x21a19050}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC295_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170110}),
@@ -5833,6 +6062,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170150}),
+	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_SPK_VOLUME,
+		{0x12, 0xb7a60140},
+		{0x13, 0xb7a60150},
+		{0x17, 0x90170110},
+		{0x1a, 0x03011020},
+		{0x21, 0x03211030}),
 	{}
 };
 
@@ -5979,8 +6214,22 @@ static int patch_alc269(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
 		break;
 	case 0x10ec0225:
+	case 0x10ec0295:
 		spec->codec_variant = ALC269_TYPE_ALC225;
 		break;
+	case 0x10ec0234:
+	case 0x10ec0274:
+	case 0x10ec0294:
+		spec->codec_variant = ALC269_TYPE_ALC294;
+		break;
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
+		spec->codec_variant = ALC269_TYPE_ALC700;
+		spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
+		alc_update_coef_idx(codec, 0x4a, 0, 1 << 15); /* Combo jack auto trigger control */
+		break;
+
 	}
 
 	if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) {
@@ -6378,6 +6627,8 @@ enum {
 	ALC668_FIXUP_AUTO_MUTE,
 	ALC668_FIXUP_DELL_DISABLE_AAMIX,
 	ALC668_FIXUP_DELL_XPS13,
+	ALC662_FIXUP_ASUS_Nx50,
+	ALC668_FIXUP_ASUS_Nx51,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -6618,6 +6869,21 @@ static const struct hda_fixup alc662_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_bass_chmap,
 	},
+	[ALC662_FIXUP_ASUS_Nx50] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_auto_mute_via_amp,
+		.chained = true,
+		.chain_id = ALC662_FIXUP_BASS_1A
+	},
+	[ALC668_FIXUP_ASUS_Nx51] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{0x1a, 0x90170151}, /* bass speaker */
+			{}
+		},
+		.chained = true,
+		.chain_id = ALC662_FIXUP_BASS_CHMAP,
+	},
 };
 
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -6640,10 +6906,15 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
-	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A),
+	SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE),
+	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50),
 	SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A),
+	SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_ASUS_Nx50),
 	SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16),
+	SND_PCI_QUIRK(0x1043, 0x177d, "ASUS N551", ALC668_FIXUP_ASUS_Nx51),
+	SND_PCI_QUIRK(0x1043, 0x17bd, "ASUS N751", ALC668_FIXUP_ASUS_Nx51),
+	SND_PCI_QUIRK(0x1043, 0x1963, "ASUS X71SL", ALC662_FIXUP_ASUS_MODE8),
 	SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16),
 	SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_BASS_MODE4_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
@@ -6874,6 +7145,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0225, "ALC225", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0231, "ALC231", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269),
@@ -6884,6 +7156,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0269, "ALC269", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0270, "ALC270", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0272, "ALC272", patch_alc662),
+	HDA_CODEC_ENTRY(0x10ec0274, "ALC274", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0275, "ALC275", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0276, "ALC276", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0280, "ALC280", patch_alc269),
@@ -6896,6 +7169,8 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0290, "ALC290", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0292, "ALC292", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0293, "ALC293", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0294, "ALC294", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0295, "ALC295", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0298, "ALC298", patch_alc269),
 	HDA_CODEC_REV_ENTRY(0x10ec0861, 0x100340, "ALC660", patch_alc861),
 	HDA_CODEC_ENTRY(0x10ec0660, "ALC660-VD", patch_alc861vd),
@@ -6911,6 +7186,9 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0670, "ALC670", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0671, "ALC671", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0680, "ALC680", patch_alc680),
+	HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
 	HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 37b70f8e878f..0abab7926dca 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -1537,6 +1537,8 @@ static const struct snd_pci_quirk stac9200_fixup_tbl[] = {
 		      "Dell Inspiron 1501", STAC_9200_DELL_M26),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x01f6,
 		      "unknown Dell", STAC_9200_DELL_M26),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0201,
+		      "Dell Latitude D430", STAC_9200_DELL_M22),
 	/* Panasonic */
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-74", STAC_9200_PANASONIC),
 	/* Gateway machines needs EAPD to be set on resume */
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 0a4ad5feb82e..12826ac0381f 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -75,7 +75,7 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
 			removefunc = false;
 		}
 		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
-			if (spec->num_adc_nids > 1)
+			if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch)
 				codec_dbg(codec,
 					  "Skipping micmute LED control due to several ADCs");
 			else {
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 42bcbac801a3..ccdab29a8b66 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2879,6 +2879,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip)
 
 static struct snd_pci_quirk intel8x0_clock_list[] = {
 	SND_PCI_QUIRK(0x0e11, 0x008a, "AD1885", 41000),
+	SND_PCI_QUIRK(0x1014, 0x0581, "AD1981B", 48000),
 	SND_PCI_QUIRK(0x1028, 0x00be, "AD1885", 44100),
 	SND_PCI_QUIRK(0x1028, 0x0177, "AD1980", 48000),
 	SND_PCI_QUIRK(0x1028, 0x01ad, "AD1981B", 48000),
diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c
index c5194f5b150a..d7e71f309299 100644
--- a/sound/pci/pcxhr/pcxhr_core.c
+++ b/sound/pci/pcxhr/pcxhr_core.c
@@ -1341,5 +1341,6 @@ irqreturn_t pcxhr_threaded_irq(int irq, void *dev_id)
 	}
 
 	pcxhr_msg_thread(mgr);
+	mutex_unlock(&mgr->lock);
 	return IRQ_HANDLED;
 }
diff --git a/sound/ppc/awacs.c b/sound/ppc/awacs.c
index 09da7b52bc2e..1468e4b7bf93 100644
--- a/sound/ppc/awacs.c
+++ b/sound/ppc/awacs.c
@@ -991,6 +991,7 @@ snd_pmac_awacs_init(struct snd_pmac *chip)
 		if (err < 0)
 			return err;
 	}
+	master_vol = NULL;
 	if (pm7500)
 		err = build_mixers(chip,
 				   ARRAY_SIZE(snd_pmac_awacs_mixers_pmac7500),
diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c
index 8276675730ef..78a985629607 100644
--- a/sound/soc/atmel/atmel-classd.c
+++ b/sound/soc/atmel/atmel-classd.c
@@ -343,7 +343,7 @@ static int atmel_classd_codec_dai_digital_mute(struct snd_soc_dai *codec_dai,
 }
 
 #define CLASSD_ACLK_RATE_11M2896_MPY_8 (112896 * 100 * 8)
-#define CLASSD_ACLK_RATE_12M288_MPY_8  (12228 * 1000 * 8)
+#define CLASSD_ACLK_RATE_12M288_MPY_8  (12288 * 1000 * 8)
 
 static struct {
 	int rate;
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index ba8def5665c4..6726143c7fc5 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -298,8 +298,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream,
 	clk_enable(ssc_p->ssc->clk);
 	ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk);
 
-	/* Reset the SSC to keep it at a clean status */
-	ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
+	/* Reset the SSC unless initialized to keep it in a clean state */
+	if (!ssc_p->initialized)
+		ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		dir = 0;
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index cda27c22812a..eb8fe212e163 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -560,6 +560,7 @@ static const struct regmap_config ak4642_regmap = {
 	.max_register		= FIL1_3,
 	.reg_defaults		= ak4642_reg,
 	.num_reg_defaults	= NUM_AK4642_REG_DEFAULTS,
+	.cache_type		= REGCACHE_RBTREE,
 };
 
 static const struct regmap_config ak4643_regmap = {
@@ -568,6 +569,7 @@ static const struct regmap_config ak4643_regmap = {
 	.max_register		= SPK_MS,
 	.reg_defaults		= ak4643_reg,
 	.num_reg_defaults	= ARRAY_SIZE(ak4643_reg),
+	.cache_type		= REGCACHE_RBTREE,
 };
 
 static const struct regmap_config ak4648_regmap = {
@@ -576,6 +578,7 @@ static const struct regmap_config ak4648_regmap = {
 	.max_register		= EQ_FBEQE,
 	.reg_defaults		= ak4648_reg,
 	.num_reg_defaults	= ARRAY_SIZE(ak4648_reg),
+	.cache_type		= REGCACHE_RBTREE,
 };
 
 static const struct ak4642_drvdata ak4642_drvdata = {
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index e07807d96b68..3670086b9227 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -148,11 +148,11 @@ SND_SOC_DAPM_OUTPUT("AOUTR"),
 };
 
 static const struct snd_soc_dapm_route cs4270_dapm_routes[] = {
-	{ "Capture", NULL, "AINA" },
-	{ "Capture", NULL, "AINB" },
+	{ "Capture", NULL, "AINL" },
+	{ "Capture", NULL, "AINR" },
 
-	{ "AOUTA", NULL, "Playback" },
-	{ "AOUTB", NULL, "Playback" },
+	{ "AOUTL", NULL, "Playback" },
+	{ "AOUTR", NULL, "Playback" },
 };
 
 /**
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index c1b87c5800b1..b3fddba4c084 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -936,7 +936,8 @@ static void nau8825_fll_apply(struct nau8825 *nau8825,
 			NAU8825_FLL_INTEGER_MASK, fll_param->fll_int);
 	/* FLL pre-scaler */
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL4,
-			NAU8825_FLL_REF_DIV_MASK, fll_param->clk_ref_div);
+			NAU8825_FLL_REF_DIV_MASK,
+			fll_param->clk_ref_div << NAU8825_FLL_REF_DIV_SFT);
 	/* select divided VCO input */
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5,
 			NAU8825_FLL_FILTER_SW_MASK, 0x0000);
diff --git a/sound/soc/codecs/nau8825.h b/sound/soc/codecs/nau8825.h
index dff8edb83bfd..a0b220726a63 100644
--- a/sound/soc/codecs/nau8825.h
+++ b/sound/soc/codecs/nau8825.h
@@ -114,7 +114,8 @@
 #define NAU8825_FLL_INTEGER_MASK		(0x3ff << 0)
 
 /* FLL4 (0x07) */
-#define NAU8825_FLL_REF_DIV_MASK		(0x3 << 10)
+#define NAU8825_FLL_REF_DIV_SFT	10
+#define NAU8825_FLL_REF_DIV_MASK	(0x3 << NAU8825_FLL_REF_DIV_SFT)
 
 /* FLL5 (0x08) */
 #define NAU8825_FLL_FILTER_SW_MASK		(0x1 << 14)
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index f2beb1aa5763..b1c8bb39cdf1 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -359,7 +359,7 @@ static const DECLARE_TLV_DB_RANGE(bst_tlv,
 
 /* Interface data select */
 static const char * const rt5640_data_select[] = {
-	"Normal", "left copy to right", "right copy to left", "Swap"};
+	"Normal", "Swap", "left copy to right", "right copy to left"};
 
 static SOC_ENUM_SINGLE_DECL(rt5640_if1_dac_enum, RT5640_DIG_INF_DATA,
 			    RT5640_IF1_DAC_SEL_SFT, rt5640_data_select);
diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h
index 3deb8babeabb..243f42633989 100644
--- a/sound/soc/codecs/rt5640.h
+++ b/sound/soc/codecs/rt5640.h
@@ -442,39 +442,39 @@
 #define RT5640_IF1_DAC_SEL_MASK			(0x3 << 14)
 #define RT5640_IF1_DAC_SEL_SFT			14
 #define RT5640_IF1_DAC_SEL_NOR			(0x0 << 14)
-#define RT5640_IF1_DAC_SEL_L2R			(0x1 << 14)
-#define RT5640_IF1_DAC_SEL_R2L			(0x2 << 14)
-#define RT5640_IF1_DAC_SEL_SWAP			(0x3 << 14)
+#define RT5640_IF1_DAC_SEL_SWAP			(0x1 << 14)
+#define RT5640_IF1_DAC_SEL_L2R			(0x2 << 14)
+#define RT5640_IF1_DAC_SEL_R2L			(0x3 << 14)
 #define RT5640_IF1_ADC_SEL_MASK			(0x3 << 12)
 #define RT5640_IF1_ADC_SEL_SFT			12
 #define RT5640_IF1_ADC_SEL_NOR			(0x0 << 12)
-#define RT5640_IF1_ADC_SEL_L2R			(0x1 << 12)
-#define RT5640_IF1_ADC_SEL_R2L			(0x2 << 12)
-#define RT5640_IF1_ADC_SEL_SWAP			(0x3 << 12)
+#define RT5640_IF1_ADC_SEL_SWAP			(0x1 << 12)
+#define RT5640_IF1_ADC_SEL_L2R			(0x2 << 12)
+#define RT5640_IF1_ADC_SEL_R2L			(0x3 << 12)
 #define RT5640_IF2_DAC_SEL_MASK			(0x3 << 10)
 #define RT5640_IF2_DAC_SEL_SFT			10
 #define RT5640_IF2_DAC_SEL_NOR			(0x0 << 10)
-#define RT5640_IF2_DAC_SEL_L2R			(0x1 << 10)
-#define RT5640_IF2_DAC_SEL_R2L			(0x2 << 10)
-#define RT5640_IF2_DAC_SEL_SWAP			(0x3 << 10)
+#define RT5640_IF2_DAC_SEL_SWAP			(0x1 << 10)
+#define RT5640_IF2_DAC_SEL_L2R			(0x2 << 10)
+#define RT5640_IF2_DAC_SEL_R2L			(0x3 << 10)
 #define RT5640_IF2_ADC_SEL_MASK			(0x3 << 8)
 #define RT5640_IF2_ADC_SEL_SFT			8
 #define RT5640_IF2_ADC_SEL_NOR			(0x0 << 8)
-#define RT5640_IF2_ADC_SEL_L2R			(0x1 << 8)
-#define RT5640_IF2_ADC_SEL_R2L			(0x2 << 8)
-#define RT5640_IF2_ADC_SEL_SWAP			(0x3 << 8)
+#define RT5640_IF2_ADC_SEL_SWAP			(0x1 << 8)
+#define RT5640_IF2_ADC_SEL_L2R			(0x2 << 8)
+#define RT5640_IF2_ADC_SEL_R2L			(0x3 << 8)
 #define RT5640_IF3_DAC_SEL_MASK			(0x3 << 6)
 #define RT5640_IF3_DAC_SEL_SFT			6
 #define RT5640_IF3_DAC_SEL_NOR			(0x0 << 6)
-#define RT5640_IF3_DAC_SEL_L2R			(0x1 << 6)
-#define RT5640_IF3_DAC_SEL_R2L			(0x2 << 6)
-#define RT5640_IF3_DAC_SEL_SWAP			(0x3 << 6)
+#define RT5640_IF3_DAC_SEL_SWAP			(0x1 << 6)
+#define RT5640_IF3_DAC_SEL_L2R			(0x2 << 6)
+#define RT5640_IF3_DAC_SEL_R2L			(0x3 << 6)
 #define RT5640_IF3_ADC_SEL_MASK			(0x3 << 4)
 #define RT5640_IF3_ADC_SEL_SFT			4
 #define RT5640_IF3_ADC_SEL_NOR			(0x0 << 4)
-#define RT5640_IF3_ADC_SEL_L2R			(0x1 << 4)
-#define RT5640_IF3_ADC_SEL_R2L			(0x2 << 4)
-#define RT5640_IF3_ADC_SEL_SWAP			(0x3 << 4)
+#define RT5640_IF3_ADC_SEL_SWAP			(0x1 << 4)
+#define RT5640_IF3_ADC_SEL_L2R			(0x2 << 4)
+#define RT5640_IF3_ADC_SEL_R2L			(0x3 << 4)
 
 /* REC Left Mixer Control 1 (0x3b) */
 #define RT5640_G_HP_L_RM_L_MASK			(0x7 << 13)
diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c
index e619d5651b09..080c78e88e10 100644
--- a/sound/soc/codecs/ssm4567.c
+++ b/sound/soc/codecs/ssm4567.c
@@ -352,6 +352,11 @@ static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable)
 	regcache_cache_only(ssm4567->regmap, !enable);
 
 	if (enable) {
+		ret = regmap_write(ssm4567->regmap, SSM4567_REG_SOFT_RESET,
+			0x00);
+		if (ret)
+			return ret;
+
 		ret = regmap_update_bits(ssm4567->regmap,
 			SSM4567_REG_POWER_CTRL,
 			SSM4567_POWER_SPWDN, 0x00);
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index a564759845f9..5a3f544bb3a8 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -126,6 +126,16 @@ static const struct reg_default aic3x_reg[] = {
 	{ 108, 0x00 }, { 109, 0x00 },
 };
 
+static bool aic3x_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case AIC3X_RESET:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static const struct regmap_config aic3x_regmap = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -133,6 +143,9 @@ static const struct regmap_config aic3x_regmap = {
 	.max_register = DAC_ICC_ADJ,
 	.reg_defaults = aic3x_reg,
 	.num_reg_defaults = ARRAY_SIZE(aic3x_reg),
+
+	.volatile_reg = aic3x_volatile_reg,
+
 	.cache_type = REGCACHE_RBTREE,
 };
 
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 54c33204541f..ff6fcd9f92f7 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -100,7 +100,7 @@ static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 		if (ret && ret != -ENOTSUPP)
 			goto err;
 	}
-
+	return 0;
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 0487cfaac538..2b96b11fbe71 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -762,6 +762,9 @@ static int sst_soc_prepare(struct device *dev)
 	struct sst_data *drv = dev_get_drvdata(dev);
 	int i;
 
+	if (!drv->soc_card)
+		return 0;
+
 	/* suspend all pcms first */
 	snd_soc_suspend(drv->soc_card->dev);
 	snd_soc_poweroff(drv->soc_card->dev);
@@ -784,6 +787,9 @@ static void sst_soc_complete(struct device *dev)
 	struct sst_data *drv = dev_get_drvdata(dev);
 	int i;
 
+	if (!drv->soc_card)
+		return;
+
 	/* restart SSPs */
 	for (i = 0; i < drv->soc_card->num_rtd; i++) {
 		struct snd_soc_dai *dai = drv->soc_card->rtd[i].cpu_dai;
diff --git a/sound/soc/intel/atom/sst/sst_pvt.c b/sound/soc/intel/atom/sst/sst_pvt.c
index adb32fefd693..b1e6b8f34a6a 100644
--- a/sound/soc/intel/atom/sst/sst_pvt.c
+++ b/sound/soc/intel/atom/sst/sst_pvt.c
@@ -279,17 +279,15 @@ int sst_prepare_and_post_msg(struct intel_sst_drv *sst,
 
 	if (response) {
 		ret = sst_wait_timeout(sst, block);
-		if (ret < 0) {
+		if (ret < 0)
 			goto out;
-		} else if(block->data) {
-			if (!data)
-				goto out;
-			*data = kzalloc(block->size, GFP_KERNEL);
-			if (!(*data)) {
+
+		if (data && block->data) {
+			*data = kmemdup(block->data, block->size, GFP_KERNEL);
+			if (!*data) {
 				ret = -ENOMEM;
 				goto out;
-			} else
-				memcpy(data, (void *) block->data, block->size);
+			}
 		}
 	}
 out:
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 7a5c9a36c1db..daba8c56b43b 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -139,7 +139,7 @@ static struct snd_soc_dai_link byt_dailink[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.codec_name = "snd-soc-dummy",
 		.platform_name = "sst-mfld-platform",
-		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dynamic = 1,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
@@ -166,6 +166,7 @@ static struct snd_soc_dai_link byt_dailink[] = {
 						| SND_SOC_DAIFMT_CBS_CFS,
 		.be_hw_params_fixup = byt_codec_fixup,
 		.ignore_suspend = 1,
+		.nonatomic = true,
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 		.ops = &byt_be_ssp2_ops,
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index caa69c4598a6..b4844f78266f 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -464,8 +464,10 @@ static int skl_probe(struct pci_dev *pci,
 
 	skl->nhlt = skl_nhlt_init(bus->dev);
 
-	if (skl->nhlt == NULL)
+	if (skl->nhlt == NULL) {
+		err = -ENODEV;
 		goto out_free;
+	}
 
 	pci_set_drvdata(skl->pci, ebus);
 
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index b837265ac3e9..8d0d45d330e7 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -390,8 +390,8 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai)
 	pm_runtime_get_sync(mcpdm->dev);
 	omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00);
 
-	ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler,
-				0, "McPDM", (void *)mcpdm);
+	ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM",
+			  (void *)mcpdm);
 
 	pm_runtime_put_sync(mcpdm->dev);
 
@@ -416,6 +416,7 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai)
 {
 	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
 
+	free_irq(mcpdm->irq, (void *)mcpdm);
 	pm_runtime_disable(mcpdm->dev);
 
 	return 0;
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index e4145509d63c..9c5219392460 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -324,7 +324,7 @@ static const struct snd_soc_component_driver s3c_ac97_component = {
 
 static int s3c_ac97_probe(struct platform_device *pdev)
 {
-	struct resource *mem_res, *dmatx_res, *dmarx_res, *dmamic_res, *irq_res;
+	struct resource *mem_res, *irq_res;
 	struct s3c_audio_pdata *ac97_pdata;
 	int ret;
 
@@ -335,24 +335,6 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 	}
 
 	/* Check for availability of necessary resource */
-	dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dmatx_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-TX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-	if (!dmarx_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-RX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmamic_res = platform_get_resource(pdev, IORESOURCE_DMA, 2);
-	if (!dmamic_res) {
-		dev_err(&pdev->dev, "Unable to get AC97-MIC dma resource\n");
-		return -ENXIO;
-	}
-
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!irq_res) {
 		dev_err(&pdev->dev, "AC97 IRQ not provided!\n");
@@ -364,11 +346,11 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 	if (IS_ERR(s3c_ac97.regs))
 		return PTR_ERR(s3c_ac97.regs);
 
-	s3c_ac97_pcm_out.channel = dmatx_res->start;
+	s3c_ac97_pcm_out.slave = ac97_pdata->dma_playback;
 	s3c_ac97_pcm_out.dma_addr = mem_res->start + S3C_AC97_PCM_DATA;
-	s3c_ac97_pcm_in.channel = dmarx_res->start;
+	s3c_ac97_pcm_in.slave = ac97_pdata->dma_capture;
 	s3c_ac97_pcm_in.dma_addr = mem_res->start + S3C_AC97_PCM_DATA;
-	s3c_ac97_mic_in.channel = dmamic_res->start;
+	s3c_ac97_mic_in.slave = ac97_pdata->dma_capture_mic;
 	s3c_ac97_mic_in.dma_addr = mem_res->start + S3C_AC97_MIC_DATA;
 
 	init_completion(&s3c_ac97.done);
diff --git a/sound/soc/samsung/dma.h b/sound/soc/samsung/dma.h
index 0e85dcfec023..085ef30f5ca2 100644
--- a/sound/soc/samsung/dma.h
+++ b/sound/soc/samsung/dma.h
@@ -15,7 +15,7 @@
 #include <sound/dmaengine_pcm.h>
 
 struct s3c_dma_params {
-	int channel;				/* Channel ID */
+	void *slave;				/* Channel ID */
 	dma_addr_t dma_addr;
 	int dma_size;			/* Size of the DMA transfer */
 	char *ch_name;
diff --git a/sound/soc/samsung/dmaengine.c b/sound/soc/samsung/dmaengine.c
index 506f5bf6d082..727008d57d14 100644
--- a/sound/soc/samsung/dmaengine.c
+++ b/sound/soc/samsung/dmaengine.c
@@ -50,14 +50,14 @@ void samsung_asoc_init_dma_data(struct snd_soc_dai *dai,
 
 	if (playback) {
 		playback_data = &playback->dma_data;
-		playback_data->filter_data = (void *)playback->channel;
+		playback_data->filter_data = playback->slave;
 		playback_data->chan_name = playback->ch_name;
 		playback_data->addr = playback->dma_addr;
 		playback_data->addr_width = playback->dma_size;
 	}
 	if (capture) {
 		capture_data = &capture->dma_data;
-		capture_data->filter_data = (void *)capture->channel;
+		capture_data->filter_data = capture->slave;
 		capture_data->chan_name = capture->ch_name;
 		capture_data->addr = capture->dma_addr;
 		capture_data->addr_width = capture->dma_size;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 7dbf899b2af2..fd6e247d9fd8 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1027,12 +1027,13 @@ static int samsung_i2s_dai_probe(struct snd_soc_dai *dai)
 static int samsung_i2s_dai_remove(struct snd_soc_dai *dai)
 {
 	struct i2s_dai *i2s = snd_soc_dai_get_drvdata(dai);
+	unsigned long flags;
 
 	if (!is_secondary(i2s)) {
 		if (i2s->quirks & QUIRK_NEED_RSTCLR) {
-			spin_lock(i2s->lock);
+			spin_lock_irqsave(i2s->lock, flags);
 			writel(0, i2s->addr + I2SCON);
-			spin_unlock(i2s->lock);
+			spin_unlock_irqrestore(i2s->lock, flags);
 		}
 	}
 
@@ -1260,27 +1261,14 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 	pri_dai->lock = &pri_dai->spinlock;
 
 	if (!np) {
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (!res) {
-			dev_err(&pdev->dev,
-				"Unable to get I2S-TX dma resource\n");
-			return -ENXIO;
-		}
-		pri_dai->dma_playback.channel = res->start;
-
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (!res) {
-			dev_err(&pdev->dev,
-				"Unable to get I2S-RX dma resource\n");
-			return -ENXIO;
-		}
-		pri_dai->dma_capture.channel = res->start;
-
 		if (i2s_pdata == NULL) {
 			dev_err(&pdev->dev, "Can't work without s3c_audio_pdata\n");
 			return -EINVAL;
 		}
 
+		pri_dai->dma_playback.slave = i2s_pdata->dma_playback;
+		pri_dai->dma_capture.slave = i2s_pdata->dma_capture;
+
 		if (&i2s_pdata->type)
 			i2s_cfg = &i2s_pdata->type.i2s;
 
@@ -1341,11 +1329,8 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 		sec_dai->dma_playback.dma_addr = regs_base + I2STXDS;
 		sec_dai->dma_playback.ch_name = "tx-sec";
 
-		if (!np) {
-			res = platform_get_resource(pdev, IORESOURCE_DMA, 2);
-			if (res)
-				sec_dai->dma_playback.channel = res->start;
-		}
+		if (!np)
+			sec_dai->dma_playback.slave = i2s_pdata->dma_play_sec;
 
 		sec_dai->dma_playback.dma_size = 4;
 		sec_dai->addr = pri_dai->addr;
diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c
index b320a9d3fbf8..c77f324e0bb8 100644
--- a/sound/soc/samsung/pcm.c
+++ b/sound/soc/samsung/pcm.c
@@ -486,7 +486,7 @@ static const struct snd_soc_component_driver s3c_pcm_component = {
 static int s3c_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct s3c_pcm_info *pcm;
-	struct resource *mem_res, *dmatx_res, *dmarx_res;
+	struct resource *mem_res;
 	struct s3c_audio_pdata *pcm_pdata;
 	int ret;
 
@@ -499,18 +499,6 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 	pcm_pdata = pdev->dev.platform_data;
 
 	/* Check for availability of necessary resource */
-	dmatx_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dmatx_res) {
-		dev_err(&pdev->dev, "Unable to get PCM-TX dma resource\n");
-		return -ENXIO;
-	}
-
-	dmarx_res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-	if (!dmarx_res) {
-		dev_err(&pdev->dev, "Unable to get PCM-RX dma resource\n");
-		return -ENXIO;
-	}
-
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem_res) {
 		dev_err(&pdev->dev, "Unable to get register resource\n");
@@ -568,8 +556,10 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 	s3c_pcm_stereo_out[pdev->id].dma_addr = mem_res->start
 							+ S3C_PCM_TXFIFO;
 
-	s3c_pcm_stereo_in[pdev->id].channel = dmarx_res->start;
-	s3c_pcm_stereo_out[pdev->id].channel = dmatx_res->start;
+	if (pcm_pdata) {
+		s3c_pcm_stereo_in[pdev->id].slave = pcm_pdata->dma_capture;
+		s3c_pcm_stereo_out[pdev->id].slave = pcm_pdata->dma_playback;
+	}
 
 	pcm->dma_capture = &s3c_pcm_stereo_in[pdev->id];
 	pcm->dma_playback = &s3c_pcm_stereo_out[pdev->id];
diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c
index df65c5b494b1..b6ab3fc5789e 100644
--- a/sound/soc/samsung/s3c-i2s-v2.c
+++ b/sound/soc/samsung/s3c-i2s-v2.c
@@ -709,7 +709,7 @@ static int s3c2412_i2s_resume(struct snd_soc_dai *dai)
 #endif
 
 int s3c_i2sv2_register_component(struct device *dev, int id,
-			   struct snd_soc_component_driver *cmp_drv,
+			   const struct snd_soc_component_driver *cmp_drv,
 			   struct snd_soc_dai_driver *dai_drv)
 {
 	struct snd_soc_dai_ops *ops = (struct snd_soc_dai_ops *)dai_drv->ops;
diff --git a/sound/soc/samsung/s3c-i2s-v2.h b/sound/soc/samsung/s3c-i2s-v2.h
index 90abab364b49..d0684145ed1f 100644
--- a/sound/soc/samsung/s3c-i2s-v2.h
+++ b/sound/soc/samsung/s3c-i2s-v2.h
@@ -101,7 +101,7 @@ extern int s3c_i2sv2_probe(struct snd_soc_dai *dai,
  * soc core.
  */
 extern int s3c_i2sv2_register_component(struct device *dev, int id,
-					struct snd_soc_component_driver *cmp_drv,
+					const struct snd_soc_component_driver *cmp_drv,
 					struct snd_soc_dai_driver *dai_drv);
 
 #endif /* __SND_SOC_S3C24XX_S3C_I2SV2_I2S_H */
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 2b766d212ce0..77d27c85a32a 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -34,13 +34,13 @@
 #include "s3c2412-i2s.h"
 
 static struct s3c_dma_params s3c2412_i2s_pcm_stereo_out = {
-	.channel	= DMACH_I2S_OUT,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_OUT,
 	.ch_name	= "tx",
 	.dma_size	= 4,
 };
 
 static struct s3c_dma_params s3c2412_i2s_pcm_stereo_in = {
-	.channel	= DMACH_I2S_IN,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_IN,
 	.ch_name	= "rx",
 	.dma_size	= 4,
 };
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index 5bf723689692..9da3a77ea2c7 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -32,13 +32,13 @@
 #include "s3c24xx-i2s.h"
 
 static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_out = {
-	.channel	= DMACH_I2S_OUT,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_OUT,
 	.ch_name	= "tx",
 	.dma_size	= 2,
 };
 
 static struct s3c_dma_params s3c24xx_i2s_pcm_stereo_in = {
-	.channel	= DMACH_I2S_IN,
+	.slave		= (void *)(uintptr_t)DMACH_I2S_IN,
 	.ch_name	= "rx",
 	.dma_size	= 2,
 };
diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c
index 36dbc0e96004..9dd7ee6d03ff 100644
--- a/sound/soc/samsung/spdif.c
+++ b/sound/soc/samsung/spdif.c
@@ -359,7 +359,7 @@ static const struct snd_soc_component_driver samsung_spdif_component = {
 static int spdif_probe(struct platform_device *pdev)
 {
 	struct s3c_audio_pdata *spdif_pdata;
-	struct resource *mem_res, *dma_res;
+	struct resource *mem_res;
 	struct samsung_spdif_info *spdif;
 	int ret;
 
@@ -367,12 +367,6 @@ static int spdif_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "Entered %s\n", __func__);
 
-	dma_res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!dma_res) {
-		dev_err(&pdev->dev, "Unable to get dma resource.\n");
-		return -ENXIO;
-	}
-
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem_res) {
 		dev_err(&pdev->dev, "Unable to get register resource.\n");
@@ -432,7 +426,7 @@ static int spdif_probe(struct platform_device *pdev)
 
 	spdif_stereo_out.dma_size = 2;
 	spdif_stereo_out.dma_addr = mem_res->start + DATA_OUTBUF;
-	spdif_stereo_out.channel = dma_res->start;
+	spdif_stereo_out.slave = spdif_pdata ? spdif_pdata->dma_playback : NULL;
 
 	spdif->dma_playback = &spdif_stereo_out;
 
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 2a5b3a293cd2..b123734f9fbd 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -437,7 +437,7 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv,
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct device_node *np = dev->of_node;
 	u32 ckr, rbgx, rbga, rbgb;
-	u32 rate, req_rate, div;
+	u32 rate, req_rate = 0, div;
 	uint32_t count = 0;
 	unsigned long req_48kHz_rate, req_441kHz_rate;
 	int i;
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index deed48ef28b8..362446c36c9e 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -192,19 +192,16 @@ void rsnd_mod_interrupt(struct rsnd_mod *mod,
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct rsnd_dai_stream *io;
 	struct rsnd_dai *rdai;
-	int i, j;
-
-	for_each_rsnd_dai(rdai, priv, j) {
+	int i;
 
-		for (i = 0; i < RSND_MOD_MAX; i++) {
-			io = &rdai->playback;
-			if (mod == io->mod[i])
-				callback(mod, io);
+	for_each_rsnd_dai(rdai, priv, i) {
+		io = &rdai->playback;
+		if (mod == io->mod[mod->type])
+			callback(mod, io);
 
-			io = &rdai->capture;
-			if (mod == io->mod[i])
-				callback(mod, io);
-		}
+		io = &rdai->capture;
+		if (mod == io->mod[mod->type])
+			callback(mod, io);
 	}
 }
 
@@ -1019,7 +1016,7 @@ static int rsnd_kctrl_put(struct snd_kcontrol *kctrl,
 		}
 	}
 
-	if (change)
+	if (change && cfg->update)
 		cfg->update(cfg->io, mod);
 
 	return change;
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 68b439ed22d7..460d29cbaaa5 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -691,13 +691,27 @@ static int _rsnd_src_stop_gen2(struct rsnd_mod *mod)
 {
 	rsnd_src_irq_disable_gen2(mod);
 
-	rsnd_mod_write(mod, SRC_CTRL, 0);
+	/*
+	 * stop SRC output only
+	 * see rsnd_src_quit_gen2
+	 */
+	rsnd_mod_write(mod, SRC_CTRL, 0x01);
 
 	rsnd_src_error_record_gen2(mod);
 
 	return rsnd_src_stop(mod);
 }
 
+static int rsnd_src_quit_gen2(struct rsnd_mod *mod,
+			      struct rsnd_dai_stream *io,
+			      struct rsnd_priv *priv)
+{
+	/* stop both out/in */
+	rsnd_mod_write(mod, SRC_CTRL, 0);
+
+	return 0;
+}
+
 static void __rsnd_src_interrupt_gen2(struct rsnd_mod *mod,
 				      struct rsnd_dai_stream *io)
 {
@@ -971,7 +985,7 @@ static struct rsnd_mod_ops rsnd_src_gen2_ops = {
 	.probe	= rsnd_src_probe_gen2,
 	.remove	= rsnd_src_remove_gen2,
 	.init	= rsnd_src_init_gen2,
-	.quit	= rsnd_src_quit,
+	.quit	= rsnd_src_quit_gen2,
 	.start	= rsnd_src_start_gen2,
 	.stop	= rsnd_src_stop_gen2,
 	.hw_params = rsnd_src_hw_params,
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 1427ec21bd7e..c62a2947ac14 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -39,6 +39,7 @@
 #define	SCKP		(1 << 13)	/* Serial Bit Clock Polarity */
 #define	SWSP		(1 << 12)	/* Serial WS Polarity */
 #define	SDTA		(1 << 10)	/* Serial Data Alignment */
+#define	PDTA		(1 <<  9)	/* Parallel Data Alignment */
 #define	DEL		(1 <<  8)	/* Serial Data Delay */
 #define	CKDV(v)		(v <<  4)	/* Serial Clock Division Ratio */
 #define	TRMD		(1 <<  1)	/* Transmit/Receive Mode Select */
@@ -286,7 +287,7 @@ static int rsnd_ssi_init(struct rsnd_mod *mod,
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 	u32 cr;
 
-	cr = FORCE;
+	cr = FORCE | PDTA;
 
 	/*
 	 * always use 32bit system word for easy clock calculation.
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index bb82bb966000..c1addf49c4f2 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -68,7 +68,8 @@ out:
 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_pcm_substream *fe_substream =
+		 fe->pcm->streams[cstream->direction].substream;
 	struct snd_soc_platform *platform = fe->platform;
 	struct snd_soc_dpcm *dpcm;
 	struct snd_soc_dapm_widget_list *list;
@@ -412,7 +413,8 @@ 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_pcm_substream *fe_substream =
+		 fe->pcm->streams[cstream->direction].substream;
 	struct snd_soc_platform *platform = fe->platform;
 	int ret = 0, stream;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index a1305f827a98..fa6b74a304a7 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1775,6 +1775,9 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card)
 	for (i = 0; i < card->num_aux_devs; i++)
 		soc_remove_aux_dev(card, i);
 
+	/* free the ALSA card at first; this syncs with pending operations */
+	snd_card_free(card->snd_card);
+
 	/* remove and free each DAI */
 	soc_remove_dai_links(card);
 
@@ -1786,9 +1789,7 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card)
 
 	snd_soc_dapm_free(&card->dapm);
 
-	snd_card_free(card->snd_card);
 	return 0;
-
 }
 
 /* removes a socdev */
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 416514fe9e63..b8a256dfed7e 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -823,6 +823,7 @@ static int dapm_create_or_share_kcontrol(struct snd_soc_dapm_widget *w,
 			case snd_soc_dapm_switch:
 			case snd_soc_dapm_mixer:
 			case snd_soc_dapm_pga:
+			case snd_soc_dapm_out_drv:
 				wname_in_long_name = true;
 				kcname_in_long_name = true;
 				break;
@@ -2188,6 +2189,13 @@ static ssize_t dapm_widget_show_component(struct snd_soc_component *cmpnt,
 	int count = 0;
 	char *state = "not set";
 
+	/* card won't be set for the dummy component, as a spot fix
+	 * we're checking for that case specifically here but in future
+	 * we will ensure that the dummy component looks like others.
+	 */
+	if (!cmpnt->card)
+		return 0;
+
 	list_for_each_entry(w, &cmpnt->card->widgets, list) {
 		if (w->dapm != dapm)
 			continue;
@@ -3008,6 +3016,9 @@ int snd_soc_dapm_get_volsw(struct snd_kcontrol *kcontrol,
 	}
 	mutex_unlock(&card->dapm_mutex);
 
+	if (ret)
+		return ret;
+
 	if (invert)
 		ucontrol->value.integer.value[0] = max - val;
 	else
@@ -3159,7 +3170,7 @@ int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol,
 	if (e->shift_l != e->shift_r) {
 		if (item[1] > e->items)
 			return -EINVAL;
-		val |= snd_soc_enum_item_to_val(e, item[1]) << e->shift_l;
+		val |= snd_soc_enum_item_to_val(e, item[1]) << e->shift_r;
 		mask |= e->mask << e->shift_r;
 	}
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 65b936e251ea..977066ba1769 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -181,6 +181,10 @@ int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
 		dev_dbg(be->dev, "ASoC: BE %s event %d dir %d\n",
 				be->dai_link->name, event, dir);
 
+		if ((event == SND_SOC_DAPM_STREAM_STOP) &&
+		    (be->dpcm[dir].users >= 1))
+			continue;
+
 		snd_soc_dapm_stream_event(be, dir, event);
 	}
 
@@ -2073,9 +2077,11 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		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:
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 6963ba20991c..70396d3f6472 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1484,6 +1484,7 @@ widget:
 	if (widget == NULL) {
 		dev_err(tplg->dev, "ASoC: failed to create widget %s controls\n",
 			w->name);
+		ret = -ENOMEM;
 		goto hdr_err;
 	}
 
diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index 1bb896d78d09..1a4999f9d56f 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -575,11 +575,11 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev)
 
 	card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL);
 	if (!card)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
 	if (!card->dai_link)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
 	card->name		= "sun4i-codec";
@@ -661,7 +661,8 @@ static int sun4i_codec_probe(struct platform_device *pdev)
 	}
 
 	card = sun4i_codec_create_card(&pdev->dev);
-	if (!card) {
+	if (IS_ERR(card)) {
+		ret = PTR_ERR(card);
 		dev_err(&pdev->dev, "Failed to create our card\n");
 		goto err_unregister_codec;
 	}
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 1f09d9591276..a1cbaa5f7fc9 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -202,7 +202,6 @@ static int snd_usb_create_stream(struct snd_usb_audio *chip, int ctrlif, int int
 	if (! snd_usb_parse_audio_interface(chip, interface)) {
 		usb_set_interface(dev, interface, 0); /* reset the current interface */
 		usb_driver_claim_interface(&usb_audio_driver, iface, (void *)-1L);
-		return -EINVAL;
 	}
 
 	return 0;
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 2ed260b10f6d..7ccbcaf6a147 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -285,6 +285,8 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, int iface,
 	unsigned char data[3];
 	int err, crate;
 
+	if (get_iface_desc(alts)->bNumEndpoints < 1)
+		return -EINVAL;
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	/* if endpoint doesn't have sampling rate control, bail out */
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 7b1cb365ffab..ae2981460cd8 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -384,6 +384,9 @@ static void snd_complete_urb(struct urb *urb)
 	if (unlikely(atomic_read(&ep->chip->shutdown)))
 		goto exit_clear;
 
+	if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags)))
+		goto exit_clear;
+
 	if (usb_pipeout(ep->pipe)) {
 		retire_outbound_urb(ep, ctx);
 		/* can be stopped during retire callback */
@@ -438,6 +441,9 @@ exit_clear:
  *
  * New endpoints will be added to chip->ep_list and must be freed by
  * calling snd_usb_endpoint_free().
+ *
+ * For SND_USB_ENDPOINT_TYPE_SYNC, the caller needs to guarantee that
+ * bNumEndpoints > 1 beforehand.
  */
 struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip,
 					      struct usb_host_interface *alts,
@@ -535,6 +541,11 @@ static int wait_clear_urbs(struct snd_usb_endpoint *ep)
 			alive, ep->ep_num);
 	clear_bit(EP_FLAG_STOPPING, &ep->flags);
 
+	ep->data_subs = NULL;
+	ep->sync_slave = NULL;
+	ep->retire_data_urb = NULL;
+	ep->prepare_data_urb = NULL;
+
 	return 0;
 }
 
@@ -899,9 +910,7 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep,
 /**
  * snd_usb_endpoint_start: start an snd_usb_endpoint
  *
- * @ep:		the endpoint to start
- * @can_sleep:	flag indicating whether the operation is executed in
- * 		non-atomic context
+ * @ep: the endpoint to start
  *
  * A call to this function will increment the use count of the endpoint.
  * In case it is not already running, the URBs for this endpoint will be
@@ -911,7 +920,7 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep,
  *
  * Returns an error if the URB submission failed, 0 in all other cases.
  */
-int snd_usb_endpoint_start(struct snd_usb_endpoint *ep, bool can_sleep)
+int snd_usb_endpoint_start(struct snd_usb_endpoint *ep)
 {
 	int err;
 	unsigned int i;
@@ -925,8 +934,6 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep, bool can_sleep)
 
 	/* just to be sure */
 	deactivate_urbs(ep, false);
-	if (can_sleep)
-		wait_clear_urbs(ep);
 
 	ep->active_mask = 0;
 	ep->unlink_mask = 0;
@@ -1007,10 +1014,6 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep)
 
 	if (--ep->use_count == 0) {
 		deactivate_urbs(ep, false);
-		ep->data_subs = NULL;
-		ep->sync_slave = NULL;
-		ep->retire_data_urb = NULL;
-		ep->prepare_data_urb = NULL;
 		set_bit(EP_FLAG_STOPPING, &ep->flags);
 	}
 }
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 6428392d8f62..584f295d7c77 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -18,7 +18,7 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep,
 				struct audioformat *fmt,
 				struct snd_usb_endpoint *sync_ep);
 
-int  snd_usb_endpoint_start(struct snd_usb_endpoint *ep, bool can_sleep);
+int  snd_usb_endpoint_start(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
diff --git a/sound/usb/hiface/pcm.c b/sound/usb/hiface/pcm.c
index 2c44139b4041..33db205dd12b 100644
--- a/sound/usb/hiface/pcm.c
+++ b/sound/usb/hiface/pcm.c
@@ -445,6 +445,8 @@ static int hiface_pcm_prepare(struct snd_pcm_substream *alsa_sub)
 
 	mutex_lock(&rt->stream_mutex);
 
+	hiface_pcm_stream_stop(rt);
+
 	sub->dma_off = 0;
 	sub->period_off = 0;
 
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 81b7da8e56d3..183311cb849e 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -29,7 +29,7 @@
 /*
 	This is Line 6's MIDI manufacturer ID.
 */
-const unsigned char line6_midi_id[] = {
+const unsigned char line6_midi_id[3] = {
 	0x00, 0x01, 0x0c
 };
 EXPORT_SYMBOL_GPL(line6_midi_id);
diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c
index 204cc074adb9..41aa3355e920 100644
--- a/sound/usb/line6/pcm.c
+++ b/sound/usb/line6/pcm.c
@@ -55,7 +55,6 @@ static int snd_line6_impulse_volume_put(struct snd_kcontrol *kcontrol,
 		err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE);
 		if (err < 0) {
 			line6pcm->impulse_volume = 0;
-			line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE);
 			return err;
 		}
 	} else {
@@ -211,7 +210,9 @@ static void line6_stream_stop(struct snd_line6_pcm *line6pcm, int direction,
 	spin_lock_irqsave(&pstr->lock, flags);
 	clear_bit(type, &pstr->running);
 	if (!pstr->running) {
+		spin_unlock_irqrestore(&pstr->lock, flags);
 		line6_unlink_audio_urbs(line6pcm, pstr);
+		spin_lock_irqsave(&pstr->lock, flags);
 		if (direction == SNDRV_PCM_STREAM_CAPTURE) {
 			line6pcm->prev_fbuf = NULL;
 			line6pcm->prev_fsize = 0;
diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c
index daf81d169a42..45dd34874f43 100644
--- a/sound/usb/line6/pod.c
+++ b/sound/usb/line6/pod.c
@@ -244,8 +244,8 @@ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value,
 static ssize_t serial_number_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct usb_interface *interface = to_usb_interface(dev);
-	struct usb_line6_pod *pod = usb_get_intfdata(interface);
+	struct snd_card *card = dev_to_snd_card(dev);
+	struct usb_line6_pod *pod = card->private_data;
 
 	return sprintf(buf, "%u\n", pod->serial_number);
 }
@@ -256,8 +256,8 @@ static ssize_t serial_number_show(struct device *dev,
 static ssize_t firmware_version_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	struct usb_interface *interface = to_usb_interface(dev);
-	struct usb_line6_pod *pod = usb_get_intfdata(interface);
+	struct snd_card *card = dev_to_snd_card(dev);
+	struct usb_line6_pod *pod = card->private_data;
 
 	return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100,
 		       pod->firmware_version % 100);
@@ -269,8 +269,8 @@ static ssize_t firmware_version_show(struct device *dev,
 static ssize_t device_id_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
-	struct usb_interface *interface = to_usb_interface(dev);
-	struct usb_line6_pod *pod = usb_get_intfdata(interface);
+	struct snd_card *card = dev_to_snd_card(dev);
+	struct usb_line6_pod *pod = card->private_data;
 
 	return sprintf(buf, "%d\n", pod->device_id);
 }
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 4f85757009b3..696de5ac69be 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -541,6 +541,8 @@ int snd_usb_mixer_vol_tlv(struct snd_kcontrol *kcontrol, int op_flag,
 
 	if (size < sizeof(scale))
 		return -ENOMEM;
+	if (cval->min_mute)
+		scale[0] = SNDRV_CTL_TLVT_DB_MINMAX_MUTE;
 	scale[2] = cval->dBmin;
 	scale[3] = cval->dBmax;
 	if (copy_to_user(_tlv, scale, sizeof(scale)))
@@ -931,9 +933,10 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 	case USB_ID(0x046d, 0x0826): /* HD Webcam c525 */
 	case USB_ID(0x046d, 0x08ca): /* Logitech Quickcam Fusion */
 	case USB_ID(0x046d, 0x0991):
+	case USB_ID(0x046d, 0x09a2): /* QuickCam Communicate Deluxe/S7500 */
 	/* Most audio usb devices lie about volume resolution.
 	 * Most Logitech webcams have res = 384.
-	 * Proboly there is some logitech magic behind this number --fishor
+	 * Probably there is some logitech magic behind this number --fishor
 	 */
 		if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
 			usb_audio_info(chip,
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index 3417ef347e40..2b4b067646ab 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -64,6 +64,7 @@ struct usb_mixer_elem_info {
 	int cached;
 	int cache_val[MAX_CHANNELS];
 	u8 initialized;
+	u8 min_mute;
 	void *private_data;
 };
 
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index ddca6547399b..1f8fb0d904e0 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -349,6 +349,16 @@ static struct usbmix_name_map bose_companion5_map[] = {
 };
 
 /*
+ * Dell usb dock with ALC4020 codec had a firmware problem where it got
+ * screwed up when zero volume is passed; just skip it as a workaround
+ */
+static const struct usbmix_name_map dell_alc4020_map[] = {
+	{ 16, NULL },
+	{ 19, NULL },
+	{ 0 }
+};
+
+/*
  * Control map entries
  */
 
@@ -431,6 +441,10 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.map = aureon_51_2_map,
 	},
 	{
+		.id = USB_ID(0x0bda, 0x4014),
+		.map = dell_alc4020_map,
+	},
+	{
 		.id = USB_ID(0x0dba, 0x1000),
 		.map = mbox1_map,
 	},
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 279025650568..5d2fc5f58bfe 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -1519,7 +1519,11 @@ static int snd_microii_spdif_default_get(struct snd_kcontrol *kcontrol,
 
 	/* use known values for that card: interface#1 altsetting#1 */
 	iface = usb_ifnum_to_if(chip->dev, 1);
+	if (!iface || iface->num_altsetting < 2)
+		return -EINVAL;
 	alts = &iface->altsetting[1];
+	if (get_iface_desc(alts)->bNumEndpoints < 1)
+		return -EINVAL;
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	err = snd_usb_ctl_msg(chip->dev,
@@ -1827,6 +1831,7 @@ void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer,
 }
 
 static void snd_dragonfly_quirk_db_scale(struct usb_mixer_interface *mixer,
+					 struct usb_mixer_elem_info *cval,
 					 struct snd_kcontrol *kctl)
 {
 	/* Approximation using 10 ranges based on output measurement on hw v1.2.
@@ -1844,10 +1849,19 @@ static void snd_dragonfly_quirk_db_scale(struct usb_mixer_interface *mixer,
 		41, 50, TLV_DB_MINMAX_ITEM(-441, 0),
 	);
 
-	usb_audio_info(mixer->chip, "applying DragonFly dB scale quirk\n");
-	kctl->tlv.p = scale;
-	kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ;
-	kctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK;
+	if (cval->min == 0 && cval->max == 50) {
+		usb_audio_info(mixer->chip, "applying DragonFly dB scale quirk (0-50 variant)\n");
+		kctl->tlv.p = scale;
+		kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ;
+		kctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK;
+
+	} else if (cval->min == 0 && cval->max <= 1000) {
+		/* Some other clearly broken DragonFly variant.
+		 * At least a 0..53 variant (hw v1.0) exists.
+		 */
+		usb_audio_info(mixer->chip, "ignoring too narrow dB range on a DragonFly device");
+		kctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK;
+	}
 }
 
 void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer,
@@ -1856,8 +1870,14 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer,
 {
 	switch (mixer->chip->usb_id) {
 	case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */
-		if (unitid == 7 && cval->min == 0 && cval->max == 50)
-			snd_dragonfly_quirk_db_scale(mixer, kctl);
+		if (unitid == 7 && cval->control == UAC_FU_VOLUME)
+			snd_dragonfly_quirk_db_scale(mixer, cval, kctl);
+		break;
+	/* lowest playback value is muted on C-Media devices */
+	case USB_ID(0x0d8c, 0x000c):
+	case USB_ID(0x0d8c, 0x0014):
+		if (strstr(kctl->id.name, "Playback"))
+			cval->min_mute = 1;
 		break;
 	}
 }
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 9245f52d43bd..48afae053c56 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -159,6 +159,8 @@ static int init_pitch_v1(struct snd_usb_audio *chip, int iface,
 	unsigned char data[1];
 	int err;
 
+	if (get_iface_desc(alts)->bNumEndpoints < 1)
+		return -EINVAL;
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	data[0] = 1;
@@ -216,7 +218,7 @@ int snd_usb_init_pitch(struct snd_usb_audio *chip, int iface,
 	}
 }
 
-static int start_endpoints(struct snd_usb_substream *subs, bool can_sleep)
+static int start_endpoints(struct snd_usb_substream *subs)
 {
 	int err;
 
@@ -229,7 +231,7 @@ static int start_endpoints(struct snd_usb_substream *subs, bool can_sleep)
 		dev_dbg(&subs->dev->dev, "Starting data EP @%p\n", ep);
 
 		ep->data_subs = subs;
-		err = snd_usb_endpoint_start(ep, can_sleep);
+		err = snd_usb_endpoint_start(ep);
 		if (err < 0) {
 			clear_bit(SUBSTREAM_FLAG_DATA_EP_STARTED, &subs->flags);
 			return err;
@@ -258,7 +260,7 @@ static int start_endpoints(struct snd_usb_substream *subs, bool can_sleep)
 		dev_dbg(&subs->dev->dev, "Starting sync EP @%p\n", ep);
 
 		ep->sync_slave = subs->data_endpoint;
-		err = snd_usb_endpoint_start(ep, can_sleep);
+		err = snd_usb_endpoint_start(ep);
 		if (err < 0) {
 			clear_bit(SUBSTREAM_FLAG_SYNC_EP_STARTED, &subs->flags);
 			return err;
@@ -837,7 +839,7 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream)
 	/* for playback, submit the URBs now; otherwise, the first hwptr_done
 	 * updates for all URBs would happen at the same time when starting */
 	if (subs->direction == SNDRV_PCM_STREAM_PLAYBACK)
-		ret = start_endpoints(subs, true);
+		ret = start_endpoints(subs);
 
  unlock:
 	snd_usb_unlock_shutdown(subs->stream->chip);
@@ -1653,7 +1655,7 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
-		err = start_endpoints(subs, false);
+		err = start_endpoints(subs);
 		if (err < 0)
 			return err;
 
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c60a776e815d..8a59d4782a0f 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2907,6 +2907,23 @@ AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"),
 AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"),
 AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 
+/* Syntek STK1160 */
+{
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
+		       USB_DEVICE_ID_MATCH_INT_CLASS |
+		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
+	.idVendor = 0x05e1,
+	.idProduct = 0x0408,
+	.bInterfaceClass = USB_CLASS_AUDIO,
+	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Syntek",
+		.product_name = "STK1160",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_AUDIO_ALIGN_TRANSFER
+	}
+},
+
 /* Digidesign Mbox */
 {
 	/* Thanks to Clemens Ladisch <clemens@ladisch.de> */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index c458d60d5030..1cc20d138dae 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -150,6 +150,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 		usb_audio_err(chip, "cannot memdup\n");
 		return -ENOMEM;
 	}
+	INIT_LIST_HEAD(&fp->list);
 	if (fp->nr_rates > MAX_NR_RATES) {
 		kfree(fp);
 		return -EINVAL;
@@ -167,19 +168,20 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	stream = (fp->endpoint & USB_DIR_IN)
 		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 	err = snd_usb_add_audio_stream(chip, stream, fp);
-	if (err < 0) {
-		kfree(fp);
-		kfree(rate_table);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	if (fp->iface != get_iface_desc(&iface->altsetting[0])->bInterfaceNumber ||
 	    fp->altset_idx >= iface->num_altsetting) {
-		kfree(fp);
-		kfree(rate_table);
-		return -EINVAL;
+		err = -EINVAL;
+		goto error;
 	}
 	alts = &iface->altsetting[fp->altset_idx];
 	altsd = get_iface_desc(alts);
+	if (altsd->bNumEndpoints < 1) {
+		err = -EINVAL;
+		goto error;
+	}
+
 	fp->protocol = altsd->bInterfaceProtocol;
 
 	if (fp->datainterval == 0)
@@ -190,6 +192,12 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	snd_usb_init_pitch(chip, fp->iface, alts, fp);
 	snd_usb_init_sample_rate(chip, fp->iface, alts, fp, fp->rate_max);
 	return 0;
+
+ error:
+	list_del(&fp->list); /* unlink for avoiding double-free */
+	kfree(fp);
+	kfree(rate_table);
+	return err;
 }
 
 static int create_auto_pcm_quirk(struct snd_usb_audio *chip,
@@ -462,6 +470,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 	fp->ep_attr = get_endpoint(alts, 0)->bmAttributes;
 	fp->datainterval = 0;
 	fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+	INIT_LIST_HEAD(&fp->list);
 
 	switch (fp->maxpacksize) {
 	case 0x120:
@@ -485,6 +494,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 	err = snd_usb_add_audio_stream(chip, stream, fp);
 	if (err < 0) {
+		list_del(&fp->list); /* unlink for avoiding double-free */
 		kfree(fp);
 		return err;
 	}
@@ -1119,14 +1129,25 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 {
 	/* devices which do not support reading the sample rate. */
 	switch (chip->usb_id) {
+	case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */
 	case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema  */
 	case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
+	case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */
 	case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */
 	case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
 	case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
+	case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */
+	case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */
 	case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
 	case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
+	case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
+	case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
 	case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
+	case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */
+	case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
+	case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */
+	case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */
+	case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */
 	case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */
 		return true;
 	}
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 8ee14f2365e7..3b23102230c0 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -316,7 +316,9 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits,
 /*
  * add this endpoint to the chip instance.
  * if a stream with the same endpoint already exists, append to it.
- * if not, create a new pcm stream.
+ * if not, create a new pcm stream. note, fp is added to the substream
+ * fmt_list and will be freed on the chip instance release. do not free
+ * fp or do remove it from the substream fmt_list to avoid double-free.
  */
 int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 			     int stream,
@@ -677,6 +679,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 					* (fp->maxpacksize & 0x7ff);
 		fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol, iface_no);
 		fp->clock = clock;
+		INIT_LIST_HEAD(&fp->list);
 
 		/* some quirks for attributes here */
 
@@ -725,6 +728,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 		dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint);
 		err = snd_usb_add_audio_stream(chip, stream, fp);
 		if (err < 0) {
+			list_del(&fp->list); /* unlink for avoiding double-free */
 			kfree(fp->rate_table);
 			kfree(fp->chmap);
 			kfree(fp);
diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index a8ab79556926..a8c4644022a6 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -5,6 +5,8 @@ PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) $(shell getconf LFS_CFLAGS)
 
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 5480e4e424eb..f1d742682317 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -37,12 +37,14 @@
 
 static int target_fd;
 static char target_fname[W_MAX_PATH];
+static unsigned long long filesize;
 
 static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 {
 	int error = HV_E_FAIL;
 	char *q, *p;
 
+	filesize = 0;
 	p = (char *)smsg->path_name;
 	snprintf(target_fname, sizeof(target_fname), "%s/%s",
 		 (char *)smsg->path_name, (char *)smsg->file_name);
@@ -98,14 +100,26 @@ done:
 static int hv_copy_data(struct hv_do_fcopy *cpmsg)
 {
 	ssize_t bytes_written;
+	int ret = 0;
 
 	bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size,
 				cpmsg->offset);
 
-	if (bytes_written != cpmsg->size)
-		return HV_E_FAIL;
+	filesize += cpmsg->size;
+	if (bytes_written != cpmsg->size) {
+		switch (errno) {
+		case ENOSPC:
+			ret = HV_ERROR_DISK_FULL;
+			break;
+		default:
+			ret = HV_E_FAIL;
+			break;
+		}
+		syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)",
+		       filesize, (long)bytes_written, strerror(errno));
+	}
 
-	return 0;
+	return ret;
 }
 
 static int hv_copy_finished(void)
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 0d9f48ec42bb..bc7adb84e679 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1433,7 +1433,7 @@ int main(int argc, char *argv[])
 	openlog("KVP", 0, LOG_USER);
 	syslog(LOG_INFO, "KVP starting; pid is:%d", getpid());
 
-	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR);
+	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
 
 	if (kvp_fd < 0) {
 		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index fa7208a32d76..8a679b21f0c4 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -115,4 +115,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #define WRITE_ONCE(x, val) \
 	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
 
+
+#ifndef __fallthrough
+# if defined(__GNUC__) && __GNUC__ >= 7
+#  define __fallthrough __attribute__ ((fallthrough))
+# else
+#  define __fallthrough
+# endif
+#endif
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
index 41446668ccce..d5677d39c1e4 100644
--- a/tools/include/linux/log2.h
+++ b/tools/include/linux/log2.h
@@ -13,12 +13,6 @@
 #define _TOOLS_LINUX_LOG2_H
 
 /*
- * deal with unrepresentable constant logarithms
- */
-extern __attribute__((const, noreturn))
-int ____ilog2_NaN(void);
-
-/*
  * non-constant log of base 2 calculators
  * - the arch may override these in asm/bitops.h if they can be implemented
  *   more efficiently than using fls() and fls64()
@@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n)				\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) < 2 ? 0 :			\
 		(n) & (1ULL << 63) ? 63 :	\
 		(n) & (1ULL << 62) ? 62 :	\
 		(n) & (1ULL << 61) ? 61 :	\
@@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 		(n) & (1ULL <<  4) ?  4 :	\
 		(n) & (1ULL <<  3) ?  3 :	\
 		(n) & (1ULL <<  2) ?  2 :	\
-		(n) & (1ULL <<  1) ?  1 :	\
-		(n) & (1ULL <<  0) ?  0 :	\
-		____ilog2_NaN()			\
-				   ) :		\
+		1 ) :				\
 	(sizeof(n) <= 4) ?			\
 	__ilog2_u32(n) :			\
 	__ilog2_u64(n)				\
diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/lib/lockdep/uinclude/linux/lockdep.h
index c808c7d02d21..e69118b2077e 100644
--- a/tools/lib/lockdep/uinclude/linux/lockdep.h
+++ b/tools/lib/lockdep/uinclude/linux/lockdep.h
@@ -8,7 +8,7 @@
 #include <linux/utsname.h>
 #include <linux/compiler.h>
 
-#define MAX_LOCK_DEPTH 2000UL
+#define MAX_LOCK_DEPTH 255UL
 
 #define asmlinkage
 #define __visible
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 0144b3d1bb77..88cccea3ca99 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1164,11 +1164,11 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		current_op = current_exp;
 
 	ret = collapse_tree(current_op, parg, error_str);
+	/* collapse_tree() may free current_op, and updates parg accordingly */
+	current_op = NULL;
 	if (ret < 0)
 		goto fail;
 
-	*parg = current_op;
-
 	free(token);
 	return 0;
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index f1ce60065258..ec30c2fcbac0 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld ", val);
 
 	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, "[%lld] ", val);
+		trace_seq_printf(s, "[%d] ", (int) val);
 
 	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
 		write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
 	trace_seq_printf(s, "%lld", val);
 
 	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
-		trace_seq_printf(s, " [%lld]", val);
+		trace_seq_printf(s, " [%d]", (int) val);
 
 	return 0;
 }
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4e074a660826..90c3558c2c12 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -62,6 +62,14 @@ OPTIONS
 --scale::
 	scale/normalize counter values
 
+-d::
+--detailed::
+	print more detailed statistics, can be specified up to 3 times
+
+	   -d:          detailed events, L1 and LLC data cache
+        -d -d:     more detailed events, dTLB and iTLB events
+     -d -d -d:     very detailed events, adding prefetch events
+
 -r::
 --repeat=<n>::
 	repeat command and print average + stddev (max: 100). 0 means forever.
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d19d5447d6c..b67e006d56cc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -420,7 +420,7 @@ $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-install-traceevent-plugins: $(LIBTRACEEVENT)
+install-traceevent-plugins: libtraceevent_plugins
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
 
 $(LIBAPI): fixdep FORCE
@@ -563,9 +563,9 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
 
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
 
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index d28c1b6a3b54..fa5d17af88b7 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -17,7 +17,7 @@ static pid_t spawn(void)
 	if (pid)
 		return pid;
 
-	while(1);
+	while(1)
 		sleep(5);
 	return 0;
 }
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
index 9223c164e545..1f86ee8fb831 100644
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ b/tools/perf/arch/x86/util/dwarf-regs.c
@@ -63,6 +63,8 @@ struct pt_regs_offset {
 # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
 #endif
 
+/* TODO: switching by dwarf address size */
+#ifndef __x86_64__
 static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_NAME_32("%ax",	eax),
 	REG_OFFSET_NAME_32("%cx",	ecx),
@@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
+#define regoffset_table x86_32_regoffset_table
+#else
 static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_NAME_64("%ax",	rax),
 	REG_OFFSET_NAME_64("%dx",	rdx),
@@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = {
 	REG_OFFSET_END,
 };
 
-/* TODO: switching by dwarf address size */
-#ifdef __x86_64__
 #define regoffset_table x86_64_regoffset_table
-#else
-#define regoffset_table x86_32_regoffset_table
 #endif
 
 /* Minus 1 for the ending REG_OFFSET_END */
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index b02af064f0f9..c53f78767568 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -499,7 +499,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	struct intel_pt_recording *ptr =
 			container_of(itr, struct intel_pt_recording, itr);
 	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
-	bool have_timing_info;
+	bool have_timing_info, need_immediate = false;
 	struct perf_evsel *evsel, *intel_pt_evsel = NULL;
 	const struct cpu_map *cpus = evlist->cpus;
 	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -653,6 +653,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				ptr->have_sched_switch = 3;
 			} else {
 				opts->record_switch_events = true;
+				need_immediate = true;
 				if (cpu_wide)
 					ptr->have_sched_switch = 3;
 				else
@@ -698,6 +699,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		tracking_evsel->attr.freq = 0;
 		tracking_evsel->attr.sample_period = 1;
 
+		if (need_immediate)
+			tracking_evsel->immediate = true;
+
 		/* In per-cpu case, always need the time of mmap events etc */
 		if (!cpu_map__empty(cpus)) {
 			perf_evsel__set_sample_bit(tracking_evsel, TIME);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 492df2752a2d..b4eb5b679081 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1570,13 +1570,13 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[32];
+		char tname[14 + 2 * 10 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {
-				memset(tname, 0, 32);
+				memset(tname, 0, sizeof(tname));
 				td = g->threads + p*g->p.nr_threads + t;
-				snprintf(tname, 32, "process%d:thread%d", p, t);
+				snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
 				print_res(tname, td->speed_gbs,
 					"GB/sec",	"thread-speed", "GB/sec/thread speed");
 				print_res(tname, td->system_time_ns / 1e9,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 72b5deb4bd79..20f0e27918dd 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1252,21 +1252,19 @@ static int is_directory(const char *base_path, const struct dirent *dent)
 	return S_ISDIR(st.st_mode);
 }
 
-#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
-	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
-	       lang_next)						\
-		if ((lang_dirent.d_type == DT_DIR ||			\
-		     (lang_dirent.d_type == DT_UNKNOWN &&		\
-		      is_directory(scripts_path, &lang_dirent))) &&	\
-		    (strcmp(lang_dirent.d_name, ".")) &&		\
-		    (strcmp(lang_dirent.d_name, "..")))
-
-#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
-	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
-	       script_next)						\
-		if (script_dirent.d_type != DT_DIR &&			\
-		    (script_dirent.d_type != DT_UNKNOWN ||		\
-		     !is_directory(lang_path, &script_dirent)))
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
+	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
+		if ((lang_dirent->d_type == DT_DIR ||			\
+		     (lang_dirent->d_type == DT_UNKNOWN &&		\
+		      is_directory(scripts_path, lang_dirent))) &&	\
+		    (strcmp(lang_dirent->d_name, ".")) &&		\
+		    (strcmp(lang_dirent->d_name, "..")))
+
+#define for_each_script(lang_path, lang_dir, script_dirent)		\
+	while ((script_dirent = readdir(lang_dir)) != NULL)		\
+		if (script_dirent->d_type != DT_DIR &&			\
+		    (script_dirent->d_type != DT_UNKNOWN ||		\
+		     !is_directory(lang_path, script_dirent)))
 
 
 #define RECORD_SUFFIX			"-record"
@@ -1412,7 +1410,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 				  const char *s __maybe_unused,
 				  int unset __maybe_unused)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	char script_path[MAXPATHLEN];
@@ -1427,19 +1425,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	if (!scripts_dir)
 		return -1;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			script_root = get_script_root(script_dirent, REPORT_SUFFIX);
 			if (script_root) {
 				desc = script_desc__findnew(script_root);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				read_script_info(desc, script_path);
 				free(script_root);
 			}
@@ -1527,7 +1525,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
  */
 int find_scripts(char **scripts_array, char **scripts_path_array)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	struct perf_session *session;
@@ -1550,9 +1548,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		return -1;
 	}
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 #ifdef NO_LIBPERL
 		if (strstr(lang_path, "perl"))
 			continue;
@@ -1566,16 +1564,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+		for_each_script(lang_path, lang_dir, script_dirent) {
 			/* Skip those real time scripts: xxxtop.p[yl] */
-			if (strstr(script_dirent.d_name, "top."))
+			if (strstr(script_dirent->d_name, "top."))
 				continue;
 			sprintf(scripts_path_array[i], "%s/%s", lang_path,
-				script_dirent.d_name);
-			temp = strchr(script_dirent.d_name, '.');
+				script_dirent->d_name);
+			temp = strchr(script_dirent->d_name, '.');
 			snprintf(scripts_array[i],
-				(temp - script_dirent.d_name) + 1,
-				"%s", script_dirent.d_name);
+				(temp - script_dirent->d_name) + 1,
+				"%s", script_dirent->d_name);
 
 			if (check_ev_match(lang_path,
 					scripts_array[i], session))
@@ -1593,7 +1591,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 
 static char *get_script_path(const char *script_root, const char *suffix)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	char script_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
@@ -1606,21 +1604,21 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	if (!scripts_dir)
 		return NULL;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			__script_root = get_script_root(&script_dirent, suffix);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			__script_root = get_script_root(script_dirent, suffix);
 			if (__script_root && !strcmp(script_root, __script_root)) {
 				free(__script_root);
 				closedir(lang_dir);
 				closedir(scripts_dir);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				return strdup(script_path);
 			}
 			free(__script_root);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7e2e72e6d9d1..4a8a02c302d2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -636,7 +636,7 @@ repeat:
 		case -1:
 			if (errno == EINTR)
 				continue;
-			/* Fall trhu */
+			__fallthrough;
 		default:
 			c = getc(stdin);
 			tcsetattr(0, TCSAFLUSH, &save);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c783d8fd3a80..ebe7115c751a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1617,6 +1617,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine,
 		color_fprintf(trace->output, PERF_COLOR_RED,
 			      "LOST %" PRIu64 " events!\n", event->lost.lost);
 		ret = machine__process_lost_event(machine, event, sample);
+		break;
 	default:
 		ret = machine__process_event(machine, event, sample);
 		break;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index ec16f7812c8b..6ebfdee3e2c6 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -146,7 +146,7 @@ prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
 	return obj;
 }
 
-static int __test__bpf(int index)
+static int __test__bpf(int idx)
 {
 	int ret;
 	void *obj_buf;
@@ -154,27 +154,27 @@ static int __test__bpf(int index)
 	struct bpf_object *obj;
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       bpf_testcase_table[index].prog_id,
+				       bpf_testcase_table[idx].prog_id,
 				       true);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
-			 bpf_testcase_table[index].msg_compile_fail);
-		if (index == 0)
+			 bpf_testcase_table[idx].msg_compile_fail);
+		if (idx == 0)
 			return TEST_SKIP;
 		else
 			return TEST_FAIL;
 	}
 
 	obj = prepare_bpf(obj_buf, obj_buf_sz,
-			  bpf_testcase_table[index].name);
+			  bpf_testcase_table[idx].name);
 	if (!obj) {
 		ret = TEST_FAIL;
 		goto out;
 	}
 
 	ret = do_test(obj,
-		      bpf_testcase_table[index].target_func,
-		      bpf_testcase_table[index].expect_result);
+		      bpf_testcase_table[idx].target_func,
+		      bpf_testcase_table[idx].expect_result);
 out:
 	bpf__clear();
 	return ret;
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index bc4cf507cde5..366e38ba8b49 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -50,7 +50,7 @@ static struct {
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
 			 size_t *p_obj_buf_sz,
-			 enum test_llvm__testcase index,
+			 enum test_llvm__testcase idx,
 			 bool force)
 {
 	const char *source;
@@ -59,11 +59,11 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 	char *tmpl_new = NULL, *clang_opt_new = NULL;
 	int err, old_verbose, ret = TEST_FAIL;
 
-	if (index >= __LLVM_TESTCASE_MAX)
+	if (idx >= __LLVM_TESTCASE_MAX)
 		return TEST_FAIL;
 
-	source = bpf_source_table[index].source;
-	desc = bpf_source_table[index].desc;
+	source = bpf_source_table[idx].source;
+	desc = bpf_source_table[idx].desc;
 
 	perf_config(perf_config_cb, NULL);
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 636d7b42d844..54af2f2e2ee4 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1727,15 +1727,14 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-#define MAX_NAME 100
 		struct evlist_test e;
-		char name[MAX_NAME];
+		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		if (!strcmp(ent->d_name, ".") ||
 		    !strcmp(ent->d_name, ".."))
 			continue;
 
-		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+		snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name);
 
 		e.name  = name;
 		e.check = test__checkevent_pmu_events;
@@ -1743,11 +1742,10 @@ static int test_pmu_events(void)
 		ret = test_event(&e);
 		if (ret)
 			break;
-		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
 		e.name  = name;
 		e.check = test__checkevent_pmu_events_mix;
 		ret = test_event(&e);
-#undef MAX_NAME
 	}
 
 	closedir(dir);
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index e9703c0829f1..07b5f5951b25 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -702,7 +702,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d4d7cc27252f..718bd46d47fa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				nd = browser->curr_hot;
 			break;
 		case K_UNTAB:
-			if (nd != NULL)
+			if (nd != NULL) {
 				nd = rb_next(nd);
 				if (nd == NULL)
 					nd = rb_first(&browser->entries);
-			else
+			} else
 				nd = browser->curr_hot;
 			break;
 		case K_F1:
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 81def6c3f24b..d802938644b5 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -684,7 +684,6 @@ static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	ui_browser__printf(arg->b, "%s", hpp->buf);
 
-	advance_hpp(hpp, ret);
 	return ret;
 }
 
@@ -2059,10 +2058,12 @@ skip_annotation:
 			 *
 			 * See hist_browser__show_entry.
 			 */
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     NULL, browser->selection->sym);
+			if (sort__has_sym && browser->selection->sym) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     NULL, browser->selection->sym);
+			}
 		}
 		nr_options += add_script_opt(browser, &actions[nr_options],
 					     &options[nr_options], NULL, NULL);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8b10621b415c..26cba64345e3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -274,7 +274,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
 		       &event->mmap2.start, &event->mmap2.len, prot,
 		       &event->mmap2.pgoff, &event->mmap2.maj,
 		       &event->mmap2.min,
@@ -416,7 +416,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	pid_t tgid, ppid;
 	int rc = 0;
 
@@ -445,11 +445,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		return 0;
 	}
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
+	while ((dirent = readdir(tasks)) != NULL) {
 		char *end;
 		pid_t _pid;
 
-		_pid = strtol(dirent.d_name, &end, 10);
+		_pid = strtol(dirent->d_name, &end, 10);
 		if (*end)
 			continue;
 
@@ -558,7 +558,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
-	struct dirent dirent, *next;
+	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
@@ -583,9 +583,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (proc == NULL)
 		goto out_free_fork;
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d1392194a9a9..b4b96120fc3b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1211,12 +1211,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
 	 */
 	if (cpus != evlist->cpus) {
 		cpu_map__put(evlist->cpus);
-		evlist->cpus = cpus;
+		evlist->cpus = cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
 		thread_map__put(evlist->threads);
-		evlist->threads = threads;
+		evlist->threads = thread_map__get(threads);
 	}
 
 	perf_evlist__propagate_maps(evlist);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9409d014b46c..eeeae0629ad3 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include <stdint.h>
 #include <inttypes.h>
+#include <linux/compiler.h>
 
 #include "../cache.h"
 #include "../util.h"
@@ -63,6 +64,25 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_FUP_NO_TIP,
 };
 
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+	switch (pkt_state) {
+	case INTEL_PT_STATE_NO_PSB:
+	case INTEL_PT_STATE_NO_IP:
+	case INTEL_PT_STATE_ERR_RESYNC:
+	case INTEL_PT_STATE_IN_SYNC:
+	case INTEL_PT_STATE_TNT:
+		return true;
+	case INTEL_PT_STATE_TIP:
+	case INTEL_PT_STATE_TIP_PGD:
+	case INTEL_PT_STATE_FUP:
+	case INTEL_PT_STATE_FUP_NO_TIP:
+		return false;
+	default:
+		return true;
+	};
+}
+
 #ifdef INTEL_PT_STRICT
 #define INTEL_PT_STATE_ERR1	INTEL_PT_STATE_NO_PSB
 #define INTEL_PT_STATE_ERR2	INTEL_PT_STATE_NO_PSB
@@ -89,6 +109,8 @@ struct intel_pt_decoder {
 	bool pge;
 	bool have_tma;
 	bool have_cyc;
+	bool fixup_last_mtc;
+	bool have_last_ip;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;
@@ -96,6 +118,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
 	uint64_t ctc_delta;
@@ -123,8 +146,6 @@ struct intel_pt_decoder {
 	bool have_calc_cyc_to_tsc;
 	int exec_mode;
 	unsigned int insn_bytes;
-	uint64_t sign_bit;
-	uint64_t sign_bits;
 	uint64_t period;
 	enum intel_pt_period_type period_type;
 	uint64_t tot_insn_cnt;
@@ -138,6 +159,7 @@ struct intel_pt_decoder {
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;
@@ -191,9 +213,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 
-	decoder->sign_bit           = (uint64_t)1 << 47;
-	decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;
 
@@ -362,21 +381,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen)
 	return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-				 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 				 uint64_t last_ip)
 {
 	uint64_t ip;
 
 	switch (packet->count) {
-	case 2:
+	case 1:
 		ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
 		     packet->payload;
 		break;
-	case 4:
+	case 2:
 		ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
 		     packet->payload;
 		break;
+	case 3:
+		ip = packet->payload;
+		/* Sign-extend 6-byte ip */
+		if (ip & (uint64_t)0x800000000000ULL)
+			ip |= (uint64_t)0xffff000000000000ULL;
+		break;
+	case 4:
+		ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+		     packet->payload;
+		break;
 	case 6:
 		ip = packet->payload;
 		break;
@@ -384,16 +412,13 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
 		return 0;
 	}
 
-	if (ip & decoder->sign_bit)
-		return ip | decoder->sign_bits;
-
 	return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-	decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-					    decoder->last_ip);
+	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
+	decoder->have_last_ip = true;
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -584,10 +609,31 @@ struct intel_pt_calc_cyc_to_tsc_info {
 	uint64_t        tsc_timestamp;
 	uint64_t        timestamp;
 	bool            have_tma;
+	bool            fixup_last_mtc;
 	bool            from_mtc;
 	double          cbr_cyc_to_tsc;
 };
 
+/*
+ * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower
+ * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC
+ * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA
+ * packet by copying the missing bits from the current MTC assuming the least
+ * difference between the two, and that the current MTC comes after last_mtc.
+ */
+static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift,
+				    uint32_t *last_mtc)
+{
+	uint32_t first_missing_bit = 1U << (16 - mtc_shift);
+	uint32_t mask = ~(first_missing_bit - 1);
+
+	*last_mtc |= mtc & mask;
+	if (*last_mtc >= mtc) {
+		*last_mtc -= first_missing_bit;
+		*last_mtc &= 0xff;
+	}
+}
+
 static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 {
 	struct intel_pt_decoder *decoder = pkt_info->decoder;
@@ -617,6 +663,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 			return 0;
 
 		mtc = pkt_info->packet.payload;
+		if (decoder->mtc_shift > 8 && data->fixup_last_mtc) {
+			data->fixup_last_mtc = false;
+			intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+						&data->last_mtc);
+		}
 		if (mtc > data->last_mtc)
 			mtc_delta = mtc - data->last_mtc;
 		else
@@ -685,6 +736,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 
 		data->ctc_delta = 0;
 		data->have_tma = true;
+		data->fixup_last_mtc = true;
 
 		return 0;
 
@@ -751,6 +803,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder,
 		.tsc_timestamp  = decoder->tsc_timestamp,
 		.timestamp      = decoder->timestamp,
 		.have_tma       = decoder->have_tma,
+		.fixup_last_mtc = decoder->fixup_last_mtc,
 		.from_mtc       = from_mtc,
 		.cbr_cyc_to_tsc = 0,
 	};
@@ -866,6 +919,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 
 	decoder->tot_insn_cnt += insn_cnt;
 	decoder->timestamp_insn_cnt += insn_cnt;
+	decoder->sample_insn_cnt += insn_cnt;
 	decoder->period_insn_cnt += insn_cnt;
 
 	if (err) {
@@ -1241,6 +1295,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
 	}
 	decoder->ctc_delta = 0;
 	decoder->have_tma = true;
+	decoder->fixup_last_mtc = true;
 	intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x  CTC rem %#x\n",
 		     decoder->ctc_timestamp, decoder->last_mtc, ctc_rem);
 }
@@ -1255,6 +1310,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 
 	mtc = decoder->packet.payload;
 
+	if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) {
+		decoder->fixup_last_mtc = false;
+		intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+					&decoder->last_mtc);
+	}
+
 	if (mtc > decoder->last_mtc)
 		mtc_delta = mtc - decoder->last_mtc;
 	else
@@ -1323,6 +1384,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 			     timestamp, decoder->timestamp);
 	else
 		decoder->timestamp = timestamp;
+
+	decoder->timestamp_insn_cnt = 0;
 }
 
 /* Walk PSB+ packets when already in sync. */
@@ -1375,7 +1438,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			intel_pt_set_last_ip(decoder);
+			if (decoder->packet.count)
+				intel_pt_set_last_ip(decoder);
 			break;
 
 		case INTEL_PT_MODE_TSX:
@@ -1579,6 +1643,8 @@ next:
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
 			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psbend(decoder);
 			if (err == -EAGAIN)
@@ -1657,6 +1723,13 @@ next:
 	}
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+	return decoder->packet.count &&
+	       (decoder->have_last_ip || decoder->packet.count == 3 ||
+		decoder->packet.count == 6);
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1670,6 +1743,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1677,8 +1751,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0) {
+			if (intel_pt_have_ip(decoder)) {
 				uint64_t current_ip = decoder->ip;
 
 				intel_pt_set_ip(decoder);
@@ -1724,6 +1797,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 			decoder->pge = false;
 			decoder->continuous_period = false;
 			intel_pt_clear_tx_flags(decoder);
+			__fallthrough;
+
 		case INTEL_PT_TNT:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1764,27 +1839,21 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-			if (decoder->last_ip || decoder->packet.count == 6 ||
-			    decoder->packet.count == 0)
+			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
 			if (decoder->ip)
 				return 0;
 			break;
 
 		case INTEL_PT_FUP:
-			if (decoder->overflow) {
-				if (decoder->last_ip ||
-				    decoder->packet.count == 6 ||
-				    decoder->packet.count == 0)
-					intel_pt_set_ip(decoder);
-				if (decoder->ip)
-					return 0;
-			}
-			if (decoder->packet.count)
-				intel_pt_set_last_ip(decoder);
+			if (intel_pt_have_ip(decoder))
+				intel_pt_set_ip(decoder);
+			if (decoder->ip)
+				return 0;
 			break;
 
 		case INTEL_PT_MTC:
@@ -1833,6 +1902,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
+			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psb(decoder);
 			if (err)
 				return err;
@@ -1858,6 +1930,8 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 {
 	int err;
 
+	decoder->set_fup_tx_flags = false;
+
 	intel_pt_log("Scanning for full IP\n");
 	err = intel_pt_walk_to_ip(decoder);
 	if (err)
@@ -1966,6 +2040,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 	decoder->pge = false;
 	decoder->continuous_period = false;
+	decoder->have_last_ip = false;
 	decoder->last_ip = 0;
 	decoder->ip = 0;
 	intel_pt_clear_stack(&decoder->stack);
@@ -1974,6 +2049,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	if (err)
 		return err;
 
+	decoder->have_last_ip = true;
 	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
 
 	err = intel_pt_walk_psb(decoder);
@@ -1992,7 +2068,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 {
-	uint64_t est = decoder->timestamp_insn_cnt << 1;
+	uint64_t est = decoder->sample_insn_cnt << 1;
 
 	if (!decoder->cbr || !decoder->max_non_turbo_ratio)
 		goto out;
@@ -2000,7 +2076,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 	est *= decoder->max_non_turbo_ratio;
 	est /= decoder->cbr;
 out:
-	return decoder->timestamp + est;
+	return decoder->sample_timestamp + est;
 }
 
 const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
@@ -2016,7 +2092,9 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_sync(decoder);
 			break;
 		case INTEL_PT_STATE_NO_IP:
+			decoder->have_last_ip = false;
 			decoder->last_ip = 0;
+			decoder->ip = 0;
 			/* Fall through */
 		case INTEL_PT_STATE_ERR_RESYNC:
 			err = intel_pt_sync_ip(decoder);
@@ -2053,15 +2131,24 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 		}
 	} while (err == -ENOLINK);
 
-	decoder->state.err = err ? intel_pt_ext_err(err) : 0;
-	decoder->state.timestamp = decoder->timestamp;
+	if (err) {
+		decoder->state.err = intel_pt_ext_err(err);
+		decoder->state.from_ip = decoder->ip;
+		decoder->sample_timestamp = decoder->timestamp;
+		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+	} else {
+		decoder->state.err = 0;
+		if (intel_pt_sample_time(decoder->pkt_state)) {
+			decoder->sample_timestamp = decoder->timestamp;
+			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		}
+	}
+
+	decoder->state.timestamp = decoder->sample_timestamp;
 	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
 	decoder->state.cr3 = decoder->cr3;
 	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
 
-	if (err)
-		decoder->state.from_ip = decoder->ip;
-
 	return &decoder->state;
 }
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index b1257c816310..7528ae4f7e28 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/compiler.h>
 
 #include "intel-pt-pkt-decoder.h"
 
@@ -292,36 +293,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
 			   const unsigned char *buf, size_t len,
 			   struct intel_pt_pkt *packet)
 {
-	switch (byte >> 5) {
+	int ip_len;
+
+	packet->count = byte >> 5;
+
+	switch (packet->count) {
 	case 0:
-		packet->count = 0;
+		ip_len = 0;
 		break;
 	case 1:
 		if (len < 3)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 2;
+		ip_len = 2;
 		packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
 		break;
 	case 2:
 		if (len < 5)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 4;
+		ip_len = 4;
 		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
 		break;
 	case 3:
-	case 6:
+	case 4:
 		if (len < 7)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->count = 6;
+		ip_len = 6;
 		memcpy_le64(&packet->payload, buf + 1, 6);
 		break;
+	case 6:
+		if (len < 9)
+			return INTEL_PT_NEED_MORE_BYTES;
+		ip_len = 8;
+		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+		break;
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
 
 	packet->type = type;
 
-	return packet->count + 1;
+	return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,
@@ -488,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
 	case INTEL_PT_FUP:
 		if (!(packet->count))
 			return snprintf(buf, buf_len, "%s no ip", name);
+		__fallthrough;
 	case INTEL_PT_CYC:
 	case INTEL_PT_VMCS:
 	case INTEL_PT_MTC:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 97f963a3dcb9..89927b5beebf 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -238,7 +238,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 
 	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-
+next:
 	buffer = auxtrace_buffer__next(queue, buffer);
 	if (!buffer) {
 		if (old_buffer)
@@ -261,9 +261,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
 		return -ENOMEM;
 
-	if (old_buffer)
-		auxtrace_buffer__drop_data(old_buffer);
-
 	if (buffer->use_data) {
 		b->len = buffer->use_size;
 		b->buf = buffer->use_data;
@@ -273,6 +270,16 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 	b->ref_timestamp = buffer->reference;
 
+	/*
+	 * If in snapshot mode and the buffer has no usable data, get next
+	 * buffer and again check overlap against old_buffer.
+	 */
+	if (ptq->pt->snapshot_mode && !b->len)
+		goto next;
+
+	if (old_buffer)
+		auxtrace_buffer__drop_data(old_buffer);
+
 	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
 						      !buffer->consecutive)) {
 		b->consecutive = false;
@@ -1127,7 +1134,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 		pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
 		       ret);
 
-	if (pt->synth_opts.callchain)
+	if (pt->synth_opts.last_branch)
 		intel_pt_reset_last_branch_rb(ptq);
 
 	return ret;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b48e87693aa5..38304b7e4f81 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-#define for_each_subsystem(sys_dir, sys_dirent, sys_next)	       \
-	while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next)	       \
-	if (sys_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(sys_dirent.d_name, ".")) &&				       \
-	   (strcmp(sys_dirent.d_name, "..")))
+#define for_each_subsystem(sys_dir, sys_dirent)			\
+	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
+		if (sys_dirent->d_type == DT_DIR &&		\
+		    (strcmp(sys_dirent->d_name, ".")) &&	\
+		    (strcmp(sys_dirent->d_name, "..")))
 
 static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 {
@@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next)	       \
-	while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next)        \
-	if (evt_dirent.d_type == DT_DIR &&				       \
-	   (strcmp(evt_dirent.d_name, ".")) &&				       \
-	   (strcmp(evt_dirent.d_name, "..")) &&				       \
-	   (!tp_event_has_id(&sys_dirent, &evt_dirent)))
+#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
+		if (evt_dirent->d_type == DT_DIR &&		\
+		    (strcmp(evt_dirent->d_name, ".")) &&	\
+		    (strcmp(evt_dirent->d_name, "..")) &&	\
+		    (!tp_event_has_id(sys_dirent, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 {
 	struct tracepoint_path *path = NULL;
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char id_buf[24];
 	int fd;
 	u64 id;
@@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	if (!sys_dir)
 		return NULL;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 
 			snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				 evt_dirent.d_name);
+				 evt_dirent->d_name);
 			fd = open(evt_path, O_RDONLY);
 			if (fd < 0)
 				continue;
@@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 					free(path);
 					return NULL;
 				}
-				strncpy(path->system, sys_dirent.d_name,
+				strncpy(path->system, sys_dirent->d_name,
 					MAX_EVENT_LENGTH);
-				strncpy(path->name, evt_dirent.d_name,
+				strncpy(path->name, evt_dirent->d_name,
 					MAX_EVENT_LENGTH);
 				return path;
 			}
@@ -1629,7 +1629,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 	char **evt_list = NULL;
@@ -1647,20 +1647,20 @@ restart:
 			goto out_close_sys_dir;
 	}
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 		if (subsys_glob != NULL &&
-		    !strglobmatch(sys_dirent.d_name, subsys_glob))
+		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
-			    !strglobmatch(evt_dirent.d_name, event_glob))
+			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
 
 			if (!evt_num_known) {
@@ -1669,7 +1669,7 @@ restart:
 			}
 
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
 			if (evt_list[evt_i] == NULL)
@@ -1722,7 +1722,7 @@ out_close_sys_dir:
 int is_valid_tracepoint(const char *event_string)
 {
 	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
 
@@ -1730,17 +1730,17 @@ int is_valid_tracepoint(const char *event_string)
 	if (!sys_dir)
 		return 0;
 
-	for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+	for_each_subsystem(sys_dir, sys_dirent) {
 
 		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent.d_name);
+			 sys_dirent->d_name);
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
 			continue;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent.d_name, evt_dirent.d_name);
+				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
 				closedir(evt_dir);
 				closedir(sys_dir);
@@ -2101,11 +2101,11 @@ char *parse_events_formats_error_string(char *additional_terms)
 
 	/* valid terms */
 	if (additional_terms) {
-		if (!asprintf(&str, "valid terms: %s,%s",
-			      additional_terms, static_terms))
+		if (asprintf(&str, "valid terms: %s,%s",
+			     additional_terms, static_terms) < 0)
 			goto fail;
 	} else {
-		if (!asprintf(&str, "valid terms: %s", static_terms))
+		if (asprintf(&str, "valid terms: %s", static_terms) < 0)
 			goto fail;
 	}
 	return str;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e4b173dec4b9..593066c68e3d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -153,7 +153,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	if (fd == -1)
 		return -1;
 
-		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	sret = read(fd, alias->unit, UNIT_MAX_LEN);
 	if (sret < 0)
 		goto error;
 
@@ -283,13 +283,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int ret = 0;
 
 	event_dir = opendir(dir);
 	if (!event_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(event_dir))) {
+	while ((evt_ent = readdir(event_dir))) {
 		char path[PATH_MAX];
 		char *name = evt_ent->d_name;
 		FILE *file;
@@ -305,17 +304,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
-		ret = -EINVAL;
 		file = fopen(path, "r");
-		if (!file)
-			break;
+		if (!file) {
+			pr_debug("Cannot open %s\n", path);
+			continue;
+		}
 
-		ret = perf_pmu__new_alias(head, dir, name, file);
+		if (perf_pmu__new_alias(head, dir, name, file) < 0)
+			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
 
 	closedir(event_dir);
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 05012bb178d7..fdd87c7e3e91 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1460,16 +1460,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
 	Dwarf_Addr _addr = 0, baseaddr = 0;
 	const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
 	int baseline = 0, lineno = 0, ret = 0;
-	bool reloc = false;
 
-retry:
+	/* We always need to relocate the address for aranges */
+	if (debuginfo__get_text_offset(dbg, &baseaddr) == 0)
+		addr += baseaddr;
 	/* Find cu die */
 	if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-		if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-			addr += baseaddr;
-			reloc = true;
-			goto retry;
-		}
 		pr_warning("Failed to find debug information for address %lx\n",
 			   addr);
 		ret = -EINVAL;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 6516e220c247..82d28c67e0f3 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
 libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
 libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
 
 CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1833103768cb..c8680984d2d6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -22,6 +22,7 @@ cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
 
+src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
@@ -30,6 +31,9 @@ libapikfs = getenv('LIBAPI')
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
 
+# use full paths with source files
+ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+
 perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4a3a72cb5805..6ce624cb7001 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
+	/*
+	 * We calculate counter's data every interval,
+	 * and the display code shows ps->res_stats
+	 * avg value. We need to zero the stats for
+	 * interval mode, otherwise overall avg running
+	 * averages will be shown for each interval.
+	 */
+	if (config->interval)
+		init_stats(ps->res_stats);
+
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
 
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index bcae659b6546..efb53772e0ec 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
 		len = strfilter_node__sprint_pt(node->l, buf);
 		if (len < 0)
 			return len;
+		__fallthrough;
 	case '!':
 		if (buf) {
 			*(buf + len++) = *node->p;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index fc8781de62db..accb7ece1d3c 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -21,6 +21,8 @@ s64 perf_atoll(const char *str)
 		case 'b': case 'B':
 			if (*p)
 				goto out_err;
+
+			__fallthrough;
 		case '\0':
 			return length;
 		default:
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 475d88d0a1c9..7c97ecaeae48 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -488,6 +488,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 				break;
 		} else {
 			int n = namesz + descsz;
+
+			if (n > (int)sizeof(bf)) {
+				n = sizeof(bf);
+				pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
+					 __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+			}
 			if (read(fd, bf, n) != n)
 				break;
 		}
@@ -1091,9 +1097,8 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		if (!symbol_conf.allow_aliases)
-			symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cd08027a6d2c..520a32a12f8a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -151,6 +151,9 @@ void symbols__fixup_duplicate(struct rb_root *symbols)
 	struct rb_node *nd;
 	struct symbol *curr, *next;
 
+	if (symbol_conf.allow_aliases)
+		return;
+
 	nd = rb_first(symbols);
 
 	while (nd) {
@@ -1275,8 +1278,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(map, filename, &delta))
 		return -1;
 
-	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0a9ae8014729..829508a21448 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -227,7 +227,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 					struct addr_location *al)
 {
 	size_t i;
-	const u8 const cpumodes[] = {
+	const u8 cpumodes[] = {
 		PERF_RECORD_MISC_USER,
 		PERF_RECORD_MISC_KERNEL,
 		PERF_RECORD_MISC_GUEST_USER,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 6ec3c5ca438f..4e666b95b87e 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -92,8 +92,8 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
-	char path[256];
-	struct dirent dirent, *next, **namelist = NULL;
+	char path[NAME_MAX + 1 + 6];
+	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)
@@ -106,16 +106,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	threads->nr = 0;
 	atomic_set(&threads->refcnt, 1);
 
-	while (!readdir_r(proc, &dirent, &next) && next) {
+	while ((dirent = readdir(proc)) != NULL) {
 		char *end;
 		bool grow = false;
 		struct stat st;
-		pid_t pid = strtol(dirent.d_name, &end, 10);
+		pid_t pid = strtol(dirent->d_name, &end, 10);
 
 		if (*end) /* only interested in proper numerical dirents */
 			continue;
 
-		snprintf(path, sizeof(path), "/proc/%s", dirent.d_name);
+		snprintf(path, sizeof(path), "/proc/%s", dirent->d_name);
 
 		if (stat(path, &st) != 0)
 			continue;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 9df61059a85d..a2fd6e79d5a5 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -95,7 +95,8 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
 	if (err)
 		die("error registering py script extension");
 
-	scripting_context = malloc(sizeof(struct scripting_context));
+	if (scripting_context == NULL)
+		scripting_context = malloc(sizeof(*scripting_context));
 }
 
 #ifdef NO_LIBPYTHON
@@ -159,7 +160,8 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
 	if (err)
 		die("error registering pl script extension");
 
-	scripting_context = malloc(sizeof(struct scripting_context));
+	if (scripting_context == NULL)
+		scripting_context = malloc(sizeof(*scripting_context));
 }
 
 #ifdef NO_LIBPERL
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 93b0aa74ca03..39c2c7d067bb 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -156,6 +156,7 @@ out:
 					 */
 			case 0x2C:	/* Westmere EP - Gulftown */
 				cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
+				break;
 			case 0x2A:	/* SNB */
 			case 0x2D:	/* SNB Xeon */
 			case 0x3A:	/* IVB */
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index d08e214ec6e7..223d88e25e05 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -2629,7 +2629,7 @@ sub do_run_test {
     }
 
     waitpid $child_pid, 0;
-    $child_exit = $?;
+    $child_exit = $? >> 8;
 
     my $end_time = time;
     $test_time = $end_time - $start_time;
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 51cf8256c6cd..f0d1c8ff8e8a 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
 #include <linux/libnvdimm.h>
 #include <linux/vmalloc.h>
 #include <linux/device.h>
@@ -1246,6 +1247,7 @@ static int nfit_test_probe(struct platform_device *pdev)
 	if (nfit_test->setup != nfit_test0_setup)
 		return 0;
 
+	flush_work(&acpi_desc->work);
 	nfit_test->setup_hotplug = 1;
 	nfit_test->setup(nfit_test);
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c8edff6803d1..24ebd3e3eb7d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -83,7 +83,7 @@ ifdef INSTALL_PATH
 	done;
 
 	@# Ask all targets to emit their test scripts
-	echo "#!/bin/bash" > $(ALL_SCRIPT)
+	echo "#!/bin/sh" > $(ALL_SCRIPT)
 	echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT)
 	echo "ROOT=\$$PWD" >> $(ALL_SCRIPT)
 
diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c
index 10a21a958aaf..763f37fecfb8 100644
--- a/tools/testing/selftests/capabilities/test_execve.c
+++ b/tools/testing/selftests/capabilities/test_execve.c
@@ -138,9 +138,6 @@ static void chdir_to_tmpfs(void)
 
 	if (chdir(cwd) != 0)
 		err(1, "chdir to private tmpfs");
-
-	if (umount2(".", MNT_DETACH) != 0)
-		err(1, "detach private tmpfs");
 }
 
 static void copy_fromat_to(int fromfd, const char *fromname, const char *toname)
@@ -248,7 +245,7 @@ static int do_tests(int uid, const char *our_path)
 			err(1, "chown");
 		if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0)
 			err(1, "chmod");
-}
+	}
 
 	capng_get_caps_process();
 
@@ -384,7 +381,7 @@ static int do_tests(int uid, const char *our_path)
 	} else {
 		printf("[RUN]\tNon-root +ia, sgidnonroot => i\n");
 		exec_other_validate_cap("./validate_cap_sgidnonroot",
-						false, false, true, false);
+					false, false, true, false);
 
 		if (fork_wait()) {
 			printf("[RUN]\tNon-root +ia, sgidroot => i\n");
diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests
index c09a682df56a..16058bbea7a8 100755
--- a/tools/testing/selftests/net/run_netsocktests
+++ b/tools/testing/selftests/net/run_netsocktests
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 
 echo "--------------------"
 echo "running socket test"
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index c22860ab9733..30e1ac62e8cb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -66,7 +66,7 @@ int pmc56_overflow(void)
 
 	FAIL_IF(ebb_event_enable(&event));
 
-	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
 	mtspr(SPRN_PMC5, 0);
 	mtspr(SPRN_PMC6, 0);
 
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 31a3035cd4eb..923e59eb82c7 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -394,6 +394,51 @@ static void *threadproc(void *ctx)
 	}
 }
 
+#ifdef __i386__
+
+#ifndef SA_RESTORE
+#define SA_RESTORER 0x04000000
+#endif
+
+/*
+ * The UAPI header calls this 'struct sigaction', which conflicts with
+ * glibc.  Sigh.
+ */
+struct fake_ksigaction {
+	void *handler;  /* the real type is nasty */
+	unsigned long sa_flags;
+	void (*sa_restorer)(void);
+	unsigned char sigset[8];
+};
+
+static void fix_sa_restorer(int sig)
+{
+	struct fake_ksigaction ksa;
+
+	if (syscall(SYS_rt_sigaction, sig, NULL, &ksa, 8) == 0) {
+		/*
+		 * glibc has a nasty bug: it sometimes writes garbage to
+		 * sa_restorer.  This interacts quite badly with anything
+		 * that fiddles with SS because it can trigger legacy
+		 * stack switching.  Patch it up.  See:
+		 *
+		 * https://sourceware.org/bugzilla/show_bug.cgi?id=21269
+		 */
+		if (!(ksa.sa_flags & SA_RESTORER) && ksa.sa_restorer) {
+			ksa.sa_restorer = NULL;
+			if (syscall(SYS_rt_sigaction, sig, &ksa, NULL,
+				    sizeof(ksa.sigset)) != 0)
+				err(1, "rt_sigaction");
+		}
+	}
+}
+#else
+static void fix_sa_restorer(int sig)
+{
+	/* 64-bit glibc works fine. */
+}
+#endif
+
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -405,6 +450,7 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 	if (sigaction(sig, &sa, 0))
 		err(1, "sigaction");
 
+	fix_sa_restorer(sig);
 }
 
 static jmp_buf jmpbuf;
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 86e698d07e20..499b8819d4c6 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -510,10 +510,11 @@ static void slab_stats(struct slabinfo *s)
 			s->alloc_node_mismatch, (s->alloc_node_mismatch * 100) / total);
 	}
 
-	if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail)
+	if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail) {
 		printf("\nCmpxchg_double Looping\n------------------------\n");
 		printf("Locked Cmpxchg Double redos   %lu\nUnlocked Cmpxchg Double redos %lu\n",
 			s->cmpxchg_double_fail, s->cmpxchg_double_cpu_fail);
+	}
 }
 
 static void report(struct slabinfo *s)
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ea6064696fe4..a7b9022b5c8f 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -86,6 +86,8 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
 	vcpu->arch.timer_cpu.armed = false;
 
+	WARN_ON(!kvm_timer_should_fire(vcpu));
+
 	/*
 	 * If the vcpu is blocked we want to wake it up so that it will see
 	 * the timer has expired when entering the guest.
@@ -93,10 +95,46 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	kvm_vcpu_kick(vcpu);
 }
 
+static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
+{
+	cycle_t cval, now;
+
+	cval = vcpu->arch.timer_cpu.cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+	if (now < cval) {
+		u64 ns;
+
+		ns = cyclecounter_cyc2ns(timecounter->cc,
+					 cval - now,
+					 timecounter->mask,
+					 &timecounter->frac);
+		return ns;
+	}
+
+	return 0;
+}
+
 static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
 {
 	struct arch_timer_cpu *timer;
+	struct kvm_vcpu *vcpu;
+	u64 ns;
+
 	timer = container_of(hrt, struct arch_timer_cpu, timer);
+	vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
+
+	/*
+	 * Check that the timer has really expired from the guest's
+	 * PoV (NTP on the host may have forced it to expire
+	 * early). If we should have slept longer, restart it.
+	 */
+	ns = kvm_timer_compute_delta(vcpu);
+	if (unlikely(ns)) {
+		hrtimer_forward_now(hrt, ns_to_ktime(ns));
+		return HRTIMER_RESTART;
+	}
+
 	queue_work(wqueue, &timer->expired);
 	return HRTIMER_NORESTART;
 }
@@ -170,8 +208,6 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-	u64 ns;
-	cycle_t cval, now;
 
 	BUG_ON(timer_is_armed(timer));
 
@@ -191,14 +227,7 @@ void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 		return;
 
 	/*  The timer has not yet expired, schedule a background timer */
-	cval = timer->cntv_cval;
-	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
-	ns = cyclecounter_cyc2ns(timecounter->cc,
-				 cval - now,
-				 timecounter->mask,
-				 &timecounter->frac);
-	timer_arm(timer, ns);
+	timer_arm(timer, kvm_timer_compute_delta(vcpu));
 }
 
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 46dbc0a7dfc1..49001fa84ead 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -868,7 +868,8 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		kvm->buses[bus_idx]->ioeventfd_count--;
+		if (kvm->buses[bus_idx])
+			kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index f0b08a2a48ba..7d31d8c5b9ea 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -40,7 +40,7 @@ int kvm_irq_map_gsi(struct kvm *kvm,
 
 	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
 					lockdep_is_held(&kvm->irq_lock));
-	if (gsi < irq_rt->nr_rt_entries) {
+	if (irq_rt && gsi < irq_rt->nr_rt_entries) {
 		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
 			entries[n] = *e;
 			++n;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7338e30421d8..cb092bd9965b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -142,6 +142,7 @@ int vcpu_load(struct kvm_vcpu *vcpu)
 	put_cpu();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vcpu_load);
 
 void vcpu_put(struct kvm_vcpu *vcpu)
 {
@@ -151,6 +152,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
 }
+EXPORT_SYMBOL_GPL(vcpu_put);
 
 static void ack_flush(void *_completed)
 {
@@ -547,6 +549,16 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
+	spin_lock_init(&kvm->mmu_lock);
+	atomic_inc(&current->mm->mm_count);
+	kvm->mm = current->mm;
+	kvm_eventfd_init(kvm);
+	mutex_init(&kvm->lock);
+	mutex_init(&kvm->irq_lock);
+	mutex_init(&kvm->slots_lock);
+	atomic_set(&kvm->users_count, 1);
+	INIT_LIST_HEAD(&kvm->devices);
+
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_no_disable;
@@ -579,16 +591,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
 			goto out_err;
 	}
 
-	spin_lock_init(&kvm->mmu_lock);
-	kvm->mm = current->mm;
-	atomic_inc(&kvm->mm->mm_count);
-	kvm_eventfd_init(kvm);
-	mutex_init(&kvm->lock);
-	mutex_init(&kvm->irq_lock);
-	mutex_init(&kvm->slots_lock);
-	atomic_set(&kvm->users_count, 1);
-	INIT_LIST_HEAD(&kvm->devices);
-
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
 		goto out_err;
@@ -613,6 +615,7 @@ out_err_no_disable:
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
 		kvm_free_memslots(kvm, kvm->memslots[i]);
 	kvm_arch_free_vm(kvm);
+	mmdrop(current->mm);
 	return ERR_PTR(r);
 }
 
@@ -651,8 +654,11 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	list_del(&kvm->vm_list);
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
-	for (i = 0; i < KVM_NR_BUSES; i++)
-		kvm_io_bus_destroy(kvm->buses[i]);
+	for (i = 0; i < KVM_NR_BUSES; i++) {
+		if (kvm->buses[i])
+			kvm_io_bus_destroy(kvm->buses[i]);
+		kvm->buses[i] = NULL;
+	}
 	kvm_coalesced_mmio_free(kvm);
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
@@ -2860,7 +2866,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;
@@ -3268,6 +3274,8 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_write(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3285,6 +3293,8 @@ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 
 	/* First try the device referenced by cookie. */
 	if ((cookie >= 0) && (cookie < bus->dev_count) &&
@@ -3335,6 +3345,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu);
+	if (!bus)
+		return -ENOMEM;
 	r = __kvm_io_bus_read(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
@@ -3347,6 +3359,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
+	if (!bus)
+		return -ENOMEM;
+
 	/* exclude ioeventfd which is limited by maximum fd */
 	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
@@ -3366,37 +3381,41 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 }
 
 /* Caller must hold slots_lock. */
-int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			      struct kvm_io_device *dev)
+void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			       struct kvm_io_device *dev)
 {
-	int i, r;
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	r = -ENOENT;
+	if (!bus)
+		return;
+
 	for (i = 0; i < bus->dev_count; i++)
 		if (bus->range[i].dev == dev) {
-			r = 0;
 			break;
 		}
 
-	if (r)
-		return r;
+	if (i == bus->dev_count)
+		return;
 
 	new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
 			  sizeof(struct kvm_io_range)), GFP_KERNEL);
-	if (!new_bus)
-		return -ENOMEM;
+	if (!new_bus)  {
+		pr_err("kvm: failed to shrink bus, removing it completely\n");
+		goto broken;
+	}
 
 	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
 	new_bus->dev_count--;
 	memcpy(new_bus->range + i, bus->range + i + 1,
 	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
 
+broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
-	return r;
+	return;
 }
 
 static struct notifier_block kvm_cpu_notifier = {
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 1dd087da6f31..111e09c3f4bf 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -47,6 +47,22 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
 	return vfio_group;
 }
 
+static bool kvm_vfio_external_group_match_file(struct vfio_group *group,
+					       struct file *filep)
+{
+	bool ret, (*fn)(struct vfio_group *, struct file *);
+
+	fn = symbol_get(vfio_external_group_match_file);
+	if (!fn)
+		return false;
+
+	ret = fn(group, filep);
+
+	symbol_put(vfio_external_group_match_file);
+
+	return ret;
+}
+
 static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 {
 	void (*fn)(struct vfio_group *);
@@ -171,18 +187,13 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		if (!f.file)
 			return -EBADF;
 
-		vfio_group = kvm_vfio_group_get_external_user(f.file);
-		fdput(f);
-
-		if (IS_ERR(vfio_group))
-			return PTR_ERR(vfio_group);
-
 		ret = -ENOENT;
 
 		mutex_lock(&kv->lock);
 
 		list_for_each_entry(kvg, &kv->group_list, node) {
-			if (kvg->vfio_group != vfio_group)
+			if (!kvm_vfio_external_group_match_file(kvg->vfio_group,
+								f.file))
 				continue;
 
 			list_del(&kvg->node);
@@ -196,7 +207,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
-		kvm_vfio_group_put_external_user(vfio_group);
+		fdput(f);
 
 		kvm_vfio_update_coherency(dev);
 
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 09a03b5a21ff..e5d5dde6bf75 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -188,7 +188,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->token == consumer->token) {
+		if (tmp->token == consumer->token || tmp == consumer) {
 			mutex_unlock(&lock);
 			module_put(THIS_MODULE);
 			return -EBUSY;
@@ -235,7 +235,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->token != consumer->token)
+		if (tmp != consumer)
 			continue;
 
 		list_for_each_entry(producer, &producers, node) {